@article {pmid39898312,
year = {2025},
author = {O'Brien, B and Yushchenko, A and Suh, J and Jung, D and Cai, Z and Nguyen, NS and Semret, M and Dufour, S and Fanning, S and Ronholm, J},
title = {Subtle genomic differences in Klebsiella pneumoniae sensu stricto isolates indicate host adaptation.},
journal = {One health (Amsterdam, Netherlands)},
volume = {20},
number = {},
pages = {100970},
pmid = {39898312},
issn = {2352-7714},
abstract = {Klebsiella pneumoniae sensu stricto (KpI) is an opportunistic pathogen capable of residing as a commensal in both human and bovine intestinal tracts and can cause serious systemic infections in humans and severe clinical mastitis in dairy cattle. It is unclear what role zoonotic and anthroponotic transmission play in the dissemination of KpI. In this study, we use a comparative genomic approach to identify differences between KpI associated with disease in humans and cattle and aimed to identify any potential genetic barriers limiting transmission of KpI between these two hosts. A total of 128 KpI strains (bovine n = 65; human n = 63) were whole genome sequenced and human and bovine strains were compared based on phylogenomics, the pangenome, mobile genetic elements, and differential gene abundance. No obvious phylogenomic differentiation was observed between isolates from these hosts. However, subtle genetic differences exist between bovine and human KpI which likely reflect environmental adaptation to different host niches, including a higher representation of gene clusters encoding ferric citrate uptake transporters, as well as histidine, arginine, and lactose utilization pathways in bovine isolates. These gene clusters may be positively selected due to the unique metabolic environment of the mammary gland, where lactose, citrate-bound iron, and amino acids like histidine and arginine provide growth advantages for KpI during mastitis. Overall, our study identified no obvious genetic barriers to zoonotic transmission of KpI within the dairy environment and provides insight into the development of host-specific therapeutic options for KpI infections in humans and bovine.},
}

@article {pmid39894347,
year = {2025},
author = {Ruperao, P and Rangan, P and Shah, T and Sharma, V and Rathore, A and Mayes, S and Pandey, MK},
title = {Developing pangenomes for large and complex plant genomes and their representation formats.},
journal = {Journal of advanced research},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.jare.2025.01.052},
pmid = {39894347},
issn = {2090-1224},
abstract = {BACKGROUND: The development of pangenomes has revolutionized genomic studies by capturing the complete genetic diversity within a species. Pangenome assembly integrates data from multiple individuals to construct a comprehensive genomic landscape, revealing both core and accessory genomic elements. This approach enables the identification of novel genes, structural variations, and gene presence-absence variations, providing insights into species evolution, adaptation, and trait variation. Representing pangenomes requires innovative visualization formats that effectively convey the complex genomic structures and variations.

AIM: This review delves into contemporary methodologies and recent advancements in constructing pangenomes, particularly in plant genomes. It examines the structure of pangenome representation, including format comparison, conversion, visualization techniques, and their implications for enhancing crop improvement strategies.

Earlier comparative studies have illuminated novel gene sequences, copy number variations, and presence-absence variations across diverse crop species. The concept of a pan-genome, which captures multiple genetic variations from a broad spectrum of genotypes, offers a holistic perspective of a species' genetic makeup. However, constructing a pan-genome for plants with larger genomes poses challenges, including managing vast genome sequence data and comprehending the genetic variations within the germplasm. To address these challenges, researchers have explored cost-effective alternatives to encapsulate species diversity in a single assembly known as a pangenome. This involves reducing the volume of genome sequences while focusing on genetic variations. With the growing prominence of the pan-genome concept in plant genomics, several software tools have emerged to facilitate pangenome construction. This review sheds light on developing and utilizing software tools tailored for constructing pan-genomes in plants. It also discusses representation formats suitable for downstream analyses, offering valuable insights into the genetic landscape and evolutionary dynamics of plant species. In summary, this review underscores the significance of pan-genome construction and representation formats in resolving the genetic architecture of plants, particularly those with complex genomes. It provides a comprehensive overview of recent advancements, aiding in exploring and understanding plant genetic diversity.},
}

@article {pmid39889851,
year = {2025},
author = {Alvarez-Maya, I and Garcia-Ulloa, M and Martinez-Guarneros, A and Vazquez-Chacon, CA and Martinez-Urtaza, J},
title = {Nationwide Phylogenomic Surveillance of Mycobacterium tuberculosis in Mexico Reveals Pathogenic and Drug Resistant Signatures of the Prevailing L4 Sublineage.},
journal = {Journal of global antimicrobial resistance},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.jgar.2025.01.013},
pmid = {39889851},
issn = {2213-7173},
abstract = {BACKGROUND: Tuberculosis disease is a major global health concern. In Mexico, information regarding the genomic variants of Mycobacterium tuberculosis (MTB) prevailing in the country and the existence of specific biogeographical patterns remains extremely scarce.

OBJECTIVE: This study aimed to identify the genotypic patterns of MTB isolates in Mexico and determine the genes and specific single nucleotide polymorphisms involved in the evolution of these populations.

METHODS: Phylogenomic and pan-genomic analyses were performed using publicly available Mexican MTB genomes along with 33 newly sequenced genomes from Jalisco, considering a global context.

RESULTS: The L4 sublineages of MTB, such as L4.1.1 (X), L4.1.2 (H), and L4.3 (LAM), were the most prevalent in Mexico. We found exclusive mutations and gene clusters in a virulent sublineage L4.1.1.3 (X3), which is endemic to Mexico. These genes encoded three PE/PPE family proteins: a multidrug transporter, thioredoxin domain-containing protein, quinone-dependent L-lactate dehydrogenase, DUF1725 domain-containing protein, amidase, poly (A) polymerase, and six hypothetical/uncharacterized proteins. Additionally, the genes encode an ESX-1 secretion-associated protein and a deazaflavin-dependent nitroreductase (ddn).

CONCLUSION: X3 was distinguished from the rest of the sublineages by containing genes related to pathogenicity and virulence, as well as a gene linked to delamanid, an antibiotic for active multidrug-resistant tuberculosis. These findings provide valuable insight into the circulation and spread of MTB in Mexico.},
}

@article {pmid39882343,
year = {2024},
author = {Sholeh, M and Beig, M and Kouhsari, E and Rohani, M and Katouli, M and Badmasti, F},
title = {Global insights into the genome dynamics of Clostridioides difficile associated with antimicrobial resistance, virulence, and genomic adaptations among clonal lineages.},
journal = {Frontiers in cellular and infection microbiology},
volume = {14},
number = {},
pages = {1493225},
pmid = {39882343},
issn = {2235-2988},
mesh = {*Clostridioides difficile/genetics/drug effects/pathogenicity/classification ; *Genome, Bacterial ; *Virulence Factors/genetics ; *Drug Resistance, Bacterial/genetics ; Virulence/genetics ; Humans ; Clostridium Infections/microbiology ; Multilocus Sequence Typing ; Anti-Bacterial Agents/pharmacology ; Plasmids/genetics ; Genomics ; Bacterial Toxins/genetics ; Phylogeny ; },
abstract = {BACKGROUND: Clostridioides difficile is a significant cause of healthcare-associated infections, with rising antimicrobial resistance complicating treatment. This study offers a genomic analysis of C. difficile, focusing on sequence types (STs), global distribution, antibiotic resistance genes, and virulence factors in its chromosomal and plasmid DNA.

METHODS: A total of 19,711 C. difficile genomes were retrieved from GenBank. Prokka was used for genome annotation, and multi-locus sequence typing (MLST) identified STs. Pan-genome analysis with Roary identified core and accessory genes. Antibiotic resistance genes, virulence factors, and toxins were detected using the CARD and VFDB databases, and the ABRicate software. Statistical analyses and visualizations were performed in R.

RESULTS: Among 366 identified STs, ST1 (1,326 isolates), ST2 (1,141), ST11 (893), and ST42 (763) were predominant. Trends of genome streamlining included reductions in chromosomal length, gene count, protein-coding genes, and pseudogenes. Common antibiotic resistance genes-cdeA (99.46%), cplR (99.63%), and nimB (99.67%)-were nearly ubiquitous. Rare resistance genes like blaCTX-M-2, cfxA3, and blaZ appeared in only 0.005% of genomes. Vancomycin susceptibility-reducing vanG cluster genes were detected at low frequencies. Virulence factors showed variability, with highly prevalent genes such as zmp1 (99.62%), groEL (99.60%), and rpoB/rpoB2 (99.60%). Moderately distributed genes included cwp66 (54.61%) and slpA (79.02%). Toxin genes tcdE (91.26%), tcdC (89.67%), and tcdB (89.06%) were widespread, while binary toxin genes cdtA (26.19%) and cdtB (26.26%) were less common. Toxin gene prevalence, particularly tcdA and tcdB, showed a gradual decline over time, with sharper reductions for cdtA and cdtB. Gene presence patterns (GPP-1) for resistance, virulence, and toxin genes were primarily linked to ST2, ST42, and ST8.

CONCLUSION: This study highlights C. difficile's adaptability and genetic diversity. The decline in toxin genes reflects fewer toxigenic isolates, but the bacterium's increasing preserved resistance factors and virulence genes enable its rapid evolution. ST2, ST42, and ST8 dominate globally, emphasizing the need for ongoing monitoring.},
}

*Clostridioides difficile/genetics/drug effects/pathogenicity/classification
*Genome, Bacterial
*Virulence Factors/genetics
*Drug Resistance, Bacterial/genetics
Virulence/genetics
Humans
Clostridium Infections/microbiology
Multilocus Sequence Typing
Anti-Bacterial Agents/pharmacology
Plasmids/genetics
Genomics
Bacterial Toxins/genetics
Phylogeny

@article {pmid39871478,
year = {2025},
author = {Zhu, X and Yang, R and Liang, Q and Yu, Y and Wang, T and Meng, L and Wang, P and Wang, S and Li, X and Yang, Q and Guo, H and Sui, Q and Wang, Q and Du, H and Chen, Q and Liang, Z and Wu, X and Zeng, Q and Huang, B},
title = {Graph-based pangenome provides insights into the structural variation and genetic basis of metabolic traits in potato.},
journal = {Molecular plant},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.molp.2025.01.017},
pmid = {39871478},
issn = {1752-9867},
abstract = {Potato is the world's most important nongrain crop. Here, we report that 29 genomes from Petota and Etuberosum sections were de novo assembled, and that 248 accessions of wild potatoes, landraces and modern cultivars were re-sequenced at > 25× depth to assess genetic diversity within the Petota section. Subsequently, a graph-based pangenome was constructed by using DM8.1 as the backbone integrated 194,330 nonredundant structural variants. To characterize the metabolome of tubers and illuminate the genomic basis of metabolic traits, LC-MS/MS was employed to obtain the metabolome of 157 accessions, and 9,321 SVs were detected to be significantly associated with 1,258 distinct metabolites via PAV-based metabolomics-GWAS analysis, including metabolites of flavonoids, phenolic acids and phospholipids. To facilitate the utilization of pangenome resources, a comprehensive platform, the potato pangenome database (PPDB, http://101.201.107.228:16666/), was developed for the potato community worldwide. Our study provides a comprehensive genomic resource that enables us to assess the genomic basis of agronomic and metabolic traits, and the genomic dataset resources will accelerate functional genomics studies and genetic improvements in potato.},
}

@article {pmid39870503,
year = {2025},
author = {Jiao, D and Dong, X and Fan, S and Liu, X and Yu, Y and Wei, C},
title = {Gastric cancer genomics study using reference human pangenomes.},
journal = {Life science alliance},
volume = {8},
number = {4},
pages = {},
pmid = {39870503},
issn = {2575-1077},
mesh = {Humans ; *Stomach Neoplasms/genetics ; *Genomics/methods ; *Genome, Human/genetics ; Microsatellite Instability ; Male ; Female ; },
abstract = {A pangenome is the sum of the genetic information of all individuals in a species or a population. Genomics research has been gradually shifted to a paradigm using a pangenome as the reference. However, in disease genomics study, pangenome-based analysis is still in its infancy. In this study, we introduced a graph-based pangenome GGCPan from 185 patients with gastric cancer. We then systematically compared the cancer genomics study results using GGCPan, a linear pangenome GCPan, and the human reference genome as the reference. For small variant detection and microsatellite instability status identification, there is little difference in using three different genomes. Using GGCPan as the reference had a significant advantage in structural variant identification. A total of 24 candidate gastric cancer driver genes were detected using three different reference genomes, of which eight were common and five were detected only based on pangenomes. Our results showed that disease-specific pangenome as a reference is promising and a whole set of tools are still to be developed or improved for disease genomics study in the pangenome era.},
}

Humans
*Stomach Neoplasms/genetics
*Genomics/methods
*Genome, Human/genetics
Microsatellite Instability
Male
Female

@article {pmid39868538,
year = {2025},
author = {Zhang, W and Macias-Velasco, JF and Zhuo, X and Belter, EA and Tomlinson, C and Garza, J and Tekkey, N and Li, D and Wang, T},
title = {methylGrapher: genome-graph-based processing of DNA methylation data from whole genome bisulfite sequencing.},
journal = {Nucleic acids research},
volume = {53},
number = {3},
pages = {},
pmid = {39868538},
issn = {1362-4962},
support = {U41HG010972/NH/NIH HHS/United States ; },
mesh = {*DNA Methylation ; Humans ; *Genome, Human ; *Whole Genome Sequencing/methods ; *Sulfites/chemistry ; *CpG Islands ; Software ; Sequence Analysis, DNA/methods ; Genomics/methods ; },
abstract = {Genome graphs, including the recently released draft human pangenome graph, can represent the breadth of genetic diversity and thus transcend the limits of traditional linear reference genomes. However, there are no genome-graph-compatible tools for analyzing whole genome bisulfite sequencing (WGBS) data. To close this gap, we introduce methylGrapher, a tool tailored for accurate DNA methylation analysis by mapping WGBS data to a genome graph. Notably, methylGrapher can reconstruct methylation patterns along haplotype paths precisely and efficiently. To demonstrate the utility of methylGrapher, we analyzed the WGBS data derived from five individuals whose genomes were included in the first Human Pangenome draft as well as WGBS data from ENCODE (EN-TEx). Along with standard performance benchmarking, we show that methylGrapher fully recapitulates DNA methylation patterns defined by classic linear genome analysis approaches. Importantly, methylGrapher captures a substantial number of CpG sites that are missed by linear methods, and improves overall genome coverage while reducing alignment reference bias. Thus, methylGrapher is a first step toward unlocking the full potential of Human Pangenome graphs in genomic DNA methylation analysis.},
}

*DNA Methylation
Humans
*Genome, Human
*Whole Genome Sequencing/methods
*Sulfites/chemistry
*CpG Islands
Software
Sequence Analysis, DNA/methods
Genomics/methods

@article {pmid39868160,
year = {2025},
author = {Kaul, A and Souque, C and Holland, M and Baym, M},
title = {Genomic resistance in historical clinical isolates increased in frequency and mobility after the age of antibiotics.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2025.01.16.633422},
pmid = {39868160},
issn = {2692-8205},
abstract = {UNLABELLED: Antibiotic resistance is frequently observed shortly after the clinical introduction of an antibiotic. Whether and how frequently that resistance occurred before the introduction is harder to determine, as isolates could not have been tested for resistance before an antibiotic was discovered. Historical collections, like the British National Collection of Type Cultures (NCTC), stretching back to 1885, provide a window into this history. Here we match 1,817 sequenced high-quality genomes from the NCTC collection to their respective year of isolation to study resistance genes before and concurrent with the age of antibiotics. Concordant with previous work, we find resistance genes in both pathogens and environmental samples before the age of antibiotics. While generally rare before the introduction of an antibiotic, we find an associated increase in frequency with antibiotic introduction. Finally, we observe a trend of resistance elements becoming both increasingly mobile and nested within multiple mobile elements as time goes on. More broadly, our findings suggest that likely-functional antibiotic resistance genes were circulating in clinically relevant isolates before the age of antibiotics, but human usage is associated with increasing both their overall prevalence and mobility.

DATA SUMMARY: Genome assemblies downloaded and analyzed are in Supplementary Table 1, and computational tools used are found in the Methods. The authors confirm all supporting data, code and protocols have been provided within the article or through supplementary data files.

IMPACT STATEMENT: Historical collections of microbial isolates enable researchers to both investigate the past and identify interesting trends over time. In this study, we queried over 1,800 isolate genomes in one such collection for genomic variation linked to antibiotic resistance. We show that numerous isolates cultured before the introduction of a given antibiotic contain genomic variation linked to antibiotic resistance; however, this phenomenon remained relatively rare. We demonstrate a strong association between the year a given antibiotic was clinically introduced and a rise in prevalence of genomic resistance to that antibiotic. Finally, we show that while mobile elements are common throughout the isolates and timeframe analyzed, genomic resistance has become increasingly mobile as time has gone on. This study shows that as expected, the clinical introduction of a given antibiotic is correlated with an increase in resistance to that antibiotic but also was linked with increased mobility of genes and alleles conferring resistance. However, we note that the effect of deposition bias in the collection cannot be excluded. Our work also indicates that numerous microbial pangenomes of pathogens naturally contained genomic resistance to a given antibiotic even before anthropogenic use of that antibiotic. Taken together, we demonstrate that although human use may affect the prevalence and mobility of genomic resistance in clinical isolates; for most antibiotics, genomic resistance existed within the pangenomes of sampled pathogens prior to clinical introduction. Quantifying and understanding the impact of antibiotic introduction in the past helps us understand how the introduction of novel antibiotics can impact bacteria; allowing better reaction to novel resistant infections as they arise.},
}

@article {pmid39866568,
year = {2025},
author = {Pucci, N and Ujčič-Voortman, J and Verhoeff, AP and Mende, DR},
title = {Priority effects, nutrition and milk glycan-metabolic potential drive Bifidobacterium longum subspecies dynamics in the infant gut microbiome.},
journal = {PeerJ},
volume = {13},
number = {},
pages = {e18602},
pmid = {39866568},
issn = {2167-8359},
mesh = {Humans ; *Gastrointestinal Microbiome/physiology ; *Milk, Human/microbiology/chemistry/metabolism ; Infant ; *Bifidobacterium/metabolism/genetics ; *Bifidobacterium longum/metabolism ; Female ; *Polysaccharides/metabolism ; Infant, Newborn ; Feces/microbiology ; Metagenome ; Breast Feeding ; Male ; },
abstract = {BACKGROUND: The initial colonization of the infant gut is a complex process that defines the foundation for a healthy microbiome development. Bifidobacterium longum is one of the first colonizers of newborns' gut, playing a crucial role in the healthy development of both the host and its microbiome. However, B. longum exhibits significant genomic diversity, with subspecies (e.g., Bifidobacterium longum subsp. infantis and subsp. longum) displaying distinct ecological and metabolic strategies including differential capabilities to break down human milk glycans (HMGs). To promote healthy infant microbiome development, a good understanding of the factors governing infant microbiome dynamics is required.

METHODOLOGY: We analyzed newly sequenced gut microbiome samples of mother-infant pairs from the Amsterdam Infant Microbiome Study (AIMS) and four publicly available datasets to identify important environmental and bifidobacterial features associated with the colonization success and succession outcomes of B. longum subspecies. Metagenome-assembled genomes (MAGs) were generated and assessed to identify characteristics of B. longum subspecies in relation to early-life gut colonization. We further implemented machine learning tools to identify significant features associated with B. longum subspecies abundance.

RESULTS: B. longum subsp. longum was the most abundant and prevalent gut Bifidobacterium at one month, being replaced by B. longum subsp. infantis at six months of age. By utilizing metagenome-assembled genomes (MAGs), we reveal significant differences between and within B. longum subspecies in their potential to break down HMGs. We further combined strain-tracking, meta-pangenomics and machine learning to understand these abundance dynamics and found an interplay of priority effects, milk-feeding type and HMG-utilization potential to govern them across the first six months of life. We find higher abundances of B. longum subsp. longum in the maternal gut microbiome, vertical transmission, breast milk and a broader range of HMG-utilizing genes to promote its abundance at one month of age. Eventually, we find B. longum subsp. longum to be replaced by B. longum subsp. infantis at six months of age due to a combination of nutritional intake, HMG-utilization potential and a diminishment of priority effects.

DISCUSSION: Our results establish a strain-level ecological framework explaining early-life abundance dynamics of B. longum subspecies. We highlight the role of priority effects, nutrition and significant variability in HMG-utilization potential in determining the predictable colonization and succession trajectories of B. longum subspecies, with potential implications for promoting infant health and well-being.},
}

Humans
*Gastrointestinal Microbiome/physiology
*Milk, Human/microbiology/chemistry/metabolism
Infant
*Bifidobacterium/metabolism/genetics
*Bifidobacterium longum/metabolism
Female
*Polysaccharides/metabolism
Infant, Newborn
Feces/microbiology
Metagenome
Breast Feeding
Male

@article {pmid39860996,
year = {2025},
author = {Wang, C and Jia, X and Wei, M and Yan, J and Sun, Q and Long, S and Zheng, M and Shi, Y and Jiang, G and Zhao, Y and Huang, H and Yang, X and Gu, L and Wang, G},
title = {Discovery of Novel Diagnostic Biomarkers for Common Pathogenic Nocardia Through Pan-Genome and Comparative Genome Analysis, with Preliminary Validation.},
journal = {Pathogens (Basel, Switzerland)},
volume = {14},
number = {1},
pages = {},
pmid = {39860996},
issn = {2076-0817},
support = {2022-3-040//Beijing Public Health Experts Project/ ; KJ2022CX044//Beijing Tongzhou Municipal Science & Technology commission/ ; YH201917//Tongzhou Yunhe Project under Grant/ ; },
mesh = {*Nocardia/genetics/isolation & purification ; *Nocardia Infections/diagnosis/microbiology ; Humans ; *Genome, Bacterial/genetics ; *Biomarkers ; Genomics/methods ; },
abstract = {The aim of this study was to reveal diagnostic biomarkers of considerable importance for common pathogenic Nocardia, utilizing pan-genomic and comparative genome analysis to accurately characterize clinical Nocardia infections. In this study, complete or assembled genome sequences of common pathogenic Nocardia and closely related species were obtained from NCBI as discovery and validation sets, respectively. Genome annotation was performed using Prokka software, and pan-genomic analysis and extraction of Nocardia core genes were performed using BPGA software. Comparative genome analysis of these core genes with the validation-set gene sequences was then performed using BLAT, with a threshold of 30% amino acid coverage and identity, in order to distinguish specific core genes. Finally, candidate gene-specific primers were designed using Snapgene software and DNA samples were obtained from clinical Nocardia strains and closely related species for validation. The analysis identified eighteen core genes specific to Nocardia spp., four core genes specific to N. farcinica, and forty-six core genes specific to N. cyriacigeorgica. After rigorous clinical validation, one gene from Nocardia spp. and five genes from N. cyriacigeorgica were confirmed to have high specificity and therefore can be used as reliable biomarkers for accurate diagnosis of Nocardia infection. This pioneering research reveals diagnostic biomarkers of considerable significance, with the potential to substantially enhance the precise diagnosis of common pathogenic Nocardia infections, thereby laying the groundwork for innovative diagnostic methodologies in subsequent studies.},
}

*Nocardia/genetics/isolation & purification
*Nocardia Infections/diagnosis/microbiology
Humans
*Genome, Bacterial/genetics
*Biomarkers
Genomics/methods

@article {pmid39858976,
year = {2025},
author = {He, Y and Dykes, GE and Kanrar, S and Liu, Y and Gunther, NW and Counihan, KL and Lee, J and Capobianco, JA},
title = {Comparative Genomic Analysis of Campylobacter Plasmids Identified in Food Isolates.},
journal = {Microorganisms},
volume = {13},
number = {1},
pages = {},
pmid = {39858976},
issn = {2076-2607},
support = {Current Research Information System number 8072-42000-093//U.S. Department of Agriculture, Agricultural Research Service (USDA-ARS), National Program 108/ ; },
abstract = {Campylobacter is one of the leading bacterial causes of gastroenteritis worldwide. It frequently contaminates poultry and other raw meat products, which are the primary sources of Campylobacter infections in humans. Plasmids, known as important mobile genetic elements, often carry genes for antibiotic resistance, virulence, and self-mobilization. They serve as the main vectors for transferring genetic material and spreading resistance and virulence among bacteria. In this study, we identified 34 new plasmids from 43 C. jejuni and C. coli strains isolated from retail meat using long-read and short-read genome sequencing. Pangenomic analysis of the plasmid assemblies and reference plasmids from GenBank revealed five distinct groups, namely, pTet, pVir, mega plasmids (>80 kb), mid plasmids (~30 kb), and small plasmids (<6 kb). Pangenomic analysis identified the core and accessory genes in each group, indicating a high degree of genetic similarity within groups and substantial diversity between the groups. The pTet plasmids were linked to tetracycline resistance phenotypes in host strains. The mega plasmids carry multiple genes (e.g., aph(3')-III, type IV and VI secretion systems, and type II toxin-antitoxin systems) important for plasmid mobilization, virulence, antibiotic resistance, and the persistence of Campylobacter. Together, the identification and comprehensive genetic characterization of new plasmids from Campylobacter food isolates contributes to understanding the mechanisms of gene transfer, particularly the spread of genetic determinants of virulence and antibiotic resistance in this important pathogen.},
}

@article {pmid39858636,
year = {2025},
author = {Castillo, G and Contreras-Liza, SE and Arbizu, CI and Rodriguez-Grados, PM},
title = {Genome Sequencing Reveals the Potential of Enterobacter sp. Strain UNJFSC003 for Hydrocarbon Bioremediation.},
journal = {Genes},
volume = {16},
number = {1},
pages = {},
doi = {10.3390/genes16010089},
pmid = {39858636},
issn = {2073-4425},
support = {530//National University Toribio Rodríguez de Mendoza/ ; },
mesh = {*Biodegradation, Environmental ; *Enterobacter/genetics/metabolism ; *Genome, Bacterial ; *Phylogeny ; Polycyclic Aromatic Hydrocarbons/metabolism ; },
abstract = {Bioremediation induced by bacteria offers a promising alternative for the contamination of aromatic hydrocarbons due to their metabolic processes suitable for the removal of these pollutants, as many of them are carcinogenic molecules and dangerous to human health. Our research focused on isolating a bacterium from the rhizosphere of the tara tree with the ability to degrade polycyclic aromatic hydrocarbons, using draft genomic sequencing and computational analysis. Enterobacter sp. strain UNJFSC 003 possesses 4460 protein-coding genes, two rRNA genes, 77 tRNA genes, and a GC content of 54.38%. A taxonomic analysis of our strain revealed that it has an average nucleotide identity (ANI) of 87.8%, indicating that it is a new native Enterobacteria. Additionally, a pangenomic analysis with 15 strains demonstrated that our strain has a phylogenetic relationship with strain FDAARGOS 1428 (Enterobacter cancerogenus), with a total of 381 core genes and 4778 accessory genes. Orthologous methods predicted that strain UNJFSC 003 possesses genes with potential for use in hydrocarbon bioremediation. Genes were predicted in the sub-pathways for the degradation of homoprotocatechuate and phenylacetate, primarily located in the cytoplasm. Studies conducted through molecular modeling and docking revealed the affinity of the predicted proteins in the degradation of benzo[a]pyrene in the homoprotocatechuate sub-pathway, specifically hpcB, which has enzymatic activity as a dioxygenase, and hpcC, which functions as an aldehyde dehydrogenase. This study provides information on native strains from Lomas de Lachay with capabilities for the bioremediation of aromatic hydrocarbons and other compounds.},
}

*Biodegradation, Environmental
*Enterobacter/genetics/metabolism
*Genome, Bacterial
*Phylogeny
Polycyclic Aromatic Hydrocarbons/metabolism

@article {pmid39855357,
year = {2025},
author = {Zheng, X and Xiang, Y and Li, X and Du, X and Wang, Y and Tian, S and Xue, J and Huang, Y and Liu, H and Wang, Q and Liu, H and Wang, H and Wang, C and Yang, M and Jia, H and Wang, L and Xu, X and Song, L and Song, H and Qiu, S},
title = {An MDR Salmonella Enteritidis sublineage associated with gastroenteritis outbreaks and invasive disease in China.},
journal = {The Journal of infection},
volume = {},
number = {},
pages = {106421},
doi = {10.1016/j.jinf.2025.106421},
pmid = {39855357},
issn = {1532-2742},
abstract = {OBJECTIVES: Salmonella enterica serovar Enteritidis (S. Enteritidis) is a commonly reported pathogen which adapts to multiple hosts and causes critical disease burden at a global level. Here, we investigated a recently derived epidemic sublineage with multidrug resistance (MDR), which have caused extended time-period and cross-regional gastroenteritis outbreaks and even invasive nontyphoidal Salmonella disease (iNTS) in China.

