@article {pmid41763707,
year = {2026},
author = {Timilsina, S and Cox, R and Kolosey, R and Verghese, B},
title = {Advanced Microbial Strain Typing Using Whole Genome Sequencing: Poster Presented at PDA Microbiology Conference 2025.},
journal = {PDA journal of pharmaceutical science and technology},
volume = {80},
number = {1},
pages = {203-204},
doi = {10.5731/pdajpst.2026.26141},
pmid = {41763707},
issn = {1948-2124},
abstract = {Microbial identification and strain typing are critical in pharmaceutical microbiology for ensuring product safety, controlling contaminants, and meeting regulatory requirements. Traditional strain typing methods like pulsed-field gel electrophoresis and multi-locus sequence typing have their limitations in scalability and resolution. Increased use of next-generation sequencing (NGS) techniques for microbial identification and characterization, coupled with the availability of bacterial whole genomes, advanced sequence analysis approaches such as single nucleotide polymorphisms (SNPs), core and pan-genome analysis, is opening the door for more modern approaches to microbial strain typing. However, several of these approaches are species-specific and require optimization per species or project. In this study, we analyzed conserved genes from several bacterial species to analyze the possibility of using these genes as a set of universal genes for prokaryotic strain typing. We compared the strain typing results using these universal genes to results from species-specific housekeeping genes and with species with no established strain typing methods. Our data demonstrated that these conserved genes successfully distinguished bacterial strains when compared to the results from established species-specific strain typing schemes, providing a path forward in the development of a rapid, universal strain typing solution using bacterial genomes that is not limited to a single species.},
}

@article {pmid41761781,
year = {2026},
author = {Collins, CF and Alston, BT and Hibdige, SGS and Raimondeau, P and Baker, ER and Sotelo, G and Papadopulos, AST and Christin, PA and Pereira, L and Dunning, LT},
title = {Regulatory features determine the evolutionary fate of laterally acquired genes in plants.},
journal = {Molecular biology and evolution},
volume = {43},
number = {2},
pages = {},
doi = {10.1093/molbev/msag042},
pmid = {41761781},
issn = {1537-1719},
support = {NE/V000012/1//Natural Environment Research Council/ ; NE/T011025/1//Natural Environment Research Council/ ; //University of Sheffield/ ; 947921//MAPAS/ ; URF\R\180022//Royal Society University Research/ ; },
abstract = {Lateral gene transfer (LGT) is widespread in eukaryotes, including in animals and plants where it can fuel adaptive evolution and innovation. However, the factors that influence the integration and long-term retention of transferred genes remain poorly understood. The pangenome of the grass Alloteropsis has a high turnover of laterally acquired genes, and here we combine expression, methylation, and genomic data to identify factors promoting their long-term persistence. Most transferred genes appear to be degenerating, showing lower expression levels and/or greater sequence truncation compared to their vertically inherited homologs. These degenerating genes also show significantly higher levels of DNA methylation, potentially indicating transcriptional silencing. The likelihood of a transferred gene being retained will be influenced by how easily it can be expressed in the recipient genome. In Alloteropsis, putatively functional laterally acquired genes had expression levels significantly more similar to their donor ortholog than to their vertically inherited homolog. Transferred genes carry cis-regulatory elements encoded on the fragment of DNA that moves between species, likely facilitating their expression in the new genomic context. Evolutionary novelty may also increase the likelihood that selection retains a transferred gene. However, only a significant difference in expression level, not sequence divergence, between donor orthologs and vertically inherited homologs is associated with successful lateral gene transfer. Overall, our results show that most transferred genes degrade over time. However, those capable of regulating their own expression are more likely to persist and contribute to long-term evolutionary innovation.},
}

@article {pmid41760847,
year = {2026},
author = {Eilers, T and Delanghe, L and De Boeck, I and Van Rillaer, T and Van Malderen, J and Bakelants, S and Van Beeck, W and Wittouck, S and Lebeer, S},
title = {Pangenome-based design of strain-specific primers enables precise monitoring of bacteria in human microbiome intervention trials.},
journal = {Scientific reports},
volume = {},
number = {},
pages = {},
doi = {10.1038/s41598-026-41449-8},
pmid = {41760847},
issn = {2045-2322},
support = {HBC.2022.1000//Agentschap Innoveren en Ondernemen/ ; HBC.2020.2873//Agentschap Innoveren en Ondernemen/ ; 12S4222N//Fonds Wetenschappelijk Onderzoek/ ; 1S08523N//Fonds Wetenschappelijk Onderzoek/ ; 1224923N//Fonds Wetenschappelijk Onderzoek/ ; 12AZ624N//Fonds Wetenschappelijk Onderzoek/ ; 852600//Horizon 2020 Framework Programme/ ; },
}

@article {pmid41759033,
year = {2026},
author = {Royer, G and Chau, F and Vallenet, D and Denamur, E and , and , and , },
title = {Identification of specific metabolic capacities associated with major extraintestinal pathogenic Escherichia coli lineages.},
journal = {Journal of bacteriology},
volume = {},
number = {},
pages = {e0042125},
doi = {10.1128/jb.00421-25},
pmid = {41759033},
issn = {1098-5530},
abstract = {Bacterial niche colonization relies on multiple factors, among which the metabolic capacity to utilize specific substrates is pivotal. As a gut commensal of humans and other vertebrates acting as an intestinal and extraintestinal opportunistic pathogen, Escherichia coli faces such environmental pressures. We therefore aimed to identify (i) metabolic patterns associated with E. coli lifestyle (commensal versus extraintestinal pathogenic E. coli [ExPEC]) and (ii) ExPEC-specific metabolic features that could help explain the emergence and success of major pandemic clones. Using a pangenomic framework coupled with metabolic pathway prediction, we analyzed 1,498 well-characterized E. coli strains collected over 17 years in France, including adult commensal strains (n = 370) and ExPEC strains involved in severe infections (bloodstream infections from various portals of entry and pneumonia) (n = 1,128). Although metabolism was more conserved than gene content, substantial metabolic diversity was observed, with over 50% pathways being variable, mainly involving biosynthetic and degradation processes. No pathway was specifically associated with lifestyle; metabolic profiles primarily reflected phylogeny. However, several clone-specific metabolic capacities were identified. Some may support extraintestinal survival during infection, such as the 5'-deoxynucleoside recycling pathway enriched in the major ExPEC clone STc69 from phylogroup D. Conversely, in phylogroup B2, clone-specific pathways enabled the degradation of plant-derived compounds, potentially facilitating gut colonization through niche-defining nutrients. Notably, D-apiose degradation pathway analysis revealed a functional pathway strongly associated with the pandemic clones STc131 and STc14. Overall, these lineage-specific metabolic capacities may contribute to the ecological success and dissemination of dominant ExPEC clones.IMPORTANCEAccording to the nutrient-niche hypothesis, bacteria must exploit distinct substrates to grow and persist in their various habitats. Such niche differentiation is at play among the commensal and pathogenic E. coli populations. With this in mind, we search for specific associations between metabolic pathways and strain origin (commensal versus severe extraintestinal infections). Metabolic profiles were predominantly shaped by phylogeny, reflecting the species' clonal structure and the close link between phylogenetic background and lifestyle. Among the lineage-specific determinants, we identified several pathways associated with worldwide spread clones responsible for bloodstream infections, supporting the existence of clone-specific strategies for niche adaptation.},
}

@article {pmid41757946,
year = {2026},
author = {Afshan, G and Yaseen, N and Khan, AU},
title = {A mutation-aware proteomics approach for designing a multi-epitope vaccine against multidrug-resistant Acinetobacter baumannii and Pseudomonas aeruginosa.},
journal = {Microbiology spectrum},
volume = {},
number = {},
pages = {e0309525},
doi = {10.1128/spectrum.03095-25},
pmid = {41757946},
issn = {2165-0497},
abstract = {UNLABELLED: The increasing prevalence of multidrug-resistant Acinetobacter baumannii and Pseudomonas aeruginosa in healthcare settings presents a critical challenge to global public health, necessitating the development of effective therapeutic strategies. Here, we report the rationale design of a mutation-aware multi-epitope vaccine targeting conserved, surface-exposed antigens derived from comparative pan-genomic and subtractive proteomic analyses of 30 proteomes. Following stringent antigenicity, allergenicity, toxicity, and homology filtering, three highly antigenic proteins were identified and used to predict immunodominant cytotoxic T-lymphocyte, helper T-lymphocyte, and B-cell epitopes. Epitope selection incorporated mutation probability profiling, and structurally labile residues, particularly serine, were substituted with conservative alternatives such as threonine to enhance conformational stability and HLA binding without compromising immunogenicity. The final construct, comprising 219 amino acids adjuvanted with human β-defensin-3 and connected by cleavable, immunologically inert linkers EAAAK (adjuvant), AAY (CTL), GPGPG (HTL), and KK (B cell) exhibited favorable physicochemical properties, structural stability, and broad global HLA coverage (79%). Structural modeling revealed a high-quality tertiary structure, with 95.8% of residues in favored regions and validated by ProSA and ERRAT scores. Docking with Toll-like receptor 4 demonstrated strong binding affinity supported by molecular dynamics simulations. In silico immune simulations predicted strong IgM and IgG responses, sustained memory B- and T-cell populations, and strong cytokine production, including IFN-γ, indicative of skewed Th1 immunity. Codon optimization and cloning analysis confirmed its expression potential in Escherichia coli. Collectively, these findings suggest the designed vaccine as a promising therapeutic candidate against polymicrobial infections caused by A. baumannii and P. aeruginosa, requiring further experimental validation.

IMPORTANCE: Multidrug resistance has become a common phenomenon leading to difficulty in infection control. No options are left to treat such infections after the emergence of colistin resistance. Therefore, this approach to developing multi-epitope therapeutic vaccines is very promising to face the challenge of infection control. This study is based on comparative pan-genomic and subtractive proteomic analyses of 30 proteomes, which provide a wider range of proteins to select multiple epitopes for effective vaccine.},
}

@article {pmid41757865,
year = {2026},
author = {Hu, X and Shi, Z and Gao, Y and Zheng, H and Lin, L and Chen, JP and Chen, Y and Zhang, CX and Li, Y},
title = {Characterization of the dynamic microbiome evolution across thrips species.},
journal = {Insect science},
volume = {},
number = {},
pages = {},
doi = {10.1111/1744-7917.70265},
pmid = {41757865},
issn = {1744-7917},
support = {2023J06040//Natural Science Foundation of Fujian Province/ ; //Ningbo Yongjiang grant/ ; 32472657//National Natural Science Foundation of China/ ; 32570491//National Natural Science Foundation of China/ ; },
abstract = {The insect microbiome profoundly influences host physiology and ecology, yet its composition and evolutionary dynamics in thrips remain poorly understood. Here, we present a systematic characterization of thrips-associated microbiomes through integrated metagenomic and culture-based approaches. Our analysis reveals that thrips microbiomes are dominated by both intracellular symbionts (e.g., Wolbachia and Spiroplasma) and extracellular taxa (e.g., Serratia, Pantoea, and Acinetobacter), with species-specific compositions exhibiting frequent gains and losses of bacterial lineages. We demonstrate that thrips microbiomes exhibit low interspecific microbial sharing, forming host-specific bacterial communities with minimal overlap between species. To address methodological challenges in microbiome research, we developed a dual-sequencing framework combining short-read sequencing (for comprehensive taxonomic detection) and long-read sequencing (for genomic verification), enabling the reconstruction of high-quality metagenome-assembled genomes that validated short-read findings. Furthermore, we isolated and sequenced the complete genomes of two dominant extracellular symbionts-Pantoea dispersa and Serratia marcescens-and performed pan-genome analyses. These revealed small core gene sets and expansive accessory genomes, including host-specific functional genes (e.g., hydrolases and neurotoxic N-acetyltransferases) likely involved in host adaptation. Our study provides a foundational genomic resource and a robust analytical pipeline for dissecting thrips microbiome evolution, with implications for understanding insect-microbe interactions and symbiont-mediated adaptations.},
}

@article {pmid41757015,
year = {2026},
author = {Kaushan, H and Marco-Sola, S and Garrison, E and Prins, P and Guarracino, A},
title = {Adaptive Tracepoints for Pangenome Alignment Compression.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.64898/2026.02.16.706236},
pmid = {41757015},
issn = {2692-8205},
abstract = {MOTIVATION: Storing millions of sequence alignments from large-scale genomic comparisons requires efficient compression methods. While fixed-size alignment encodings offer uniform spacing and bounded reconstruction cost, they cannot adapt to variable alignment complexity across sequences, missing compression opportunities in conserved regions.

RESULTS: We present adaptive tracepoints, a complexity-aware alignment encoding that segments alignments using configurable complexity metrics (edit distance or diagonal distance) rather than fixed intervals. Segments are bounded by either the number of differences or the deviation from the main diagonal, adapting to local alignment characteristics. Reconstruction guarantees that alignments maintain identical or improved alignment scores. We validate the correctness of our method on simulated and real pangenomes with varying lengths and divergences. Diagonal-bounded tracepoints achieve 10.5-13.7 × better compression than fixed-length encodings (l =100) on simulated long sequence alignments (100 Kb), while edit-bounded tracepoints provide a tunable trade-off between compression and reconstruction cost, approaching diagonal-bounded compression at higher thresholds with substantially lower memory and runtime. On real pangenomes (390M alignments), these methods compress alignments by 23-139 × relative to uncompressed representations, with no score degradation and reconstruction time linear in alignment length.

AVAILABILITY: Code and documentation are publicly available at https://github.com/AndreaGuarracino/tracepoints , https://github.com/AndreaGuarracino/tpa , and https://github.com/AndreaGuarracino/cigzip .

CONTACT: aguarracino@tgen.org.

SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.},
}

@article {pmid41753615,
year = {2026},
author = {Nedashkovskaya, O and Bystritskaya, E and Savicheva, Y and Bronnikova, Y and Otstavnykh, N and Eremeev, V and Kim, SG and Zhukova, N and Isaeva, M},
title = {Genome Analysis and Characterization of Formosa bonchosmolovskayae sp. nov. Isolated from Brown and Green Algae, and a Proposal to Reclassify Formosa maritima Cao et al. 2020 and Bizionia arctica Li et al. 2015 as Xanthomarina New Members.},
journal = {Microorganisms},
volume = {14},
number = {2},
pages = {},
doi = {10.3390/microorganisms14020328},
pmid = {41753615},
issn = {2076-2607},
support = {15.BRK.25.14 (Contract No. 075-15-2025-467)//Ministry of Science and Higher Education, Russian Federation/ ; },
abstract = {Two marine bacteria, designated strains 4Alg 33[T]and 3Alg 14/1, were isolated from brown (Saccharina japonica) and green (Ulva fenestrata) macroalgae, respectively. These isolates were aerobic Gram-negative rods exhibiting a gliding motility. The 16S rRNA gene phylogenetic analysis clearly showed their belonging to the genus Formosa, the family Flavobacteriaceae, and the phylum Bacteroidota. The closest relatives of the new strains were Formosa undariae KCTC 32328[T] (99.05%), Formosa arctica IMCC 9485[T] (99.05%) and Formosa agariphila KMM 3901[T] (98.96%). The ANI and dDDH values between the two new strains were 97.9% and 85.3%, respectively. The AAI values between 4Alg 33[T] and Formosa type strains ranged from 80.1% (Formosa haliotis MA1[T]) to 91.4% (F. undariae KCTC 32328[T]). The cellular fatty acid and polar lipid profiles of the new isolates were generally similar to those of the type strains of Formosa species. The genomes of 4Alg 33[T] and 3Alg 14/1 are represented by a circular chromosome of 4,157,724 bp and 4,316,096 bp in size with 3536 and 3879 protein-coding genes, respectively. They shared a DNA G+C content of 34.3 mol% and comprised four rrn operons. The pangenome of the genus Formosa belongs to the open type and is characterized by an abundance of CAZymes. The proportion of CAZyme genes in novel genomes was more than 5%, with a prevalence of glycoside hydrolase genes, suggesting great potential for utilizing marine-derived polysaccharides. Based on the results of polyphasic characterization, the two algal isolates represent a distinct species lineage within the genus Formosa, for which we propose the name Formosa bonchosmolovskayae sp. nov. with the type strain 4Alg 33[T] (= KMM 3963[T] = KCTC 72008[T]). In addition, we have proposed to transfer Formosa maritima Cao et al. 2020 and Bizionia arctica Li et al. 2015 to the genus Xanthomarina Vaidya et al. 2015 as Xanthomarina maritima comb. nov. and Xanthomarina arctica comb. nov. based on a combination of the genomic and phenotypic characteristics.},
}

@article {pmid41753583,
year = {2026},
author = {da Silva, FR and Costa, LGA and Sousa Junior, EC and Santos, WS and Garcez, LM},
title = {Whole-Genome Sequencing and Comparative Genomic Analysis of Leishmania (Viannia) naiffi and L. (Viannia) shawi Reveal Species-Specific Genes and Novel Potential Drug Targets.},
journal = {Microorganisms},
volume = {14},
number = {2},
pages = {},
doi = {10.3390/microorganisms14020296},
pmid = {41753583},
issn = {2076-2607},
support = {01.22.0495.00//Financiadora de Estudos e Projetos/ ; 001//Coordenação de Aperfeicoamento de Pessoal de Nível Superior/ ; },
abstract = {This study presents the complete sequencing and comparative genomic analysis of Leimania (Viannia) naiffi and Leishmania (Viannia) shawi, species of epidemiological relevance in the Brazilian Amazon. Genome assemblies yielded sizes of 32.13 Mb and 32.51 Mb, with 8170 and 7767 annotated genes, respectively. Predicted gene functions were primarily related to catalytic, binding, and ATP-dependent activities. Pangenome analysis revealed a core genome of 6256 genes alongside notable species-specific differences, including 46 and 25 unique genes in L. naiffi and L. shawi. Functional screening identified pharmacologically promising proteins such as calpains, ABC transporters, and notably, GSK-3. Ploidy analysis indicated tetraploidy on chromosome 8 in L. naiffi and chromosome 2 in L. shawi. Genetic variability assessment detected 34,480 SNPs in L. naiffi and 26,562 in L. shawi, indicating greater genomic diversity in the former. Phylogenetic inference based on the polA1 gene confirmed the placement of both species within the Leishmania (Viannia) subgenus. These findings advance Leishmania genomics knowledge by highlighting unique genetic signatures, regions of high variability, and potential therapeutic targets. This work establishes a foundation for future research on evolution, pathogenicity, and drug development for leishmaniasis.},
}

@article {pmid41751553,
year = {2026},
author = {Andrade Alvarado, CK and Honorio Durand, ZF and Contreras-Liza, SE and Castillo, G and Guzman Sanchez, WA and Takei-Idiaquez, DH and Ballen-Gavidia, JE and Arbizu, CI and Rodriguez-Grados, PM},
title = {Functional Genome Prediction and Genome-Scale Metabolic Modeling of the Rhizobacteria Serratia liquefaciens Strain UNJFSC002.},
journal = {Genes},
volume = {17},
number = {2},
pages = {},
doi = {10.3390/genes17020169},
pmid = {41751553},
issn = {2073-4425},
support = {UNTRM-00025446//Universidad Nacional Toribo Rodriguez de Mendoza de Amazonas/ ; },
abstract = {BACKGROUND/OBJECTIVES: Serratia liquefaciens is a bacterium commonly found in the rhizosphere and may possess PGPR capabilities. The present study aimed to elucidate the genomic, phylogenomic, and metabolic characteristics of S. liquefaciens strain UNJFSC002 to determine whether it is an effective PGPR.

METHODS: The genome of strain UNJFSC002 was obtained from NCBI and annotated using Prokka. Functional genome prediction, phylogenetic reconstruction, and comparative genomics were performed using bioinformatics tools. A GEM model was reconstructed to simulate metabolic fluxes associated with nitrogen fixation, phosphate solubilization, and phytohormone biosynthesis. Computational phenotyping and in silico functional validation were also performed.

RESULTS: The draft genome (5.19 Mb, GC 55.33%) contained 4792 protein-coding genes, 4 rRNAs, and 81 tRNAs, with 100% completeness. ANI and core genome phylogeny confirmed its taxonomic position within S. liquefaciens, with an identity higher than 98.8%. Pangenome analysis of 25 Serratia genomes revealed an open and highly dynamic pangenome (30,515 orthologous groups), indicating extensive genetic plasticity. Functional annotation identified key genes associated with nitrogen and phosphate acquisition, as well as the biosynthesis of IAA and GABA, findings that were supported by GEM simulations, reinforcing its potential as a biofertilizer.

CONCLUSIONS: The genomic approach confirmed that strain UNJFSC002 harbors multiple active genes and metabolic pathways associated with plant growth promotion and environmental resilience.},
}

@article {pmid41751520,
year = {2026},
author = {Xia, Z and Zhao, J and Wang, C and Wu, S and Zang, Y and Wang, D and Zhu, S and Min, Y},
title = {Pan-Genome Analysis and Expression Profiling of HIPP Gene Family in Cassava.},
journal = {Genes},
volume = {17},
number = {2},
pages = {},
doi = {10.3390/genes17020136},
pmid = {41751520},
issn = {2073-4425},
support = {SKJC-JYRC-2025-22//Project of Sanya Yazhou Bay Science and Technology City/ ; 822RC651//the Natural Science Foundation of Hainan Province/ ; 31960039//National Natural Science Foundation of China/ ; },
abstract = {Background: Cassava (Manihot esculenta Crantz) ranks as the sixth largest food crop worldwide and serves as an important cash and energy crop. Heavy-metal-associated isoprenylated plant proteins (HIPPs) are metallochaperones involved in metal homeostasis and stress adaptation in vascular plants. However, research on the identification and function of HIPPs in cassava has been poorly explored. Methods: This study conducted a pan-genome-wide investigation to identify and characterize MeHIPPs in 31 cassava accessions. Subsequent analyses examined their physicochemical properties, subcellular localization, phylogeny, Ka/Ks, chromosomal localization, synteny, gene structure, and cis-acting elements. Additionally, the expression profiles of MeHIPPs in different tissues and cell subsets and under different stress conditions were analyzed using transcriptome data and quantitative real-time polymerase chain reaction (qRT-PCR). Results: A total of 59 MeHIPP pan-genes were identified, including five core genes, 22 softcore genes, 17 dispensable genes, and 15 private genes, which were unevenly distributed on chromosomes. Based on phylogenetic analysis, these genes were classified into five major subgroups. Evolutionary analyses indicated that segmental duplication predominated in family expansion and that most members may be subjected to purifying selection. Cis-element analysis highlighted the importance of MeHIPPs in plant adaptation to environmental stress. The expression profiles suggested widespread involvement of MeHIPP genes in response to Xanthomonas phaseoli pv. manihotis (Xpm) infection and drought stress. Different MeHIPP genes exhibited varying transcript levels in different tissues and cell subsets. qRT-PCR analysis revealed that the selected MeHIPP genes had distinct expression patterns under Cd stress. Conclusions: This study provides valuable insights into the functional characteristics of MeHIPP genes and their evolutionary relationships, laying a theoretical foundation for further functional research on stress resistance.},
}

@article {pmid41750509,
year = {2026},
author = {Meroni, G and Soggiu, A and Sciannimanico, D and Pop, RA and Bonizzi, L and Martino, PA},
title = {Genomic Characterisation of Pyometra-Associated Escherichia coli in a Lombardy Veterinary Clinic: A Nanopore-Based Case Series.},
journal = {Antibiotics (Basel, Switzerland)},
volume = {15},
number = {2},
pages = {},
doi = {10.3390/antibiotics15020212},
pmid = {41750509},
issn = {2079-6382},
abstract = {BACKGROUND/OBJECTIVES: Pyometra is a life-threatening uterine infection of intact bitches and queens. Despite growing reports of multidrug-resistant (MDR) Escherichia coli in canine reproductive and urinary infections, no whole-genome data were previously available for pyometra isolates from Italy. This study aimed to characterise, by whole-genome sequencing and comparative genomics, the population structure, resistome and virulome of E. coli causing pyometra in companion animals from northern Italy in the context of European datasets.

METHODS: Four E. coli isolates (two canine, two feline) from pyometra cases underwent nanopore long-read sequencing. Genomes were compared with Brazilian and Finnish pyometra isolates using core- and accessory-genome analyses, pan-genome partitioning, phylogeny, and gene-based profiling of antimicrobial resistance and virulence determinants.

RESULTS: All Italian isolates belonged to phylogroup B2 and to recognised ExPEC sequence types (ST706/O51:H1, ST141/O2:H6, ST372/O75:H31, ST646/O22:H5). Phenotypically, they were uniformly resistant to several penicillins and early/third-generation cephalosporins but remained susceptible to fluoroquinolones, aminoglycosides and trimethoprim-sulphonamide. The combined 57-genome pan-genome was open yet strongly core-dominated; Italian strains shared an efflux- and regulator-centred intrinsic resistome and a rich ExPEC virulence repertoire (P, S, F1C and type 1 fimbriae, multiple siderophores, colibactin, Vat, haemolysin, CNF1) with Brazilian and Finnish isolates.

CONCLUSIONS: Pyometra-associated E. coli from northern Italian pets belong to globally disseminated high-risk B2 lineages that combine extensive virulence with a largely intrinsic resistome, and currently retain susceptibility to several key drug classes, underscoring an important but vulnerable therapeutic window.},
}

@article {pmid41750284,
year = {2026},
author = {Wen, J and Qiu, H and Deng, S and Wang, S and Liu, Y and Lin, M and Yang, J and Wu, Z and Liu, L and Qiu, Y},
title = {De Novo Assembly of Eight Commercial Crossbred Pig Genomes Provides Insights into the Potential Functional Impact of Structural Variation Hotspots.},
journal = {Biomolecules},
volume = {16},
number = {2},
pages = {},
doi = {10.3390/biom16020214},
pmid = {41750284},
issn = {2218-273X},
support = {NK20221101//National Major Agricultural Science and Technology Project/ ; 2023YFD1300200//National Key Research and Development Program of China/ ; 32502859//Young Scientists Fund of the National Natural Science Foundation of China/ ; 2022B0202090002//Key Technologies R&D Program of Guangdong Province project/ ; 2019BTO2N630//Local Innovative and Research Teams Project of Guangdong Province/ ; 2023B10564001/2023B10564003//South China Agricultural University discipline construction and development project/ ; NA//China Overseas Postdoctoral Recruitment Program/ ; },
abstract = {The Duroc × (Landrace × Yorkshire) (DLY) pig is a cornerstone of three-way crossbreeding system. Nevertheless, advances in commercial crossbred performance have been constrained by the dearth of high-resolution genomic resources for this key population. Here, we report the sequencing and assembly of 16 haplotype-resolved, chromosome-level genome assemblies derived from eight DLY pigs. These assemblies exhibited high continuity (contig N50: 18.17-29.54 Mb) and completeness (BUSCO: 99.3-99.4%), with sequences successfully localized to the 19 chromosomes. Genome annotation revealed an average of 21,922 protein-coding genes and 44.66% repetitive sequences per assembly. Comparative genomic analysis against the current reference genome Sscrofa11.1 enabled the construction of a non-redundant SV catalog comprising 130,416 variants, nearly half of which (48.99%) were novel relative to existing pig pan-genome SV panel. These SVs clustered non-randomly into 231 "SV hotspots" that were significantly enriched in protein-coding genes and putative regulatory elements. Functional analyses further linked these SV hotspots to quantitative trait loci (QTLs) associated with economically important traits. A focused analysis of a 3.43 Mb hotspot on chromosome 1, overlapping a known QTL for average daily gain, revealed eight high-frequency SVs in open chromatin regions near candidate genes (NCS1, HMCN2, FUBP3, ABL1, and FIBCD1), suggesting a cis-regulatory mechanism that may influence gene expression. Collectively, this work provides the first haplotype-resolved genomic resource for commercial crossbred pigs, and establishes a foundational framework for deciphering the genomic architecture of hybrid vigor and advancing precision breeding in swine.},
}

@article {pmid41749108,
year = {2026},
author = {Hou, C and Yan, L and Liu, W and Liu, JN and Liu, Z},
title = {Pan-genome-wide characterization of the ascorbate peroxidase gene family reveals evolutionary dynamics and salt-responsive mechanisms in Fraxinus.},
journal = {BMC plant biology},
volume = {},
number = {},
pages = {},
doi = {10.1186/s12870-026-08450-9},
pmid = {41749108},
issn = {1471-2229},
support = {2023LZGC012//the Key Research and Development Program of Shandong Province/ ; SDCX-ZG-202400079//Shandong Provincial Postdoctoral Innovation Project/ ; tsqn202211135//'Taishan Scholars' of Shandong Province/ ; },
}

@article {pmid41749098,
year = {2026},
author = {Chamonara, K and Masum, MHU and Uddin, MS and Siddiqua, A and Sultana, S and Islam, S},
title = {Genomic and phenotypic characterization of Vibrio cholerae strain SU109: a genomic investigation of a shrimp-associated strain from Bangladesh.},
journal = {BMC genomics},
volume = {},
number = {},
pages = {},
doi = {10.1186/s12864-026-12635-9},
pmid = {41749098},
issn = {1471-2164},
abstract = {BACKGROUND: Shrimp exports generate substantial employment opportunities and revenue in Bangladesh. Nevertheless, the occurrence of Vibrio-associated epidemics remains a significant public health concern, with broader socio-economic consequences. This study characterizes the genomic and pathogenic features of the V. cholerae strain associated with local seafood market in Bangladesh. We employed whole-genome sequencing (WGS) using Nanopore long-read sequencing technology to investigate the genetic diversity, antimicrobial resistance, and virulence determinants of V. cholerae isolated from giant freshwater shrimps in Noakhali, Bangladesh.