METHODS: Whole-genome sequencing and antimicrobial resistance (AMR) testing were applied to 729 Chinese S. Enteritidis isolates in relation to gastroenteritis outbreaks, gastrointestinal-sporadic and iNTS infections, spanning 28 years (1994-2021) in China. Phylogenomic analysis was performed to explore the population structure and evolutionary history of the Chinese isolates within a global context. Molecular investigations of AMR genes, virulence factors, mobile genetic elements and pan-genomes were also performed.

RESULTS: The Chinese S. Enteritidis collections exhibited a high level of multidrug resistance (MDR), including high resistance to nalidixic acid (97.67%). Notably, the multidrug resistance rate of iNTS strains has significantly increased over the past decade. Phylogenomic analysis showed that the majority of the Chinese isolates (98.63%) were distributed in the global pandemic lineage L1, while the other lineages were highly continent-specific. Particularly, the Chinese isolates were predominantly distributed in sublineages L1.2 (37.45%) and L1.3 (59.26%), forming two main Chinese clades (MCC1&2). The most recent common ancestor of MCC1&2 dated back to 1944 and 2004, respectively. The lineage L1, especially MCC1&2, harbored the most amount of AMR determinants and virulence genes, which was mainly due to the presence of a hybrid virulence-resistance plasmid and coexistence of different types of AMR plasmids in S. Enteritidis.

CONCLUSIONS: S. Enteritidis has evolved unique clonal clusters, MCC1&2, with critical MDR in China, which phylogenetically constitute an extension of the globally epidemic lineage and were characterized by distinct genetic traits. These clades have induced extensive outbreaks of gastroenteritis and serious cases of iNTS in China, underscoring the pressing nature and severity of this public health crisis. Implementing the One-Health strategy, longstanding routine surveillance and further genomic epidemiological studies are urgently required to capture epidemics, monitor changes in bacterial populations and determine the consequent risk to global public health.},
}

@article {pmid39855107,
year = {2025},
author = {Gloanec, N and Guyard-Nicodème, M and Chemaly, M and Dory, D},
title = {Reverse vaccinology: A strategy also used for identifying potential vaccine antigens in poultry.},
journal = {Vaccine},
volume = {48},
number = {},
pages = {126756},
doi = {10.1016/j.vaccine.2025.126756},
pmid = {39855107},
issn = {1873-2518},
abstract = {Vaccination of livestock plays a major role in improving animal health, welfare and productivity, but also in public health by preventing zoonotic diseases. Advances in bioinformatics and whole-genome sequencing techniques since the 2000s have led to the development of genome-based vaccinology, called reverse vaccinology. Reverse vaccinology is a rapid and competitive strategy that uses pathogen genome sequences to screen for and identify potential vaccine antigens and, unlike conventional methods, does not require culturing the pathogenic microorganism, at least initially. Based on in silico approaches and dedicated software, reverse vaccinology has led to the identification of a wide range of proteins as putative vaccine candidates against human pathogens and has been applied more recently to several animal diseases. After a brief overview of the principle of the approach and its applications in human medicine, this review focuses on the use of reverse vaccinology for the development of vaccines specifically for poultry, a representative example of livestock vaccination, and discusses the important points to consider when using this method.},
}

@article {pmid39854309,
year = {2025},
author = {Coomber, AL and Saville, AC and Carbone, I and Martin, M and Bieker, VC and Ristaino, JB},
title = {A pangenome analysis reveals the center of origin and evolutionary history of Phytophthora infestans and 1c clade species.},
journal = {PloS one},
volume = {20},
number = {1},
pages = {e0314509},
doi = {10.1371/journal.pone.0314509},
pmid = {39854309},
issn = {1932-6203},
mesh = {*Phytophthora infestans/genetics/classification ; *Phylogeny ; *Evolution, Molecular ; South America ; Genetic Variation ; Mexico ; },
abstract = {We examined the evolutionary history of Phytophthora infestans and its close relatives in the 1c clade. We used whole genome sequence data from 69 isolates of Phytophthora species in the 1c clade and conducted a range of genomic analyses including nucleotide diversity evaluation, maximum likelihood trees, network assessment, time to most recent common ancestor and migration analysis. We consistently identified distinct and later divergence of the two Mexican Phytophthora species, P. mirabilis and P. ipomoeae, from P. infestans and other 1c clade species. Phytophthora infestans exhibited more recent divergence from other 1c clade species of Phytophthora from South America, P. andina and P. betacei. Speciation in the 1c clade and evolution of P. infestans occurred in the Andes. P. andina-P. betacei-P. infestans formed a species complex with indistinct species boundaries, hybridizations between the species, and short times to common ancestry. Furthermore, the distinction between modern Mexican and South American P. infestans proved less discrete, suggesting gene flow between populations over time. Admixture analysis indicated a complex relationship among these populations, hinting at potential gene flow across these regions. Historic P. infestans, collected from 1845-1889, were the first to diverge from all other P. infestans populations. Modern South American populations diverged next followed by Mexican populations which showed later ancestry. Both populations were derived from historic P. infestans. Based on the time of divergence of P. infestans from its closest relatives, P. andina and P. betacei in the Andean region, we consider the Andes to be the center of origin of P. infestans, with modern globalization contributing to admixture between P. infestans populations today from Mexico, the Andes and Europe.},
}

*Phytophthora infestans/genetics/classification
*Phylogeny
*Evolution, Molecular
South America
Genetic Variation
Mexico

@article {pmid39849617,
year = {2025},
author = {Yu, X and Qu, M and Wu, P and Zhou, M and Lai, E and Liu, H and Guo, S and Li, S and Yao, X and Gao, L},
title = {Super pan-genome reveals extensive genomic variations associated with phenotypic divergence in Actinidia.},
journal = {Molecular horticulture},
volume = {5},
number = {1},
pages = {4},
pmid = {39849617},
issn = {2730-9401},
support = {32170395//National Natural Science Foundation of China/ ; 32070377//National Natural Science Foundation of China/ ; 2024AFA035//Natural Science Foundation of Hubei Province/ ; },
abstract = {Kiwifruit is an economically and nutritionally important horticultural fruit crop worldwide. The genomic data of several kiwifruit species have been released, providing an unprecedented opportunity for pan-genome analysis to comprehensively investigate the inter- and intra-species genetic diversity and facilitate utilization for kiwifruit breeding. Here, we generated a kiwifruit super pan-genome using 15 high-quality assemblies of eight Actinidia species. For gene-based pan-genome, a total of 61,465 gene families were identified, and the softcore and dispensable genes were enriched in biological processes like response to endogenous stimulus, response to hormone and cell wall organization or biogenesis. Then, structural variations (SVs) against A. chinensis 'Donghong' were identified and then used to construct a graph-based genome. Further population-scale SVs based on resequencing data from 112 individuals of 20 species revealed extensive SVs which probably contributed to the phenotypic diversity among the Actinidia species. SV hotspot regions were found contributed to environmental adaptation. Furthermore, we systematically identified resistance gene analogs (RGAs) in the 15 assemblies and generated a pan-RGA dataset to reveal the diversity of genes potentially involved in disease resistance in Actinidia. The pan-genomic data obtained here is useful for evolutionary and functional genomic studies in Actinidia, and facilitates breeding design.},
}

@article {pmid39843749,
year = {2025},
author = {Cheng, L and Wang, N and Bao, Z and Zhou, Q and Guarracino, A and Yang, Y and Wang, P and Zhang, Z and Tang, D and Zhang, P and Wu, Y and Zhou, Y and Zheng, Y and Hu, Y and Lian, Q and Ma, Z and Lassois, L and Zhang, C and Lucas, WJ and Garrison, E and Stein, N and Städler, T and Zhou, Y and Huang, S},
title = {Leveraging a phased pangenome for haplotype design of hybrid potato.},
journal = {Nature},
volume = {},
number = {},
pages = {},
pmid = {39843749},
issn = {1476-4687},
abstract = {The tetraploid genome and clonal propagation of the cultivated potato (Solanum tuberosum L.)[1,2] dictate a slow, non-accumulative breeding mode of the most important tuber crop. Transitioning potato breeding to a seed-propagated hybrid system based on diploid inbred lines has the potential to greatly accelerate its improvement[3]. Crucially, the development of inbred lines is impeded by manifold deleterious variants; explaining their nature and finding ways to eliminate them is the current focus of hybrid potato research[4-10]. However, most published diploid potato genomes are unphased, concealing crucial information on haplotype diversity and heterozygosity[11-13]. Here we develop a phased potato pangenome graph of 60 haplotypes from cultivated diploids and the ancestral wild species, and find evidence for the prevalence of transposable elements in generating structural variants. Compared with the linear reference, the graph pangenome represents a broader diversity (3,076 Mb versus 742 Mb). Notably, we observe enhanced heterozygosity in cultivated diploids compared with wild ones (14.0% versus 9.5%), indicating extensive hybridization during potato domestication. Using conservative criteria, we identify 19,625 putatively deleterious structural variants (dSVs) and reveal a biased accumulation of deleterious single nucleotide polymorphisms (dSNPs) around dSVs in coupling phase. Based on the graph pangenome, we computationally design ideal potato haplotypes with minimal dSNPs and dSVs. These advances provide critical insights into the genomic basis of clonal propagation and will guide breeders to develop a suite of promising inbred lines.},
}

@article {pmid39842315,
year = {2025},
author = {Zhao, Y and Xie, J and Yu, S and Wu, Q and Wang, Z and Shang, Y and Wang, Z and Zhang, J and Zhai, H and Huang, Z and Ding, Y and Wang, J},
title = {A novel method of species-specific molecular target mining and accurate discrimination of Bacillus cereus sensu lato.},
journal = {International journal of food microbiology},
volume = {431},
number = {},
pages = {111068},
doi = {10.1016/j.ijfoodmicro.2025.111068},
pmid = {39842315},
issn = {1879-3460},
abstract = {Bacillus cereus, a member of the Bacillus cereus sensu lato (B. cereus s.l.), is widely distributed in nature and can contaminate a variety of foods, leading to foodborne illnesses and substantial losses in the food industry. Although culture-based methods remain the gold standard for identifying B. cereus due to their high sensitivity under specific conditions, they are often complex and labor-intensive to implement. Furthermore, the high genetic similarity among certain members of the B. cereus s.l. makes it challenging to identify species-specific molecular targets, hindering the rapid and accurate differentiation of these bacteria. In this study, we introduce a novel method, comparative analysis based on whole genome slices (CAWGS), combined with the Basic Local Alignment Search Tool (BLAST) for efficient molecular target mining. Using CAWGS-BLAST and pan-genome analysis, we successfully identified new molecular targets for B. cereus, Bacillus thuringiensis, emetic B. cereus, Bacillus anthracis, Bacillus mycoides, Bacillus weihenstephanensis, and Bacillus megaterium. Based on these newly discovered targets, we developed a PCR-CRISPR/Cas12a method for detecting B. cereus s.l. and related species. Our research not only provides a rapid and accurate approach for discriminating B. cereus s.l. and related species, but also offers a universal and valuable reference for detecting foodborne pathogens, especially those with highly similar phenotypic and genetic characteristics.},
}

@article {pmid39838887,
year = {2025},
author = {Cohen, ZP and Perkin, LC and Raszick, TJ and Sim, SB and Geib, SM and Childers, AK and Sword, GA and Suh, CP},
title = {Pangenomics Links Boll Weevil Divergence With Ancient Mesoamerican Cotton Cultivation.},
journal = {Molecular ecology resources},
volume = {},
number = {},
pages = {e14054},
doi = {10.1111/1755-0998.14054},
pmid = {39838887},
issn = {1755-0998},
support = {16-352//Cotton Incorporated/ ; 3091//USDA CRIS/ ; -22000-038-00D//USDA CRIS/ ; },
abstract = {The boll weevil, Anthonomus grandis grandis Boheman, and thurberia weevil, Anthonomus grandis thurberiae Pierce, together comprise a species complex that ranges throughout Mexico, the southwestern regions of the United States and parts of South America. The boll weevil is a historically damaging and contemporaneously threatening pest to commercial upland cotton, Gossypium hirsutum L. (Malvales: Malvaceae), whereas the thurberia weevil is regarded as an innocuous non-pest subspecies that is mostly found on non-cultivated Thurber's or Arizona cotton, Gossypium thurberi L., throughout its native range in western Mexico and the southwestern United States. Recent independent analyses, using mitochondrial and whole-genome markers, have suggested the independent evolution of these lineages is more attributable to geographic isolation than biotic factors. We suggest a combination of drivers after employing comparative genomic, population genetic and pangenome methodologies to identify large and small polymorphisms. By leveraging genetic differences, we determined 39,310 diagnostic loci between the subspecies, find genes under selection, and model the subspecies' shared and unique evolutionary history. Interestingly, structural variations capture a large proportion of genes at the population level and demographic reconstruction suggests a split between approximately 3,320-16,300 before present (YBP), which coincides with cotton cultivation in Mesoamerica, approximately 3,000-5,000 YBP. Observed polymorphisms are enriched for reproductive, regulatory, and metabolic genes, which may be attributed to the subspecies split and coevolution with cultivated cotton. Our results demonstrate the utility of a holistic, comparative framework utilising small and large polymorphisms to reconstruct demography and identify genetic novelty via pangenomics.},
}

@article {pmid39838784,
year = {2025},
author = {Sun, T and Song, J and Luo, J and Jiang, Y and Tan, D and Zhou, L and Wu, W and Han, M and Hu, H and Tong, X and Lu, C and Dai, F},
title = {Dysfunction of a lepidopteran conserved gene, BmBLOC1S6, causes a translucent larval integument in the silkworm, Bombyx mori.},
journal = {Pest management science},
volume = {},
number = {},
pages = {},
doi = {10.1002/ps.8664},
pmid = {39838784},
issn = {1526-4998},
support = {//Funds of China Agriculture Research System of MOF and MARA (No. CARS-18-ZJ0102)/ ; //National Natural Science Foundation of China (Grant Nos. 32330102, U20A2058, 31830094, and 32272939)/ ; //Natural Science Foundation of Chongqing, China (Grant no. cstc2021jcyj-cxttX0005)/ ; },
abstract = {BACKGROUND: Diverse lepidopteran insects cause serious damage to plants, and their larvae possess a crucial epidermal barrier against environmental stimuli. Their ultraviolet (UV) resistance is enhanced by accumulating uric acid granules in the epidermis, suggesting that genes involved in this process may be potential targets for lepidopteran pest management.

RESULTS: The silkworm pan-genome dataset is a valuable source for studying genomic mutations and phenotype-genotype associations. Hoarfrost translucent (oh) is a recessive silkworm mutant with a translucent larval integument. Using comparative genomic analysis, we found that the oh mutant has an 828-bp deletion in the BmBLOC1S6 genome. BmBLOC1S6 encodes a BLOC-1 complex subunit and is conserved during lepidopteran evolution. Knockout of BmBLOC1S6 replicated the oh phenotype. Furthermore, BmBLOC1S6 knockout and oh larvae are more sensitive to UV irradiation compared to the wild-type. These results revealed that BmBLOC1S6 is essential in forming uric acid granules for silkworm epidermal UV resistance.

CONCLUSION: Our results showed that BmBLOC1S6 is responsible for the oh phenotype in silkworms and is conserved during lepidopteran evolution. This study may help us better clarify uric acid granules formation in the epidermis, explore their function in UV resistance and identify a potential molecular target for lepidopteran pest control. © 2025 Society of Chemical Industry.},
}

@article {pmid39836460,
year = {2025},
author = {Lao, HY and Wong, AYP and Ng, TT and Wong, RY and Yau, MC and Lam, JY and Siu, GK},
title = {Scrofimicrobium appendicitidis sp. nov., isolated from a patient with ruptured appendicitis.},
journal = {International journal of systematic and evolutionary microbiology},
volume = {75},
number = {1},
pages = {},
doi = {10.1099/ijsem.0.006633},
pmid = {39836460},
issn = {1466-5034},
mesh = {*Appendicitis/microbiology ; *RNA, Ribosomal, 16S/genetics ; *Phylogeny ; Humans ; *DNA, Bacterial/genetics ; *Base Composition ; *Bacterial Typing Techniques ; *Sequence Analysis, DNA ; Genome, Bacterial ; Retrospective Studies ; Actinomycetaceae/genetics/isolation & purification/classification ; Male ; },
abstract = {A clinical isolate, R131, was isolated from the peritoneal swab of a patient who suffered from ruptured appendicitis with abscess and gangrene in Hong Kong in 2018. Cells are facultatively anaerobic, non-motile, Gram-positive coccobacilli. Colonies were small, grey, semi-translucent, low convex and alpha-haemolytic. The bacterium grew on blood agar but not on Brain Heart Infusion (BHI) and Mueller-Hinton agars. It was negative for catalase, oxidase, indole and aesculin hydrolysis. The initial identification attempts via matrix-assisted laser desorption ionization-time of flight mass spectrometry and 16S rRNA gene sequencing yielded inconclusive results. The 16S rRNA gene analysis showed that R131 shared >99% nucleotide identity with certain uncultured Actinomycetales bacteria. In this retrospective investigation, a complete genome of R131 was constructed, disclosing a DNA G+C content of 64%. Phylogenetic analysis showed that the bacterium was mostly related to Scrofimicrobium canadense WB03_NA08, which was first described in 2020. However, its 16S rRNA gene shared only 94.15% nucleotide identity with that of S. canadense WB03_NA08. Notably, the orthoANI between R131 and S. canadense WB03_NA08 was 67.81%. A pan-genome analysis encompassing R131 and 4 Scrofimicrobium genomes showed 986 core gene clusters shared with the Scrofimicrobium species, along with 601 cloud genes. The average nucleotide identity comparisons within the pan-genome analysis ranged from 59.78 to 62.51% between R131 and the other Scrofimicrobium species. Correspondingly, the dDDH values ranged from 19.20 to 22.30%, while the POCP values spanned from 57.48 to 60.94%. Therefore, a novel species, Scrofimicrobium appendicitidis sp. nov., is proposed. The type strain is R131[T] (=JCM 36615[T]=LMG 33627[T]).},
}

*Appendicitis/microbiology
*RNA, Ribosomal, 16S/genetics
*Phylogeny
Humans
*DNA, Bacterial/genetics
*Base Composition
*Bacterial Typing Techniques
*Sequence Analysis, DNA
Genome, Bacterial
Retrospective Studies
Actinomycetaceae/genetics/isolation & purification/classification
Male

@article {pmid39833680,
year = {2025},
author = {Sbissi, I and Chouikhi, F and Ghodhbane-Gtari, F and Gtari, M},
title = {Ecogenomic insights into the resilience of keystone Blastococcus Species in extreme environments: a comprehensive analysis.},
journal = {BMC genomics},
volume = {26},
number = {1},
pages = {51},
pmid = {39833680},
issn = {1471-2164},
mesh = {*Extreme Environments ; Genome, Bacterial ; Phylogeny ; Genomics/methods ; Ecosystem ; Adaptation, Physiological/genetics ; Metals, Heavy/toxicity ; Biodegradation, Environmental ; Soil Microbiology ; },
abstract = {BACKGROUND: The stone-dwelling genus Blastococcus plays a key role in ecosystems facing extreme conditions such as drought, salinity, alkalinity, and heavy metal contamination. Despite its ecological significance, little is known about the genomic factors underpinning its adaptability and resilience in such harsh environments. This study investigates the genomic basis of Blastococcus's adaptability within its specific microniches, offering insights into its potential for biotechnological applications.

RESULTS: Comprehensive pangenome analysis revealed that Blastococcus possesses a highly dynamic genetic composition, characterized by a small core genome and a large accessory genome, indicating significant genomic plasticity. Ecogenomic assessments highlighted the genus's capabilities in substrate degradation, nutrient transport, and stress tolerance, particularly on stone surfaces and archaeological sites. The strains also exhibited plant growth-promoting traits, enhanced heavy metal resistance, and the ability to degrade environmental pollutants, positioning Blastococcus as a candidate for sustainable agriculture and bioremediation. Interestingly, no correlation was found between the ecological or plant growth-promoting traits (PGPR) of the strains and their isolation source, suggesting that these traits are not linked to their specific environments.

CONCLUSIONS: This research highlights the ecological and biotechnological potential of Blastococcus species in ecosystem health, soil fertility improvement, and stress mitigation strategies. It calls for further studies on the adaptation mechanisms of the genus, emphasizing the need to validate these findings through wet lab experiments. This study enhances our understanding of microbial ecology in extreme environments and supports the use of Blastococcus in environmental management, particularly in soil remediation and sustainable agricultural practices.},
}

*Extreme Environments
Genome, Bacterial
Phylogeny
Genomics/methods
Ecosystem
Adaptation, Physiological/genetics
Metals, Heavy/toxicity
Biodegradation, Environmental
Soil Microbiology

@article {pmid39833199,
year = {2025},
author = {Sivarajan, V and Ganesh, AV and Subramani, P and Ganesapandi, P and Sivanandan, RN and Prakash, S and Manikandan, N and Dharmarajan, A and Arfuso, F and Warrier, S and Raj, M and Perumal, K},
title = {Prevalence and genomic insights of carbapenem resistant and ESBL producing Multidrug resistant Escherichia coli in urinary tract infections.},
journal = {Scientific reports},
volume = {15},
number = {1},
pages = {2541},
pmid = {39833199},
issn = {2045-2322},
mesh = {*Urinary Tract Infections/microbiology/drug therapy ; Humans ; *Drug Resistance, Multiple, Bacterial/genetics ; *Escherichia coli/genetics/drug effects/isolation & purification ; *Escherichia coli Infections/microbiology/drug therapy/epidemiology ; *beta-Lactamases/genetics ; *Carbapenems/pharmacology ; Prevalence ; *Anti-Bacterial Agents/pharmacology ; Microbial Sensitivity Tests ; Whole Genome Sequencing/methods ; Female ; Male ; Middle Aged ; Adult ; Genome, Bacterial ; Aged ; Genomics/methods ; Phylogeny ; Young Adult ; Adolescent ; Child ; },
abstract = {Urinary tract infections are a common condition affecting people globally, with multidrug-resistant (MDR) Escherichia coli (E. coli) being a major causative agent. Antimicrobial susceptibility profiling was performed using the VITEK 2 automated system for 1254 E. coli isolates, revealing that 831(66.2%) isolates were determined as MDR E. coli. A significant resistance pattern was observed for nalidixic acid (86.04%), ampicillin (74.16%), ticarcillin (70.73%), cefalotin (65.23%), cefixime (62.68%), ciprofloxacin (55.18%), ceftriaxone (53.75%), amoxicillin-clavulanic acid (22.81%), ertapenem (7.18%), and fosfomycin (2.23%). Whole Genome Sequencing of Carbapenem-resistant E. coli (CREC)-CREC 3 (ST405), CREC 4 (ST448), and CREC 5 (ST167) was performed to determine genomic characteristics. CREC 3, CREC 4, and CREC 5 belong to the phylogroup D, B1, and A, respectively. The NDM-5 gene was common in all three isolates, with CTX-M-15 being present in CREC 3 and CREC 4. Virulence factors of CREC 3 (fliC, shuA), CREC 4 (spaS), CREC 5 (iucA, papH, papG, iucB, yigF), and plasmids (IncFIA, IncFIB) were identified to be significant. The use of pangenome analysis enhances our understanding of resistance traits of isolates ST167, ST405, and ST448, offering valuable insights into comparative genomics of uropathogenic MDR E. coli.},
}

*Urinary Tract Infections/microbiology/drug therapy
Humans
*Drug Resistance, Multiple, Bacterial/genetics
*Escherichia coli/genetics/drug effects/isolation & purification
*Escherichia coli Infections/microbiology/drug therapy/epidemiology
*beta-Lactamases/genetics
*Carbapenems/pharmacology
Prevalence
*Anti-Bacterial Agents/pharmacology
Microbial Sensitivity Tests
Whole Genome Sequencing/methods
Female
Male
Middle Aged
Adult
Genome, Bacterial
Aged
Genomics/methods
Phylogeny
Young Adult
Adolescent
Child

@article {pmid39829883,
year = {2025},
author = {Beebe, MA and Paredes-Sabja, D and Kociolek, LK and Rodríguez, C and Sorg, JA},
title = {Phenotypic analysis of various Clostridioides difficile ribotypes reveals consistency among core processes.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2025.01.10.632434},
pmid = {39829883},
issn = {2692-8205},
abstract = {UNLABELLED: Clostridioides difficile infections (CDI) cause almost 300,000 hospitalizations per year of which ∼15-30% are the result of recurring infections. The prevalence and persistence of CDI in hospital settings has resulted in an extensive collection of C. difficile clinical isolates and their classification, typically by ribotype. While much of the current literature focuses on one or two prominent ribotypes (e.g ., RT027), recent years have seen several other ribotypes dominate the clinical landscape (e.g. , RT106 and RT078). Some ribotypes are associated with severe disease and / or increased recurrence rates, but why are certain ribotypes more prominent or harmful than others remains unknown. Because C. difficile has a large, open pan-genome, this observed relationship between ribotype and clinical outcome could be a result of the genetic diversity of C. difficile . Thus, we hypothesize that core biological processes of C. difficile are conserved across ribotypes / clades. We tested this hypothesis by observing the growth kinetics, sporulation, germination, bile acid sensitivity, bile salt hydrolase activity, and surface motility of fifteen strains belonging to various ribotypes spanning each known C. difficile clade. In viewing these phenotypes across each strain, we see that core phenotypes (growth, germination, sporulation, and resistance to bile salt toxicity) are remarkably consistent across clades / ribotypes. This suggests that variations observed in the clinical setting may be due to unidentified factors in the accessory genome or due to unknown host-factors.

IMPORTANCE: C. difficile infections impact thousands of individuals every year many of whom experience recurring infections. Clinical studies have reported an unexplained correlation between some clades / ribotypes of C. difficile and disease severity / recurrence. Here, we demonstrate that C. difficile strains across the major clades / ribotypes are consistent in their core phenotypes. This suggests that such phenotypes are not responsible for variations in disease severity / recurrence and are ideal targets for the development of therapeutics meant to treat C. difficile related infections.},
}

@article {pmid39829834,
year = {2025},
author = {Frias-De-Diego, A and Jara, M and Lanzas, C},
title = {Influence of Sequencing Technology on Pangenome-level Analysis and Detection of Antimicrobial Resistance Genes in ESKAPE Pathogens.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2025.01.08.631980},
pmid = {39829834},
issn = {2692-8205},
abstract = {UNLABELLED: As sequencing costs decrease, short-read and long-read technologies are indispensable tools for uncovering the genetic drivers behind bacterial pathogen resistance. This study explores the differences between the use of short-read (Illumina) and long-read (Oxford Nanopore Technologies, ONT) sequencing in detecting antimicrobial resistance (AMR) genes in ESKAPE pathogens (Enterococcus faecium, Staphylococcus aureus, Klebsiella pneumoniae, Acinetobacter baumannii, Pseudomonas aeruginosa, and Enterobacter cloacae). Utilizing a dataset of 1,385 whole genome sequences and applying commonly used bioinformatic methods in bacterial genomics, we assessed the differences in genomic completeness, pangenome structure, and AMR gene and point mutation identification. Illumina presented higher genome completeness, while ONT identified a broader pangenome. Hybrid assembly outperformed both Illumina and ONT at identifying key AMR genetic determinants, presented results closer to Illumina's completeness, and revealed ONT-like pangenomic content. Notably, Illumina consistently detected more AMR-related point mutations than its counterparts. This highlights the importance of method selection based on research goals. Differences were also observed for specific gene classes and bacterial species, underscoring the need for a nuanced understanding of technology limitations. Overall, this study reveals the strengths and limitations of each approach, advocating for the use of Illumina for common AMR analysis; ONT for studying complex genomes and novel species, and hybrid assembly for a more comprehensive characterization, leveraging the benefits of both technologies.

IMPACT STATEMENT: This study provides a comprehensive comparison of short-read (Illumina) and long-read (Oxford Nanopore Technologies, ONT) sequencing technologies in the context of antimicrobial resistance (AMR) detection in ESKAPE pathogens. By analyzing a large dataset of 1,385 whole genome sequences, the research offers valuable insights into the strengths and limitations of each approach, as well as the benefits of the novel approach of hybrid assembly. These findings have broad utility across microbiology, genomics, and infectious disease research. In particular, they apply to the work of researchers and clinicians dealing with AMR surveillance, investigation into outbreaks, and bacterial genome analysis. Given the nuance with which technological differences in genomic completeness, pangenome structure, and AMR determinant detection have been explored in this study, it is a good basis for informed method selection for future research. While the output represents an incremental advance, its significance lies in its practical implications. It thus enables researchers to take more reasonable decisions in designing genomic studies of bacterial pathogens by showing the complementarity of various sequencing approaches and their specific strengths. This could lead to more accurate and comprehensive detection of AMR, which would contribute ultimately to improved antibiotic stewardship and public health strategies.

DATA SUMMARY: The authors confirm all supporting data, code and protocols have been provided within the article or through supplementary data files.

REPOSITORIES: All the sequences used for this study are publicly accessible from GenBank, and their individual IDs are disclosed in Supplementary Table 1.},
}

@article {pmid39828703,
year = {2025},
author = {Zhao, Q and Yin, Z and Hou, Z},
title = {Near telomere-to-telomere genome assemblies of Silkie Gallus gallus and Mallard Anas platyrhynchos restored the structure of chromosomes and "missing" genes in birds.},
journal = {Journal of animal science and biotechnology},
volume = {16},
number = {1},
pages = {9},
pmid = {39828703},
issn = {1674-9782},
abstract = {BACKGROUND: Chickens and ducks are vital sources of animal protein for humans. Recent pangenome studies suggest that a single genome is insufficient to represent the genetic information of a species, highlighting the need for more comprehensive genomes. The bird genome has more than tens of microchromosomes, but comparative genomics, annotations, and the discovery of variations are hindered by inadequate telomere-to-telomere level assemblies. We aim to complete the chicken and duck genomes, recover missing genes, and reveal common and unique chromosomal features between birds.

RESULTS: The near telomere-to-telomere genomes of Silkie Gallus gallus and Mallard Anas platyrhynchos were successfully assembled via multiple high-coverage complementary technologies, with quality values of 36.65 and 44.17 for Silkie and Mallard, respectively; and BUSCO scores of 96.55% and 96.97% for Silkie and Mallard, respectively; the mapping rates reached over 99.52% for both assembled genomes, these evaluation results ensured high completeness and accuracy. We successfully annotated 20,253 and 19,621 protein-coding genes for Silkie and Mallard, respectively, and assembled gap-free sex chromosomes in Mallard for the first time. Comparative analysis revealed that microchromosomes differ from macrochromosomes in terms of GC content, repetitive sequence abundance, gene density, and levels of 5mC methylation. Different types of arrangements of centromeric repeat sequence centromeres exist in both Silkie and the Mallard genomes, with Mallard centromeres being invaded by CR1. The highly heterochromatic W chromosome, which serves as a refuge for ERVs, contains disproportionately long ERVs. Both Silkie and the Mallard genomes presented relatively high 5mC methylation levels on sex chromosomes and microchromosomes, and the telomeres and centromeres presented significantly higher 5mC methylation levels than the whole genome. Finally, we recovered 325 missing genes via our new genomes and annotated TNFA in Mallard for the first time, revealing conserved protein structures and tissue-specific expression.

CONCLUSIONS: The near telomere-to-telomere assemblies in Mallard and Silkie, with the first gap-free sex chromosomes in ducks, significantly enhanced our understanding of genetic structures in birds, specifically highlighting the distinctive chromosome features between the chicken and duck genomes. This foundational work also provides a series of newly identified missing genes for further investigation.},
}

@article {pmid39827750,
year = {2025},
author = {Galasong, Y and Kijpatanasilp, I and Çobo, M and Asadatorn, N and Wang, R and Assatarakul, K and Worobo, RW},
title = {Spoilage investigation of pasteurized apple juice with visual defects identifies a potentially novel Acetobacter species as the primary spoilage agent.},
journal = {International journal of food microbiology},
volume = {430},
number = {},
pages = {111056},
doi = {10.1016/j.ijfoodmicro.2025.111056},
pmid = {39827750},
issn = {1879-3460},
abstract = {Jellified materials were observed in spoiled pasteurized apple juice that contained dimethyl dicarbonate (DMDC). Microbiological analysis showed a high microbial load (4-5 log CFU/mL) in the sample. Acetobacter spp. was identified as the spoilage microorganism by 16S rRNA gene sequencing. Metataxonomic analysis showed Acetobacter represented 99 % of the bacterial community. Three Acetobacter isolates (LX5, LX9 and LX16) were selected for whole genome sequencing and characterized for their susceptibility to DMDC. Genome-based phylogeny supported the species-level classification of LX5 as A. fabarum. It also suggested LX9 and LX16 are the same microorganisms from a potentially novel species closely related to A. lovaniensis. The minimum inhibitory concentrations (MICs) of DMDC for Acetobacter isolates in sterile apple juice (pH ∼3) at 30 °C were 46 ppm and 329 ppm for A. fabarum LX5 and Acetobacter LX9/LX16, respectively. The minimum bactericidal concentrations (MBCs) were 250 and 500 ppm for A. fabarum LX5 and Acetobacter LX9/LX16, respectively. The inoculum concentration for the MIC assay was approximately 6 log10 CFU/mL, representing the "worst-case" scenario. When the contamination level was reduced to 500 CFU/mL per US federal regulation (21 CFR 172.133) and the apple juice was refrigerated, Acetobacter isolates did not grow and were completely inhibited by 238 ppm DMDC. Pangenome analysis identified gene clusters that potentially play a role in biofilm development, carbohydrate metabolism, and oxidative stress tolerance, but it also ruled out the involvement of Acetobacter in apple juice gel formation. The investigation concluded that post-pasteurization contamination, high microbial load and ambient storage were factors leading to this spoilage incident.},
}

@article {pmid39826711,
year = {2025},
author = {Uchiyama, I and Mihara, M and Nishide, H and Chiba, H and Takayanagi, M and Kawai, M and Takami, H},
title = {MBGD: Microbial genome database for comparative analysis featuring enhanced functionality to characterize gene and genome functions through large-scale orthology analysis.},
journal = {Journal of molecular biology},
volume = {},
number = {},
pages = {168957},
doi = {10.1016/j.jmb.2025.168957},
pmid = {39826711},
issn = {1089-8638},
abstract = {Microbial Genome Database for Comparative Analysis (MBGD) is a comprehensive ortholog database encompassing published complete microbial genomes. The ortholog tables in MBGD are constructed in a hierarchical manner. The top-level ortholog table is now constructed from 1,812 genus-level pan-genomes, 6,268 species-level pan-genomes, and 34,079 genomes in total. To support analyses of newly sequenced genomes, MBGD updates MyMBGD functionality, which offers two analysis modes: assignment mode and clustering mode. Assignment mode rapidly classifies genes in the query genomes into existing MBGD ortholog groups, while clustering mode performs de novo clustering of query genomes using the DomClust program. In assignment mode, users can evaluate the presence of genomic functions, as defined in the KEGG Module database, in each query genome using the Genomaple software and compare the results across multiple genomes. To enhance this analysis, we developed a method to subdivide MBGD ortholog groups as needed to improve cross-references to the KEGG Orthology groups. Another notable feature is the phylogenetic profile search interface, which enables users to specify a set of organisms in which orthologs are present or absent (i.e., a phylogenetic profile), and search for ortholog groups with similar phylogenetic profiles. To construct a phylogenetic profile, users can search organisms by specifying phenotype, environment, taxonomy, or a particular ortholog group. MBGD is available at https://mbgd.nibb.ac.jp/.},
}

@article {pmid39826720,
year = {2025},
author = {Akhoon, BA and Qiao, Q and Stewart, A and Chen, J and Rodriguez Lopez, CM and Corbin, KR},
title = {Pangenomic analysis of the bacterial cellulose-producing genera Komagataeibacter and Novacetimonas.},
journal = {International journal of biological macromolecules},
volume = {},
number = {},
pages = {139980},
doi = {10.1016/j.ijbiomac.2025.139980},
pmid = {39826720},
issn = {1879-0003},
abstract = {Bacterial cellulose (BC) holds significant commercial potential due to its unique structural and chemical properties, making it suitable for applications in electronics, medicine, and pharmaceuticals. However, large-scale BC production remains limited by challenges in bacterial performance. In this study, we compared 79 microbial genomes from three genera-Komagataeibacter, Novacetimonas, and Gluconacetobacter-to investigate their pangenomes, genetic diversity, and evolutionary relationships. Through comparative genomic and phylogenetic analyses, we identified distinct genome compositions and evolutionary patterns that differ from previous reports. The role of horizontal gene transfer (HGT) in shaping the genetic diversity and adaptability of these bacteria was also explored. Key determinants in BC production, such as variations in the bacterial cellulose biosynthesis (bcs) operon, carbohydrate uptake genes, and carbohydrate-active enzymes, were examined. Additionally, several biosynthetic gene clusters (BGCs), including Linocin M18 and sactipeptides, which encode for antimicrobial peptides known as bacteriocins, were identified. These findings reveal new aspects of the genetic diversity in cellulose-producing bacteria and present a comprehensive genomic toolkit that will support future efforts to optimize BC production and improve microbial performance for commercial applications.},
}

@article {pmid39813779,
year = {2025},
author = {He, G and Liu, C and Wang, M},
title = {Perspectives and opportunities in forensic human, animal, and plant integrative genomics in the Pangenome era.},
journal = {Forensic science international},
volume = {367},
number = {},
pages = {112370},
doi = {10.1016/j.forsciint.2025.112370},
pmid = {39813779},
issn = {1872-6283},
abstract = {The Human Pangenome Reference Consortium, the Chinese Pangenome Consortium, and other plant and animal pangenome projects have announced the completion of pilot work aimed at constructing high-quality, haplotype-resolved reference graph genomes representative of global ethno-linguistically different populations or different plant and animal species. These graph-based, gapless pangenome references, which are enriched in terms of genomic diversity, completeness, and contiguity, have the potential for enhancing long-read sequencing (LRS)-based genomic research, as well as improving mappability and variant genotyping on traditional short-read sequencing platforms. We comprehensively discuss the advancements in pangenome-based genomic integrative genomic discoveries across forensic-related species (humans, animals, and plants) and summarize their applications in variant identification and forensic genomics, epigenetics, transcriptomics, and microbiome research. Recent developments in multiplexed array sequencing have introduced a highly efficient and programmable technique to overcome the limitations of short forensic marker lengths in LRS platforms. This technique enables the concatenation of short RNA transcripts and DNA fragments into LRS-optimal molecules for sequencing, assembly, and genotyping. The integration of new pangenome reference coordinates and corresponding computational algorithms will benefit forensic integrative genomics by facilitating new marker identification, accurate genotyping, high-resolution panel development, and the updating of statistical algorithms. This review highlights the necessity of integrating LRS-based platforms, pangenome-based study designs, and graph-based pangenome references in short-read mapping and LRS-based innovations to achieve precision forensic science.},
}

@article {pmid39812022,
year = {2025},
author = {Gamblin, J and Lambert, A and Blanquart, F},
title = {Persistent, Private and Mobile genes: a model for gene dynamics in evolving pangenomes.},
journal = {Molecular biology and evolution},
volume = {},
number = {},
pages = {},
doi = {10.1093/molbev/msaf001},
pmid = {39812022},
issn = {1537-1719},
abstract = {The pangenome of a species is the set of all genes carried by at least one member of the species. In bacteria, pangenomes can be much larger than the set of genes carried by a single organism. Many questions remain unanswered regarding the evolutionary forces shaping the patterns of presence/absence of genes in pangenomes of a given species. We introduce a new model for bacterial pangenome evolution along a species phylogeny that explicitly describes the timing of appearance of each gene in the species and accounts for three generic types of gene evolutionary dynamics: persistent genes that are present in the ancestral genome, private genes that are specific to a given clade, and mobile genes that are imported once into the gene pool and then undergo frequent horizontal gene transfers. We call this model the Persistent-Private-Mobile (PPM) model. We develop an algorithm fitting the PPM model and apply it to a dataset of 902 Salmonella enterica genomes. We show that the best fitting model is able to reproduce the global pattern of some multivariate statistics like the gene frequency spectrum and the parsimony vs. frequency plot. Moreover, the gene classification induced by the PPM model allows us to study the position of accessory genes on the chromosome depending on their category, as well as the gene functions that are most present in each category. This work paves the way for a mechanistic understanding of pangenome evolution, and the PPM model developed here could be used for dynamics-aware gene classification.},
}

@article {pmid39810189,
year = {2025},
author = {Mohite, OS and Jørgensen, TS and Booth, TJ and Charusanti, P and Phaneuf, PV and Weber, T and Palsson, BO},
title = {Pangenome mining of the Streptomyces genus redefines species' biosynthetic potential.},
journal = {Genome biology},
volume = {26},
number = {1},
pages = {9},
pmid = {39810189},
issn = {1474-760X},
mesh = {*Streptomyces/genetics/metabolism ; *Genome, Bacterial ; *Multigene Family ; Biosynthetic Pathways/genetics ; Phylogeny ; Genomics ; Synteny ; },
abstract = {BACKGROUND: Streptomyces is a highly diverse genus known for the production of secondary or specialized metabolites with a wide range of applications in the medical and agricultural industries. Several thousand complete or nearly complete Streptomyces genome sequences are now available, affording the opportunity to deeply investigate the biosynthetic potential within these organisms and to advance natural product discovery initiatives.

RESULTS: We perform pangenome analysis on 2371 Streptomyces genomes, including approximately 1200 complete assemblies. Employing a data-driven approach based on genome similarities, the Streptomyces genus was classified into 7 primary and 42 secondary Mash-clusters, forming the basis for comprehensive pangenome mining. A refined workflow for grouping biosynthetic gene clusters (BGCs) redefines their diversity across different Mash-clusters. This workflow also reassigns 2729 known BGC families to only 440 families, a reduction caused by inaccuracies in BGC boundary detections. When the genomic location of BGCs is included in the analysis, a conserved genomic structure, or synteny, among BGCs becomes apparent within species and Mash-clusters. This synteny suggests that vertical inheritance is a major factor in the diversification of BGCs.

CONCLUSIONS: Our analysis of a genomic dataset at a scale of thousands of genomes refines predictions of BGC diversity using Mash-clusters as a basis for pangenome analysis. The observed conservation in the order of BGCs' genomic locations shows that the BGCs are vertically inherited. The presented workflow and the in-depth analysis pave the way for large-scale pangenome investigations and enhance our understanding of the biosynthetic potential of the Streptomyces genus.},
}

*Streptomyces/genetics/metabolism
*Genome, Bacterial
*Multigene Family
Biosynthetic Pathways/genetics
Phylogeny
Genomics
Synteny

@article {pmid39807864,
year = {2025},
author = {Nakatsu, G and Ko, D and Michaud, M and Franzosa, EA and Morgan, XC and Huttenhower, C and Garrett, WS},
title = {Virulence factor discovery identifies associations between the Fic gene family and Fap2[+] fusobacteria in colorectal cancer microbiomes.},
journal = {mBio},
volume = {},
number = {},
pages = {e0373224},
doi = {10.1128/mbio.03732-24},
pmid = {39807864},
issn = {2150-7511},
abstract = {Fusobacterium is a bacterium associated with colorectal cancer (CRC) tumorigenesis, progression, and metastasis. Fap2 is a fusobacteria-specific outer membrane galactose-binding lectin that mediates Fusobacterium adherence to and invasion of CRC tumors. Advances in omics analyses provide an opportunity to profile and identify microbial genomic features that correlate with the cancer-associated bacterial virulence factor Fap2. Here, we analyze genomes of Fusobacterium colon tumor isolates and find that a family of post-translational modification enzymes containing Fic domains is associated with Fap2 positivity in these strains. We demonstrate that Fic family genes expand with the presence of Fap2 in the fusobacterial pangenome. Through comparative genomic analysis, we find that Fap2[+] Fusobacteriota are highly enriched with Fic gene families compared to other cancer-associated and human gut microbiome bacterial taxa. Using a global data set of CRC shotgun metagenomes, we show that fusobacterial Fic and Fap2 genes frequently co-occur in the fecal microbiomes of individuals with late-stage CRC. We further characterize specific Fic gene families harbored by Fap2[+] Fusobacterium animalis genomes and detect recombination events and elements of horizontal gene transfer via synteny analysis of Fic gene loci. Exposure of a F. animalis strain to a colon adenocarcinoma cell line increases gene expression of fusobacterial Fic and virulence-associated adhesins. Finally, we demonstrate that Fic proteins are synthesized by F. animalis as Fic peptides are detectable in F. animalis monoculture supernatants. Taken together, our study uncovers Fic genes as potential virulence factors in Fap2[+] fusobacterial genomes.IMPORTANCEAccumulating data support that bacterial members of the intra-tumoral microbiota critically influence colorectal cancer progression. Yet, relatively little is known about non-adhesin fusobacterial virulence factors that may influence carcinogenesis. Our genomic analysis and expression assays in fusobacteria identify Fic domain-containing genes, well-studied virulence factors in pathogenic bacteria, as potential fusobacterial virulence features. The Fic family proteins that we find are encoded by fusobacteria and expressed by Fusobacterium animalis merit future investigation to assess their roles in colorectal cancer development and progression.},
}

@article {pmid39805704,
year = {2025},
author = {Miao, Z and Yue, JX},
title = {Interactive visualization and interpretation of pangenome graphs by linear-reference-based coordinate projection and annotation integration.},
journal = {Genome research},
volume = {},
number = {},
pages = {},
doi = {10.1101/gr.279461.124},
pmid = {39805704},
issn = {1549-5469},
abstract = {With the increasing availability of high-quality genome assemblies, pangenome graphs emerged as a new paradigm in the genomics field for identifying, encoding, and presenting genomic variation at both population and species levels. However, it remains challenging to truly dissect and interpret pangenome graphs via biologically informative visualization. To facilitate better exploration and understanding of pangenome graphs towards novel biological insights, here we present a web-based interactive Visualization and interpretation framework for linear-Reference-projected Pangenome Graphs (VRPG). VRPG provides efficient and intuitive supports for exploring and annotating pangenome graphs along a linear-genome-based coordinate system (e.g., that of a primary linear reference genome). Moreover, VRPG offers many unique features such as in-graph path highlighting for graph-constituent input assemblies, copy number characterization for graph-embedding nodes, graph-based mapping for query sequences, all of which are highly valuable for researchers working with pangenome graphs. Additionally, VRPG enables side-by-side visualization between the graph-based pangenome representation and the conventional primary-linear-reference-genome-based feature annotations, therefore seamlessly bridging the graph and linear genomic contexts. To further demonstrate its functionality and scalability, we applied VRPG to the cutting-edge yeast and human reference pangenome graphs derived from hundreds of high-quality genome assemblies via a dedicated web portal and examined their local genome diversity in the graph contexts.},
}

@article {pmid39803467,
year = {2025},
author = {Shivakumar, VS and Langmead, B},
title = {Mumemto: efficient maximal matching across pangenomes.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2025.01.05.631388},
pmid = {39803467},
issn = {2692-8205},
abstract = {Aligning genomes into common coordinates is central to pangenome analysis and construction, but it is also computationally expensive. Multi-sequence maximal unique matches (multi-MUMs) are guideposts for core genome alignments, helping to frame and solve the multiple alignment problem. We introduce Mumemto, a tool that computes multi-MUMs and other match types across large pangenomes. Mumemto allows for visualization of synteny, reveals aberrant assemblies and scaffolds, and highlights pangenome conservation and structural variation. Mumemto computes multi-MUMs across 320 human genome assemblies (960GB) in 25.7 hours with under 800 GB of memory, and over hundreds of fungal genome assemblies in minutes. Mumemto is implemented in C++ and Python and available open-source at https://github.com/vikshiv/mumemto .},
}