RESULTS: The genome of V. cholerae strain SU109 was assembled with high completeness (97.63%) and contiguity (L50 = 1). Functional and pathway investigations revealed that the strain possesses a sophisticated network of genes and metabolic processes, demonstrating its survival capabilities across various conditions. The pathway analysis identified numerous biosynthetic gene clusters (ectoine, vibriobactin, terpene, isocyanide, and β-lactone) associated with the synthesis of secondary metabolites, suggesting environmental resilience, iron acquisition, stress adaptation, microbial competitiveness, and may contribute to the strain's virulence and ecological fitness. Pangenome studies identified 2,120 core genes, highlighting substantial genetic diversity and adaptability. A phylogenetic study indicated a close evolutionary link between shrimp and clinical strains, suggesting potential genome conservation across environmental and clinical isolates.

CONCLUSION: These findings indicate that V. cholerae strain SU109 may serve as a reservoir of virulence- and resistance-associated traits in seafood, highlighting the need for continued surveillance, stringent hygiene practices, and careful interpretation of genomic predictions to evaluate public health risks.},
}

@article {pmid41749082,
year = {2026},
author = {Sorin, V and Sanchez, MP and Drouilhet, L and Tosser-Klopp, G and Naji, MM and Boichard, D and Pausch, H and Boussaha, M and Leonard, AS},
title = {Pangenome-based association testing between a structural variant located upstream of the KIT gene and head depigmentation across a diverse panel of cattle breeds.},
journal = {Genetics, selection, evolution : GSE},
volume = {},
number = {},
pages = {},
doi = {10.1186/s12711-026-01037-w},
pmid = {41749082},
issn = {1297-9686},
abstract = {Coat color variation is a key phenotypic trait in domestic animals. Among the genetic factors involved, the KIT gene has frequently been associated with pigmentation diversity across species. In cattle, spotting or piebald phenotypes have been linked to variation in the genomic region encompassing KIT, but the identification of causal variants was not always possible. This is largely due to the regulatory nature of the underlying variants and the structural complexity of this genomic region, which remains difficult to investigate with linear reference genome-based approaches. In the present study, we used a local pangenome strategy to investigate a genomic region on chromosome 6 encompassing KIT which was recently suggested to be associated with head depigmentation in white-headed cattle breeds. We constructed a 2 Mb pangenome graph encompassing the associated region using 79 assemblies from 20 cattle breeds. Through the evaluation of the coverage at the node level on this pangenome graph, we identified a ~ 7 kb structural variant which was supported by 21 assemblies only from breeds exhibiting a white-headed phenotype. To validate these findings, we aligned 564 short-read sequencing data to a local graph of 30 kb, spanning the structural variant identified, and computed normalized coverage across the region. White-headed cattle breeds consistently exhibited higher coverage values, while color-headed breeds displayed nearly zero coverage. Together, these results confirm the association between a structural variant upstream of KIT with the white-headed phenotype. More broadly, our study demonstrates how targeted local pangenome graphs can efficiently resolve complex structural variants (SVs) with phenotypic impact, offering an interesting and computationally feasible alternative to whole-genome graph approaches.},
}

@article {pmid41748614,
year = {2026},
author = {Ma, Z and Xu, X and Peng, W and Zhang, T and Chen, Z and Cao, S and Zhang, F and Wang, Y and Xiao, H and Zhang, Y and Liu, Z and Liu, Z and Xue, H and Long, Q and Hou, T and Wang, W and Liu, Y and Jin, Z and Zhang, M and Peng, Y and Wen, J and Gaut, B and Zhou, Y},
title = {Population genomics reveals association of transposable elements variants with climatic adaptation in wild Amur grape.},
journal = {Nature communications},
volume = {},
number = {},
pages = {},
doi = {10.1038/s41467-026-70026-w},
pmid = {41748614},
issn = {2041-1723},
support = {32300191//National Natural Science Foundation of China (National Science Foundation of China)/ ; 32372662//National Natural Science Foundation of China (National Science Foundation of China)/ ; },
abstract = {Amur grape (Vitis amurensis Rupr.) is widely recognized for its cold tolerance traits and serves as a valuable genetic resource for breeding climate-resilient grape cultivars. Here, we construct a graph pangenome reference (Vampan_V1.0) and generate a variant map comprising 48,308,434 short variants and 127,094 TE-associated structural variants (TEVs) using deep resequencing data from 330 samples across 31 natural populations covering the species' distribution range. We discover a biased accumulation of SNPs around TEVs and identify 823 candidate adaptive genes associated with environmental variables. Using machine learning-based genetic offset models, we further show that putative adaptive TEVs significantly reduce genetic offsets by 7.3% to 8.2% under future climate scenarios. Our study shows the power of a graph-based pangenome to resolve complex variation and highlights the impact of TEVs on genetic diversity, local adaptation, and resilience to future climate change, providing insights into utilizing crop wild relatives in climate-resilient crop breeding.},
}

@article {pmid41746338,
year = {2026},
author = {Calvanese, CM and Valentino, V and De Prisco, A and Allesina, S and Amoruso, A and Deidda, F and Visciglia, A and Ercolini, D and Pane, M and De Filippis, F},
title = {Women's health is a team effort: probiogenomics supports the development of a multi-species vaginal probiotic.},
journal = {Cellular and molecular life sciences : CMLS},
volume = {},
number = {},
pages = {},
doi = {10.1007/s00018-026-06107-2},
pmid = {41746338},
issn = {1420-9071},
}

@article {pmid41746281,
year = {2026},
author = {Valadez-Cano, C and Wallace, RL and Chuan, J and Mahoney, D and Yin, X and Clairmont, L and Lepp, D and Li, S and Diarra, MS and Chen, W},
title = {Phylogenomic and functional insights into Staphylococcus shinii from blueberry production environments: intra-species structure, probiotic traits and antimicrobial resistance.},
journal = {Microbial genomics},
volume = {12},
number = {2},
pages = {},
pmid = {41746281},
issn = {2057-5858},
abstract = {Staphylococcus shinii is a recently proposed staphylococcal species identified in animal-associated microbiomes and fermented foods, with promising probiotic and biotechnological applications. However, its genomic diversity, functional traits and safety profile need to be well established. Here, we report the first recovery and genome sequencing of 41 S. shinii isolates from blueberry fruit washes and surrounding air. Phylogenomic analysis, including reference genomes, revealed at least 15 well-supported intra-species lineages (genomovars) defined by phylogenetic relationship and average nucleotide identity (>99.5% within genomovars; <99.5% between them). Pangenome analysis showed a highly conserved core genome comprising 83.3% of genes, alongside diverse accessory genes across genomovars. Core functions in S. shinii included carbohydrate metabolism, vitamin biosynthesis and short-chain fatty acid production, traits potentially linked to probiotic properties. Biosynthetic gene clusters for bioactive compounds were broadly conserved, although genes encoding ribosomally synthesized and post-translationally modified peptides varied among genomovars. About 10-18 antimicrobial resistance genes (ARGs) were identified per S. shinii genome, several of which were located on the chromosome. Phenotypic testing confirmed susceptibility to ciprofloxacin, gentamicin and ampicillin, while resistance to other antimicrobials varied and was often plasmid-associated. Resistance patterns differed across genomovars, emphasizing the need for intra-species resolution in risk assessment. Although major virulence factors listed in the Virulence Factor Database were absent, putative pathogenicity-related genes were found in the core genome using the Pathogen-Host Interaction Database. Their presence, along with ARGs, underscores the need for caution in clinical contexts. Nonetheless, the absence of major virulence determinants and the presence of beneficial traits in some S. shinii isolates support their potential use in the agri-food system or environmental biotechnology, pending strain-specific safety evaluation.},
}

@article {pmid41745283,
year = {2026},
author = {Su, J and Zhang, S and Lu, Q and Yang, J and Zheng, C and Li, X and Chen, X and Liu, H and Wang, Z and Hu, H},
title = {A Near-T2T Genome Assembly of Elsinoe fawcettii Provides Insights into Host Adaptation Driven by Cis-Regulatory Evolution.},
journal = {Journal of fungi (Basel, Switzerland)},
volume = {12},
number = {2},
pages = {},
pmid = {41745283},
issn = {2309-608X},
support = {103-725025010//FAFU Fund/ ; 31800008//National Natural Science Foundation of China/ ; },
abstract = {Elsinoe fawcettii is a devastating citrus pathogen worldwide, yet high-quality genomic resources are lacking, limiting insights into its adaptive mechanisms. Seventeen strains collected from 13 host species across 5 Chinese provinces were confirmed as E. fawcettii by multi-loci (ITS, rpb2, tef1-α) phylogenetic and morphological analyses. A near-telomere-to-telomere (near-T2T) genome for representative strain FJ-Y-3 was constructed using integrated PacBio and Hi-C sequencing. The 24.40 Mb assembly was organized into 11 chromosomes with exceptional completeness (BUSCO: 97.1%) and continuity (scaffold N50: 2.18 Mb). Pan-genome analysis revealed a closed structure, with core genes representing 77.19% of the total, suggesting evolutionary adaptation through fine-regulation of conserved elements rather than extensive gene content variation. Accessory genes were significantly enriched in terpenoid/polyketide metabolism, cell surface remodeling, and xenobiotic degradation, underscoring metabolic plasticity. Whole-genome resequencing showed single-nucleotide polymorphisms as the dominant variant, with ~60% residing in regulatory regions, implicating cis-regulation as a key adaptive mechanism. This work provides a high-quality genome and multi-omics framework for E. fawcettii, establishing a crucial molecular foundation for understanding pathogen adaptation and developing sustainable disease management strategies.},
}

@article {pmid41744226,
year = {2026},
author = {Cudby, J and Bonfield, J and Zhou, C and Durbin, R and Strelchuk, S},
title = {Pangenome-guided sequence assembly via binary optimization.},
journal = {Briefings in bioinformatics},
volume = {27},
number = {1},
pages = {},
doi = {10.1093/bib/bbag084},
pmid = {41744226},
issn = {1477-4054},
support = {//Wellcome Leap/ ; //EPSRC/ ; 220540/Z/20/A/WT_/Wellcome Trust/United Kingdom ; //Royal Society University Research Fellowship/ ; },
abstract = {De novo genome assembly is challenging in highly repetitive regions; however, reference-guided assemblers often suffer from bias. We propose a framework for pangenome-guided sequence assembly that can resolve short-read data in complex regions without bias towards a single reference genome. Our primary contribution is to frame the assembly as a graph traversal optimization problem, which can be implemented classically or on a quantum computer. The workflow involves first annotating pangenome graphs with estimated copy numbers for each node, then finding a path on the graph that best explains those copy numbers. On simulated data, our approach significantly reduces the number of contigs compared with de novo assemblers. While they introduce a small increase in inaccuracies, such as false joins, our optimization-based methods are competitive with current exhaustive search techniques. They are also designed to scale more efficiently as the problem size grows and will run effectively on future quantum computers; a small experiment on a real quantum device showcases this behaviour. Moreover, they are more resilient to noise in copy number estimation inherent in short-read-based assembly. We also develop novel tools for creating realistic synthetic pangenomes, aligning reads to pangenomes and for evaluating assembly quality.},
}

@article {pmid41743541,
year = {2025},
author = {Ramachandran, P and Konganti, K and Windsor, AM and Grim, CJ and Pradhan, AK},
title = {Population structure analysis of Salmonella serovar Muenchen to redefine geno-serotyping using genome indexing approaches.},
journal = {Frontiers in microbiology},
volume = {16},
number = {},
pages = {1681711},
pmid = {41743541},
issn = {1664-302X},
abstract = {Accurate identification of Salmonella serovars for source attribution in foodborne illness outbreaks. Traditional serotyping, which relies on antigenic properties, continues to serve as gold standard; however, advances in whole-genome sequencing (WGS) have enabled to the development of in-silico serotyping tools such as SeqSero2 and Salmonella In Silico Typing Resource (SISTR). Genome-indexing methods, such as bettercallsal, integrate DNA sketching and genome proximity analysis, have emerged as a promising tool for improving serovar resolution. This study examines the performance of DNA sketching-based serotyping in conjunction with established in-silico methods, focusing especially on Salmonella Muenchen, a polyphyletic serovar that ranks among the top 20 serovars linked with human infections in the United States. In this study, SeqSero2 was employed for antigen-based serotyping, SISTR for core genome Multi-locus Sequence Typing (cgMLST)-based phylogenetic clustering, pangenome analysis using PIRATE for microevolutionary insights, and bettercallsal for genome-indexing-based serovar calls. The results demonstrate that bettercallsal, leveraging the National Centre for Biotechnology Information (NCBI) Pathogen Detection database, enhances serovar resolution by incorporating genome proximity calls. The integration of SeqSero2 with bettercallsal yields complementary insights, maintaining historical serotyping nomenclature while enhancing serovar classification. This dual-tool strategy improves the discrimination of genomically distinct but antigenically similar serovars, therefore addressing limitations of traditional and molecular serotyping. Overall, integrating genome indexing through DNA sketching with validated in-silico serotyping tools establishes a robust framework for pathogen characterization. In this study, the tool is specifically applied for Salmonella serovar characterization. This methodology enhances the source attribution accuracy in outbreak investigations and establishes a framework for updating serovar classification in the era of genomic epidemiology.},
}