@article {pmid39802740,
year = {2025},
author = {Liu, Z and Bernard, A and Wang, Y and Dirlewanger, E and Wang, X},
title = {Genomes and integrative genomic insights into the genetic architecture of main agronomic traits in the edible cherries.},
journal = {Horticulture research},
volume = {12},
number = {1},
pages = {uhae269},
pmid = {39802740},
issn = {2662-6810},
abstract = {Cherries are one of the economically important fruit crops in the Rosaceae family, Prunus genus. As the first fruits of the spring season in the northern hemisphere, their attractive appearance, intensely desirable tastes, high nutrients content, and consumer-friendly size captivate consumers worldwide. In the past 30 years, although cherry geneticists and breeders have greatly progressed in understanding the genetic and molecular basis underlying fruit quality, adaptation to climate change, and biotic and abiotic stress resistance, the utilization of cherry genomic data in genetics and molecular breeding has remained limited to date. Here, we thoroughly investigated recent discoveries in constructing genetic linkage maps, identifying quantitative trait loci (QTLs), genome-wide association studies (GWAS), and validating functional genes of edible cherries based on available de novo genomes and genome resequencing data of edible cherries. We further comprehensively demonstrated the genetic architecture of the main agronomic traits of edible cherries by methodically integrating QTLs, GWAS loci, and functional genes into the identical reference genome with improved annotations. These collective endeavors will offer new perspectives on the availability of sequence data and the construction of an interspecific pangenome of edible cherries, ultimately guiding cherry breeding strategies and genetic improvement programs, and facilitating the exploration of similar traits and breeding innovations across Prunus species.},
}

@article {pmid39802648,
year = {2025},
author = {Kan, NP and Yin, Z and Qiu, YF and Zheng, E and Chen, J and Huang, J and Du, Y},
title = {A pan-genome perspective on the evolutionary dynamics of polyphyly, virulence, and antibiotic resistance in Salmonella enterica serovar Mbandaka highlights emerging threats to public health and food safety posed by cloud gene families.},
journal = {Current research in food science},
volume = {10},
number = {},
pages = {100957},
pmid = {39802648},
issn = {2665-9271},
abstract = {Salmonella enterica serovar Mbandaka, a prevalent foodborne pathogen, poses a threat to public health but remains poorly understood. We have determined the phylogenomic tree, genetic diversity, virulence, and antimicrobial resistance (AMR) profiles on a large genomic scale to elucidate the evolutionary dynamics within the Mbandaka pan-genome. The polyphyletic nature of this serovar is characterized by two distinct phylogenetic groups and inter-serovar recombination boundaries, that potentially arising from recombination events at the H2-antigen loci. The open pan-genome exhibited a flexible gene repertoire, with numerous cloud gene families involved in virulence and AMR. Extensive gene gain and loss observed at the terminal nodes of the phylogenetic tree indicate that Mbandaka individuals have undergone frequent gene turnover. The resulting changes in virulence and AMR genes potentially pose emerging threats to public health. We explored serovar conversion due to recombination of H-antigen loci, inter-serovar divergences in gene gain and loss, prophage-mediated acquisition of virulence factors, and the role of incompatibility group plasmids in acquiring resistance determinants as key molecular mechanisms driving the pathogenicity and antibiotic resistance of Mbandaka. Our work contributes to a comprehensive understanding of the complex mechanisms of pathogenesis and the ongoing evolutionary arms race with current therapeutic approaches in serovar Mbandaka.},
}

@article {pmid39799915,
year = {2025},
author = {Yang, J and Zhang, S and Geng, L and Zhao, D and Xing, S and Ji, X and Yan, L},
title = {Comparative genomics analysis of the reason for [12]C[6+] heavy-ion irradiation in improving Fe3O4 nanoparticle yield of Acidithiobacillus ferrooxidans.},
journal = {Ecotoxicology and environmental safety},
volume = {289},
number = {},
pages = {117668},
doi = {10.1016/j.ecoenv.2025.117668},
pmid = {39799915},
issn = {1090-2414},
abstract = {The Fe3O4 nanoparticle synthesized by Acidithiobacillus ferrooxidans have a broad practical value, while the low yield limits their commercial application. Herein, we employed a [12]C[6+] heavy-ion beam to induce mutagenesis of A. ferrooxidans BYM and successfully screened a mutant BYMT-200 with a 1.36 mg/L Fe3O4 nanoparticle yield, which could stably inherit over many generations based on assessing cell magnetism and Fe3O4 nanoparticle synthesis. Comparative genome analysis detected 14 mutation sites, causing six synonymous mutations, one missense mutation, and one nonsense mutation. We further annotated the genes involved in the mutation, such as hcp, hsdM, yghU, K7B00_11365, and K7B00_11355, which are responsible for the substantial changes in the Fe3O4 nanoparticle yield of A. ferrooxidans. Additionally, we performed a pan-genome analysis to understand how these genes regulate Fe3O4 nanoparticle synthesis. The core genome of 2376 orthologous clusters was identified and visualized by progressive Mauve alignment and OrthoVenn. A total of 109 regulatory genes related to iron metabolism were identified, mainly involved in electron transport, iron acquisition, iron storage, and oxidative stress. The mutant genes are closely related to iron-sulfur clusters and oxidative stress. Accordingly, we proposed a hypothetical mechanism for increasing Fe3O4 nanoparticle production in A. ferrooxidans BYMT-200 to withstand high oxidative stress caused by heavy ion radiation. Our study offers significant theoretical guidance for further acquiring the high-yield Fe3O4 nanoparticle-producing bacteria and studying the mechanism of its synthesis.},
}

@article {pmid39799174,
year = {2025},
author = {Shin, HD and Park, W and Chai, HH and Lee, Y and Jung, J and Ko, BJ and Kim, H},
title = {Chromosome-level Genome Assembly of Korean Long-tailed Chicken and Pangenome of 40 Gallus gallus Assemblies.},
journal = {Scientific data},
volume = {12},
number = {1},
pages = {51},
pmid = {39799174},
issn = {2052-4463},
support = {PJ013341//Rural Development Administration (RDA)/ ; },
mesh = {Animals ; *Chickens/genetics ; *Genome ; *Chromosomes ; Republic of Korea ; },
abstract = {This study presents the first chromosome-level genome assembly of the Korean long-tailed chicken (KLC), a unique breed of Gallus gallus known as Ginkkoridak. Our assembly achieved a super contig N50 of 5.7 Mbp and a scaffold N50 exceeding 90 Mb, with a genome completeness of 96.3% as assessed by BUSCO using the aves_odb10 set. We also constructed a comprehensive pangenome graph, incorporating 40 Gallus gallus assemblies, including the KLC genome. This graph comprises 87,934,214 nodes, 121,720,974 edges, and a total sequence length of 1,709,850,352 bp. Notably, our KLC assembly contributed 1,919,925 bp of new sequences to the pangenome, underscoring the unique genetic makeup of this breed. Furthermore, in comparison with the pangenome, we identified 36,818 structural variants in KLC, which included 2,529 insertions, 27,743 deletions, and 6,546 of either insertions or deletions shorter than 1 kb. We also successfully identified pan-genome wide non-reference sequences. Our KLC assembly and pangenome graph provide valuable genomic resources for studying G. gallus populations.},
}

Animals
*Chickens/genetics
*Genome
*Chromosomes
Republic of Korea

@article {pmid39797734,
year = {2025},
author = {Ryu, H and Han, H and Kim, C and Kim, J},
title = {GDBr: genomic signature interpretation tool for DNA double-strand break repair mechanisms.},
journal = {Nucleic acids research},
volume = {53},
number = {2},
pages = {},
pmid = {39797734},
issn = {1362-4962},
support = {RS-2023-00247499//National Research Foundation of Korea/ ; CRC22013-300//National Research Council of Science and Technology/ ; HI22C132200//Korea Health Industry Development Institute/Republic of Korea ; //Korea Research Institute of Bioscience and Biotechnology/ ; CRC22013-300//NST grant funded by the Korea government (MSIT)/ ; },
mesh = {*DNA Breaks, Double-Stranded ; Humans ; *Software ; *Genomics/methods ; *DNA Repair/genetics ; Genome, Human ; DNA End-Joining Repair/genetics ; Homologous Recombination ; },
abstract = {Large genetic variants can be generated via homologous recombination (HR), such as polymerase theta-mediated end joining (TMEJ) or single-strand annealing (SSA). Given that these HR-based mechanisms leave specific genomic signatures, we developed GDBr, a genomic signature interpretation tool for DNA double-strand break repair mechanisms using high-quality genome assemblies. We applied GDBr to a draft human pangenome reference. We found that 78.1% of non-repetitive insertions and deletions and 11.0% of non-repetitive complex substitutions contained specific signatures. Of these, we interpreted that 98.7% and 1.3% of the insertions and deletions were generated via TMEJ and SSA, respectively, and all complex substitutions via TMEJ. Since population-level pangenome datasets are being dramatically accumulated, GDBr can provide mechanistic insights into how variants are formed. GDBr is available on GitHub at https://github.com/Chemical118/GDBr.},
}

*DNA Breaks, Double-Stranded
Humans
*Software
*Genomics/methods
*DNA Repair/genetics
Genome, Human
DNA End-Joining Repair/genetics
Homologous Recombination

@article {pmid39795357,
year = {2025},
author = {Jung, H and Han, G and Lee, D and Jung, HK and Kim, YS and Kong, HJ and Kim, YO and Seo, YS and Park, J},
title = {Understanding the Impact of Salt Stress on Plant Pathogens Through Phenotypic and Transcriptomic Analysis.},
journal = {Plants (Basel, Switzerland)},
volume = {14},
number = {1},
pages = {},
doi = {10.3390/plants14010097},
pmid = {39795357},
issn = {2223-7747},
support = {R2024019//National Institute of Fisheries Science/ ; },
abstract = {For plant diseases to become established, plant pathogens require not only virulence factors and susceptible hosts, but also optimal environmental conditions. The accumulation of high soil salinity can have serious impacts on agro-biological ecosystems. However, the interactions between plant pathogens and salinity have not been fully characterized. This study investigated the effects of salt stress on representative plant pathogens, such as Burkholderia gladioli, Burkholderia glumae, Pectobacterium carotovorum subsp. carotovorum (Pcc), Ralstonia solanacearum, and Xanthomonas oryzae pv. oryzae. Phenotypic assays revealed that B. gladioli and R. solanacearum are highly sensitive to salt stress, exhibiting significant reductions in growth, motility, and enzyme production, whereas Pcc showed notable tolerance. Pan-genome-based comparative transcriptomics identified co-downregulated patterns in B. gladioli and R. solanacearum under stress conditions, indicating the suppression of bacterial chemotaxis and type III secretion systems. Uniquely upregulated patterns in Pcc were associated with enhanced survival under high salinity, such as protein quality control, osmotic equilibrium, and iron acquisition. Additionally, the application of salt stress combined with the beneficial bacterium Chryseobacterium salivictor significantly reduced tomato wilt caused by R. solanacearum, suggesting a potential management strategy. This study underscores practical implications for effectively understanding and controlling plant pathogens under future climate changes involving salt stress.},
}

@article {pmid39794865,
year = {2025},
author = {Passarelli-Araujo, H and Venancio, TM and Hanage, WP},
title = {Relating ecological diversity to genetic discontinuity across bacterial species.},
journal = {Genome biology},
volume = {26},
number = {1},
pages = {8},
pmid = {39794865},
issn = {1474-760X},
mesh = {*Genome, Bacterial ; *Bacteria/genetics/classification ; Genetic Variation ; Phylogeny ; Mycobacterium tuberculosis/genetics ; Machine Learning ; Evolution, Molecular ; Biodiversity ; },
abstract = {BACKGROUND: Genetic discontinuity represents abrupt breaks in genomic identity among species. Advances in genome sequencing have enhanced our ability to track and characterize genetic discontinuity in bacterial populations. However, exploring the degree to which bacterial diversity exists as a continuum or sorted into discrete and readily defined species remains a challenge in microbial ecology. Here, we aim to quantify the genetic discontinuity (δ) and investigate how this metric is related to ecology.

RESULTS: We harness a dataset comprising 210,129 genomes to systematically explore genetic discontinuity patterns across several distantly related species, finding clear breakpoints which vary depending on the taxa in question. By delving into pangenome characteristics, we uncover a significant association between pangenome saturation and genetic discontinuity. Closed pangenomes are associated with more pronounced breaks, exemplified by Mycobacterium tuberculosis. Additionally, through a machine learning approach, we detect key features such as gene conservation patterns and functional annotations that significantly impact genetic discontinuity prediction.

CONCLUSIONS: Our study clarifies bacterial genetic patterns and their ecological impacts, enhancing the delineation of species boundaries and deepening our understanding of microbial diversity.},
}

*Genome, Bacterial
*Bacteria/genetics/classification
Genetic Variation
Phylogeny
Mycobacterium tuberculosis/genetics
Machine Learning
Evolution, Molecular
Biodiversity

@article {pmid39791953,
year = {2025},
author = {Huang, Y and Sahu, SK and Liu, X},
title = {Deciphering recent transposition patterns in plants through comparison of 811 genome assemblies.},
journal = {Plant biotechnology journal},
volume = {},
number = {},
pages = {},
doi = {10.1111/pbi.14570},
pmid = {39791953},
issn = {1467-7652},
abstract = {Transposable elements (TEs) are significant drivers of genome evolution, yet their recent dynamics and impacts within and among species, as well as the roles of host genes and non-coding RNAs in the transposition process, remain elusive. With advancements in large-scale pan-genome sequencing and the development of open data sharing, large-scale comparative genomics studies have become feasible. Here, we performed complete de novo TE annotations and identified active TEs in 310 plant genome assemblies across 119 species and seven crop populations. Using 811 high-quality genomes, we detected 13 844 553 TE-induced structural variants (TE-SVs), providing unprecedented resolution in delineating recent TE activities. Our integrative analysis revealed a mutual evolutionary relationship between TEs and host genomes. On one hand, host genes and ncRNAs are involved in the transposition process, as evidenced by their colocalization and coactivation with TEs, and may play a role in chromatin regulation. On the other hand, TEs drive genetic innovation by promoting the duplication of host genes and inserting into regulatory regions. Moreover, genes influenced by active TEs are linked to plant growth, nutrient absorption, storage metabolism and environmental adaptation, aiding in crop domestication and adaptation. This TE dynamics atlas not only reveals evolutionary and functional features linked to transposition activity but also highlights the role of TEs in crop domestication and adaptation, paving the way for future exploration of TE-mediated genome evolution and crop improvement strategies.},
}

@article {pmid39789611,
year = {2025},
author = {Chen, W and Xie, Q and Fu, J and Li, S and Shi, Y and Lu, J and Zhang, Y and Zhao, Y and Ma, R and Li, B and Zhang, B and Grierson, D and Yu, M and Fei, Z and Chen, K},
title = {Graph pangenome reveals the regulation of malate content in blood-fleshed peach by NAC transcription factors.},
journal = {Genome biology},
volume = {26},
number = {1},
pages = {7},
pmid = {39789611},
issn = {1474-760X},
mesh = {*Malates/metabolism ; *Prunus persica/genetics/metabolism ; *Transcription Factors/metabolism/genetics ; *Fruit/genetics/metabolism ; *Plant Proteins/genetics/metabolism ; *Genome, Plant ; Gene Expression Regulation, Plant ; Genome-Wide Association Study ; Promoter Regions, Genetic ; },
abstract = {BACKGROUND: Fruit acidity and color are important quality attributes in peaches. Although there are some exceptions, blood-fleshed peaches typically have a sour taste. However, little is known about the genetic variations linking organic acid and color regulation in peaches.

RESULTS: Here, we report a peach graph-based pangenome constructed from sixteen individual genome assemblies, capturing abundant structural variations and 82.3 Mb of sequences absent in the reference genome. Pangenome analysis reveals a long terminal repeat retrotransposon insertion in the promoter of the NAC transcription factor (TF) PpBL in blood-fleshed peaches, which enhances PpBL expression. Genome-wide association study identifies a significant association between PpBL and malate content. Silencing PpBL in peach fruit and ectopic overexpression of PpBL in tomatoes confirm that PpBL is a positive regulator of malate accumulation. Furthermore, we demonstrate that PpBL works synergistically with another NAC TF, PpNAC1, to activate the transcription of the aluminum-activated malate transporter PpALMT4, leading to increased malate content.

CONCLUSIONS: These findings, along with previous research showing that PpBL and PpNAC1 also regulate anthocyanin accumulation, explain the red coloration and sour taste in blood-fleshed peach fruits.},
}

*Malates/metabolism
*Prunus persica/genetics/metabolism
*Transcription Factors/metabolism/genetics
*Fruit/genetics/metabolism
*Plant Proteins/genetics/metabolism
*Genome, Plant
Gene Expression Regulation, Plant
Genome-Wide Association Study
Promoter Regions, Genetic

@article {pmid39789465,
year = {2025},
author = {Yacoub, E and Baby, V and Sirand-Pugnet, P and Arfi, Y and Mardassi, H and Blanchard, A and Chibani, S and Ben Abdelmoumen Mardassi, B},
title = {A sweeping view of avian mycoplasmas biology drawn from comparative genomic analyses.},
journal = {BMC genomics},
volume = {26},
number = {1},
pages = {24},
pmid = {39789465},
issn = {1471-2164},
abstract = {BACKGROUND: Avian mycoplasmas are small bacteria associated with several pathogenic conditions in many wild and poultry bird species. Extensive genomic data are available for many avian mycoplasmas, yet no comparative studies focusing on this group of mycoplasmas have been undertaken so far.

RESULTS: Here, based on the comparison of forty avian mycoplasma genomes belonging to ten different species, we provide insightful information on the phylogeny, pan/core genome, energetic metabolism, and virulence of these avian pathogens. Analyses disclosed considerable inter- and intra-species genomic variabilities, with genome sizes that can vary by twice as much. Phylogenetic analysis based on concatenated orthologous genes revealed that avian mycoplasmas fell into either Hominis or Pneumoniae groups within the Mollicutes and could split into various clusters. No host co-evolution of avian mycoplasmas can be inferred from the proposed phylogenetic scheme. With 3,237 different gene clusters, the avian mycoplasma group under study proved diverse enough to have an open pan genome. However, a set of 150 gene clusters was found to be shared between all avian mycoplasmas, which is likely encoding essential functions. Comparison of energy metabolism pathways showed that avian mycoplasmas rely on various sources of energy. Superposition between phylogenetic and energy metabolism groups revealed that the glycolytic mycoplasmas belong to two distinct phylogenetic groups (Hominis and Pneumoniae), while all the arginine-utilizing mycoplasmas belong only to Hominis group. This can stand for different evolutionary strategies followed by avian mycoplasmas and further emphasizes the diversity within this group. Virulence determinants survey showed that the involved gene arsenals vary significantly within and between species, and could even be found in species often reported apathogenic. Immunoglobulin-blocking proteins were detected in almost all avian mycoplasmas. Although these systems are not exclusive to this group, they seem to present some particular features making them unique among mycoplasmas.

CONCLUSION: This comparative genomic study uncovered the significant variable nature of avian mycoplasmas, furthering our knowledge on their biological attributes and evoking new hallmarks.},
}

@article {pmid39780644,
year = {2025},
author = {Yasuoka, K and Gotoh, Y and Taniguchi, I and Nagano, DS and Nakamura, K and Mizuno, Y and Abe, T and Ogura, Y and Nakajima, H and Uesugi, M and Miura, M and Seto, K and Wakabayashi, Y and Isobe, J and Watari, T and Senda, S and Hayakawa, N and Ogawa, E and Sato, T and Nanishi, E and Sakai, Y and Kato, A and Miyata, I and Ouchi, K and Ohga, S and Hara, T and Hayashi, T},
title = {Genome Analysis of Japanese Yersinia pseudotuberculosis Strains Isolated From Kawasaki Disease Patients and Other Sources and Their Phylogenetic Positions in the Global Y. pseudotuberculosis Population.},
journal = {Microbiology and immunology},
volume = {},
number = {},
pages = {},
doi = {10.1111/1348-0421.13199},
pmid = {39780644},
issn = {1348-0421},
support = {//This work was supported by a grant for Kawasaki Disease Research from the Japan Blood Products Organization and JSPS KAKENHI (Grant Number 23k15366)./ ; },
abstract = {Yersinia pseudotuberculosis (Ypt) is a gram-negative bacterium that infects both humans and animals primarily through fecal‒oral transmission. While Ypt causes acute gastroenteritis in humans, an association with Kawasaki disease (KD), a disease that primarily affects infants and young children and causes multisystemic vasculitis, has also been suspected. Although KD represents a significant health concern worldwide, the highest annual incidence rate is reported in Japan. Previously, a geographical origin-dependent population structure of Ypt comprising the Asian, transitional, and European clades was proposed. However, genomic data on KD-associated Ypt strains is currently unavailable. In this study, to analyze the phylogenetic and genomic features of KD-associated strains, we determined the whole-genome sequences of 35 Japanese Ypt strains, including 11 KD-associated strains, and constructed a genome set (n = 204) representing the global population of Ypt by adding publicly available Ypt genomes. In a phylogenetic analysis, all sequenced Japanese strains, including the KD-associated strains, belonged to the Asian clade, which appeared to be the ancestral clade of Ypt, and the KD-associated strains belonged to multiple lineages in this clade. Strains from patients with Far East scarlet-like fever (FESLF), a KD-related disease, also belonged to the Asian clade. Moreover, no KD strain-specific genes were identified in pan-genome-wide association study analyses. Notably, however, the gene encoding a superantigen called Yersinia pseudotuberculosis-derived mitogen (YPM) showed a distribution pattern highly biased to the Asian clade. Although further studies are needed, our results suggest that Asian clade strains may have a greater potential to trigger KD.},
}

@article {pmid39779953,
year = {2025},
author = {Secomandi, S and Gallo, GR and Rossi, R and Rodríguez Fernandes, C and Jarvis, ED and Bonisoli-Alquati, A and Gianfranceschi, L and Formenti, G},
title = {Pangenome graphs and their applications in biodiversity genomics.},
journal = {Nature genetics},
volume = {},
number = {},
pages = {},
pmid = {39779953},
issn = {1546-1718},
abstract = {Complete datasets of genetic variants are key to biodiversity genomic studies. Long-read sequencing technologies allow the routine assembly of highly contiguous, haplotype-resolved reference genomes. However, even when complete, reference genomes from a single individual may bias downstream analyses and fail to adequately represent genetic diversity within a population or species. Pangenome graphs assembled from aligned collections of high-quality genomes can overcome representation bias by integrating sequence information from multiple genomes from the same population, species or genus into a single reference. Here, we review the available tools and data structures to build, visualize and manipulate pangenome graphs while providing practical examples and discussing their applications in biodiversity and conservation genomics across the tree of life.},
}

@article {pmid39777507,
year = {2025},
author = {Shelton, AN and Yu, FB and Grossman, AR and Bhaya, D},
title = {Abundant and active community members respond to diel cycles in hot spring phototrophic mats.},
journal = {The ISME journal},
volume = {},
number = {},
pages = {},
doi = {10.1093/ismejo/wraf001},
pmid = {39777507},
issn = {1751-7370},
abstract = {Photosynthetic microbial mats in hot springs can provide insights into the diel behaviors of communities in extreme environments. In this habitat, photosynthesis dominates during the day, leading to super-oxic conditions, with a rapid transition to fermentation and anoxia at night. Multiple samples were collected from two springs over several years to generate metagenomic and metatranscriptomic datasets. Metagenome assembled genomes comprised 71 taxa (in 19 different phyla), of which twelve core taxa were present at high abundance in both springs. The eight most active taxa identified by metatranscriptomics were an oxygenic cyanobacterium (Synechococcus sp.), five anoxygenic phototrophs from three different phyla, and two understudied heterotrophs from phylum Armatimonadota. In all eight taxa, a significant fraction of genes exhibited a diel expression pattern although peak timing varied considerably. The two abundant heterotrophs exhibit starkly different peak timing of expression, which we propose is shaped by their metabolic and genomic potential to use carbon sources that become differentially available during the diel cycle. Network analysis revealed pathway expression patterns that had not previously been linked to diel cycles, including ribosome biogenesis and chaperones. This provides a framework for analyzing metabolically coupled communities and the dominant role of the diel cycle.},
}

@article {pmid39772210,
year = {2024},
author = {Jdeed, G and Morozova, VV and Tikunova, NV},
title = {Genome Analysis of Anti-Phage Defense Systems and Defense Islands in Stenotrophomonas maltophilia: Preservation and Variability.},
journal = {Viruses},
volume = {16},
number = {12},
pages = {},
doi = {10.3390/v16121903},
pmid = {39772210},
issn = {1999-4915},
support = {075-15-2021-1085//the Ministry of Science and Higher Education of the Russian Federation/ ; },
mesh = {*Stenotrophomonas maltophilia/genetics/virology ; *Bacteriophages/genetics/physiology ; *Phylogeny ; *Genome, Bacterial ; Genomic Islands ; },
abstract = {Anti-phage defense systems are widespread in bacteria due to the latter continuous adaptation to infection by bacteriophages (phages). Stenotrophomonas maltophilia has a high degree of intrinsic antibiotic resistance, which makes phage therapy relevant for the treatment of infections caused by this species. Studying the array of anti-phage defense systems that could be found in S. maltophilia helps in better adapting the phages to the systems present in the pathogenic bacteria. Pangenome analysis of the available S. maltophilia strains with complete genomes that were downloaded from GenBank, including five local genomes, indicated a wide set of 72 defense systems and subsystems that varied between the strains. Seven of these systems were present in more than 20% of the studied genomes and the proteins encoded by the systems were variable in most of the cases. A total of 27 defense islands were revealed where defense systems were found; however, more than 60% of the instances of systems were found in four defense islands. Several elements linked to the transfer of these systems were found. No obvious associations between the pattern of distribution of the anti-phage defense systems of S. maltophilia and the phylogenetic features or the isolation site were found.},
}

*Stenotrophomonas maltophilia/genetics/virology
*Bacteriophages/genetics/physiology
*Phylogeny
*Genome, Bacterial
Genomic Islands

@article {pmid39770839,
year = {2024},
author = {Gonzalez-Silva, A and San Juan-Mendo, M and Delgado-Prudencio, G and Hernández-García, JA and Larios-Serrato, V and Aguilar, C and Villa-Tanaca, L and Hernández-Rodríguez, C},
title = {Comparative Genomics and Biosynthetic Cluster Analysis of Antifungal Secondary Metabolites of Three Strains of Streptomyces albidoflavus Isolated from Rhizospheric Soils.},
journal = {Microorganisms},
volume = {12},
number = {12},
pages = {},
doi = {10.3390/microorganisms12122637},
pmid = {39770839},
issn = {2076-2607},
support = {CB 283225//Consejo Nacional de Humanidades, Ciencia y Tecnología/ ; SIP 20220742, 20220795, 20231480, 20231481, 20240945, 20240946//Instituto Politécnico Nacional/ ; },
abstract = {Streptomyces is a genus of Gram-positive bacteria with high GC content. It remains attractive for studying and discovering new antibiotics, antifungals, and chemotherapeutics. Streptomyces genomes can contain more than 30 cryptic and expressed biosynthetic gene clusters (BGC) encoding secondary metabolites. In this study, three Streptomyces strains isolated from jungle rhizospheric soil exhibited supernatants that can inhibit sensitive and fluconazole-resistant Candida spp. The genomes of the strains Streptomyces sp. A1, J25, J29 ori2 were sequenced, assembled de novo, and analyzed. The genome assemblies revealed that the size of the genomes was 6.9 Mb, with linear topology and 73.5% GC. A phylogenomic approach identified the strains with high similitudes between 98.5 and 98.7% with Streptomyces albidoflavus SM254 and R-53649 strains, respectively. Pangenomic analysis of eight genomes of S. albidoflavus strains deposited in the Genomes database recognized 4707 core protein orthogroups and 745 abundant accessory and exclusive protein orthogroups, suggesting an open pangenome in this species. The antiSMASH software detected candicidin and surugamide BGC-encoding polyene and octapeptide antifungal secondary metabolites in other S. albidoflavus. CORASON software was used to compare the synteny, and the abundance of genes harbored in the clusters was used. In conclusion, although the three strains belong to the same species, each possesses a distinct genome, as evidenced by the different phenotypes, including antifungal and extracellular enzymatic activities.},
}

@article {pmid39770825,
year = {2024},
author = {Heidarpanah, S and Li, K and Thibodeau, A and Meniaï, I and Parreira, VR and Quessy, S and Segura, M and Fittipaldi, N and Gaucher, ML},
title = {Genomic Diversity and Virulence Factors of Clostridium perfringens Isolated from Healthy and Necrotic Enteritis-Affected Broiler Chicken Farms in Quebec Province.},
journal = {Microorganisms},
volume = {12},
number = {12},
pages = {},
doi = {10.3390/microorganisms12122624},
pmid = {39770825},
issn = {2076-2607},
support = {IT09545//Mitacs/ ; },
abstract = {Avian necrotic enteritis due to the Gram-positive bacterium Clostridium perfringens has re-emerged following the ban on antibiotic growth promoters in many poultry producing countries. The limited number of previous studies has left important gaps in our understanding of the genetic diversity and virulence traits of the pathogen. To address these knowledge gaps, in this study, we sequenced the genomes of 41 Clostridium perfringens isolates recovered from commercial broiler chicken flocks in Quebec, Canada, including isolates from healthy birds and those affected by necrotic enteritis. We sought to understand the pangenome diversity and interrogated the genomes for key virulence factors involved in necrotic enteritis pathogenesis. On average, the genomes had a GC content of 28% and contained 3206 coding sequences. A variable presence of toxins, degradative hydrolytic enzymes, and collagen-binding proteins was also found. Through pangenome analysis, we revealed a total of 10,223 genes, 652 (6.4%) of which formed the core genome. Additionally, we identified 17 different plasmids, 12 antibiotic resistance genes, and nine prophage regions. Overall, our results demonstrated a relatively high genetic diversity among chicken Clostridium perfringens isolates collected from the same geographical location, offering new insights into potential virulence mechanisms and adaptation of the pathogen within poultry populations.},
}

@article {pmid39770754,
year = {2024},
author = {Bidzhieva, SK and Tourova, TP and Grouzdev, DS and Samigullina, SR and Sokolova, DS and Poltaraus, AB and Avtukh, AN and Tereshina, VM and Mardanov, AV and Zhaparov, NS and Nazina, TN},
title = {Sulfate-Reducing Bacteria Isolated from an Oil Field in Kazakhstan and a Description of Pseudodesulfovibrio karagichevae sp. nov.},
journal = {Microorganisms},
volume = {12},
number = {12},
pages = {},
doi = {10.3390/microorganisms12122552},
pmid = {39770754},
issn = {2076-2607},
support = {21-64-00019//Russian Science Foundation/ ; },
abstract = {Sulfidogenic bacteria cause numerous issues in the oil industry since they produce sulfide, corroding steel equipment, reducing oil quality, and worsening the environmental conditions in oil fields. The purpose of this work was to isolate and taxonomically identify the sulfidogenic bacteria responsible for the corrosion of steel equipment at the Karazhanbas oil field (Kazakhstan). In this study, we characterized five sulfidogenic strains of the genera Pseudodesulfovibrio, Oleidesulfovibrio, and Acetobacterium isolated from the formation water of the Karazhanbas oil field (Kazakhstan). Sulfate-reducing strain 9FUS[T] revealed 98.9% similarity of the 16S rRNA gene sequence with the closely related strain 'Pseudodesulfovibrio methanolicus' 5S69[T] and was studied in detail to enhance the taxonomic resolution. Strain 9FUS[T] grew optimally at 23-28 °C, pH 6.5, and 0-2% (w/v) NaCl. The strain used lactate, pyruvate, methanol, ethanol, fructose, ribose, and H2/CO2 (in the presence of acetate) as carbon and energy sources for sulfate reduction. Iso-C17:1 ω11, C15:0, iso-C15:0, and C16:0 were the predominant fatty acids. The genome is 4.20 Mbp with a G + C content of 64.0%. The average nucleotide identity and digital DNA-DNA hybridization values with Pseudodesulfovibrio spp. genomes were 72.5-91.6% (<95%) and 18.5-45.0% (<70%), respectively, and supported our conclusion that 9FUS[T] (=VKM B-3654[T] = KCTC 25498[T]) belonged to a novel Pseudodesulfovibrio species, for which the name Pseudodesulfovibrio karagichevae sp. nov. is proposed. Pangenome analysis of sixteen Pseudodesulfovibrio species and functional annotation analysis of identified genes revealed complete modules of enzymes of the main metabolic pathways, characteristic of bacteria of this genus, and unique genes highlighting the adaptations of strain 9FUS[T] in carbohydrate metabolism, nutrient uptake, and environmental stress response. Isolation of these strains expands our understanding of the diversity of sulfidogens in oil reservoirs and can be used to test the effectiveness of biocides used in an oil field.},
}

@article {pmid39770704,
year = {2024},
author = {You, Y and Xu, X and Liu, H and Zhang, L},
title = {Locust Pathogen Aspergillus oryzae XJ1 Is Different from Aspergillus oryzae and Aspergillus flavus Based on Genomics Comparisons.},
journal = {Microorganisms},
volume = {12},
number = {12},
pages = {},
doi = {10.3390/microorganisms12122501},
pmid = {39770704},
issn = {2076-2607},
support = {CXGC2024F05, CXGC2024D05//Agricultural scientific and technological innovation project of Shandong Academy of Ag-ricultural Sciences/ ; ZR2022MC117//Shandong Provincial Natural Science Foundation/ ; },
abstract = {Fungi play an increasingly important role in the biological control of insect pests. Aspergillus oryzae XJ1 is highly virulent to locust adults and nymphs, which are a destructive economic pest worldwide. Because of its host association with locusts, which is unique in Aspergillus, in this study, we examined the genetic relationships of A. oryzae XJ1 within Aspergillus. We sequenced the genome of A. oryzae XJ1 and compared it with the genomes of other Aspergillus species. The complete genome of A. oryzae XJ1 is 37.9 Mb, comprising 11,720 putative genes, assembled into eight chromosomes. The genome size is similar to that of other A. oryzae strains. Phylogenomic analysis indicated that A. oryzae XJ1 was most closely related to A. flavus NRRL3357, not A. oryzae RIB40. Core/pan-genome analysis of A. oryzae XJ1 and other Aspergillus species revealed that A. oryzae XJ1 had 704 strain-specific genes, whereas A. flavus NRRL3357, A. oryzae KDG 21, and A. parasiticus NRRL 2999 had 646, 955, and 779 unique genes, respectively. The A. oryzae XJ1 genome showed structural differences compared with the genomes of A. oryzae RIB40 and A. flavus NRRL3357 in genomic synteny analysis. These results indicate that A. oryzae XJ1 is genetically distinct at the genome level from other Aspergillus species, including A. oryzae and A. flavus, and may be as a distinct species. This will provide new insight into the classification of Aspergillus based on genomics.},
}

@article {pmid39770688,
year = {2024},
author = {Reynoso, EC and Delgado-Suárez, EJ and Hernández-Pérez, CF and Chavarin-Pineda, Y and Godoy-Lozano, EE and Fierros-Zárate, G and Aguilar-Vera, OA and Castillo-Ramírez, S and Gómez-Pedroso, LDCS and Sánchez-Zamorano, LM},
title = {Geography, Antimicrobial Resistance, and Genomics of Salmonella enterica (Serotypes Newport and Anatum) from Meat in Mexico (2021-2023).},
journal = {Microorganisms},
volume = {12},
number = {12},
pages = {},
doi = {10.3390/microorganisms12122485},
pmid = {39770688},
issn = {2076-2607},
support = {CF-2020-87198//Consejo Nacional de Humanidades, Ciencias y Tecnologías/ ; I1200/311/2023//Consejo Nacional de Humanidades, Ciencias y Tecnologías/ ; },
abstract = {Salmonella enterica non-typhoidal is a major contributor to diarrheal diseases, with over 2600 serovars identified across diverse environments. In Mexico, serovars Newport and Anatum have shown a marked increase, especially in foodborne disease, posing a public health problem. We conducted a cross-sectional study from 2021 to 2023 using active epidemiological surveillance to assess contamination in ground beef and pork at butcher shops nationwide. It involved isolation, phenotypic antimicrobial resistance, comparative genomics, spatial distribution, antimicrobial-resistance genes, and pangenome analysis. A total of 402 non-typhoidal S. enterica strains were isolated, including 59 Newport and 50 Anatum. After curating for redundancy, 45 Newport and 32 Anatum strains remained. We found that 75% of Newport strains exhibited multidrug resistance (MDR), compared to 25% of Anatum strains. Salmonella Newport also showed a broader distribution and stronger antibiotic-resistance capacity, particularly due to genes such as mphA and ramA. Our pangenome analysis showed a predominance of cell maintenance and survival-process genes in the accessory genome of both serotypes. Considering unique genes, Salmonella Anatum and Newport showed a notorious abundance of genes with functions related to replication, recombination, and repair. The substantial rise of Anatum and Newport strains in meat samples for human consumption presents an epidemiological alert, highlighting the critical need for stringent surveillance programs to mitigate human and ecosystem health risks.},
}

@article {pmid39770679,
year = {2024},
author = {Mwamburi, SM and Islam, SI and Dinh-Hung, N and Dangsawat, O and Sowanpreecha, R and Khang, LTP and Montha, N and Therdtatha, P and Dwinanti, SH and Permpoonpattana, P and Linh, NV},
title = {Genomic Characterization of Bacillus sp. THPS1: A Hot Spring-Derived Species with Functional Features and Biotechnological Potential.},
journal = {Microorganisms},
volume = {12},
number = {12},
pages = {},
doi = {10.3390/microorganisms12122476},
pmid = {39770679},
issn = {2076-2607},
abstract = {Bacillus sp. THPS1 is a novel strain isolated from a high-temperature hot spring in Thailand, exhibiting distinctive genomic features that enable adaptation to an extreme environment. This study aimed to characterize the genomic and functional attributes of Bacillus sp. THPS1 to understand its adaptation strategies and evaluate its potential for biotechnological applications. The draft genome is 5.38 Mbp with a GC content of 35.67%, encoding 5606 genes, including those linked to stress response and sporulation, which are essential for survival in high-temperature conditions. Phylogenetic analysis and average nucleotide identity (ANI) values confirmed its classification as a distinct species within the Bacillus genus. Pangenome analysis involving 19 others closely related thermophilic Bacillus species identified 1888 singleton genes associated with heat resistance, sporulation, and specialized metabolism, suggesting adaptation to nutrient-deficient, high-temperature environments. Genomic analysis revealed 12 biosynthetic gene clusters (BGCs), including those for polyketides and non-ribosomal peptides, highlighting its potential for synthesizing secondary metabolites that may facilitate its adaptation. Additionally, the presence of three Siphoviridae phage regions and 96 mobile genetic elements (MGEs) suggests significant genomic plasticity, whereas the existence of five CRISPR arrays implies an advanced defense mechanism against phage infections, contributing to genomic stability. The distinctive genomic features and functional capacities of Bacillus sp. THPS1 make it a promising candidate for biotechnological applications, particularly in the production of heat-stable enzymes and the development of resilient bioformulations.},
}

@article {pmid39768397,
year = {2024},
author = {Klaysubun, C and Chaichana, N and Suwannasin, S and Singkhamanan, K and Yaikhan, T and Kantachote, D and Pomwised, R and Wonglapsuwan, M and Surachat, K},
title = {Genomic Characterization of Probiotic Purple Nonsulfur Bacteria Cereibacter sphaeroides Strains S3W10 and SS15: Implications for Enhanced Shrimp Aquaculture.},
journal = {Life (Basel, Switzerland)},
volume = {14},
number = {12},
pages = {},
doi = {10.3390/life14121691},
pmid = {39768397},
issn = {2075-1729},
support = {B13F660074 and B13F670076//NSRF via the Program Management Unit for Human Resources and Institutional Development, Research and Innovation/ ; },
abstract = {Cereibacter sphaeroides strains S3W10 and SS15, isolated from shrimp ponds, exhibit potential probiotic benefits for aquaculture. In this study, the genomic features of S3W10 and SS15 were thoroughly characterized to evaluate their probiotic properties and safety for aquaculture use. The genomes of S3W10 and SS15 consist of 130 and 74 contigs, with sizes of 4.6 Mb and 4.4 Mb and GC contents of 69.2%. Average nucleotide identity (ANI), digital DNA-DNA hybridization (dDDH), and phylogenomic analyses confirmed that these strains belong to C. sphaeroides. Genome annotation predicted 4260 coding sequences (CDS) in S3W10 and 4086 CDS in SS15, including genes associated with stress tolerance, nutrient absorption, and antioxidant activity. Notably, genes related to vitamin B12 synthesis, digestive enzyme production, and carotenoid biosynthesis, which support shrimp health, were identified in both genomes. CAZyme analysis identified 116 and 115 carbohydrate-active enzymes in S3W10 and SS15, respectively, supporting adaptation to gastrointestinal environments and the host immune response. Pan-genome analysis across C. sphaeroides strains revealed 7918 gene clusters, highlighting the open pan-genome structure of this species and its high genetic diversity. Further bioinformatic analyses assessing mobile genetic elements, antibiotic-resistance genes, and virulence factors demonstrated the safety of both strains for aquaculture, as no plasmids or virulence genes were identified. The genomic insights in this study provide a deeper understanding of the strains' adaptability and functional potential, aligning with previous in vitro and in vivo studies and highlighting their potential for use in shrimp cultivation.},
}

@article {pmid39768396,
year = {2024},
author = {Adedibu, PA and Son, O and Tekutyeva, L and Balabanova, L},
title = {Pathogenomic Insights into Xanthomonas oryzae pv. oryzae's Resistome, Virulome, and Diversity for Improved Rice Blight Management.},
journal = {Life (Basel, Switzerland)},
volume = {14},
number = {12},
pages = {},
doi = {10.3390/life14121690},
pmid = {39768396},
issn = {2075-1729},
support = {15.BRK.21.0004 (Contract No. 075-15-2021-1052/9)//Ministry of Science and Higher Education of Russian Federation/ ; },
abstract = {Oryza sativa (rice) is a major staple food targeted for increased production to achieve food security. However, increased production is threatened by several biotic and abiotic factors, of which bacterial blight disease caused by Xanthomonas oryzae pathovar oryzae is severe. Developing effective control strategies requires an up-to-date understanding of its pathogenomics. This study analyzes the genomes of 30 X. oryzae strains collected from rice-producing regions across five continents to identify genetic elements critical for its pathogenicity and adaptability and for an intraspecific diversity assessment using advanced genomics and bioinformatics tools. Resistome analysis revealed 28 distinct types of antibiotic resistance genes (ARGs), both innate and acquired, indicating a growing threat from multidrug-resistant X. oryzae strains. Sixteen virulent genes, including type III and VI secretion systems, motility genes, and effector proteins, were identified. A unique 'MexCD-OprJ' multidrug efflux system was detected in the Tanzanian strains, conferring resistance to multiple antibiotic classes. To curb further ARG emergence, there is a need to regulate the use of antibiotics for X. oryzae control and adopt resistant rice varieties. Transposable elements were also discovered to contribute to X. oryzae pathogenicity, facilitating the horizontal transfer of virulence genes. Pangenome analysis revealed intraspecific variation among the population, with 112 unique CDS having diverse functional roles. Strains registered in the Philippines had the most unique genes. Phylogenetic analysis confirmed the divergent evolution of X. oryzae. This study's results will aid in identifying more effective management strategies and biocontrol alternatives for sustainable rice production.},
}

@article {pmid39766787,
year = {2024},
author = {Muto, Y and Tanaka, K},
title = {Comparative Evolutionary Genomics Reveals Genetic Diversity and Differentiation in Bacteroides fragilis.},
journal = {Genes},
volume = {15},
number = {12},
pages = {},
doi = {10.3390/genes15121519},
pmid = {39766787},
issn = {2073-4425},
support = {22K10486//Japan Society for the Promotion of Science/ ; },
mesh = {*Bacteroides fragilis/genetics/classification ; *Phylogeny ; *Genome, Bacterial ; *Evolution, Molecular ; *Genetic Variation ; *Genomics/methods ; Bacteroides Infections/microbiology/genetics ; },
abstract = {BACKGROUND/OBJECTIVES: Bacteroides fragilis is the pathogenic anaerobe most commonly isolated from intra-abdominal infections, abscesses, and blood. Despite its clinical importance, research on its pan-genome-scale evolution is still limited.

METHODS: Herein, we analyzed the pan-genome architecture of 374 B. fragilis strains to explore their intra-species genomic diversity and evolutionary patterns.

RESULTS: Our analysis revealed an open pan-genome with a high proportion of accessory genomes, indicating high genetic variability. Accessory genome genes were substantially enriched in the functions of "Replication, Recombination, and Repair" suggesting their roles in gene transfer and divergence. Phylogenomic analysis divided B. fragilis into two distinct clades: divisions I and II, differing in gene content, antimicrobial resistance genes, and mobile genetic elements. Division II revealed higher Tajima's D values, suggesting that it separated after B. fragilis's recent species diversification. The extreme shift in the distribution of gene-wise Hudson's fixation index (Fst) values for each division suggested that several genes are highly differentiated or evolved between the two clades. Average nucleotide identity and 16S rRNA analyses showed that B. fragilis division II represents a distinct species, Bacteroides hominis. Additionally, a considerable depletion of recombination in genes with Fst values > 0.99 was noted, suggesting that the highest Fst genes with little recombination are the basis for differentiation between divisions.

CONCLUSIONS: Overall, this study enhances the understanding of B. fragilis's genomic diversity, evolutionary dynamics, and potential role in pathogenesis, shedding light on its adaptation and diversification.},
}

*Bacteroides fragilis/genetics/classification
*Phylogeny
*Genome, Bacterial
*Evolution, Molecular
*Genetic Variation
*Genomics/methods
Bacteroides Infections/microbiology/genetics

@article {pmid39763808,
year = {2024},
author = {Ojeda, IG and Palace, SG and Martinez, PP and Azarian, T and Grant, LR and Hammitt, LL and Hanage, WP and Lipsitch, M},
title = {Linkage-based ortholog refinement in bacterial pangenomes with CLARC.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2024.12.18.629228},
pmid = {39763808},
issn = {2692-8205},
abstract = {Bacterial genomes exhibit significant variation in gene content and sequence identity. Pangenome analyses explore this diversity by classifying genes into core and accessory clusters of orthologous groups (COGs). However, strict sequence identity cutoffs can misclassify divergent alleles as different genes, inflating accessory gene counts. CLARC (Connected Linkage and Alignment Redefinition of COGs) [ https://github.com/IndraGonz/CLARC ] improves pangenome analyses by condensing accessory COGs using functional annotation and linkage information. Through this approach, orthologous groups are consolidated into more practical units of selection. Analyzing 8,000+ Streptococcus pneumoniae genomes, CLARC reduced accessory gene estimates by more than 30% and improved evolutionary predictions based on accessory gene frequencies. By refining COG definitions, CLARC offers critical insights into bacterial evolution, aiding genetic studies across diverse populations.},
}

@article {pmid39763645,
year = {2024},
author = {Zhou, Q and Ghezelji, M and Hari, A and Ford, MKB and Holley, C and Sahinalp, SC and Numanagić, I},
title = {Geny: a genotyping tool for allelic decomposition of killer cell immunoglobulin-like receptor genes.},
journal = {Frontiers in immunology},
volume = {15},
number = {},
pages = {1494995},
pmid = {39763645},
issn = {1664-3224},
mesh = {*Receptors, KIR/genetics ; Humans ; *Alleles ; *Genotyping Techniques/methods ; *Genotype ; High-Throughput Nucleotide Sequencing/methods ; Computational Biology/methods ; Software ; },
abstract = {INTRODUCTION: Accurate genotyping of Killer cell Immunoglobulin-like Receptor (KIR) genes plays a pivotal role in enhancing our understanding of innate immune responses, disease correlations, and the advancement of personalized medicine. However, due to the high variability of the KIR region and high level of sequence similarity among different KIR genes, the generic genotyping workflows are unable to accurately infer copy numbers and complete genotypes of individual KIR genes from next-generation sequencing data. Thus, specialized genotyping tools are needed to genotype this complex region.

METHODS: Here, we introduce Geny, a new computational tool for precise genotyping of KIR genes. Geny utilizes available KIR allele databases and proposes a novel combination of expectation-maximization filtering schemes and integer linear programming-based combinatorial optimization models to resolve ambiguous reads, provide accurate copy number estimation, and estimate the correct allele of each copy of genes within the KIR region.