@article {pmid41741285,
year = {2026},
author = {Blackman, BK and Burke, JM and Nasti, RA and Todesco, M and Wang, J and Rieseberg, LH},
title = {Sunflower genetics and genomics: from fundamental evolutionary insights to crop improvement.},
journal = {Trends in genetics : TIG},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.tig.2026.01.002},
pmid = {41741285},
issn = {0168-9525},
abstract = {The sunflower genus, Helianthus, not only includes two crops (cultivated sunflower and Jerusalem artichoke) but also comprises approximately 50 diverse wild species that have served both as a model for foundational studies of adaptation and speciation and as a source of alleles for crop improvement. Extensive genomic resources, including genome assemblies, association populations, and a comprehensive expression atlas, have facilitated both evolutionary and agronomic studies. Despite these advances, sunflower remains recalcitrant to genetic transformation, which impedes functional analyses. The development of tools for functional genetics and genomics, including a graph-based pangenome, improved transformation methods, and doubled haploid technology, is needed to accelerate sunflower improvement and enhance its utility as an evolutionary model.},
}

@article {pmid41733604,
year = {2026},
author = {Tao, H and Wu, S and Wu, G and Chen, X and Sun, Y and Zhu, X and Chen, L and Feng, C and Kabore, MAF and Woldegiorgis, ST and Zhang, L and Ai, Y and Liu, W and He, H},
title = {Pan-genome of wild and cultivated rice uncovers genetic diversity, lost and selected sequences during rice domestication.},
journal = {Rice (New York, N.Y.)},
volume = {},
number = {},
pages = {},
doi = {10.1186/s12284-026-00893-w},
pmid = {41733604},
issn = {1939-8425},
support = {32370709//Natural Science Foundation of China/ ; 2025NZ01210036//Fujian Provincial Science and Technology Key Project/ ; },
}

@article {pmid41733351,
year = {2026},
author = {Yin, Z and Chen, X and Xiao, J and Tian, X and Li, Z and Zhang, M and Jing, B and Li, D and Deng, X and Peng, L},
title = {Insights into novel diagnostic assay development, antimicrobial resistance, and pathogenicity in Proteus mirabilis through pan-genome analysis.},
journal = {Applied and environmental microbiology},
volume = {},
number = {},
pages = {e0189825},
doi = {10.1128/aem.01898-25},
pmid = {41733351},
issn = {1098-5336},
abstract = {Proteus mirabilis, a significant pathogen associated with human urinary tract infections (UTIs), demonstrates escalating multidrug resistance (MDR) that complicates clinical management. Accurate identification and in-depth genomic analysis are essential for monitoring and controlling this pathogen. This study aimed to identify the species-specific gene repertoire, antimicrobial resistance (AMR), and virulence genetic profiles through pan-genome analysis to develop novel detection methods and better understand emerging public health threats. The genus Proteus exhibits an open pan-genome, with P. mirabilis harboring a distinct species-specific gene repertoire. Two species-specific core genes, PMI3020 and PMI3598, were identified as molecular targets. We developed conventional PCR and TaqMan probe-based real-time PCR assays, which demonstrated high specificity when tested against P. mirabilis and non-P. mirabilis isolates. The TaqMan probe-based real-time PCR demonstrated a sensitivity of 3.43 × 10[2] CFU/mL using serial dilutions of P. mirabilis DNA. Comparative genomic analysis revealed significant differences in AMR and pathogenicity-related gene repertoires between P. mirabilis and other Proteus spp. The higher prevalence of AMR phenotypes in P. mirabilis correlated with its greater abundance of AMR genes. Emerging AMR genes acquired through horizontal gene transfer (HGT) have increased MDR risks, particularly to carbapenems and cephalosporins. Additionally, P. mirabilis genomes contain more virulence genes mainly related to adherence and iron acquisition. Our findings establish pan-genome analysis as an effective tool for identifying specific genetic markers to detect pathogens accurately and provide a comprehensive genomic framework illuminating AMR dynamics and virulence in P. mirabilis, thereby providing a valuable foundation for future public health risk assessments.IMPORTANCEP. mirabilis is a major uropathogen with increasing AMR prevalence. The dissemination of AMR genes across healthcare and community settings poses critical challenges to infection control. This study conducted pan-genome analysis of Proteus to identify P. mirabilis-specific gene repertoire, of which species-specific core genes were used as molecular targets to develop highly sensitive PCR assays for accurate detection of this pathogen. Compared with other Proteus spp., P. mirabilis possesses a greater abundance of AMR genes, resulting in a higher prevalence of AMR phenotypes, including significant resistance to carbapenems and cephalosporins. This study establishes pan-genome analysis as an effective strategy for mining species-specific genetic markers, enabling the development of novel PCR assays for accurate pathogen detection. The comprehensive genomic framework enhances understanding of AMR dynamics and virulence mechanisms essential for public health risk assessment.},
}

@article {pmid41724873,
year = {2026},
author = {de Almeida, LN and Silva, MJFE and de Freitas Rodrigues Jesuino, B and Tupy, SM and Vieira, JHR and Xavier, GA and da Rocha, JPL and Gonçalves, OS and Santana, MF},
title = {Comparative genomic analyses reveal key traits for biocontrol and the promotion of plant growth in Paenibacillus strains.},
journal = {World journal of microbiology & biotechnology},
volume = {42},
number = {3},
pages = {},
pmid = {41724873},
issn = {1573-0972},
abstract = {UNLABELLED: Paenibacillus species have emerged as promising candidates for sustainable agriculture due to their functional versatility in plant growth promotion and biocontrol. We performed a comparative genomic analysis of 428 high-quality Paenibacillus genomes to assess their ecological adaptability and biotechnological potential. The analyzed strains originated from diverse environments, reflecting broad ecological distribution. Functional annotation revealed a widespread occurrence of plant growth-promoting traits (PGPTs), including phosphate and potassium solubilization, siderophore biosynthesis, nitrogen fixation, and phytohormone-related compounds. On average, the genomes contained 249 genes associated with biofertilization, 190 with phytohormone production, 97 linked to bioremediation, and around 322 involved in competitive exclusion. The open pan-genome configuration (b = 0.503) highlights notable genetic plasticity and ongoing gene acquisition. While the core genome was enriched in essential functions, accessory and unique fractions carried genes associated with environmental adaptation and niche specialization. Analysis of mobile genetic elements (MGEs) showed that some PGPT-related genes occur in mobile regions, suggesting horizontal gene transfer contributes to the dissemination of beneficial traits. Diverse BGCs, including those encoding Bacillopaline, Tridecaptin, Fusaricidin B, Paeninodin, and Polymyxin, were identified, many with antimicrobial potential. CAZyme profiling revealed abundant chitinases, supporting pathogen suppression capacity. No virulence factors were detected, and antibiotic resistance genes were rare, underscoring the genus’ low pathogenicity. Altogether, these findings position Paenibacillus as a genetically and functionally diverse group with strong potential as a safe, sustainable resource for developing biofertilizers and biopesticides.

SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1007/s11274-026-04811-6.},
}

@article {pmid41730891,
year = {2026},
author = {You, Q and Peng, Z and Li, Z and Jiang, Y and Wan, P and Zhao, Y and Zhao, W and Zhang, S and Cheng, H and Chen, C and Heng, Z and Hu, M and Zhou, Y and Gaut, BS and Sun, B and Li, T and Liao, Y},
title = {Sub-pangenome analysis reveals structural variants associated with fruit color and bacterial wilt resistance in eggplant.},
journal = {Nature communications},
volume = {},
number = {},
pages = {},
doi = {10.1038/s41467-026-69764-8},
pmid = {41730891},
issn = {2041-1723},
abstract = {Eggplant (Solanum melongena L.) is a globally important Solanaceae crop, yet trait-relevant genomic variants remain poorly characterized. Here, we perform population genomic analyses of 226 eggplant accessions sampled mainly from a major domestication center spanning Southeast Asia and South China, and find that genetic relationships closely track geographic origin. We generate chromosome-scale assemblies for 11 representative accessions using long-read sequencing and integrate six published genomes to build a pangenome resource. Using this resource, association scans identify a 12.4 Mb inversion on chromosome 10 segregating at 50.44% frequency that is strongly associated with fruit color, likely through hitchhiking with SmMYB1. We also detect variants associated with bacterial wilt resistance, including a premature stop codon in SmCYP82D47 and copy number variations in SmEPS1 and SmRoq1 homologs. Together, our results illuminate the evolution and phenotypic impact of large structural variants and provide genomic resources for eggplant genetics and breeding.},
}

@article {pmid41726154,
year = {2026},
author = {Martin, FM and Morin, E and Kuo, A and Miquel, I and Labbé, J and Tacon, FL and Fauchery, L and Kohler, A and Andreopoulos, W and Copeland, A and Sun, H and Salamov, A and Lipzen, A and Han, J and LaButti, K and Tritt, A and Barry, K and Grigoriev, IV},
title = {Draft Genomes of Geographically Distinct Strains and Progeny of the Ectomycorrhizal Basidiomycete Laccaria bicolor.},
journal = {Journal of genomics},
volume = {14},
number = {},
pages = {10-17},
pmid = {41726154},
issn = {1839-9940},
abstract = {The ectomycorrhizal fungus Laccaria bicolor is a key symbiotic mutualist in forest ecosystems, where it enhances nutrient uptake and promotes the growth of host trees. Here, we present genome assemblies of 14 geographically distinct strains and progeny of L. bicolor, providing new insights into the intraspecific genomic diversity. Pangenome analysis revealed substantial variation in assembly size (42-96 Mbp), gene content (16,084-26,800 genes), and single nucleotide polymorphism (SNP) density (0.04-12.08 SNPs/kb). This variation likely reflects genuine biological differences among strains adapted to diverse environmental conditions, although differences in assembly quality and repeat content may also play a role. These genomic resources, comprising draft genome assemblies with comprehensive annotations, will facilitate comparative studies of the genetic diversity and functional traits underlying the ecological success of this model ectomycorrhizal fungus.},
}

@article {pmid41725811,
year = {2026},
author = {Fahim, NAI and Sarwer, A and Firdous, Z and Rana, ML and Islam, MS and Rahman, S and Pondit, A and Hassan, J and Walsh, TR and Farzana, R and Rahman, MT},
title = {Genome-wide analysis of extended-spectrum beta-lactamase-producing Escherichia coli from seafood in Bangladesh: population structure, resistome, virulome, and global dissemination patterns.},
journal = {Frontiers in microbiology},
volume = {17},
number = {},
pages = {1737712},
pmid = {41725811},
issn = {1664-302X},
abstract = {OBJECTIVES: This study aimed to identify multilocus sequence type (MLST), serotype, average nucleotide identity (ANI), antimicrobial resistance genes (ARGs), virulence genes (VGs), and mobile genetic elements (MGEs) from whole-genome sequences of 10 Escherichia coli isolated from seafood in Bangladesh and compared them with the global datasets of beta-lactamase-producing E. coli.

METHODS: Ten E. coli isolates (crab = 3, shrimp = 1, tuna = 6) were subjected to whole-genome sequencing using Oxford Nanopore Technologies (Oxford, UK). In-silico bioinformatics analyses were performed using online tools and Linux-based commands. A systematic advanced search in PubMed identified 722 global genomes of beta-lactamase-producing E. coli for comparative analysis. A population structure and global phylogeny were constructed to illustrate the current status of beta-lactamase-producing E. coli from diverse sources (seafood, human, aquatic, wastewater, and environmental) across countries, based on their STs, ARGs, VGs, MGEs, and serotypes.

RESULTS: Bioinformatics analysis revealed that most isolates displayed unique sequence types (STs) and core genome sequence types (cgSTs), while three isolates shared both ST1431 and cgST104784, indicating close genetic relatedness supported by ANI analysis. In shrimp and tuna isolates, both O and H antigens were detected, whereas crab isolates carried either O or H antigens. Pangenome analysis identified 56.4% strain-specific genes, 34.2% dispensable genes, and 9.4% core genes, with functions categorized into clusters of orthologous groups (COGs). Several ARGs, including beta-lactamase genes (CTX-M-15, AmpC, bla DHA-1), were detected across isolates, with crabs harboring the highest number. The VGs were more common in tuna isolates. Plasmids were only detected in crabs (Col440I, IncFIA, IncFIB(pHCM2), and ColRNAI) carrying qnrB4, dfrA17, qacE, mph(A), sul1, bla DHA-1 ARGs, but were absent in shrimp and tuna. Population structure analysis showed that ST345 in Bangladesh closely matched wastewater (Czech Republic) and human (USA) isolates. Some STs overlapped with international records, while others appeared novel, suggesting limited global distribution. Globally, wastewater and human isolates from the Czech Republic showed the greatest similarity to our strains.

CONCLUSION: These findings underscore the potential role of seafood in disseminating beta-lactamase-producing E. coli, highlighting the urgent need for integrated surveillance to mitigate antimicrobial resistance risks in humans, animals, and the food chain.},
}

@article {pmid41612191,
year = {2026},
author = {Choudhury, ST and Andam, CP},
title = {Genome-wide co-occurrence patterns link mobile genetic elements, antimicrobial resistance and defense systems in Pseudomonas aeruginosa.},
journal = {BMC genomics},
volume = {27},
number = {1},
pages = {226},
pmid = {41612191},
issn = {1471-2164},
support = {R35GM142924/NH/NIH HHS/United States ; R35GM142924/NH/NIH HHS/United States ; },
abstract = {BACKGROUND: Pseudomonas aeruginosa remains an urgent public health threat due to the many life-threatening diseases it causes, wide dissemination of multidrug resistant strains, and ability to survive and persist on hospital surfaces. Its accessory genome, composed of genes present in a subset of strains, may provide a clue to its success as an opportunistic pathogen. Here, we aim to characterize the pool of mobile genetic elements (MGE), anti-phage defenses and antimicrobial resistance (AMR) genes in P. aeruginosa.

RESULTS: Using a dataset of 1,045 complete genomes, we identified 173 plasmids, 745 ICE/IME, 4,351 phage sequences, and 40,110 insertion sequence (IS) elements. Most pairs of genomes carrying specific combinations of defenses and MGEs exhibit low Jaccard similarity coefficient (< 20%) indicating that most unique MGE-defense combinations can be found in dissimilar genomes. Nonetheless, despite their considerable diversity and differential distribution among genomes, we found a highly connected network of co-occurring MGEs and AMR genetic determinants. IncP was connected to the largest and most diverse set of AMR determinants (n = 93) from nine antimicrobial classes (aminoglycoside, beta-lactam, phenicol, polymyxin, quinolone, sulfonamide, tetracycline, trimethoprim, multiple drugs) and heavy metals. Genetic elements conferring resistance to aminoglycoside, beta-lactam and quinolone were enriched in genomes carrying IS3. Genes conferring resistance to aminoglycoside, beta-lactam and trimethoprim were more frequently found in genomes carrying Autographiviridae sequences.