RESULTS & DISCUSSION: We evaluated Geny on a large set of simulated short-read datasets covering the known validated KIR region assemblies and a set of Illumina short-read samples sequenced from 40 validated samples from the Human Pangenome Reference Consortium collection and showed that it outperforms the existing state-of-the-art KIR genotyping tools in terms of accuracy, precision, and recall. We envision Geny becoming a valuable resource for understanding immune system response and consequently advancing the field of patient-centric medicine.},
}

*Receptors, KIR/genetics
Humans
*Alleles
*Genotyping Techniques/methods
*Genotype
High-Throughput Nucleotide Sequencing/methods
Computational Biology/methods
Software

@article {pmid39759836,
year = {2024},
author = {Nesbø, CL and Kublanov, I and Yang, M and Sharan, AA and Meyer, T and Edwards, EA},
title = {High quality Bathyarchaeia MAGs from lignocellulose-impacted environments elucidate metabolism and evolutionary mechanisms.},
journal = {ISME communications},
volume = {4},
number = {1},
pages = {ycae156},
pmid = {39759836},
issn = {2730-6151},
abstract = {The archaeal class Bathyarchaeia is widely and abundantly distributed in anoxic habitats. Metagenomic studies have suggested that they are mixotrophic, capable of CO2 fixation and heterotrophic growth, and involved in acetogenesis and lignin degradation. We analyzed 35 Bathyarchaeia metagenome-assembled genomes (MAGs), including the first complete circularized MAG (cMAG) of the Bathy-6 subgroup, from the metagenomes of three full-scale pulp and paper mill anaerobic digesters and three laboratory methanogenic enrichment cultures maintained on pre-treated poplar. Thirty-three MAGs belong to the Bathy-6, lineage while two are from the Bathy-8 lineage. In our previous analysis of the microbial community in the pulp mill digesters, Bathyarchaeia were abundant and positively correlated to hydrogenotrophic and methylotrophic methanogenesis. Several factors likely contribute to the success of the Bathy-6 lineage compared to Bathy-8 in the reactors. The Bathy-6 genomes are larger than those of Bathy-8 and have more genes involved in lignocellulose degradation, including carbohydrate-active enzymes not present in the Bathy-8. Bathy-6 also shares the Bathyarchaeal O-demethylase system recently identified in Bathy-8. All the Bathy-6 MAGs had numerous membrane-associated pyrroloquinoline quinone-domain proteins that we suggest are involved in lignin modification or degradation, together with Radical-S-adenosylmethionine (SAM) and Rieske domain proteins, and AA2, AA3, and AA6-family oxidoreductases. We also identified a complete B12 synthesis pathway and a complete nitrogenase gene locus. Finally, comparative genomic analyses revealed that Bathyarchaeia genomes are dynamic and have interacted with other organisms in their environments through gene transfer to expand their gene repertoire.},
}

@article {pmid39758981,
year = {2024},
author = {Zakeri, M and Brown, NK and Ahmed, OY and Gagie, T and Langmead, B},
title = {Movi: A fast and cache-efficient full-text pangenome index.},
journal = {iScience},
volume = {27},
number = {12},
pages = {111464},
pmid = {39758981},
issn = {2589-0042},
abstract = {Pangenome indexes are promising tools for many applications, including classification of nanopore sequencing reads. Move structure is a compressed-index data structure based on the Burrows-Wheeler Transform (BWT). It offers simultaneous O(1)-time queries and O(r) space, where r is the number of BWT runs (consecutive sequence of identical characters). We developed Movi based on the move structure for indexing and querying pangenomes. Movi scales very well for repetitive text as its size grows strictly by r. Movi computes sophisticated matching queries for classification such as pseudo-matching lengths and backward search up to 30 times faster than existing methods by minimizing the number of cache misses and using memory prefetching to attain a degree of latency hiding. Movi's fast constant-time query loop makes it well suited to real-time applications like adaptive sampling for nanopore sequencing, where decisions must be made in a small and predictable time interval.},
}

@article {pmid39756800,
year = {2025},
author = {Jonkheer, EM and de Ridder, D and van der Lee, TAJ and de Haan, JR and Berke, L and Smit, S},
title = {Exploring intra- and intergenomic variation in haplotype-resolved pangenomes.},
journal = {Plant biotechnology journal},
volume = {},
number = {},
pages = {},
doi = {10.1111/pbi.14545},
pmid = {39756800},
issn = {1467-7652},
support = {ETEC.2019.019//Netherlands eScience Center/ ; //Genetwister Technologies B.V./ ; //Biointeractions and Plant Health, Wageningen Plant Research/ ; },
abstract = {With advances in long-read sequencing and assembly techniques, haplotype-resolved (phased) genome assemblies are becoming more common, also in the field of plant genomics. Computational tools to effectively explore these phased genomes, particularly for polyploid genomes, are currently limited. Here we describe a new strategy adopting a pangenome approach. To analyse both intra- and intergenomic variation in phased genome assemblies, we have made the software package PanTools ploidy-aware by updating the pangenome graph representation and adding several novel functionalities to assess synteny and gene retention, profile repeats and calculate synonymous and nonsynonymous mutation rates. Using PanTools, we constructed and analysed a pangenome comprising of one diploid and four tetraploid potato cultivars, and a pangenome of five diploid apple species. Both pangenomes show high intra- and intergenomic allelic diversity in terms of gene absence/presence, SNPs, indels and larger structural variants. Our findings show that the new functionalities and visualizations are useful to discover introgressions and detect likely misassemblies in phased genomes. PanTools is available at https://git.wur.nl/bioinformatics/pantools.},
}

@article {pmid39755794,
year = {2025},
author = {Sawaswong, V and Wongjarit, K and Petsong, S and Yuliani, Y and Somsukpiroh, U and Faksri, K and Forde, T and Payungporn, S and Rotcheewaphan, S},
title = {Diversity and antimicrobial resistance profiles of Mycobacterium avium complex clinical isolates in Thailand based on whole genome comparative analysis.},
journal = {Scientific reports},
volume = {15},
number = {1},
pages = {772},
pmid = {39755794},
issn = {2045-2322},
support = {HEA663000042//Thailand Science research and Innovation Fund Chulalongkorn University/ ; RA66/026//Ratchadapiseksompotch Fund, Faculty of Medicine, Chulalongkorn University/ ; },
mesh = {Thailand/epidemiology ; *Mycobacterium avium Complex/genetics/drug effects/isolation & purification ; Humans ; *Phylogeny ; *Microbial Sensitivity Tests ; *Drug Resistance, Bacterial/genetics ; *Mycobacterium avium-intracellulare Infection/microbiology/drug therapy ; *Genome, Bacterial ; Anti-Bacterial Agents/pharmacology ; Whole Genome Sequencing/methods ; Genetic Variation ; Male ; Female ; Middle Aged ; Aged ; Adult ; },
abstract = {The Mycobacterium avium complex (MAC) is a group of closely related nontuberculous mycobacteria that can cause various diseases in humans. In this study, genome sequencing, comprehensive genomic analysis, and antimicrobial susceptibility testing of 66 MAC clinical isolates from King Chulalongkorn Memorial Hospital, Bangkok, Thailand were carried out. Whole-genome average nucleotide identity (ANI) revealed the MAC species distribution, comprising 54 (81.8%) M. intracellulare, 6 (9.1%) M. avium, 5 (7.6%) M. colombiense, and 1 (1.5%) M. timonense. Phylogenetic analysis revealed a high diversity of M. intracellulare isolates and their evolutionary relationships which could be divided into 2 subspecies: M. intracellulare subsp. intracellulare and M. intracellulare subsp. chimaera. In addition, M. intracellulare subsp. chimaera mostly clustered in the distinct clades separated from M. intracellulare strains originating from other countries. Most MAC isolates were resistant to linezolid and moxifloxacin based on phenotypic antimicrobial susceptibility testing. Mutations within rrl gene associated with clarithromycin resistance were detected in M. intracellulare and M. colombiense. The pan-genome analysis presented clade-specific proteins for M. intracellulare, such as PE and PPE protein families. This study provides valuable insights into the genomic diversity and antimicrobial resistance profiles of MAC isolates circulating in Thailand, which are useful for clinical management, guiding the development of targeted diagnostic, and treatment strategies for MAC infections.},
}

Thailand/epidemiology
*Mycobacterium avium Complex/genetics/drug effects/isolation & purification
Humans
*Phylogeny
*Microbial Sensitivity Tests
*Drug Resistance, Bacterial/genetics
*Mycobacterium avium-intracellulare Infection/microbiology/drug therapy
*Genome, Bacterial
Anti-Bacterial Agents/pharmacology
Whole Genome Sequencing/methods
Genetic Variation
Male
Female
Middle Aged
Aged
Adult

@article {pmid39754036,
year = {2025},
author = {Pan, M and O'Flaherty, S and Hibberd, A and Gerdes, S and Morovic, W and Barrangou, R},
title = {The curated Lactobacillus acidophilus NCFM genome provides insights into strain specificity and microevolution.},
journal = {BMC genomics},
volume = {26},
number = {1},
pages = {1},
pmid = {39754036},
issn = {1471-2164},
abstract = {BACKGROUND: The advent of next generation sequencing technologies has enabled a surge in the number of whole genome sequences in public databases, and our understanding of the composition and evolution of bacterial genomes. Besides model organisms and pathogens, some attention has been dedicated to industrial bacteria, notably members of the Lactobacillaceae family that are commonly studied and formulated as probiotic bacteria. Of particular interest is Lactobacillus acidophilus NCFM, an extensively studied strain that has been widely commercialized for decades and is being used for the delivery of vaccines and therapeutics.

RESULTS: Here, we revisit the L. acidophilus genome, which was sequenced twenty years ago, and determined the core and pan genomes of 114 publicly available L. acidophilus strains, spanning commercial isolates, academic strains and clones from the scientific literature. Results indicate a predictable high level of homogeneity within the species, but also reveal surprising mis-assemblies. Furthermore, by investigating twenty one available L. acidophilus NCFM-derived variants, we document overall genomic stability, with no observed genomic re-arrangement or inversions.

CONCLUSION: This study provides a comparative analysis of the currently available genomes for L. acidophilus and examines microevolution patterns for several strains derived from L. acidophilus NCFM, which revealed no to very few SNPs with strains sequenced at different points in time using different sequencing technologies and platforms. This re-affirms its suitability for industrial deployment as a probiotic and its use as an engineering chassis and delivery modality for novel biotherapeutics.},
}

@article {pmid39752324,
year = {2025},
author = {van Dijk, LR and Manson, AL and Earl, AM and Garimella, KV and Abeel, T},
title = {Fast exact gap-affine partial order alignment with POASTA.},
journal = {Bioinformatics (Oxford, England)},
volume = {},
number = {},
pages = {},
doi = {10.1093/bioinformatics/btae757},
pmid = {39752324},
issn = {1367-4811},
abstract = {MOTIVATION: Partial order alignment is a widely used method for computing multiple sequence alignments, with applications in genome assembly and pangenomics, among many others. Current algorithms to compute the optimal, gap-affine partial order alignment do not scale well to larger graphs and sequences. While heuristic approaches exist, they do not guarantee optimal alignment and sacrifice alignment accuracy.

RESULTS: We present POASTA, a new optimal algorithm for partial order alignment that exploits long stretches of matching sequence between the graph and a query. We benchmarked POASTA against the state-of-the-art on several diverse bacterial gene datasets and demonstrated an average speed-up of 4.1x and up to 9.8x, using less memory. POASTA's memory scaling characteristics enabled the construction of much larger POA graphs than previously possible, as demonstrated by megabase-length alignments of 342 Mycobacterium tuberculosis sequences.

POASTA is available on Github at https://github.com/broadinstitute/poasta.},
}

@article {pmid39749377,
year = {2024},
author = {Oh, JY and Do, KH and Jeong, JH and Kwak, S and Choe, S and An, D and Chae, JC and Lee, K and Seo, KW},
title = {Whole genome sequencing analysis of enteropathogenic Escherichia coli from human and companion animals in Korea.},
journal = {Journal of veterinary science},
volume = {},
number = {},
pages = {},
doi = {10.4142/jvs.24225},
pmid = {39749377},
issn = {1976-555X},
support = {2022-ER2103-01/KDCA/Korea Disease Control and Prevention Agency/Korea ; 2024-ER2103-00/KDCA/Korea Disease Control and Prevention Agency/Korea ; 23194MFDS012/MFDS/Ministry of Food and Drug Safety/Korea ; },
abstract = {IMPORTANCE: This study is essential for comprehending the zoonotic transmission, antimicrobial resistance, and genetic diversity of enteropathogenic Escherichia coli (EPEC).

OBJECTIVE: To improve our understanding of EPEC, this study focused on analyzing and comparing the genomic characteristics of EPEC isolates from humans and companion animals in Korea.

METHODS: The whole genome of 26 EPEC isolates from patients with diarrhea and 20 EPEC isolates from companion animals in Korea were sequenced using the Illumina HiSeq X (Illumina, USA) and Oxford Nanopore MinION (Oxford Nanopore Technologies, UK) platforms.

RESULTS: Most isolates were atypical EPEC, and did not harbor the bfpA gene. The most prevalent virulence genes were found to be ompT (humans: 61.5%; companion animals: 60.0%) followed by lpfA (humans: 46.2%; companion animals: 60.0%). Although pan-genome analyses showed no apparent correlation among the origin of the strains, virulence profiles, and antimicrobial resistance profiles, isolates included in clade A obtained from both humans and companion animals exhibited high similarity. Additionally, all the isolates included in clade A encoded the ompT gene and did not encode the hlyE gene. The two isolates from companion animals harbored an incomplete bundle-forming pilus region encoding bfpA and bfpB. Moreover, the type IV secretion system-associated genes tra and trb were found in the bfpA-encoding isolates from humans.

CONCLUSIONS AND RELEVANCE: Whole-genome sequencing enabled a more accurate analysis of the phylogenetic structure of EPEC and provided better insights into the understanding of EPEC epidemiology and pathogenicity.},
}

@article {pmid39748179,
year = {2025},
author = {Michael, TP},
title = {Can a plant biologist fix a thermostat?.},
journal = {The New phytologist},
volume = {},
number = {},
pages = {},
doi = {10.1111/nph.20382},
pmid = {39748179},
issn = {1469-8137},
support = {INV-040541/GATES/Bill & Melinda Gates Foundation/United States ; },
abstract = {The shift to reductionist biology at the dawn of the genome era yielded a 'parts list' of plant genes and a nascent understanding of complex biological processes. Today, with the genomics era in full swing, advances in high-definition genomics enabled precise temporal and spatial analyses of biological systems down to the single-cell level. These insights, coupled with artificial intelligence-driven in silico design, are propelling the development of the first synthetic plants. By integrating reductionist and systems approaches, researchers are not only reimagining plants as sources of food, fiber, and fuel but also as 'environmental thermostats' capable of mitigating the impacts of a changing climate.},
}

@article {pmid39748007,
year = {2025},
author = {Islam, MR and Mondol, SM and Hossen, MA and Khatun, MP and Selim, S and Amiruzzaman, and Gomes, DJ and Rahaman, MM},
title = {First report on comprehensive genomic analysis of a multidrug-resistant Enterobacter asburiae isolated from diabetic foot infection from Bangladesh.},
journal = {Scientific reports},
volume = {15},
number = {1},
pages = {424},
pmid = {39748007},
issn = {2045-2322},
mesh = {*Diabetic Foot/microbiology ; *Enterobacter/genetics/isolation & purification/drug effects/pathogenicity ; Humans ; Bangladesh ; *Drug Resistance, Multiple, Bacterial/genetics ; *Anti-Bacterial Agents/pharmacology ; Genome, Bacterial ; Genomics/methods ; Whole Genome Sequencing ; Microbial Sensitivity Tests ; Virulence Factors/genetics ; Phylogeny ; Enterobacteriaceae Infections/microbiology ; Biofilms/drug effects ; },
abstract = {Enterobacter asburiae (E. asburiae) is a gram-negative rod-shaped bacterium which has emerging significance as an opportunistic pathogen having high virulence pattern and drug resistant properties. In this study, we present the detailed analysis of the whole genome sequence of a multidrug-resistant (MDR) E. asburiae strain BDW1M3 from Bangladesh. The isolate was collected from an infected foot wound of a diabetic foot ulcer patient. Through sophisticated genomic techniques encompassing whole genome sequencing and in-depth bioinformatic analyses, this research unveils a profound understanding of the isolate's antimicrobial resistance patterns, virulence determinants, biosynthetic gene clusters, metabolic pathways and pathogenic potential. The isolate displayed resistance to Ampicillin, Fosfomycin, Cefoxitin, Tigecycline, Meropenem, Linezolid, Vancomycin antibiotics and demonstrated the capacity for biofilm formation. Several antimicrobial resistance genes such as blaACT-2,fosA2, baeR, qnrE2, vanA and numbers of virulence genes including ybaJ, csrA, barA, uvrY, pgaD, hlyD, hlyC, terC, purD were detected. Metal resistance genes investigation revealed the presence of cusCFBA operon system, and many other genes including zntA, zitB, czrB. Prophage region of Myoviridae was detected. Comparative genomics with 47 whole genome sequence (n = 47) shed light on the genetic diversity of E. asburiae strains from diverse sources and countries, with a notable observation that strains from both human and non-human origins exhibited significant pathogenicity potential, genomic and phylogenomic relations hinting at potential cross-species transmission. Pangenome analysis indicated toward an expanding pangenome of E. asburiae. Further research and in-depth comprehensive studies are required to investigate the prevalence of E. asburiae in Bangladesh and emphasize towards unraveling the bacterium's inherent pathogenic potential and the intricate molecular mechanisms that underlie its resistance traits and virulence properties.},
}

*Diabetic Foot/microbiology
*Enterobacter/genetics/isolation & purification/drug effects/pathogenicity
Humans
Bangladesh
*Drug Resistance, Multiple, Bacterial/genetics
*Anti-Bacterial Agents/pharmacology
Genome, Bacterial
Genomics/methods
Whole Genome Sequencing
Microbial Sensitivity Tests
Virulence Factors/genetics
Phylogeny
Enterobacteriaceae Infections/microbiology
Biofilms/drug effects

@article {pmid39746989,
year = {2025},
author = {Hu, H and Zhao, J and Thomas, WJW and Batley, J and Edwards, D},
title = {The role of pangenomics in orphan crop improvement.},
journal = {Nature communications},
volume = {16},
number = {1},
pages = {118},
pmid = {39746989},
issn = {2041-1723},
support = {LP230100351//Department of Education and Training | Australian Research Council (ARC)/ ; DP210100296//Department of Education and Training | Australian Research Council (ARC)/ ; DP200100762//Department of Education and Training | Australian Research Council (ARC)/ ; },
mesh = {*Crops, Agricultural/genetics ; *Genomics/methods ; *Genome, Plant ; *Plant Breeding/methods ; Gene Editing/methods ; Genetic Variation ; Food Security ; },
abstract = {Global food security depends heavily on a few staple crops, while orphan crops, despite being less studied, offer the potential benefits of environmental adaptation and enhanced nutritional traits, especially in a changing climate. Major crops have benefited from genomics-based breeding, initially using single genomes and later pangenomes. Recent advances in DNA sequencing have enabled pangenome construction for several orphan crops, offering a more comprehensive understanding of genetic diversity. Orphan crop research has now entered the pangenomics era and applying these pangenomes with advanced selection methods and genome editing technologies can transform these neglected species into crops of broader agricultural significance.},
}

*Crops, Agricultural/genetics
*Genomics/methods
*Genome, Plant
*Plant Breeding/methods
Gene Editing/methods
Genetic Variation
Food Security

@article {pmid39745367,
year = {2024},
author = {Chauhan, SM and Ardalani, O and Hyun, JC and Monk, JM and Phaneuf, PV and Palsson, BO},
title = {Decomposition of the pangenome matrix reveals a structure in gene distribution in the Escherichia coli species.},
journal = {mSphere},
volume = {},
number = {},
pages = {e0053224},
doi = {10.1128/msphere.00532-24},
pmid = {39745367},
issn = {2379-5042},
abstract = {UNLABELLED: Thousands of complete genome sequences for strains of a species that are now available enable the advancement of pangenome analytics to a new level of sophistication. We collected 2,377 publicly available complete genomes of Escherichia coli for detailed pangenome analysis. The core genome and accessory genomes consisted of 2,398 and 5,182 genes, respectively. We developed a machine learning approach to define the accessory genes characterizing the major phylogroups of E. coli plus Shigella: A, B1, B2, C, D, E, F, G, and Shigella. The analysis resulted in a detailed structure of the genetic basis of the phylogroups' differential traits. This pangenome structure was largely consistent with a housekeeping-gene-based MLST distribution, sequence-based Mash distance, and the Clermont quadruplex classification. The rare genome (consisting of genes found in <6.8% of all strains) consisted of 163,619 genes, about 79% of which represented variations of 315 underlying transposon elements. This analysis generated a mathematical definition of the genetic basis for a species.

IMPORTANCE: The comprehensive analysis of the pangenome of Escherichia coli presented in this study marks a significant advancement in understanding bacterial genetic diversity. By employing machine learning techniques to analyze 2,377 complete E. coli genomes, the study provides a detailed mapping of core, accessory, and rare genes. This approach reveals the genetic basis for differential traits across phylogroups, offering insights into pathogenicity, antibiotic resistance, and evolutionary adaptations. The findings enhance the potential for genome-based diagnostics and pave the way for future studies aimed at achieving a global genetic definition of bacterial phylogeny.},
}

@article {pmid39745363,
year = {2024},
author = {Akusobi, C and Choudhery, S and Benghomari, BS and Wolf, ID and Singhvi, S and Ioerger, TR and Rubin, EJ},
title = {Transposon-sequencing across multiple Mycobacterium abscessus isolates reveals significant functional genomic diversity among strains.},
journal = {mBio},
volume = {},
number = {},
pages = {e0337624},
doi = {10.1128/mbio.03376-24},
pmid = {39745363},
issn = {2150-7511},
abstract = {UNLABELLED: Mycobacterium abscessus (Mab) is a clinically significant pathogen and a highly genetically diverse species due to its large accessory genome. The functional consequence of this diversity remains unknown mainly because, to date, functional genomic studies in Mab have been primarily performed on reference strains. Given the growing public health threat of Mab infections, understanding the functional genomic differences among Mab clinical isolates can provide more insight into how its genetic diversity influences gene essentiality, clinically relevant phenotypes, and importantly, potential drug targets. To determine the functional genomic diversity among Mab strains, we conducted transposon-sequencing (TnSeq) on 21 genetically diverse clinical isolates, including 15 M. abscessus subsp. abscessus isolates and 6 M. abscessus subsp. massiliense isolates, cataloging all the essential and non-essential genes in each strain. Pan-genome analysis revealed a core set of 3,845 genes and a large accessory genome of 11,507. We identified 259 core essential genes across the 21 clinical isolates and 425 differentially required genes, representing ~10% of the Mab core genome. We also identified genes whose requirements were subspecies, lineage, and isolate-specific. Finally, by correlating TnSeq profiles, we identified 19 previously uncharacterized genetic networks in Mab. Altogether, we find that Mab clinical isolates are not only genetically diverse but functionally diverse as well.

IMPORTANCE: This study investigates the genetic diversity of Mycobacterium abscessus (Mab), a bacteria known for causing difficult-to-treat infections. Researchers performed transposon-sequencing (TnSeq) on 21 different clinical isolates of Mab to identify essential and non-essential genes in each strain. Through this analysis, they identified core genes required for growth across all strains. Interestingly, they also identified genes whose requirement for growth or "essentiality" were subspecies, lineage, and isolate-specific. This study reveals that Mab's genetic diversity translates into significant functional differences among clinical isolates. Insights from this paper lay essential groundwork for future studies exploring the biological and clinical implications of genetic diversity in Mab clinical isolates. Understanding this diversity could guide targeted therapies and offer new insights into managing infections caused by Mab, a growing public health concern.},
}

@article {pmid39742300,
year = {2024},
author = {Li, D and Wang, Y and Yuan, T and Cao, M and He, Y and Zhang, L and Li, X and Jiang, Y and Li, K and Sun, J and Lv, G and Su, G and Wang, Q and Pan, Y and Li, X and Jiang, Y and Yang, G and Groenen, MAM and Derks, MFL and Ding, R and Ding, X and Yu, T},
title = {Pangenome and genome variation analyses of pigs unveil genomic facets for their adaptation and agronomic characteristics.},
journal = {iMeta},
volume = {3},
number = {6},
pages = {e257},
pmid = {39742300},
issn = {2770-596X},
abstract = {The development of a comprehensive pig graph pangenome assembly encompassing 27 genomes represents the most extensive collection of pig genomic data to date. Analysis of this pangenome reveals the critical role of structural variations in driving adaptation and defining breed-specific traits. Notably, the study identifies BTF3 as a key candidate gene governing intramuscular fat deposition and meat quality in pigs. These findings underscore the power of pangenome approaches in uncovering novel genomic features underlying economically important agricultural traits. Collectively, these results demonstrate the value of leveraging large-scale, multi-genome analyses for advancing our understanding of livestock genomes and accelerating genetic improvement.},
}

@article {pmid39741590,
year = {2024},
author = {Banerjee, R and Chaudhari, NM and Lahiri, A and Gautam, A and Bhowmik, D and Dutta, C and Chattopadhyay, S and Huson, DH and Paul, S},
title = {Corrigendum: Interplay of various evolutionary modes in genome diversification and adaptive evolution of the family Sulfolobaceae.},
journal = {Frontiers in microbiology},
volume = {15},
number = {},
pages = {1538738},
doi = {10.3389/fmicb.2024.1538738},
pmid = {39741590},
issn = {1664-302X},
abstract = {[This corrects the article DOI: 10.3389/fmicb.2021.639995.].},
}

@article {pmid39738919,
year = {2024},
author = {Han, JE and Kang, S and Lee, SY and Bae, JW},
title = {Characterisation of Aequorivita ciconiae sp. nov., isolated from oriental stork, Ciconia boyciana.},
journal = {Antonie van Leeuwenhoek},
volume = {118},
number = {2},
pages = {47},
pmid = {39738919},
issn = {1572-9699},
support = {RS-2023-00227274//National Research Foundation of Korea/ ; NRF-2020R1A2C3012797//Mid-Career Researcher Programme/ ; 22213MFDS537//Ministry of Food and Drug Safety/ ; },
mesh = {*Phylogeny ; *RNA, Ribosomal, 16S/genetics ; *Flavobacteriaceae/genetics/classification/isolation & purification ; Animals ; *DNA, Bacterial/genetics ; *Base Composition ; *Fatty Acids/chemistry/analysis ; Republic of Korea ; *Bacterial Typing Techniques ; Birds/microbiology ; Feces/microbiology ; Sequence Analysis, DNA ; Phospholipids/analysis ; },
abstract = {A single novel bacterial strain designated as H23M31[T] was isolated from the faecal sample of oriental stork (Ciconia boyciana) that inhabits the Republic of Korea. It was a rod-shaped, facultative anaerobic, Gram-negative, and non-motile strain. Phylogenetic analysis based on the 16S rRNA gene sequence revealed that it branched from Aequorivita within Flavobacteriaceae. It was most closely related to A. capsosiphonis DSM 23843[ T], which shared the sequence similarity of 96.36%. The strain exhibited optimal growth at pH 7.0 in a marine broth medium with 1% NaCl incubated at 30 °C. Chemotaxonomic characteristics indicated that the predominant cellular fatty acids were iso-C15:0 (24.4%), iso-C17:0 3-OH (15.9%), and anteiso-C15:0 (13.9%). The polar lipid of the strain contained phosphatidylcholine (PC), phosphatidylglycerol (PG), and diphosphatidylglycerol (DPG). The major isoprenoid quinone was menaquinone 6 (MK-6), which was identical with that of a closely related Aequorivita species. The genomic G + C contents of the strain was 38.25 mol%. Average nucleotide identity (ANI), average amino acid identity (AAI), and digital DNA-DNA hybridization (dDDH) values between the novel isolate and A. viscosa CGMCC 1.11023[ T] were 75.83%, 80.34% and 20.50%, respectively. Phylogenetic analyses revealed the evolutionary relationships of the strain, demonstrating that the strain clusters with other Aequorivita species. Pan-genome analyses and genome comparisons indicated that, unlike other environmentally isolated species, it possesses unique genes that enhance its ability to colonise the harsh animal gut environment. Taxonomic characterisation suggested that strain H23M31[T] represents a novel Aequorivita species, and the proposed name is Aequorivita ciconiae sp. nov. The type strain of A. ciconiae is H23M31[T] (= KCTC 62809[ T] = JCM 33229[ T]).},
}

*Phylogeny
*RNA, Ribosomal, 16S/genetics
*Flavobacteriaceae/genetics/classification/isolation & purification
Animals
*DNA, Bacterial/genetics
*Base Composition
*Fatty Acids/chemistry/analysis
Republic of Korea
*Bacterial Typing Techniques
Birds/microbiology
Feces/microbiology
Sequence Analysis, DNA
Phospholipids/analysis

@article {pmid39736996,
year = {2024},
author = {Lu, W and Zha, B and Lyu, J and LingHu, C and Chen, J and Deng, S and Zhang, X and Li, L and Wang, G},
title = {Whole-genome sequencing and genomic analysis of four Akkermansia strains newly isolated from human feces.},
journal = {Frontiers in microbiology},
volume = {15},
number = {},
pages = {1500886},
pmid = {39736996},
issn = {1664-302X},
abstract = {BACKGROUND: Numerous studies have demonstrated that Akkermansia is closely associated with human health. These bacteria colonize the mucus layer of the gastrointestinal tract and utilize mucin as their sole source of carbon and nitrogen. Akkermansia spp. exhibit potential as probiotics under specific conditions. However, the gene accumulation curve derived from pan-genome analysis suggests that the genome of Akkermansia strains remains open. Consequently, current genome mining efforts are insufficient to fully capture the intraspecific and interspecific characteristics of Akkermansia, necessitating continuous exploration of the genomic and phenotypic diversity of new isolates.