CONCLUSIONS: Our study highlights the need for public health strategies that disrupt MGE-mediated transmission of AMR genes, integrate genomic surveillance of MGEs and other accessory genes into infection control programs, and guide the design of combination therapies that consider bacterial defense systems. Our findings have implications to understanding the contributions of strain diversity in health and disease, the evolution of multidrug resistance, and the nature of the bacterial pan-genome.

SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1186/s12864-026-12585-2.},
}

@article {pmid41721206,
year = {2026},
author = {Michelioudakis, V and Zafranas, A and Myrisiotis, C and Makri, S and Katsoula, A and Campos, M and Vasileiadis, S and Karpouzas, DG},
title = {Comparative Genomic and Transcriptomic Analysis Reveals Why Paenarthrobacter Strains Are Specialists in the Degradation of the Fungicide Iprodione.},
journal = {Microbial biotechnology},
volume = {19},
number = {2},
pages = {e70319},
doi = {10.1111/1751-7915.70319},
pmid = {41721206},
issn = {1751-7915},
support = {MIS 5002636//Omic-Engine RI project/ ; //Co-financed Greece and European Union/ ; //European Regional Development Fund/ ; },
abstract = {Paenarthrobacters degrade the fungicide iprodione through a pathway involving an amidase (IpaH), a deacetylase (DdaH) and a hydrolase (DuaH). We aimed to elucidate the mechanisms of this catabolic specialisation and its evolution in Paenarthrobacters. Two new iprodione-degrading Paenarthrobacter strains TA1.8 and C1 were sequenced, and their genomes were analysed comparatively to the iprodione-degrading Paenarthrobacter strains YJN-5 and YJN-D. We noted different gene organisation motifs amongst strains, suggesting different stages of pathway evolution in the studied strains depending on their prior exposure to iprodione. Strains derived from soils exposed to iprodione (TA1.8, YJN-5 and YJN-D) carry multiple copies of ipaH, ddaH and duaH. Conversely, strain C1, isolated from a pristine soil, carried one copy of the set. Comparative genomics and pangenome analysis of Paenarthrobacters suggested an evolution route of the iprodione transformation pathway which involves acquisition of ddaH through horizontal gene transfer, gene duplication of the chromosomally encoded ipaH and ddaH, and further genetic rearrangements for pathway optimisation, complementing duaH, a core gene in Paenarthrobacters. Transcriptomic analysis of TA1.8 verified the importance of all ipaH, ddaH and duaH homologues in iprodione transformation and pointed to hydantoinases as potential facilitators of the transformation of the hydantoin-containing intermediate N-(3,-5-dichlorophenyl)-2,4-dioxoimida-zolidine, a step mediated by DdaH.},
}

@article {pmid41720456,
year = {2026},
author = {Mu, J and Ma, Z and Li, J and Cai, X and Meng, Q and Qiao, J},
title = {Identification of Conserved Vaccine Targets in Mycoplasma bovis through Integrated Pan-Genome and Reverse Vaccinology Approaches with In Vivo Immunogenicity and Safety Evaluation.},
journal = {Veterinary journal (London, England : 1997)},
volume = {},
number = {},
pages = {106603},
doi = {10.1016/j.tvjl.2026.106603},
pmid = {41720456},
issn = {1532-2971},
abstract = {Mycoplasma bovis is a major etiological agent of bovine respiratory disease, causing substantial economic losses to the cattle industry. To address this challenge, we performed a pan-genome analysis of 80 globally sourced M. bovis genomes and identified 1,058 core genes. Reverse vaccinology and immunoinformatics approaches were subsequently integrated to screen three potential vaccine candidates: namely lipoate protein ligase 2 (LplA), elongation factor 4 (LepA) and glyceraldehyde-3-phosphate dehydrogenase (GAPDH). Codon-optimized gene sequences were cloned into the pET-28a vector and successfully expressed and purified using E. coli expression system. Thirty female BALB/c mice were randomized into five groups (n = 6 per group). For primary immunization, each mouse received 100μg of recombinant protein emulsified in Freund's complete adjuvant via subcutaneous injection, followed by booster immunizations with 50μg of protein formulated with Freund's incomplete adjuvant at weeks 2 and 4. Fourteen days after primary immunization, all vaccinated groups exhibited significantly elevated antigen-specific antibody levels, which remained high through week 6. Notably, rLplA and rGAPDH induced higher antibody titers than rLepA. Analysis of the IgG2a/IgG1 subtype ratio indicated that rLplA, rGAPDH, and rLepA predominantly elicited Th2-type immune responses. In addition, all three recombinant proteins significantly increased cytokine production. Moreover, no adverse physiological reactions or histopathological abnormalities were observed throughout the immunization period, confirming the favorable safety profile of the candidates. Collectively, these findings identify promising targets for the development of M. bovis subunit vaccines to address pathogen variability, antibiotic resistance, and the limited efficacy of current vaccines.},
}

@article {pmid41720069,
year = {2026},
author = {Mondal, R and Manna, A and Mandal, P and Kurt, H and Sen, A and Jangid, K and Mandal, AK},
title = {Stenotrophomonas raiganjensis sp. nov., an extensively drug-resistant bacterium isolated from Bombyx mori L., described under the SeqCode.},
journal = {Systematic and applied microbiology},
volume = {49},
number = {2},
pages = {126699},
doi = {10.1016/j.syapm.2026.126699},
pmid = {41720069},
issn = {1618-0984},
abstract = {SeqCode allows a single strain or a high-quality genome to serve as type material, making it compatible with modern genomics and biodiversity governance frameworks, especially for countries such as India. We, therefore, describe a novel bacterium, designated RAC2[TS] under the SeqCode. RAC2[TS] was isolated from the hemolymph of infected Bombyx mori L. and characterized using a polyphasic taxonomic approach. While 16S rRNA gene sequence based phylogenetics showed Stenotrophomonas maltophilia NBRC 14161ᵀ to be the closest relative, multilocus sequence analysis (MLSA) based on seven housekeeping genes (atpD, gapA, guaA, mutM, nuoD, ppsA, recA) and genome-based relatedness indices confirmed RAC2[TS] as a distinct lineage within the genus Stenotrophomonas. Whole-genome analysis identified a 4.6 Mbp genome with 66.5% G + C content; and 4276 coding sequences, including several antimicrobial resistance genes alongside multidrug efflux pump sme operon genes and a single virulence-associated gene, pilG. RAC2[TS] showed 91-93% average nucleotide identity (ANI) and 41-48% digital DNA-DNA hybridization (dDDH) with closely related taxa. Pangenome analysis revealed an open pangenome (α = 0.257), with 12,623 gene clusters including 229 core genes and 6994 strain-specific genes. Antibiotic susceptibility testing demonstrated extensive drug resistance (XDR) characteristics of RAC2[TS]. Fatty acid methyl ester (FAME) analysis revealed isoC15:0 (24.56%), anteiso-C15:0 (14.27%), and summed feature 3 (16:1 ω7c/16:1 ω6c; 11.18%) as major components. Combined phenotypic, chemotaxonomic, phylogenomic, and genomic evidence supports the recognition of RAC2[TS] as a novel species within the genus Stenotrophomonas. Under the SeqCode, we propose the name S. raiganjensis sp. nov. for strain RAC2[TS] (=MCM-B-1506[TS]) with the type genome GCA_030658505.2[TS].},
}

@article {pmid41716894,
year = {2026},
author = {Yang, F and Chai, S and Yan, L and He, Y and Ma, X and Shen, L and Gao, S and Guo, Y and Zhang, Z and Ni, W and Bao, J and Gao, Z},
title = {Comparative Genomic Analysis of Pseudomonas aeruginosa Isolates from Community-Acquired and Hospital-Acquired Pneumonia.},
journal = {Infection and drug resistance},
volume = {19},
number = {},
pages = {566637},
pmid = {41716894},
issn = {1178-6973},
abstract = {PURPOSE: To characterize the genomic features of Pseudomonas aeruginosa isolates causing community-acquired pneumonia (CAP) and compare them with hospital-acquired pneumonia (HAP) genomes to identify setting-associated genetic determinants.

PATIENTS AND METHODS: Three CAP isolates collected in China underwent antimicrobial susceptibility testing and whole-genome sequencing. Comparative genomic analyses were performed against 84 complete HAP-associated genomes retrieved from NCBI RefSeq (accessed in December 2023), including core genome SNP phylogeny, profiling of antimicrobial resistance (AMR) determinants, virulence genes, and pangenome analysis to identify CAP-specific genes.

RESULTS: The three CAP cases presented with severe pneumonia (including septic shock), with one fatality; however, all CAP isolates remained susceptible to the most commonly used antipseudomonal agents. CAP genomes were 6.5-7.1 Mb (GC 65.76-66.41%) and contained 5908-6633 predicted coding sequences. Core-SNP phylogeny showed clustering of the three CAP isolates. Compared with HAP genomes, CAP isolates harbored fewer acquired AMR genes and fewer resistance-associated mutations. Virulence profiling identified a subset of virulence genes absent from all CAP genomes (n = 40), largely annotated as immune modulation and including loci consistent with highly variable surface polysaccharide regions, together with several genes annotated to biofilm-related functions and effector delivery systems. Major type III secretion system effector profiles differed across CAP isolates (exoU in one isolate; exoS in two). Pangenome analysis identified 10,225 gene families, and 157 genes were specific to the CAP isolates, most encoding hypothetical proteins, with a subset related to lipid transport and metabolism, including fatty acid uptake and functions associated with β-oxidation. Given the limited number of CAP isolates, comparisons between groups are descriptive.

CONCLUSION: CAP-associated P. aeruginosa showed a distinct comparative genomic profile with reduced AMR determinant burden and a distinct virulence gene repertoire despite severe clinical presentation. CAP-specific genes, including those linked to lipid metabolism, may contribute to niche adaptation and warrant functional validation.},
}

@article {pmid41716264,
year = {2026},
author = {Wang, J and Li, C and Zheng, X and Chen, Z and Ye, W and Xu, Y and Qiu, W and Chen, S and Pei, H and Zhong, Y},
title = {Genome and drug resistance analysis of Mycobacterium abscessus complex on tropical islands in China.},
journal = {Frontiers in microbiology},
volume = {17},
number = {},
pages = {1702466},
pmid = {41716264},
issn = {1664-302X},
abstract = {OBJECTIVE: Based on whole-genome sequencing (WGS) technology, the species distribution, genetic correlations, virulence and drug resistance gene characteristics of the clinical isolates of Mycobacterium abscessus complex (MABC) in the tropical island of China (Hainan) were analyzed to provide a basis for clinical precise diagnosis and treatment.

METHODS: A total of 113 MABC strains from the Second Affiliated Hospital of Hainan Medical University from 2014 to 2023 were collected. Whole-genome sequencing (WGS) was used for subspecies identification (Average Nucleotide Identity, ANI), genetic distance analysis (single nucleotide polymorphism, SNP), and pan-genome analysis. The distribution of virulence and antibiotic resistance genes was analyzed through the Virulence Factor Database (VFDB) and the Comprehensive Antibiotic Resistance Database (CARD). The drug susceptibility phenotypes were detected by the microbroth dilution method.

RESULTS: Among the 113 MABC strains, M. abscessus subsp. abscessus (Mab) accounted for 65.5%, M. abscessus subsp. massiliense (Mma) accounted for 33.6%, and M. abscessus subsp. bolletii (Mbo) accounted for 0.9%. The strains showed high genetic diversity among them, but two pairs of Mab strains with high genetic similarity (differing by 5 and 8 SNPs respectively) were identified, suggesting the possibility of local common exposure. The pan-genome is open-ended and consists of 3,626 core genes and highly variable accessory/unique genes. The virulence genes show species-specific differences: the detection rate of the phenolic lipid synthesis gene papA5 in Mma is significantly higher than that in Mab (92.1% vs. 47.3%, p < 0.001), while the PDIM synthesis gene ppsE is significantly lower in Mma (0.0% vs. 98.6%, p < 0.001). The drug sensitivity test shows that the 14-day induction of resistance rate of Mma to clarithromycin is significantly lower than that of Mab (5.3% vs. 86.5%, p < 0.001). Resistance genes are widely carried, including rrs a1408g (99.1%), rrl a2059g (98.2%) mutations, and the efflux pump gene qacJ in Mma (97.4%).

CONCLUSION: In Hainan region, environmental exposure is the main source of MABC infection. Whole genome analysis suggests the potential risk of local common exposure. Mma has a better treatment prospect due to its low clindamycin resistance rate. The differentiation of virulence and resistance genes among subtypes provides a molecular basis for the precise prevention and control of MABC infection in tropical regions.},
}

@article {pmid41588321,
year = {2026},
author = {Zhang, B and Deng, Y},
title = {Pan-NLR gene family analyses decipher evolutionary dynamics, population diversity, and potential disease resistance genes in cucumber.},
journal = {BMC plant biology},
volume = {26},
number = {1},
pages = {345},
pmid = {41588321},
issn = {1471-2229},
support = {Qianke Hefuqi [2022] 014//the Department of Science and Technology of Guizhou Province/ ; Qiannongke Outstanding Team [2026] No. 07//Guizhou Academy of Agricultural Sciences/ ; },
abstract = {BACKGROUND: Cucumber (Cucumis sativus L.) is a globally important crop, yet its production is severely hampered by pathogen attacks, leading to substantial economic losses. Nucleotide-binding site-leucine-rich repeat (NLR) genes are critical components of the plant immune system, but a comprehensive understanding of their genetic diversity and evolutionary mechanisms in cucumber has been lacking.

METHODS: Leveraging a cucumber pan-genome of 12 representative accessions, this study systematically investigated the NLR gene family through orthologous gene group (OGG) analysis, focusing on presence/absence variation (PAV), phylogeny, gene structure, integrated domains (IDs), NLR-pairs, copy number variation, and selection pressures. Publicly available transcriptome data were also integrated to analyze NLR gene expression patterns upon pathogen inoculation.