METHODS: Based on this finding, we sequenced, assembled, and functionally annotated the whole genomes of four new human isolates from our laboratory: AKK-HX001, AKK-HX002, AKK-HX003, and AKK-HX004.

RESULTS: Phylogenetic analysis revealed that all four isolates belonged to the AmII phylogroup, whereas the type strain DSM 22959 is classified within the AmI phylogroup. Moreover, 2,184 shared homologous genes were identified among the four isolates. Functional annotation using the COG, KEGG, and CAZy databases indicated that the functional genes of the four isolates were primarily associated with metabolism. Two antibiotic resistance genes were identified in AKK-HX001 and AKK-HX002, while three resistance genes were detected in AKK-HX003 and AKK-HX004. Additionally, each of the four isolates possessed two virulence genes and three pathogenicity genes, none of which were associated with pathogenicity. The prediction of mobile genetic elements indicated unequal distributions of GIs among the isolates, and a complete CRISPR system was identified in all isolates except AKK-HX003. Two annotated regions of secondary metabolite biosynthesis genes, both belonging to Terpene, were detected using the antiSMASH online tool.

CONCLUSION: These findings indicate that the four Akkermansia isolates, which belong to a phylogroup distinct from the model strain DSM 22959, exhibit lower genetic risk and may serve as potential probiotic resources for future research.},
}

@article {pmid39736538,
year = {2024},
author = {Radjasa, OK and Steven, R and Natanael, Y and Nugrahapraja, H and Radjasa, SK and Kristianti, T and Moeis, MR and Trinugroho, JP and Suharya, HB and Rachmatsyah, AO and Dwijayanti, A and Putri, MR and de Fretes, CE and Siallagan, ZL and Fadli, M and Opier, RDA and Farahyah, JD and Rahmawati, V and Rizanti, M and Humaira, Z and Prihatmanto, AS and Hananto, ND and Susanto, RD and Chahyadi, A and Elfahmi, and Priharto, N and Kamarisima, and Dwivany, FM},
title = {From the depths of the Java Trench: genomic analysis of Priestia flexa JT4 reveals bioprospecting and lycopene production potential.},
journal = {BMC genomics},
volume = {25},
number = {1},
pages = {1259},
pmid = {39736538},
issn = {1471-2164},
mesh = {*Lycopene/metabolism ; Indonesia ; *Genome, Bacterial ; Bioprospecting ; Genomics/methods ; Phylogeny ; Multigene Family ; Peptide Synthases/genetics/metabolism ; Whole Genome Sequencing ; Carotenoids/metabolism ; Actinobacteria/genetics/metabolism ; },
abstract = {BACKGROUND: The marine environment boasts distinctive physical, chemical, and biological characteristics. While numerous studies have delved into the microbial ecology and biological potential of the marine environment, exploration of genetically encoded, deep-sea sourced secondary metabolites remains scarce. This study endeavors to investigate marine bioproducts derived from deep-sea water samples at a depth of 1,000 m in the Java Trench, Indonesia, utilizing both culture-dependent and whole-genome sequencing methods.

RESULTS: Our efforts led to the successful isolation and cultivation of a bacterium Priestia flexa JT4 from the water samples, followed by comprehensive genome sequencing. The resultant high-quality draft genome, approximately 4 Mb, harbored 5185 coding sequences (CDSs). Notably, 61.97% of these CDSs were inadequately characterized, presenting potential novel CDSs. This study is the first to identify the "open-type" (α < 1) pangenome within the genus Priestia. Moreover, our analysis uncovered eight biosynthetic gene clusters (BGCs) using the common genome mining pipeline, antiSMASH. Two non-ribosomal peptide synthetase (NRPS) BGCs within these clusters exhibited the potential to generate novel biological compounds. Noteworthy is the confirmation that the terpene BGC in P. flexa JT4 can produce lycopene, a compound in substantial industrial demand. The presence of lycopene in the P. flexa JT4 cells was verified using Ultra-performance liquid chromatography-mass spectrometry (UPLC-MS/MS) in multiple reaction modes.

CONCLUSIONS: This study highlights the bioprospecting opportunity to explore novel bioproducts and lycopene compounds from P. flexa JT4. It marks the pioneering exploration of deep-sea bacterium bioprospecting in Indonesia, seeking to unveil novel bioproducts and lycopene compounds through a genome mining approach.},
}

*Lycopene/metabolism
Indonesia
*Genome, Bacterial
Bioprospecting
Genomics/methods
Phylogeny
Multigene Family
Peptide Synthases/genetics/metabolism
Whole Genome Sequencing
Carotenoids/metabolism
Actinobacteria/genetics/metabolism

@article {pmid39725890,
year = {2024},
author = {Javier-López, R and Geliashvili, N and Birkeland, NK},
title = {Comparative genomics of Fervidobacterium: a new phylogenomic landscape of these wide-spread thermophilic anaerobes.},
journal = {BMC genomics},
volume = {25},
number = {1},
pages = {1248},
pmid = {39725890},
issn = {1471-2164},
support = {328955//Norges Forskningsråd/ ; 328955//Norges Forskningsråd/ ; 862555//ERA-NET Cofund on Food Systems and Climate (FOSC)/ ; 862555//ERA-NET Cofund on Food Systems and Climate (FOSC)/ ; 862555//ERA-NET Cofund on Food Systems and Climate (FOSC)/ ; CPEA-LT-2017/10061//Norwegian Directorate for Higher Education and Skills/ ; CPEA-LT-2017/10061//Norwegian Directorate for Higher Education and Skills/ ; },
mesh = {*Phylogeny ; *Genome, Bacterial ; *Genomics ; RNA, Ribosomal, 16S/genetics ; Base Composition ; },
abstract = {BACKGROUND: Fervidobacterium is a genus of thermophilic anaerobic Gram-negative rod-shaped bacteria belonging to the phylum Thermotogota. They can grow through fermentation on a wide range of sugars and protein-rich substrates. Some can also break down feather keratin, which has significant biotechnological potential. Fervidobacteria genomes have undergone several horizontal gene transfer events, sharing DNA with unrelated microbial taxa. Despite increasing biotechnological and evolutionary interest in this genus, only seven species have been described to date. Here, we present and describe six new and complete Fervidobacterium genomes, including the type strains Fervidobacterium gondwanense CBS-1[ T], F. islandicum H-21[ T] and F. thailandense FC2004[T], one novel isolate from Georgia (strain GSH) and two strains (DSM 21710 and DSM 13770) that have not been previously described along with an evolutionary and phylogenomic analysis of the genus.

RESULTS: The complete genomes were around 2 Mb with approximately 2,000 CDS identified and annotated in each of them and a G + C content ranging from 38.9 mol% to 45.8 mol%. Phylogenomic comparisons of all currently available Fervidobacterium genomes, including OrthoANI and TYGS analyses, as well as a phylogenetic analysis based on the 16S rRNA gene, identified six species and nine subspecies clusters across the genus, with a consistent topology and a distant and separately branching species, Fervidobacterium thailandense. F. thailandense harbored the highest number of transposases, CRISPR clusters, pseudo genes and horizontally transferred regions The pan genome of the genus showed that 44% of the genes belong to the cloud pangenome, with most of the singletons found also in F. thailandense.

CONCLUSIONS: The additional genome sequences described in this work and the comparison with all available Fervidobacterium genome sequences provided new insights into the evolutionary history of this genus and supported a phylogenetic reclassification. The phylogenomic results from OrthoANI and TYGS analyses revealed that F. riparium and F. gondwanense belong to the same genome species, and includes Fervidobacterium sp. 13770, while "F. pennivorans" strain DYC belongs to a separate genome species, whereas Fervidobacterium sp. 21710 and Fervidobacterium sp. GSH within the Fervidobacterium pennivorans clade represent two subspecies. F. changbaicum is reclassified as F. islandicum.},
}

*Phylogeny
*Genome, Bacterial
*Genomics
RNA, Ribosomal, 16S/genetics
Base Composition

@article {pmid39724170,
year = {2024},
author = {Farrell, AA and Nesbø, CL and Zhaxybayeva, O},
title = {Bacterial growth temperature as a horizontally acquired polygenic trait.},
journal = {Genome biology and evolution},
volume = {},
number = {},
pages = {},
doi = {10.1093/gbe/evae277},
pmid = {39724170},
issn = {1759-6653},
abstract = {Evolutionary events leading to organismal preference for a specific growth temperature, as well as genes whose products are needed for a proper function at that temperature, are poorly understood. Using 64 bacteria from phylum Thermotogota as a model system, we examined how optimal growth temperature changed throughout Thermotogota history. We inferred that Thermotogota's last common ancestor was a thermophile and that some Thermotogota evolved the mesophilic and hyperthermophilic lifestyles secondarily. By modeling gain and loss of genes throughout Thermotogota history and by reconstructing their phylogenies, we demonstrated that adaptations to lower and higher growth temperature involve both the acquisition of necessary genes and loss of unnecessary genes. Via a pangenome-wide association study, we correlated presence/absence of 68 genes with specific optimal growth temperature intervals. While some of these genes are poorly characterized, most are involved in metabolism of amino acids, nucleotides, carbohydrates, and lipids, as well as in signal transduction and regulation of transcription. Most of the 68 genes have a history of horizontal gene transfer with other bacteria and archaea that often grow at similar temperatures, suggesting that parallel acquisitions of genes likely promote independent adaptations of different Thermotogota species to specific growth temperatures.},
}

@article {pmid39722670,
year = {2024},
author = {Yakubov, LA and Taranov, OS and Sidorov, SV and Nikonov, SD and Ostanin, AA and Chernykh, ER and Kolchanov, NA and Bogachev, SS},
title = {The concept of natural genome reconstruction.Part 1. Basic provisions of the "natural genome reconstruction" concept. Changing the genome of hematopoietic stem cells using several natural cellular mechanisms that are inherent in the hematopoietic cell and determine its biological status as "the source of the body's reparative potential".},
journal = {Vavilovskii zhurnal genetiki i selektsii},
volume = {28},
number = {7},
pages = {696-705},
doi = {10.18699/vjgb-24-78},
pmid = {39722670},
issn = {2500-0462},
abstract = {We present a series of articles proving the existence of a previously unknown mechanism of interaction between hematopoietic stem cells and extracellular double-stranded DNA (and, in particular, double-stranded DNA of the peripheral bloodstream), which explains the possibility of emergence and fixation of genetic information contained in double-stranded DNA of extracellular origin in hematopoietic stem cells. The concept of the possibility of stochastic or targeted changes in the genome of hematopoietic stem cells is formulated based on the discovery of new, previously unknown biological properties of poorly differentiated hematopoietic precursors. The main provisions of the concept are as follows. The hematopoietic stem cell takes up and internalizes fragments of extracellular double-stranded DNA via a natural mechanism. Specific groups of glycocalyx factors, including glycoproteins/proteoglycans, glycosylphosphatidylinositol-anchored proteins and scavenger receptors, take part in the internalization event. The binding sites for DNA fragments are heparin-binding domains and clusters of positively charged amino acid residues that are parts of protein molecules of these factors. Extracellular fragments delivered to the internal compartments of hematopoietic stem cells initiate terminal differentiation, colony formation, and proliferation of hematopoietic precursors. The molecular manifestation of these processes is the emergence and repair of pangenomic single-strand breaks. The occurrence of pangenomic single-strand breaks and restoration of genome (genomic DNA) integrity are associated with activation of a "recombinogenic situation" in the cell; during its active phase, stochastic homologous recombination or other recombination events between extracellular fragments localized in the nucleus and chromosomal DNA are possible. As a result, genetic material of initially extracellular localization either integrates into the recipient genome with the replacement of homologous chromosomal segments, or is transitively present in the nucleus and can manifest itself as a new genetic trait. It is assumed that as a result of stochastic acts of homologous exchange, chromosome loci are corrected in hematopoietic stem cells that have acquired mutations during the existence of the organism, which are the cause of clonal hematopoiesis associated with old age. In this regard, there is a fundamental possibility of changing the hematopoietic status of hematopoietic stem cells in the direction of polyclonality and the original diversity of clones. Such events can form the basis for the rejuvenation of the blood-forming cell system. The results of the laboratory's work indicate that other stem cells in the body capture extracellular DNA fragments too. This fact creates a paradigm for the overall rejuvenation of the body.},
}

@article {pmid39722539,
year = {2025},
author = {Zepeda-Rivera, MA and Eisele, Y and Baryiames, A and Wu, H and Mengoni, C and Piccinno, G and McMahon, EF and LaCourse, KD and Jones, DS and Hauner, H and Minot, SS and Segata, N and Dewhirst, FE and Johnston, CD and Bullman, S},
title = {Fusobacterium sphaericum sp. nov., isolated from a human colon tumor adheres to colonic epithelial cells and induces IL-8 secretion.},
journal = {Gut microbes},
volume = {17},
number = {1},
pages = {2442522},
doi = {10.1080/19490976.2024.2442522},
pmid = {39722539},
issn = {1949-0984},
mesh = {Humans ; *Interleukin-8/metabolism/genetics ; *Colonic Neoplasms/microbiology/pathology ; *Fusobacterium/isolation & purification/genetics ; *Epithelial Cells/microbiology ; *Phylogeny ; Bacterial Adhesion ; Colon/microbiology/pathology ; Feces/microbiology ; Adenocarcinoma/microbiology/pathology ; Gastrointestinal Microbiome ; RNA, Ribosomal, 16S/genetics ; Genome, Bacterial ; },
abstract = {Cancerous tissue is a largely unexplored microbial niche that provides a unique environment for the colonization and growth of specific bacterial communities, and with it, the opportunity to identify novel bacterial species. Here, we report distinct features of a novel Fusobacterium species, F. sphaericum sp. nov. (Fs), isolated from primary colon adenocarcinoma tissue. We acquire the complete closed genome and associated methylome of this organism and phylogenetically confirm its classification into the Fusobacterium genus, with F. perfoetens as its closest neighbor. Fs is phenotypically and genetically distinct, with morphological analysis revealing its coccoid shape, that while similar to F. perfoetens is rare for most Fusobacterium members. Fs displays a metabolic profile and antibiotic resistance repertoire consistent with other Fusobacterium species. In vitro, Fs has adherent and immunomodulatory capabilities, as it intimately associates with human colon cancer epithelial cells and promotes IL-8 secretion. An analysis of the prevalence and abundance of Fs in > 20,000 human metagenomic samples shows that it is a rarely detected member within human stool with variable relative abundance, found in both healthy controls and patients with colorectal cancer (CRC). Our study sheds light on a novel bacterial species isolated directly from the human CRC tumor niche and given its in vitro interaction with cancer epithelial cells suggests that its role in human health and disease warrants further investigation.},
}

Humans
*Interleukin-8/metabolism/genetics
*Colonic Neoplasms/microbiology/pathology
*Fusobacterium/isolation & purification/genetics
*Epithelial Cells/microbiology
*Phylogeny
Bacterial Adhesion
Colon/microbiology/pathology
Feces/microbiology
Adenocarcinoma/microbiology/pathology
Gastrointestinal Microbiome
RNA, Ribosomal, 16S/genetics
Genome, Bacterial

@article {pmid39722458,
year = {2024},
author = {He, W and Li, X and Qian, Q and Shang, L},
title = {The Developments and Prospects of Plant Super Pangenomes: Demands, Approaches and Applications.},
journal = {Plant communications},
volume = {},
number = {},
pages = {101230},
doi = {10.1016/j.xplc.2024.101230},
pmid = {39722458},
issn = {2590-3462},
abstract = {By integrating genomes of different accessions, the pangenome can offer more comprehensive and reference-bias-free population genetic information in a species than a single reference genome. With the rapid accumulation of genomic sequencing data and the expanding scope of plant research, the focus of plant pangenomics research has gradually evolved from a single species to multiple species in recent years, giving rise to the concept of super pangenome that cover all genomic sequences of a genus-level taxonomic groups. By integrating more cultivated and wild species, the super pangenome has made significant contributions to the resolution of multiple research areas such as plant genetic diversity, evolution, domestication, and molecular breeding. Here, we provide a comprehensive overview of the plant super pangenomes, focusing on its unique value and development demands, construction approaches, potential applications and achievements. We highlight the distinctive advantages and promising prospects of super pangenomes and discuss the current challenges and future directions.},
}

@article {pmid39719828,
year = {2024},
author = {Zhang, L and Liu, Y and Huang, Y and Zhang, Y and Fu, Y and Xiao, Y and Chen, S and Zhang, K and Cheng, F},
title = {SolPGD: Solanaceae Pan-genomes Reveal Extensive Fractionation and Functional Innovation of Duplicated Genes.},
journal = {Plant communications},
volume = {},
number = {},
pages = {101231},
doi = {10.1016/j.xplc.2024.101231},
pmid = {39719828},
issn = {2590-3462},
abstract = {The Solanaceae family contains many agriculturally important crops, including tomato, potato, pepper, and tobacco, as well as others with growing potential, such as the orphan crops groundcherry, wolfberry, and pepino. Research progress varies greatly among these species, with model crops like tomato far ahead, which limits the broader agricultural application of other solanaceous species. Here, we constructed the interspecies pan-genome for the Solanaceae family and identified distinct patterns of gene retention. We reveal that the activity of specific transposable elements is associated with gene fractionation and transposition. The pan-genome is further resolved at the level of T subgenomes that were generated by Solanaceae specific paleo-hexaploidization (T event). We show the strong fractionation (loss) and divergence of genes resulting from ancient duplications. For example, all the class A and E flower model genes in Solanaceae originally evolved from two tandemly duplicated genes, which further expanded through the γ and T events and then fractionated into ten genes in tomato, acquiring distinct functions critical for fruit development. Based on these results, we developed the Solanaceae Pan-Genome Database (SolPGD, http://www.bioinformaticslab.cn/SolPGD), which integrates various datasets of the inter- and intra-pangenomes of Solanaceae. These findings and valuable resources will further promote studies of solanaceous species, including the orphan crops.},
}

@article {pmid39718018,
year = {2024},
author = {Tian, R and Xie, F and Wang, X and Dai, L and Wang, J and Liu, Y and Zhao, C and Li, Q and Zhang, W},
title = {Epidemiological investigation and drug resistance analysis of Avian pathogenic Escherichia coli (APEC) of Wenchang chickens in Hainan, China.},
journal = {Avian pathology : journal of the W.V.P.A},
volume = {},
number = {},
pages = {1-41},
doi = {10.1080/03079457.2024.2447296},
pmid = {39718018},
issn = {1465-3338},
abstract = {Avian pathogenic Escherichia coli (APEC) is one of the major causes of poultry morbidity worldwide, severely reducing egg production and embryo hatchability in laying hens. Hainan Wenchang chicken is an important poultry breed in Hainan, China, and its culture has been affected by APEC for a long time. In this study, in order to investigate the causes of low hatchability and a large number of weak chicks during the breeding of Wenchang chicken, a total of 130 strains of APEC were isolated from 591 chicken embryo samples collected from five large-scale farms of Wenchang chicken in Hainan area. The APEC isolates from Hainan Wenchang chicken embryos were analyzed in terms of serotypes, drug resistance, genomes and evolutionary relationships. O8 was the main prevalent serotype of APEC from embryos, and the isolates were highly resistant to antibiotics and multi-drug resistant. 19.2% of the isolates were resistant to 14 antibiotics with a resistance rate of more than 73%. The number of resistance genes carried by APEC isolates from embryos was stabilized at 53. The results of pan-genomic analysis showed that the genomes of Hainan Wenchang chicken embryo APEC isolates would be concentrated in 2 evolutionary clusters, and the isolates of the same serotype had extremely close evolutionary relationships. This study is the first large-scale isolation and analysis of APEC isolated from Wenchang chicken embryos, which can provide a reference for the prevention and control of APEC and antibiotic use in Hainan Wenchang chickens.},
}

@article {pmid39717611,
year = {2024},
author = {Baati, H and Siala, M and Benali, S and Azri, C and Dunlap, C and Martínez-Espinosa, RM and Trigui, M},
title = {Elucidating metabolic pathways through genomic analysis in highly heavy metal-resistant Halobacterium salinarum strains.},
journal = {Heliyon},
volume = {10},
number = {23},
pages = {e40822},
pmid = {39717611},
issn = {2405-8440},
abstract = {The annotated and predicted genomes of five archaeal strains (AS1, AS2, AS8, AS11 and AS19), isolated from Sfax solar saltern sediments (Tunisia) and affiliated with Halobacterium salinarum, were performed by RAST webserver (Rapid Annotation using Subsystem Technology) and NCBI prokaryotic genome annotation pipeline (PGAP). The results showed the ability of strains to use a reduced semi-phosphorylative Entner-Doudoroff pathway for glucose degradation and an Embden-Meyerhof one for gluconeogenesis. They could use glucose, fructose, glycerol, and acetate as sole source of carbon and energy. ATP synthase, various cytochromes and aerobic respiration proteins were encoded. All strains showed fermentation capability through the arginine deiminase pathway and facultative anaerobic respiration using electron acceptors (Dimethyl sulfoxide and trimethylamine N-oxide). Several biosynthesis pathways for many amino acids were identified. Comparative and pangenome analyses between the strains and the well-studied halophilic archaea Halobacterium NRC-1 highlighted a notable dissimilarity. Besides, the strains shared a core genome of 1973 genes and an accessory genome of 767 genes. 129, 94, 67, 15 and 29 unique genes were detected in the AS1, AS2, AS8, AS11 and AS19 genomes, respectively. Most of these unique genes code for hypothetical proteins. The strains displayed plant-growth promoting characteristics under heavy metal stress (Ammonium assimilation, phosphate solubilization, chemotaxis, cell motility and production of indole acetic acid, siderophore and phenazine). Therefore, they could be used as a biofertilizer to promote plant growth. The genomes encoded numerous biotechnologically relevant genes responsible for vitamin biosynthesis, including cobalamin, folate, biotin, pantothenate, riboflavin, thiamine, menaquinone, nicotinate, and nicotinamide. The carotenogenetic pathway of the studied strains was also predicted. Consequently, the findings of this study contribute to a better understanding of the halophilic archaea metabolism providing valuable insights into their ecophysiology as well as relevant biotechnological applications.},
}

@article {pmid39713061,
year = {2024},
author = {Ning, W and Wang, W and Liu, Z and Xie, W and Chen, H and Hong, D and Yang, QY and Cheng, S and Guo, L},
title = {The pan-NLRome analysis based on 23 genomes reveals the diversity of NLRs in Brassica napus.},
journal = {Molecular breeding : new strategies in plant improvement},
volume = {44},
number = {12},
pages = {2},
pmid = {39713061},
issn = {1572-9788},
abstract = {Brassica napus, a globally significant oilseed crop, exhibits a wide distribution across diverse climatic zones. B. napus is being increasingly susceptible to distinct diseases, such as blackleg, clubroot and sclerotinia stem rot, leading to substantial reductions in yield. Nucleotide-binding site leucine-rich repeat genes (NLRs), the most pivotal family of resistance genes, can be effectively harnessed by identifying and uncovering their diversity to acquire premium disease-resistant gene resources. Here, we collected the genomes of 23 accessions and established the first comprehensive pan-NLRome in B. napus by leveraging multiple genomic resources. We observe significant variation in the number of NLR genes across different B. napus accessions, ranging from 189 to 474. Notably, TNL (TIR-NBS-LRR) genes constitute approximately half of the total count, indicating their predominant presence in B. napus. The number of NLRs in the C subgenome is significantly higher than that in the A subgenome, and chromosome C09 exhibits the highest density of NLR genes with featuring multiple NLR clusters. Domain analysis reveals that the integrated domains significantly enhance the diversity of NLRs, with B3 DNA binding, VQ, and zinc fingers being the most prevalent integrated domains. Pan-genomic analysis reveals that the core type of NLR genes, which is present in most accessions, constitutes approximately 58% of the total NLRs. Furthermore, we conduct a comparative analysis of the diversity of NLR genes across distinct ecotypes, leading to the identification of ecotype-specific NLRs and their integrated domains. In conclusion, our study effectively addresses the limitations of a single reference genome and provides valuable insights into the diversity of NLR genes in B. napus, thereby contributing to disease resistance breeding.},
}

@article {pmid39708886,
year = {2024},
author = {Bano, S and Khatoon, A and Quareshi, U and Ul-Haq, Z and Karim, A},
title = {Pan-genome analysis and drug repurposing strategies for extensively drug-resistant Salmonella Typhi: Subtractive genomics and e-pharmacophore approaches.},
journal = {International journal of biological macromolecules},
volume = {},
number = {},
pages = {139003},
doi = {10.1016/j.ijbiomac.2024.139003},
pmid = {39708886},
issn = {1879-0003},
abstract = {In the current study, we presented the genome sequence and taxonomic classification of the new extensively drug-resistant (XDR) Salmonella enterica serovar Typhi strain JRCGR-ST-AK02. Its genome size was found to be 4,780,534 bp, containing 4864 genes. Taxonomic classification was performed based on the Average Nucleotide Identity (ANI), Genome-to-Genome Distance Calculator (GGDC) and Average Amino Acid Identity (AAI) analysis. Pan-genome analysis revealed 34,4915 core genes, which are predominantly involved in general functions and carbohydrate metabolism. We used a subtractive genomics approach and identified the PocR protein as a drug target. Its 3D structure was built using homology modeling, and an e-pharmacophore hypothesis was created using its binding site. The pharmacophore hypothesis was screened against FDA-approved ligands library and a total of 2018 out 9392 drugs were selected for molecular docking. Cangrelor and Pentagastrin presented the highest docking scores (≥ -9.0). The binding dynamics of these promising FDA-approved drugs were further confirmed through 200 ns molecular dynamics simulation, highlighting their stable and strong interactions with the PocR protein. Our study highlights the potential of Cangrelor and Pentagastrin for repurposing against XDR Salmonella Typhi. By identifying these drugs as promising candidates, we pave the way for new treatments for XDR Salmonella Typhi infections.},
}

@article {pmid39702388,
year = {2024},
author = {Liu, H and Fan, Z and Tong, N and Lin, J and Huang, Y and Duan, Y and Zhu, X},
title = {The exploration of high production of tiancimycins in Streptomyces sp. CB03234-S revealed potential influences of universal stress proteins on secondary metabolisms of streptomycetes.},
journal = {Microbial cell factories},
volume = {23},
number = {1},
pages = {337},
pmid = {39702388},
issn = {1475-2859},
support = {CX20210112//the Hunan Provincial Innovation Foundation for Postgraduate/ ; 2021zzts0330//the Fundamental Research Funds for the Central Universities of Central South University (CSU)/ ; 2023SK2071//the Science and Technology Innovation Program of Hunan Province/ ; BP0820034//the Chinese Ministry of Education 111 Project/ ; BP0820034//the Chinese Ministry of Education 111 Project/ ; },
mesh = {*Streptomyces/metabolism/genetics ; *Secondary Metabolism ; *Bacterial Proteins/genetics/metabolism ; Genome, Bacterial ; },
abstract = {BACKGROUND: Universal stress proteins (USPs) are prevalent in various bacteria to cope with different adverse stresses, while their possible effects on secondary metabolisms of hosts are unclear. Tiancimycins (TNMs) are ten-membered endiynes possessing excellent potential for development of anticancer antibody-drug conjugates. During our efforts to improve TNMs titer, a high-producing strain Streptomyces sp. CB03234-S had been obtained and its possible high yield mechanism is being continuously explored to further enhance TNMs production.