RESULTS: This study identified a total of 879 pan-NLR genes, which were clustered into 33 core and 54 dispensable orthologous gene groups (OGGs). Comparative genomic analysis revealed that the cucumber NLR repertoire has undergone a contraction during its evolution. Phylogenetic analysis uncovered distinct evolutionary paths among NLR subfamilies: RNLs are highly conserved, CNLs and TNLs exhibit species-specific expansions, and NLs show a polyphyletic distribution, primarily arising from N-terminal domain loss events. Compared to wild populations (Indian), cultivated populations (especially the Eurasian group) exhibit reduced NLR diversity, mainly due to the loss of dispensable genes. This study identified specific IDs and NLR-pairs in wild germplasm, which are potentially associated with responses to specific pathogen pressures. Selection pressure analysis indicated that the NLR family is predominantly under purifying selection, although some genes experienced strong positive selection during domestication. Transcriptome analysis identified a candidate gene, CsaV4_2G000768, which contains a unique ID and shows a broad-spectrum response to multiple pathogens.

CONCLUSION: This study provides a systematic, pan-genomic view of the contraction and divergent evolution of the cucumber NLR gene family and elucidates the impact of domestication on its diversity. The identification of unique NLR-IDs and NLR-pairs from wild germplasm, along with a candidate gene potentially associated with broad-spectrum response, offers valuable theoretical insights and genetic resources for cucumber disease resistance breeding.

SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1186/s12870-026-08208-3.},
}

@article {pmid41711050,
year = {2026},
author = {Kumar, A and Männistö, MK and Kerkhof, LJ and Häggblom, MM},
title = {Genome Analysis Reveals Diversity and Functional Potential of Novel Janthinobacterium Species From Subarctic Soils.},
journal = {MicrobiologyOpen},
volume = {15},
number = {1},
pages = {e70239},
doi = {10.1002/mbo3.70239},
pmid = {41711050},
issn = {2045-8827},
support = {2129351//US National Science Foundation/ ; //USDA-NIFA Hatch Accession/ ; //the Research Council of Finland/ ; },
mesh = {*Soil Microbiology ; Phylogeny ; Arctic Regions ; *Genome, Bacterial ; RNA, Ribosomal, 16S/genetics ; Tundra ; Carbon/metabolism ; DNA, Bacterial/genetics ; Soil/chemistry ; Sequence Analysis, DNA ; },
abstract = {The Arctic tundra and boreal forest regions are affected by ongoing climate change, leading to increased warming, increased plant production, and heightened microbial activity. Microbes play a key role in carbon release from stored soil organic matter, and characterizing their diversity and function in high-latitude soils is thus of significant interest. The Pseudomonadota are abundant and diverse members of high-latitude soils. Here, we describe two novel species of the genus Janthinobacterium, of the order Burkholderiales, isolated from tundra heath and northern boreal forest soils. The isolates are aerobic, chemoorganotrophic psychrophiles and are well-adapted to the subarctic climate conditions. Phylogenomic analyses and ANI values confirmed the novelty of the strains, designated as Janthinobacterium silvisoli sp. nov. K2Li3 and Janthinobacterium saanense sp. nov. S3T4. Genome analysis revealed that the new species have the metabolic potential for degradation of complex carbon and polyphenols, which are abundant in tundra heath and lichen-dominated, nutrient-poor forest soils. The strains are well-adapted to nitrogen-limited soil ecosystems and can scavenge nitrogen from both organic and inorganic sources. Additionally, the strains harbor secondary metabolite gene clusters that encode antimicrobial compound production, potentially enhancing their competitiveness in the subarctic environment. The comparative pangenome analysis indicated that the strains have unique gene clusters for carbohydrate transport and metabolism, and energy generation and conservation. The genome-based functional exploration enhances our understanding of this genus and how environmental conditions may shape the functionality and interactions of Janthinobacterium species in subarctic soil ecosystems.},
}

*Soil Microbiology
Phylogeny
Arctic Regions
*Genome, Bacterial
RNA, Ribosomal, 16S/genetics
Tundra
Carbon/metabolism
DNA, Bacterial/genetics
Soil/chemistry
Sequence Analysis, DNA

@article {pmid41708786,
year = {2026},
author = {Shi, C and Chen, S and Wang, J and Chen, W and Sun, C and Guo, Q and Liao, S and Wang, H and Mu, Y and Shu, X and Meng, D and Zhao, J and Dong, L and Zhao, L and Hou, S and Guo, L and Yang, C},
title = {A tomato telomere-to-telomere super-pangenome empowers stress resilience breeding.},
journal = {Nature genetics},
volume = {},
number = {},
pages = {},
pmid = {41708786},
issn = {1546-1718},
support = {SYS202206//Natural Science Foundation of Shandong Province (Shandong Provincial Natural Science Foundation)/ ; ZR2023JQ010//Natural Science Foundation of Shandong Province (Shandong Provincial Natural Science Foundation)/ ; },
abstract = {Tomato (Solanum lycopersicum), one of the world's most valuable vegetable crops, has suffered from diminished genetic diversity and stress resistance. Wild tomatoes serve as an invaluable genetic reservoir, yet their potential for stress resilience remains largely unexploited in tomato breeding. Here we report a genus-wide super-pangenome across 16 tomato species by integrating 20 telomere-to-telomere genomes and 27 published chromosome-scale genomes. Genus-wide population analysis demonstrates broad genetic diversity with limited gene flows among principal clades. Pan-centromere analysis reveals a diverse landscape and dynamic evolution of the mysterious tomato centromeres involving rapid diversification, satellite emergence and repositioning. A comprehensive catalog of structural variants uncovers extensive rearrangements, especially from wild tomatoes, and discovers key molecular markers associated with salinity resistance. Structural-variant-based genome-wide association studies identified a leucine-rich repeat receptor gene SlGMAK conferring gray mold resistance. Our telomere-to-telomere super-pangenome will accelerate exploiting the untapped potential of wild relatives to improve modern tomatoes for stress resilience.},
}

@article {pmid41705345,
year = {2026},
author = {Nie, S and Li, F and Li, R and Wang, J and Ma, Y and Chan, CKK and Zhao, J and Hu, H},
title = {Challenges in Bringing Pangenome Research Into Breeding: A Case Study in Rice.},
journal = {Plant biotechnology journal},
volume = {},
number = {},
pages = {},
doi = {10.1111/pbi.70591},
pmid = {41705345},
issn = {1467-7652},
support = {2024YFD1200801//National Key Research and Development Program of China/ ; 32400512//National Natural Science Foundation of China/ ; 2024QN11N336//Guangdong Provincial Pearl River Talents Program/ ; 2024A1515011981//The GuangDong Basic and Applied Basic Research Foundation/ ; 2025A1515012969//The GuangDong Basic and Applied Basic Research Foundation/ ; SKXRC2025531//Guangdong Provincial Association for Science and Technology Youth Talent Cultivation Program/ ; 2023YG04//The "YouGu" Plan of Rice Research Institute of Guangdong Academy of Agricultural Sciences/ ; 2024YG07//The "YouGu" Plan of Rice Research Institute of Guangdong Academy of Agricultural Sciences/ ; 2025YG03//The "YouGu" Plan of Rice Research Institute of Guangdong Academy of Agricultural Sciences/ ; 2024YG01//The "Outstanding youth Researcher" Plan of Rice Research Institute of Guangdong Academy of Agricultural Sciences/ ; R2023YJ-QC001//The Introduction of Young Key Talents of Guangdong Academy of Agricultural Sciences/ ; 2024B03J320//Guangzhou Science and Technology Plan Project/ ; },
abstract = {Crop breeding has entered the pangenomics era, unlocking a far more comprehensive view of genetic diversity than a single reference genome can capture. In rice (Oryza sativa), a staple crop critical to global food security, the construction of pangenome resources has uncovered extensive structural variations (SVs), presence/absence variations (PAVs) and novel genes that underpin key agronomic traits. As the rice pangenome matures from a research resource into a practical breeding tool, it promises to accelerate the development of higher-yielding, stress-resilient and disease-resistant varieties. This transition represents a pivotal advance toward sustainable agriculture and enhanced global food security, while also establishing a model for applying pangenomics to other crops. Here, we review how rice pangenome research, encompassing both cultivated and wild species, has advanced trait discovery from yield improvement and disease resistance to stress tolerance and enabled new molecular breeding strategies. Despite these advances, several challenges remain before pangenomic data can be routinely integrated into breeding pipelines. The complexity of graph-based data structures, difficulties in detecting multiallelic variants from population-wide resequencing data and the lack of breeder-friendly genotyping tools are significant barriers. Additionally, while artificial intelligence (AI) and machine learning (ML) approaches show great promise for interpreting complex pangenomic data and accelerating trait discovery by genomic selection, their practical adoption is hindered by the absence of breeder-oriented interfaces, integration challenges with multi-omics data and high computational demands. Overcoming these issues will require interdisciplinary collaboration, robust infrastructure and innovations focused on practical breeding needs across diverse crop species.},
}

@article {pmid41704310,
year = {2026},
author = {Romero-Rivera, M and Fernández-de-Bobadilla, MD and Beltrán, M and Del Campo, R and Avendaño-Ortiz, J and Herencias, C},
title = {Genome assembly and functional predation analysis of novel Bdellovibrio isolates from human gut microbiota.},
journal = {Frontiers in microbiology},
volume = {17},
number = {},
pages = {1752098},
pmid = {41704310},
issn = {1664-302X},
abstract = {INTRODUCTION: Predatory bacteria of the Bdellovibrio and like organisms (BALOs) have long been postulated as living antimicrobials, yet their occurrence and ecological roles within human-associated microbiota have remained uncertain due to the absence of culturable human-derived isolates. Here, we report the first successful isolation and comprehensive characterization of viable Bdellovibrio bacteriovorus from human fecal samples.

METHODS: Targeted enrichment was applied to five pooled fecal samples to facilitate predator recovery. We performed whole-genome sequencing on the isolates and conducted comparative genomics across 162 publicly available Bdellovibrio genomes. Additionally, pangenome analysis of 22 high-quality genomes and phenotypic assays against clinical pathogens were conducted to assess genomic diversity, prey specificity, and biosafety profiles.

RESULTS: Despite extremely low natural abundance, targeted enrichment recovered predators in two of five pooled samples, which produced characteristic lytic plaques. Sequencing revealed >99% average nucleotide identity to reference strain HD100 with only 26 core single-nucleotide polymorphisms across both isolates, indicating minimal divergence between human-associated and environmental lineages. Comparative genomics showed that only 10.4% of public genomes fulfill criteria for B. bacteriovorus sensu stricto. Pangenome analysis revealed a stable, highly conserved core (~2,500-2,650 genes) and an expanding accessory genome. Phenotypically, the human-derived isolates displayed narrower prey ranges concentrated on Pseudomonas spp., including multidrug-resistant clinical strains, and no acquired virulence factors were detected.

DISCUSSION: Collectively, these findings suggest predation in the human gut and that viable Bdellovibrio could be natural, genomically conserved members of the intestinal ecosystem. This work advances a testable keystone-predator framework for human microbiome ecology and opens an ecologically informed therapeutic pathway in which human-associated Bdellovibrio may help control multidrug-resistant pathogens while supporting microbiota homeostasis.},
}

@article {pmid41588056,
year = {2026},
author = {Al-Hasan, BA and Janabi, AHD and Helmer, C},
title = {Complete genome sequence and functional characterization of Bacillus amyloliquefaciens NJF-55: a sheep-derived probiotic candidate.},
journal = {Scientific reports},
volume = {16},
number = {1},
pages = {6408},
pmid = {41588056},
issn = {2045-2322},
abstract = {UNLABELLED: Bacillus amyloliquefaciens strain NJF-55, which was isolated from the distal colon of a healthy ram, was investigated as a probiotic candidate. We produced a high-quality assembly comprising a single circular chromosome (3,854,703 bp; 46.1% GC) and a small plasmid (6033 bp), and reconciled multi pipeline annotations to derive a consensus feature set. Functional profiling mapped 2334 genes to 2027 KEGG orthologs (1835 unique), indicating complete central metabolism, broad transport capacity, and stress-adaptation pathways; 94 CAZymes supported glycan turnover and cell-envelope remodeling. Secondary-metabolite mining revealed hallmark Bacillus BGCs—surfactin, fengycin, bacillaene, and macrolactin—and flagged putative novel compounds (a PKS-like region with ~ 7% similarity to the butirosin A/B reference); Five bacteriocin/RiPP regions were identified (class IV lanthipeptide, amylocyclicin, ComX2 pheromone, UviB-like and colicin-like). Genome-safety screening detected no classical virulence determinants or acquired clinically relevant AMR genes; four intact prophages lacked toxin/AMR cargo, and the plasmid encoded no risk loci. Comparative genomics with four reference bacilli yielded a 5,398-cluster pangenome; NJF-55 retained 325 probiotic-associated clusters (largely core) and showed 30 copy-number expansions, notably in the NRPS/PKS and DNA replication/repair families, consistent with a “core-driven, dosage-tuned” architecture. These features suggest that NJF-55 may represent a safe and robust candidate for ruminant gut applications, while underscoring the need for targeted metabolomics and controlled in vivo validation.

SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1038/s41598-026-35600-8.},
}

@article {pmid41702706,
year = {2026},
author = {Xie, D and Ye, P and Ma, Y and Zhao, Z},
title = {Pangenome analysis reveals families of ubiquitin-ligase adaptors as key genomic divergence drivers that lead to hybrid incompatibility.},
journal = {Genome research},
volume = {},
number = {},
pages = {},
doi = {10.1101/gr.280885.125},
pmid = {41702706},
issn = {1549-5469},
abstract = {Understanding how genomic divergence drives biodiversity remains a central question in evolutionary biology. The nematodes Caenorhabditis briggsae and its sister species Caenorhabditis nigoni provide an ideal model system to address this question, as they exhibit extensive genomic divergence with limited gene flow from C. briggsae to C. nigoni Despite previous comparative genomic studies, a comprehensive analysis of both conspecific and interspecific variations, and their potential impact on hybrid incompatibility, remains lacking. Here, we present a pangenome study of populations from both species, revealing that C. nigoni consistently possesses larger genomes and higher gene counts than C. briggsae This difference primarily results from markedly larger interspecific unaligned regions in C. nigoni, which overlap significantly with C. nigoni intraspecific unaligned segments that are also substantially larger than those in C. briggsae Moreover, the increased gene number in C. nigoni is largely owing to the expansion of species-specific dispensable gene families. Notably, both the inter- and intraspecific unaligned regions and the expanded dispensable genes in C. nigoni show a significant enrichment in rapidly evolving genes encoding Cullin-E3 ubiquitin-ligase adaptors, particularly F-box proteins, which are speculated to mediate immune and stress responses in nematodes. A detailed examination of a recently evolved F-box gene family (fbxn family), which includes a speciation gene Cni-neib-1, demonstrates extensive polymorphism among populations, which may contribute to hybrid incompatibility. Collectively, our findings underscore the significance of fast-evolving ubiquitination and protein degradation pathways in driving genomic divergence, and suggest a potential link between incompatible immunity and speciation.},
}

@article {pmid41702340,
year = {2026},
author = {Asha, IJ and Gupta, SD and Munim, MA and Akter, NN and Tamanna, S and Rahman, A and Imran, A and Das, SC and Hossain, MM and Islam, MM and Barman, DN},
title = {Emerging zoonotic risks: whole-genome sequencing reveals antimicrobial resistance and genomic diversity in Providencia stuartii isolated from broiler chickens in Noakhali, Bangladesh.},
journal = {Poultry science},
volume = {105},
number = {5},
pages = {106602},
doi = {10.1016/j.psj.2026.106602},
pmid = {41702340},
issn = {1525-3171},
abstract = {Providencia stuartii is emerging as an Extensively Drug-Resistant (XDR) pathogen commonly found in animals, insects, and in burned and immunocompromised conditions. The misuse of antibiotics in poultry feed causes the emergence of XDR bacteria in the poultry industry. The knowledge of zoonotic transmissibility of poultry-derived P. stuartii remains elusive in Noakhali, Bangladesh. Poultry fecal and rectal swab samples were collected from selected farms in Noakhali, Bangladesh. Bacterial isolation and identification were performed using MacConkey agar, biochemical tests, and 16S rRNA Sanger sequencing. Antimicrobial susceptibility was assessed by the Kirby-Bauer disk diffusion method, and isolates with high multiple antibiotic resistance (MAR) indices were selected for whole-genome sequencing (WGS). Quality control, genome assembly, annotation, gene identification, pan-genome analysis, pathogenicity profiling, and comparative proteome analyses were subsequently conducted. Antibiogram analysis showed that ps_nstu_001 and ps_nstu_002 were resistant to 17 and 13 tested antibiotics, respectively. Furthermore, whole-genome sequencing revealed that both strains harbored resistance determinants to aminoglycosides, tetracyclines, sulfonamides, cephalosporins, β-lactams, and carbapenems. Additionally, mobile genetic elements (MGEs) and plasmids were identified, which represent the horizontal gene transfer capability. Moreover, pangenome analysis revealed ongoing gene acquisition and substantial genomic diversity among the isolates. The isolate ps_nstu_001 was identified as a putative human pathogen and clustered closely with a clinical strain isolated in the United States. In contrast, ps_nstu_002 was predicted to be a non-human pathogen; however, it exhibited a clear evolutionary relationship with a clinical isolate obtained from a diarrheal patient in Bangladesh, suggesting potential pathogenic relevance. Global pathogenic potential of the studied strains and key proteomic similarities between pathogenic and non-pathogenic strains revealed by pathogenicity profiling and proteome comparison. To conclude, these XDR isolates indicate the potential for zoonotic transmission and the spread of resistant genes to other animals, posing a significant public health risk.},
}

@article {pmid41696028,
year = {2026},
author = {Tian, W and Petrová, E and Sakai, S and Nweze, JE and Daebeler, A and Angel, R},
title = {Cultivation and genomic characterization of novel methanogens from arid desert biocrust.},
journal = {ISME communications},
volume = {6},
number = {1},
pages = {ycag013},
pmid = {41696028},
issn = {2730-6151},
abstract = {Methanogens are strictly anaerobic archaea capable of energy conservation by methane production, yet their presence in oxic and arid environments challenges existing paradigms. In this study, we enriched and genomically characterized seven methanogenic cultures from desert biocrusts, affiliated with the genera Methanobacterium, Methanosarcina, and Methanocella. Six of these new enrichment cultures represent new species. Nonetheless, phylogenomic analyses revealed close genetic relationships with organisms from anoxic environments, indicating the absence of an evolutionary distinction. Comparative genomics exposed diverse though non-unique repertories of antioxidant (e.g. catalase, superoxide dismutase and desulfoferrodoxin), and desiccation-resistance genes (including genes for maintaining osmotic pressure and repair of cell wall and membrane), with Methanobacterium spp possessing the lowest gene abundance and diversity for oxygen and desiccation tolerance. Nevertheless, the occurrence of a Class I methanogen such as Methanobacterium in arid soils challenges the notion that members of this class are less oxygen tolerant than Class II. Pangenome analysis further uncovered unique genes enriched in membrane-associated functions and potentially non-functional stress-related genes. Via a global metagenomic survey we find that methanogens are underdetected in dryland soils, likely due to sequencing depth limitations. Our findings highlight previously overlooked methanogen diversity and ecological plasticity in oxic and desiccated habitats, and emphasize the need for further studies to elucidate their survival strategies.},
}

@article {pmid41694508,
year = {2026},
author = {Scaglione, G and Mastroianni, N and Rizzo, A and Palomba, E and Carcione, D and Brigante, G and Principe, L and Colaneri, M and Gori, A and Borgonovo, F},
title = {Integrating artificial intelligence with genome sequencing against antimicrobial resistance: a narrative review.},
journal = {Frontiers in public health},
volume = {14},
number = {},
pages = {1757161},
pmid = {41694508},
issn = {2296-2565},
mesh = {Humans ; *Artificial Intelligence ; *Whole Genome Sequencing/methods ; Machine Learning ; *Drug Resistance, Bacterial/genetics ; Anti-Bacterial Agents/pharmacology ; },
abstract = {Antimicrobial resistance (AMR) represents an escalating global health threat, demanding diagnostic strategies capable of rapid, accurate, and comprehensive pathogen characterization. Genomic sequencing has transformed our ability to elucidate resistance mechanisms and track their evolution, yet its routine clinical adoption remains limited by cost, workflow constraints, and extended turnaround times. This narrative review examines how artificial intelligence (AI) and machine learning (ML) can enhance and operationalize sequencing-based diagnostics across the clinical microbiology continuum. We summarize current AI applications in whole-genome sequencing for AMR prediction, pan-genome feature extraction, and multicenter model generalizability, including emerging approaches such as federated learning. We then explore AI-driven metagenomic analytics for pathogen detection, resistome profiling, outbreak investigation, and prognostic modeling. Complementary non-genomic technologies, Raman spectroscopy and MALDI-TOF MS, are also evaluated for their potential to deliver rapid resistance profiling when integrated with ML. Finally, we discuss practical barriers, including cost, dataset standardization, interpretability, and regulatory challenges, while outlining future directions toward scalable, explainable, and equitable AI-guided diagnostics. Integrating AI with genomic and rapid phenotypic tools offers a pathway to real-time surveillance, optimized antimicrobial stewardship, and strengthened preparedness against emerging infectious threats.},
}

Humans
*Artificial Intelligence
*Whole Genome Sequencing/methods
Machine Learning
*Drug Resistance, Bacterial/genetics
Anti-Bacterial Agents/pharmacology

@article {pmid41691473,
year = {2026},
author = {Zhou, Z and Cai, D and Zhao, C and Zhang, S and Li, J and Zhang, Z and Kong, S and Yang, X and Zhou, X and Bordbar, F and Chen, F and Xu, Y and Zhang, Z and Gu, L and Li, Z and Zhang, X and Luo, W and Shu, J and Cai, B and Nie, Q},
title = {Pan-3D Genome Analysis Reveals the Roles of Structural Variation in Chicken Chromatin Architectures, Domestication and Production Traits.},
journal = {Advanced science (Weinheim, Baden-Wurttemberg, Germany)},
volume = {},
number = {},
pages = {e20068},
doi = {10.1002/advs.202520068},
pmid = {41691473},
issn = {2198-3844},
support = {2023ZD04064//Biological Breeding-National Science and Technology Major Project/ ; 2021YFD1300100//National Key R&D Program of China/ ; U24A20440//National Natural Scientific Foundation of China/ ; 32302728//National Natural Scientific Foundation of China/ ; CARS-41//China Agriculture Research System of MOF and MARA/ ; 2023B1212060057//Science and Technology Program of Guangdong Province/ ; 2024-XPY-00-003//Project of the Seed Industry Revitalization of Department of Agriculture/ ; },
abstract = {As the first sequenced non-mammalian amniote, the chicken (Gallus gallus) has served as a major source of cost-effective and protein-enriched foods since domestication. However, how structural variations (SVs) affect 3D genome reorganization to influence domestication and production traits remains unclear in chickens. Here, fifteen de novo chromosome-level genome assemblies are newly generated, along with high-throughput chromosome conformation capture (Hi-C), ATAC and RNA sequencing data. By integrating 13 published assemblies, the first pan-3D genome resource is constructed, spanning genes, SVs, and chromatin architectures, to investigate the dynamic characteristics of the 3D genome at different levels and the roles of SVs in the conservation and reorganization of chromatin architectures. Furthermore, candidate SVs and their linked genes are identified for domestication and production traits based on 1,735 resequencing accessions. Notably, the 240-bp and 81-bp SVs in the TSHR and DIO2 genes are considered the key targets in artificial selection for seasonal reproduction, and a 266-bp deletion upstream of the KLF3 gene affects carcass performance by rewriting the chromatin loop interaction network. Finally, SVs significantly improve the predictive accuracy in genomic selection models. Collectively, this study presents a comprehensive pan-3D resource to advance functional genomic research and breeding practice for the community.},
}

@article {pmid41690242,
year = {2026},
author = {C, S and S, MM},
title = {Molecular identification and pathogenicity confirmation of multi-azole resistant Malassezia species isolated from dandruff infected individuals prevailing in Mysuru, India.},
journal = {Diagnostic microbiology and infectious disease},
volume = {115},
number = {1},
pages = {117299},
doi = {10.1016/j.diagmicrobio.2026.117299},
pmid = {41690242},
issn = {1879-0070},
abstract = {Worldwide distribution of dandruff associated scalp infections is caused by lipophilic Malassezia spp. This rationale lead the study to investigate the prevalence and etiologic species in a cross-sectional study involving 300 subjects who visited dermatology hospitals to seek treatment in K.R. Hospital, JSS Hospital and CSI Holdsworth Memorial Mission Hospital, Mysuru region, Karnataka, India. With the consent of participants, dandruff flakes samples were collected. The presence of Malassezia spp. were assessed by morphological and biochemical characterization, where six major yeast groups M. furfur (36%), M. globosa (21%), M. restricta (18%), M. sympodialis (12%), M. japonica (8%) and M. obtusa (5%) causing dandruff were found to be present in 79.6% of collected test samples. High resistant patterns to antimycotic data of minimal inhibitory concentration (MIC90) to Fluconazole, Ketoconazole and Miconazole indicated the emergence of multi azole resistant Malassezia spp. The isolates being pathogenic was hemolysis positive. The dandruff specific isolates M. furfur, M. restricta and M. globosa exhibited typical phospholipase activity indicating the pan-genome attributes for inducing severe itching along with scalp infections in infected individuals. It was evident from SEM data that Malassezia spp. had characteristics of yeast like structure with collarets appearing during blastospore formation. Further with M13RAPD-PCR, ITS-PCR, epidemiological specificity and genotypic relatedness of isolates to Malassezia spp. was confirmed and 18S rDNA sequences were submitted to NCBI database with the accession numbers PP189840 to PP189845. The data acquired during study can be of prime diagnostic method for timely management and accurate analysis of dandruff caused by Malassezia spp. at global settings.},
}

@article {pmid41688492,
year = {2026},
author = {Staack, M and Haufschild, T and Hammer, J and Kallscheuer, N and Kumar, G and Jogler, C},
title = {A novel strain isolated from methane seeps in the Kattegat belongs to the planctomycetal species Novipirellula methanifontis sp. nov.},
journal = {Scientific reports},
volume = {},
number = {},
pages = {},
doi = {10.1038/s41598-025-33410-y},
pmid = {41688492},
issn = {2045-2322},
}

@article {pmid41688004,
year = {2026},
author = {Siddiqa, A and Sultan, NM and Irfan, M and Ullah, A and Alshaharni, MO and Fayad, E and Alharthy, OM and Alhelaify, SS and Hadadi, F and Alhomodi, AF and Alshaya, DS and Camps, I and de Carvalho, PVSD and Rozental, R and Islam, A and Hassan, SS},
title = {Comparative genomics and e-pharmacophore search to identify novel therapeutic targets in the druggable genome of MDR Providencia stuartii.},
journal = {Infection, genetics and evolution : journal of molecular epidemiology and evolutionary genetics in infectious diseases},
volume = {},
number = {},
pages = {105900},
doi = {10.1016/j.meegid.2026.105900},
pmid = {41688004},
issn = {1567-7257},
abstract = {OBJECTIVES/BACKGROUND: Providencia species of the Enterobacteriaceae family is a frequent cause of hospitalised infections, primarily urinary tract infections. It has a major influence on patient morbidity, mortality, and therapy. They can cause pneumonia, meningitis, endocarditis, wound and bloodstream infections, thereby requiring serious attention for novel therapeutics identification at the preliminary stages of disease.

METHODS: The AST (antimicrobial susceptibility test) of P. stuartii strains (n = 91) was followed by whole-genome sequencing using Oxford Nanopore MinION technology, comparative genomics (n = 19), resistome, and pharmacogenomics analyses. Pharmacokinetics and physicochemical characterisation of putative druggable targets and novel inhibitors were also evaluated.

RESULTS: The reported genome is ~4.43 Mb long, and the resistome has 30 different AMR genes. The pangenome revealed that it is open ('b' = 0.2314), and the core genome (n = 2611) revealed three potential targets that were screened against a peptidomimetic (n = 30,695) and a synthetic Isosteviol library (n = 37) for ensuing docking analyses. The top hit for each target was rendered to an MD (molecular dynamics) simulation. The stability of the apo- and complexes showed good indicators; RMSD (root mean square deviation) (proteins <5 Å, ligands <2 Å). However, an initial fluctuation followed by stability for RMSF (root mean square fluctuation) (< 15 Å), Rg (radius of gyration), and ∆E (binding free energy) was observed for the remaining 100 ns. The ∆E surged negatively, whereas the proportion of ∆G (Gibbs free energy), electrostatic, and Van der Waals contributions was similar.