RESULTS: In this work, the whole-genome resequencing and analysis results revealed a notable 583 kb terminal deletion containing 8 highly expressed usp genes in the genome of CB03234-S. The individual complementation of lost USPs in CB03234-S all showed differential effects on secondary metabolism, especially TNMs production. Among them, the overexpression of USP3 increased TNMs titer from 12.8 ± 0.2 to 31.1 ± 2.3 mg/L, while the overexpression of USP8 significantly reduced TNMs titer to only 1.0 ± 0.1 mg/L, but activated the production of porphyrin-type compounds. Subsequent genetic manipulations on USP3/USP8 orthologs in Streptomyces. coelicolor A3(2) and Streptomyces sp. CB00271 also presented clear effects on the secondary metabolisms of hosts. Further sequence similarity network analysis and Streptomyces-based pan‑genomic analysis suggested that the USP3/USP8 orthologs are widely distributed across Streptomyces.

CONCLUSION: Our studies shed light on the potential effects of USPs on secondary metabolisms of streptomycetes for the first time, and USPs could become novel targets for exploring and exploiting natural products in streptomycetes.},
}

*Streptomyces/metabolism/genetics
*Secondary Metabolism
*Bacterial Proteins/genetics/metabolism
Genome, Bacterial

@article {pmid39699575,
year = {2024},
author = {Xie, X and Deng, X and Chen, L and Yuan, J and Chen, H and Wei, C and Feng, C and Liu, X and Qiu, G},
title = {From Gene to Structure: Unraveling Genomic Dark Matter in Ca. Accumulibacter.},
journal = {Environmental science & technology},
volume = {},
number = {},
pages = {},
doi = {10.1021/acs.est.4c09948},
pmid = {39699575},
issn = {1520-5851},
abstract = {"Candidatus Accumulibacter" is a unique and pivotal genus of polyphosphate-accumulating organisms prevalent in wastewater treatment plants and plays mainstay roles in the global phosphorus cycle. However, the efforts to fully understand their genetic and metabolic characteristics are largely hindered by major limitations in existing sequence-based annotation methods. Here, we reported an integrated approach combining pangenome analysis, protein structure prediction and clustering, and meta-omic characterization, to uncover genetic and metabolic traits previously unexplored for Ca. Accumulibacter. The identification of a previously overlooked pyrophosphate-fructose 6-phosphate 1-phosphotransferase gene (pfp) suggested that all Ca. Accumulibacter encoded a complete Embden-Meyerhof-Parnas pathway. A homologue of the phosphate-specific transport system accessory protein (PhoU) was suggested to be an inorganic phosphate transport (Pit) accessory protein (Pap) conferring effective and efficient phosphate transport. Additional lineage members were found to encode complete denitrification pathways. A pipeline was built, generating a pan-Ca. Accumulibacter annotation reference database, covering >200,000 proteins and their encoding genes. Benchmarking on 27 Ca. Accumulibacter genomes showed major improvement in the average annotation coverage from 51% to 82%. This pipeline is readily applicable to diverse cultured and uncultured bacteria to establish high-coverage annotation reference databases, facilitating the exploration of genomic dark matter in the bacterial domain.},
}

@article {pmid39696427,
year = {2024},
author = {Sarashetti, P and Lipovac, J and Tomas, F and Šikić, M and Liu, J},
title = {Evaluating data requirements for high-quality haplotype-resolved genomes for creating robust pangenome references.},
journal = {Genome biology},
volume = {25},
number = {1},
pages = {312},
pmid = {39696427},
issn = {1474-760X},
support = {IP-2018-01-5886//Hrvatska Zaklada za Znanost/ ; KK.01.1.1.01.0009//European Regional Development Fund/ ; MOH-000588-01//National Precision Medicine Program/ ; },
mesh = {*Haplotypes ; Humans ; Genomics/methods ; Genome, Human ; },
abstract = {BACKGROUND: Long-read technologies from Pacific Biosciences (PacBio) and Oxford Nanopore Technologies (ONT) have transformed genomics research by providing diverse data types like HiFi, Duplex, and ultra-long ONT. Despite recent strides in achieving haplotype-phased gapless genome assemblies using long-read technologies, concerns persist regarding the representation of genetic diversity, prompting the development of pangenome references. However, pangenome studies face challenges related to data types, volumes, and cost considerations for each assembled genome, while striving to maintain sensitivity. The absence of comprehensive guidance on optimal data selection exacerbates these challenges.

RESULTS: Our study evaluates recommended data types and volumes required to establish a robust de novo genome assembly pipeline for population-level pangenome projects, extensively examining performance between ONT's Duplex and PacBio HiFi datasets in the context of achieving high-quality phased genomes with enhanced contiguity and completeness. The results show that achieving chromosome-level haplotype-resolved assembly requires 20 × high-quality long reads such as PacBio HiFi or ONT Duplex, combined with 15-20 × of ultra-long ONT per haplotype and 10 × of long-range data such as Omni-C or Hi-C. High-quality long reads from both platforms yield assemblies with comparable contiguity, with HiFi excelling in phasing accuracies, while Duplex generates more T2T contigs.

CONCLUSION: Our study provides insights into optimal data types and volumes for robust de novo genome assembly in population-level pangenome projects. Reassessing the recommended data types and volumes in this study and aligning them with practical economic limitations are vital to the pangenome research community, contributing to their efforts and pushing genomic studies with broader impacts.},
}

*Haplotypes
Humans
Genomics/methods
Genome, Human

@article {pmid39695301,
year = {2024},
author = {Rey, E and Abrouk, M and Dufau, I and Rodde, N and Saber, N and Cizkova, J and Fiene, G and Stanschewski, C and Jarvis, DE and Jellen, EN and Maughan, PJ and von Baer, I and Troukhan, M and Kravchuk, M and Hribova, E and Cauet, S and Krattinger, SG and Tester, M},
title = {Genome assembly of a diversity panel of Chenopodium quinoa.},
journal = {Scientific data},
volume = {11},
number = {1},
pages = {1366},
pmid = {39695301},
issn = {2052-4463},
mesh = {*Chenopodium quinoa/genetics ; *Genome, Plant ; Genetic Variation ; },
abstract = {Quinoa (Chenopodium quinoa) is an important crop for the future challenges of food and nutrient security. Deep characterization of quinoa diversity is needed to support the agronomic improvement and adaptation of quinoa as its worldwide cultivation expands. In this study, we report the construction of chromosome-scale genome assemblies of eight quinoa accessions covering the range of phenotypic and genetic diversity of both lowland and highland quinoas. The assemblies were produced from a combination of PacBio HiFi reads and Bionano Saphyr optical maps, with total assembly sizes averaging 1.28 Gb with a mean N50 of 71.1 Mb. Between 43,733 and 48,564 gene models were predicted for the eight new quinoa genomes, and on average, 66% of each quinoa genome was classified as repetitive sequences. Alignment between the eight genome assemblies allowed the identification of structural rearrangements including inversions, translocations, and duplications. These eight novel quinoa genome assemblies provide a resource for association genetics, comparative genomics, and pan-genome analyses for the discovery of genetic components and variations underlying agriculturally important traits.},
}

*Chenopodium quinoa/genetics
*Genome, Plant
Genetic Variation

@article {pmid39694196,
year = {2024},
author = {Panigrahi, M and Rajawat, D and Nayak, SS and Jain, K and Nayak, A and Rajput, AS and Sharma, A and Dutt, T},
title = {A Comprehensive Review on Genomic Insights and Advanced Technologies for Mastitis Prevention in Dairy Animals.},
journal = {Microbial pathogenesis},
volume = {},
number = {},
pages = {107233},
doi = {10.1016/j.micpath.2024.107233},
pmid = {39694196},
issn = {1096-1208},
abstract = {Mastitis, is a multi-etiological disease that significantly impacts milk production and reproductive efficiency. This is highly prevalent in dairy populations subjected to intensive selection for higher milk yield and where inbreeding is common. The issue is amplified by climate change and poor hygiene management, making disease control challenging. Key obstacles include antibiotic resistance, maximum residue levels, horizontal gene transfer, and limited success in breeding for resistance. Predictive genomics offers a promising solution for mastitis prevention by identifying genetic traits linked with susceptibility to mastitis. This review compiles the research and findings on genomics and its allied approaches such as pan-genomics, epigenetics, proteomics, and transcriptomics for diagnosing, understanding, and treating mastitis. In dairy production, artificial intelligence (AI), particularly deep learning (DL) techniques like convolutional neural networks (CNNs), has demonstrated significant potential to enhance milk production and improve farm profitability. It highlights the integration of advanced technologies like machine learning (ML), CRISPR, and pan-genomics to enhance our knowledge of mastitis epidemiology, pathogen evolution, and the development of more effective diagnostic, preventive, and therapeutic strategies for dairy herds. Genomic advancements provide critical insights into the complexities of mastitis, offering new avenues for understanding its dynamics. Integrating these findings with key predisposing factors can drive targeted prevention and more effective disease management.},
}

@article {pmid39694857,
year = {2024},
author = {Milia, S and Leonard, A and Mapel, XM and Bernal Ulloa, SM and Drögemüller, C and Pausch, H},
title = {Taurine pangenome uncovers a segmental duplication upstream of KIT associated with depigmentation in white-headed cattle.},
journal = {Genome research},
volume = {},
number = {},
pages = {},
doi = {10.1101/gr.279064.124},
pmid = {39694857},
issn = {1549-5469},
abstract = {Cattle have been selectively bred for coat color, spotting, and depigmentation patterns. The assumed autosomal dominant inherited genetic variants underlying the characteristic white head of Fleckvieh, Simmental, and Hereford cattle have not been identified yet, although the contribution of structural variation upstream the KIT gene has been proposed. Here, we construct a graph pangenome from 24 haplotype assemblies representing seven taurine cattle breeds to identify and characterize the white head-associated locus for the first time based on long-read sequencing data and pangenome analyses. We introduce a pangenome-wide association mapping approach which examines assembly path similarities within the graph to reveal an association between two most likely serial alleles of a complex structural variant 66 kb upstream KIT and facial depigmentation. The complex structural variant contains a variable number of tandemly duplicated 14.3 kb repeats, consisting of LTRs, LINEs, and other repetitive elements, leading to misleading alignments of short and long reads when using a linear reference. We align 250 short-read sequencing samples spanning 15 cattle breeds to the pangenome graph, further validating that the alleles of the structural variant segregate with head depigmentation. We estimate an increased count of repeats in Hereford relative to Simmental and other white-headed cattle breeds from the graph alignment coverage, suggesting a large under-assembly in the current Hereford-based cattle reference genome which had fewer copies. Our work shows that exploiting assembly path similarities within graph pangenomes can reveal trait-associated complex structural variants.},
}

@article {pmid39687382,
year = {2024},
author = {Shayerul Abedin Shayer, KM and Shuvo, SR and Jabeen, I and Hossain, M and Islam, S},
title = {Draft genome sequence data of Serratia marcescens strain harboring blaNDM-7 from Dhaka, Bangladesh.},
journal = {Data in brief},
volume = {57},
number = {},
pages = {111133},
doi = {10.1016/j.dib.2024.111133},
pmid = {39687382},
issn = {2352-3409},
abstract = {Here, the draft genome sequence of a multi-drug resistant (MDR) Serratia marcescens strain BMD28, isolated from a clinical source from Dhaka, Bangladesh, has been reported. The sequence raw read files were generated using Illumina sequencing technology utilizing genomic DNA from the pure culture of this strain. The strain has a genome size of around 5.4 million base pairs, a GC content of 59.70 %, and 5,141 coding sequences. We conducted genomic studies using several bioinformatics tools focusing on resistance genes, virulence factors, toxin-antitoxin systems, and pangenome analysis. Strain BMD28 harbored the blaNDM-7 gene in an IncX3 plasmid. A phylogenomic study with S. marcescens strains isolated worldwide revealed that our strain is in the same clade as other strains reported in Bangladesh. The data can be used primarily to understand the genomic content, epidemiology, and evolution of S. marcescens in Bangladesh. The genome sequence data of BMD28 has been deposited in the NCBI database under BioSample accession number SAMN41260295.},
}

@article {pmid39684382,
year = {2024},
author = {Salgado-Morales, R and Barba-Xochipa, K and Martínez-Ocampo, F and Dantán-González, E and Hernández-Mendoza, A and Quiterio-Trenado, M and Rodríguez-Santiago, M and Rivera-Ramírez, A},
title = {Pangenome-Wide Association Study in the Chlamydiaceae Family Reveals Key Evolutionary Aspects of Their Relationship with Their Hosts.},
journal = {International journal of molecular sciences},
volume = {25},
number = {23},
pages = {},
doi = {10.3390/ijms252312671},
pmid = {39684382},
issn = {1422-0067},
mesh = {*Chlamydiaceae/genetics ; Animals ; *Genome, Bacterial ; *Genome-Wide Association Study ; Humans ; *Chlamydia/genetics/classification ; Phylogeny ; Host-Pathogen Interactions/genetics ; Evolution, Molecular ; Chlamydophila/genetics ; },
abstract = {The Chlamydiaceae are a family of obligate intracellular bacteria known for their unique biphasic developmental cycle. Chlamydial are associated with various host organisms, including humans, and have been proposed as emerging pathogens. Genomic studies have significantly enhanced our understanding of chlamydial biology, host adaptation, and evolutionary processes. In this study, we conducted a complete pangenome association analysis (pan-GWAS) using 101 genomes from the Chlamydiaceae family to identify differentially represented genes in Chlamydia and Chlamydophila, revealing their distinct evolutionary strategies for interacting with eukaryotic hosts. Our analysis identified 289 genes with differential abundance between the two clades: 129 showed a strong association with Chlamydia and 160 with Chlamydophila. Most genes in Chlamydia were related to the type III secretion system, while Chlamydophila genes corresponded to various functional categories, including translation, replication, transport, and metabolism. These findings suggest that Chlamydia has developed a high dependence on mammalian cells for replication, facilitated by a complex T3SS for intracellular manipulation. In contrast, the metabolic and functional diversity in Chlamydophila allows it to colonize a broad range of hosts, such as birds, reptiles, amphibians, and mammals, making it a less specialized clade.},
}

*Chlamydiaceae/genetics
Animals
*Genome, Bacterial
*Genome-Wide Association Study
Humans
*Chlamydia/genetics/classification
Phylogeny
Host-Pathogen Interactions/genetics
Evolution, Molecular
Chlamydophila/genetics

@article {pmid39675005,
year = {2024},
author = {Rubio, A and Garzón, A and Moreno-Rodríguez, A and Pérez-Pulido, AJ},
title = {Biological warfare between two bacterial viruses in a defense archipelago sheds light on the spread of CRISPR-Cas systems.},
journal = {Cell reports},
volume = {43},
number = {12},
pages = {115085},
doi = {10.1016/j.celrep.2024.115085},
pmid = {39675005},
issn = {2211-1247},
abstract = {CRISPR-Cas systems are adaptive immunity systems of bacteria and archaea that prevent infection by viruses and other external mobile genetic elements. It is currently known that these defense systems can be co-opted by the same viruses. We have found one of these viruses in the opportunistic pathogen Acinetobacter baumannii, and the same system has been also found in an integration hotspot of the bacterial genome that harbors other multiple defense systems. The CRISPR-Cas system appears to especially target another virus that could compete with the system itself for the same integration site. This virus is prevalent in strains of the species belonging to the so-called Global Clone 2, which causes the most frequent outbreaks worldwide. Knowledge of this viral warfare involving antiviral systems could be useful in the fight against infections caused by bacteria, and it would also shed light on how CRISPR-Cas systems expand in bacteria.},
}

@article {pmid39673077,
year = {2024},
author = {Alkemade, JA and Hohmann, P and Messmer, MM and Barraclough, TG},
title = {Comparative Genomics Reveals Sources of Genetic Variability in the Asexual Fungal Plant Pathogen Colletotrichum lupini.},
journal = {Molecular plant pathology},
volume = {25},
number = {12},
pages = {e70039},
pmid = {39673077},
issn = {1364-3703},
support = {//Bundesamt für Landwirtschaft/ ; //Calleva Research Centre for Evolution and Human Science/ ; 727230//Horizon 2020 Framework Programme/ ; 17.00090//Staatssekretariat für Bildung, Forschung und Innovation/ ; RYC2022-037997//MICIU/AEI/10.13039/501100011033 and FSE+/ ; },
mesh = {*Colletotrichum/genetics/pathogenicity ; *Genetic Variation ; *Genome, Fungal ; *Genomics ; *Phylogeny ; Plant Diseases/microbiology ; DNA Transposable Elements/genetics ; Reproduction, Asexual/genetics ; Genome Size ; },
abstract = {Fungal plant pathogens cause major crop losses worldwide, with many featuring compartmentalised genomes that include both core and accessory regions, which are believed to drive adaptation. The highly host-specific fungus Colletotrichum lupini greatly impacts lupin (Lupinus spp.) cultivation. This pathogen is part of clade 1 of the C. acutatum species complex and comprises four genetically uniform, presumably clonal, lineages (I-IV). Despite this, variation in virulence and morphology has been observed within these lineages. To investigate the potential sources of genetic variability in this asexual fungus, we compared the genomes of 16 C. lupini strains and 17 related Colletotrichum species. Phylogenomics confirmed the presence of four distinct lineages, but further examination based on genome size, gene content, transposable elements (TEs), and deletions revealed that lineage II could be split into two groups, II-A and II-B. TE content varied between lineages and correlated strongly with genome size variation, supporting a role for TEs in genome expansion in this species. Pangenome analysis revealed a highly variable accessory genome, including a minichromosome present in lineages II, III, and IV, but absent in lineage I. Accessory genes and effectors appeared to cluster in proximity to TEs. Presence/absence variation of putative effectors was lineage-specific, suggesting that these genes play a crucial role in determining host range. Notably, no effectors were found on the TE-rich minichromosome. Our findings shed light on the potential mechanisms generating genetic diversity in this asexual fungal pathogen that could aid future disease management.},
}

*Colletotrichum/genetics/pathogenicity
*Genetic Variation
*Genome, Fungal
*Genomics
*Phylogeny
Plant Diseases/microbiology
DNA Transposable Elements/genetics
Reproduction, Asexual/genetics
Genome Size

@article {pmid39671861,
year = {2024},
author = {Buzzanca, D and Giordano, M and Chiarini, E and Ferrocino, I and Cocolin, L and Zeppa, G and Alessandria, V},
title = {Delving into Roccaverano PDO cheese: A comprehensive examination of microbial diversity and flavour profiles compared to non-PDO cheeses.},
journal = {International journal of food microbiology},
volume = {429},
number = {},
pages = {111014},
doi = {10.1016/j.ijfoodmicro.2024.111014},
pmid = {39671861},
issn = {1879-3460},
abstract = {Roccaverano Protected Designation of Origin (PDO) is a fresh soft cheese produced in Roccaverano area (Italy). This study aimed to evaluate Roccaverano PDO microbiota, together with aromatic profile and sensory analysis to be compared with 15 non-PDO cheeses of the same type. Microbiota was evaluated through shotgun metagenomics sequencing, while GC-MS analysis was conducted to study volatile organic compounds (VOCs) presence and concentration. Sensory analyses were conducted through ONAF (Italian National Organization of Cheese Tasters) evaluation parameters followed by flash profile sensory analysis of selected cheeses. The results demonstrated Lactococcus lactis predominance in both non-PDO and PDO cheeses, while Streptococcus thermophilus was more abundant in non-PDO group. A higher abundance of Kluyveromyces lactis was observed in Roccaverano PDO, which exhibited greater fungal diversity compared to non-PDO cheeses. Metagenome-Assembled Genomes of 26 L. lactis and 19 Leuconostoc mesenteroides showed absence of significant differences in terms of average nucleotide identity and pangenomes partitions. The ONAF sensory evaluation demonstrated a higher average score of Roccaverano PDO group. Flash profile analysis demonstrated that lactic aroma/odour, acid, astringent, vegetal odour, exotic fruit and fermented aroma, hazelnut flavour and sweet were associated with high ONAF scores. The concentration of butanoic acid, 2-methyl-, ethyl ester and butanoic acid, 3-methyl- (sweat, acid, rancid related) were higher in PDO cheeses, while reads related to butanoate metabolism were less abundant compared to non-PDO samples. Several fungal species (included K. lactis) were associated with astringents, acid and chalky flavours. Roccaverano PDO demonstrates unique characteristics even maintaining a certain degree of variability between samples.},
}

@article {pmid39670914,
year = {2024},
author = {Yang, Y and Yan, X and Haley, BJ and Li, C and Nou, X},
title = {Genomic Comparison of Reoccurring, Emerging, and Persistent (REP) Shiga Toxin-Producing Escherichia coli O157:H7.},
journal = {Foodborne pathogens and disease},
volume = {},
number = {},
pages = {},
doi = {10.1089/fpd.2024.0144},
pmid = {39670914},
issn = {1556-7125},
abstract = {Escherichia coli O157:H7 strains associated with several recent (2017-2020) multi-state outbreaks linked to leafy green vegetables have been characterized as "reoccurring, emerging, and persistent" (REP). Our recent unpublished work demonstrated that the REP strains had significantly enhanced potential for biofilm formation. In this study, comparative genomic analyses were conducted for a better understanding of the mechanisms behind the enhanced biofilm formation, and thereby potentially increased environmental fitness, by the REP strains. Phylogenetically, the recent outbreak strains formed two distinct clusters represented by REPEXH01 and REPEXH02. Compared with EDL933 and other previous outbreak reference strains, the REP strains (clustering with REPEXH02) exhibiting strong biofilm formation were found to have acquired two genes encoding proteins of unknown functions (hypothetical proteins) and lost certain prophage-related genes. In addition, several single nucleotide polymorphisms in genes related to biofilm formation were identified.},
}

@article {pmid39670058,
year = {2024},
author = {Kantor, EJH and Robicheau, BM and Tolman, J and Archibald, JM and LaRoche, J},
title = {Metagenomics reveals the genetic diversity between sublineages of UCYN-A and their algal host plastids.},
journal = {ISME communications},
volume = {4},
number = {1},
pages = {ycae150},
pmid = {39670058},
issn = {2730-6151},
abstract = {UCYN-A (or Cand. Atelocyanobacterium thalassa) has been recognized as a globally distributed, early stage, nitrogen-fixing organelle (the "nitroplast") of cyanobacterial origin present in the haptophyte alga Braarudosphaera bigelowii. Although the nitroplast was recognized as UCYN-A2, not all sublineages of UCYN-A have been confirmed as nitroplasts, and full genomes are still lacking for several known sublineages. We investigated the differences between UCYN-A sublineages by sequencing and assembly of metagenomic sequences acquired from cultured biomass from NW Atlantic seawater, which yielded near-complete Metagenome Assembled Genomes (MAGs) corresponding to UCYN-A1, -A4, and the plastid of the UCYN-A4-associated B. bigelowii. Weekly time-series data paired with the recurrence of specific microbes in cultures used for metagenomics gave further insight into the microbial community associated with the algal/UCYN-A complex. The UCYN-A1 MAG was found to have 99% average nucleotide identity (ANI) to the Pacific-derived reference genome despite its Atlantic Ocean origin. Comparison of the UCYN-A4 MAG (the initial genome sequenced from this sublineage) to other genomes showed that UCYN-A4 is sufficiently genetically distinct from both UCYN-A1 and UCYN-A2 (ANI of ~83% and ~85%, respectively) to be considered its own sublineage, but more similar to UCYN-A2 than -A1, supporting its possible classification as a nitroplast. The B. bigelowii plastid sequence was compared with published plastid sequences (sharing 78% ANI with Chrysochromulina parva) adding to our understanding of genomic variation across Haptophyta organelles and emphasizing the need for further full genomic sequencing of B. bigelowii genotypes and their organelles.},
}