CONCLUSION: All three complexes, F1510072_ATP (multidrug export ATP-binding permease), ZC440183_PchR (regulatory protein), and F7240201_MT (murein transglycosylase), represent potential therapeutic targets. Such studies could robustly identify targets in the druggable genome of P. stuartii and other microbial pathogens.},
}

@article {pmid41687981,
year = {2026},
author = {Chen, X and Wang, Y and Han, F and Xu, M and Shen, T},
title = {Tissue-specific transcriptomics and evolutionary dynamics of terpene synthase genes in Picea purpurea.},
journal = {Gene},
volume = {},
number = {},
pages = {150046},
doi = {10.1016/j.gene.2026.150046},
pmid = {41687981},
issn = {1879-0038},
abstract = {This study presents a comprehensive transcriptomic atlas of Picea purpurea, an endemic Qinghai-Tibet Plateau conifer, integrating full-length and short-read transcriptome datasets. We identified 39,156 non-redundant transcripts across four tissues (roots, stems, needles, cones), with 61.52% showing broad expression and 6.15% exhibiting tissue specificity. Tissue-specific transcripts were markedly enriched in secondary metabolism, particularly terpenoid biosynthesis. Phylogenomic analysis of 1642 terpene synthase (TPS) genes from 25 gymnosperms (covering 75% of extant orders) yielded an updated classification of three gymnosperm-specific subfamilies: TPS-d1 (monoterpene synthases), TPS-d2 (sesquiterpene synthases), and TPS-d3 (diterpene synthases). Pan-genome comparisons across six Picea species identified 74 TPS orthogroups, including 6 core conserved families and 38 lineage-specific expansions. These findings elucidate the molecular basis of terpenoid diversification in this ecologically pivotal genus.},
}

@article {pmid41686637,
year = {2026},
author = {Gorzynski, J and Harling-Lee, JD and Figueroa, W and Alves, J and Yebra, G and Freeman, T and Penadés, JR and Fitzgerald, JR},
title = {Bacterial defense systems and host ecology drive the evolution of intra-species lineages.},
journal = {Cell reports},
volume = {45},
number = {2},
pages = {116957},
doi = {10.1016/j.celrep.2026.116957},
pmid = {41686637},
issn = {2211-1247},
abstract = {Horizontal gene transfer (HGT) is a major driver of diversity in bacterial populations. However, our understanding of its impact on the evolution of intra-species lineages is limited. The multi-host bacterial pathogen Staphylococcus aureus is differentiated into genetic lineages known as clonal complexes (CC) with variable host and disease tropisms. Here, we demonstrate that CCs exhibit extensive variation in pangenome size, structure, and gene flow, influenced by both genetic and ecological barriers to HGT. Examination of pangenome openness for each CC revealed remarkable variation that correlated strongly with host-species promiscuity. Notably, CCs were defined by horizontally acquired defense systems, and genetic subpopulations have diverged by changes to their type I restriction-modification (R-M) system repertoire, suggesting a role in lineage emergence. Overall, our data indicate a key role of HGT of defense systems in promoting the differentiation of S. aureus into lineages, with host ecology as a major driver of accessory genome variation.},
}

@article {pmid41684645,
year = {2026},
author = {Yang, M and Zhou, C and Kong, X and Kuang, R and Liu, C and Wu, X and Xu, Z and He, H and Wei, Y},
title = {The pangenome enhances the understanding of the genetic diversity of papaya.},
journal = {Horticulture research},
volume = {13},
number = {2},
pages = {uhaf282},
pmid = {41684645},
issn = {2662-6810},
abstract = {Papaya (Carica papaya L.) is a nutritionally and medicinally important tropical fruit crop, yet its genetic improvement has been limited by insufficient genomic resources. In this study, we constructed chromosome-level genomes for three key varieties (Zhufeng, T3, and T5) and integrated them with three existing assemblies to build a comprehensive pangenome, including graph-based, linear, and syntelog-based representations. The syntelog-based pangenome revealed 24 453 syntelog groups (SGs). Leveraging resequencing data from 222 accessions aligned to the graph-based pangenome, we identified 26 173 structural variations (SVs), including a functionally relevant 94-bp deletion in the RETARDED ROOT GROWTH (RRG) gene in the T3 genome. This deletion affects the expression of the RRG, resulting in a reduction in its expression level in T3. Further phenotypic analysis showed that RRG can influence papaya root length by promoting the proliferation of root meristem cells and inhibiting cell elongation. Additionally, the linear pangenome uncovered 5273 translocations and 1440 inversions, significantly expanding the known SV repertoire in papaya. This study provides a critical genomic resource for deciphering domestication-related traits and accelerating marker-assisted breeding, ultimately advancing the genetic improvement of papaya.},
}

@article {pmid41684101,
year = {2026},
author = {Yu, F and Tao, Y and Liu, L and Xie, P and Mace, E and Jordan, D and Xie, Q},
title = {Sorghum2035: A decadal vision for sorghum functional genomics and molecular breeding.},
journal = {Molecular plant},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.molp.2026.02.003},
pmid = {41684101},
issn = {1752-9867},
abstract = {Sorghum (Sorghum bicolor L. Moench), the fifth most important cereal crop worldwide, serves as a staple food in arid and semi-arid regions, and a critical resource for livestock forage, bioenergy production, and industrial applications. Given its small genome size and high tolerance to abiotic stresses, such as drought, salt-alkali, and heat, it has become an ideal crop model for abiotic stress research. This review synthesizes recent advances in sorghum genomics, including the development of gapless reference genomes, pan-genome analyses revealing extensive structural variation, and population resequencing studies that have uncovered domestication signatures and stress adaptation loci. Moreover, we summarize progress in sorghum genetic resource collection, selection strategies, and breeding improvement. Genetic functional studies have identified key genes regulating yield-related traits, quality attributes, and tolerance to abiotic/biotic stresses. In molecular breeding, notable achievements include the establishment of efficient transformation systems, CRISPR/Cas9-mediated gene editing enhanced by morphogenic regulators, and mutagenized populations for gene function validation. Notably, challenges persist, such as the functional characterization of complex quantitative traits, integration of multi-omics datasets, and genotype-dependent transformation efficiency. Future research directions emphasize the utilization of wild germplasm, in-depth structural variation analysis, population-level transcriptomics, exploration of microbiome-plant interactions, and AI-driven intelligent breeding approaches. These strategies aim to engineer climate-resilient sorghum varieties to ensure global food security and promote sustainable bioenergy production.},
}

@article {pmid41677312,
year = {2026},
author = {Lee, J and Moon, JS and Song, H and Cho, S},
title = {Distinct ESBL dissemination mechanism associated with the hybrid transposon Tn1721/Tn21 in blaCTX-M-15-carrying Salmonella Enteritidis from poultry in South Korea.},
journal = {Microbiology spectrum},
volume = {},
number = {},
pages = {e0375525},
doi = {10.1128/spectrum.03755-25},
pmid = {41677312},
issn = {2165-0497},
abstract = {UNLABELLED: Extended-spectrum beta-lactamase (ESBL)-producing Salmonella enterica serovar Enteritidis (S. Enteritidis) is emerging as a significant threat to food safety via its limitation of therapeutic options and potential transmission through poultry products. However, the structural and genetic characteristics of mobile genetic elements (MGEs) associated with horizontal transfer of the ESBL gene in S. Enteritidis isolates from poultry remain insufficiently characterized. The present study aimed to identify and characterize the ESBL gene and its associated MGEs and to assess their distribution. Whole-genome sequencing was applied to ESBL-producing and non-ESBL-producing isolates in combination with pan-genome analysis, conjugation assays, and comparative genomics using publicly available genomes. Among 17 isolates, 9 were ESBL-producing and all carried blaCTX-M-15. We observed co-transfer of blaCTX-M-15, tetA, and the IncF plasmid at relatively high frequencies (2.0-5.3 × 10[-2]) in ESBL-producing isolates. Moreover, we identified a hybrid transposon (Tn1721/Tn21) inserted into IncF plasmids that comprised elements of Tn21 (merRTPCADE, tniA, and urf2) and Tn1721 (tetA, tetR, a DMT-family efflux gene, and a partial tnpA), with ISEcp1 and blaCTX-M-15 adjacent to the hybrid transposon. Tn1721/Tn21 was prevalent among blaCTX-M-15-carrying S. Enteritidis isolates from South Korea (19/20) but absent in those from other countries (n = 9), suggesting geographical variation. This study identified a unique hybrid Tn1721/Tn21 transposon as the dominant MGE in blaCTX-M-15-carrying S. Enteritidis from South Korean poultry, highlighting its potential role in the regional dissemination of antimicrobial resistance. Continued surveillance and targeted intervention in poultry production are warranted to mitigate the spread of ESBL-producing S. Enteritidis.

IMPORTANCE: Extended-spectrum beta-lactamase (ESBL)-producing Salmonella enterica serovar Enteritidis from poultry represents a growing public health threat due to limited treatment options and the potential for transmission through the food chain. Despite this concern, the mobile genetic elements underlying ESBL gene dissemination remain insufficiently characterized in South Korean poultry-associated S. Enteritidis isolates. In this study, we identified a hybrid transposon, Tn1721/Tn21, embedded within IncF plasmids and linked to blaCTX-M-15 in S. Enteritidis isolates. This association between Tn1721/Tn21 and blaCTX-M-15 suggests a region-specific mechanism of resistance dissemination that may reflect antimicrobial selective pressure within poultry production systems. These findings highlight the importance of integrated One Health surveillance to mitigate the emergence and spread of antimicrobial resistance across animal and human populations.},
}

@article {pmid41676497,
year = {2026},
author = {Lindstedt, K and Wheelock, A and Samutela, M and Kabir, W and Chasaya, M and Namuziya, N and Marsden, EJ and Kapasa, M and Mumba, C and Mulenga, B and Nkole, L and Pieciak, R and Mudenda, V and Chikoti, C and Ngoma, B and Chimoga, C and Chirwa, S and Pemba, L and Nzara, D and Lungu, J and Forman, L and Simulundu, E and MacLeod, W and Moyo, C and Somwe, SW and Holt, KE and Sundsfjord, A and Gill, CJ},
title = {Genomic analysis of Klebsiella pneumoniae causing community-acquired respiratory deaths among Zambian infants and children using targeted RNA-probe hybridization-capture metagenomics.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.64898/2026.02.02.703236},
pmid = {41676497},
issn = {2692-8205},
abstract = {UNLABELLED: Klebsiella pneumoniae (Kp) is a leading cause of neonatal and infant deaths in sub-Saharan Africa and frequently associated with antimicrobial resistance. Previously, we identified Kp as a major cause of fatal community-associated lower respiratory infections among infants and children under five years in Lusaka, Zambia, using postmortem tissue sampling and pathogen specific multiplex qPCR. In this follow-up study, we employed a novel culture-independent RNA-probe hybridization-capture metagenomic sequencing approach, targeting Kp pan-genome core and accessory genes, to perform in-depth genomic analysis of Kp from eleven post-mortem lung biopsy samples from seven of these children. Analysis detected Kp in all cases except one, which identified Klebsiella quasipneumoniae subspecies similipneumoniae . Core-genome multi-locus sequence typing (cgMLST) revealed six clonal groups (CG607, CG1123, CG10072, CG280, CG3648, and CG10344) belonging to five sublineages (SL607, SL17, SL280, SL37, and SL10072), with perfect concordance between paired samples from the same case. Two infants sampled the same month harbored SL607 lineages sharing 621 out of 629 cgMLST alleles, suggesting clonal spread. Kp capsule (K) loci were detected in all but one case and included potential vaccine targets KL25, KL23, and KL122. Antimicrobial resistance genes were widespread among samples, particularly encoding resistance toward aminoglycosides, β-lactams, sulphonamides, tetracyclines, and trimethoprim. Extended spectrum β-lactamases were identified in four cases, three of which were bla CTX-M-15 . The acquired Kp sideophore yersiniabactin (lineage ybt14) was identified in both cases associated with SL607, and the acquired siderophore aerobactin (lineage iuc5) was identified in one of these, suggesting possible convergence of antimicrobial resistance and hypervirulence. The detection of Kp with extensive antimicrobial resistance causing fatal community acquired pneumonia signals a deeply concerning epidemiologic shift from a largely nosocomial pathogen. This calls for urgent epidemiological investigations to better understand the burden, transmission dynamics, antimicrobial resistances, and potential vaccine targets for Kp in other community settings across sub-Saharan Africa.

AUTHOR SUMMARY: Klebsiella pneumoniae is a major cause of infections and death among newborns and young children, particularly in low-income countries, where it is frequently resistant to antibiotics. While well-known as a hospital-associated pathogen, we previously showed K. pneumoniae is also a leading cause of fatal community lung infections among infants and children in Lusaka, Zambia. In this follow-on analysis, we performed deeper genetic analysis of K. pneumoniae detected from the cluster of community pneumonia deaths using lung tissue samples from seven of these children. Since traditional bacterial cultures were unavailable, we instead used a novel approach that enriched and sequenced specific regions of the K. pneumoniae genome directly from the biopsy samples without culturing bacterial isolates. We identified five different K. pneumoniae genetic subtypes, known as sublineages. Two sublineages, which came from children sampled the same month, were highly similar, suggesting clonal spread. Multiple acquired antimicrobial resistance genes were detected across all sublineages. Acquired virulence factors, which may cause more aggressive infections, were also detected in two cases. We also identified capsule types previously suggested as potential vaccine targets. This study underscores the urgent need to better understand and address the emerging burden of antibiotic-resistant K. pneumoniae pneumonia and other invasive infections among infants and children in community settings in sub-Saharan Africa.},
}

@article {pmid41674597,
year = {2026},
author = {Behera, S and Rossi, M and Wang, Y and Izydorczyk, MB and Tran, D and Dalgard, CL and Kalef-Ezra, E and Kottapalli, K and Mehta, H and Parnaby, G and Risse-Adams, OS and Scholz, SW and Shen, H and Nelson, TM and Visvanath, A and Zheng, X and Doddapaneni, H and Garcia, T and Mason, CE and Proukakis, C and Han, J and Mehio, R and Catreux, S and Sedlazeck, FJ},
title = {Scalable and comprehensive mosaic variant calling using DRAGEN.},
journal = {medRxiv : the preprint server for health sciences},
volume = {},
number = {},
pages = {},
doi = {10.64898/2026.02.03.26345450},
pmid = {41674597},
abstract = {Detecting low variant allele fraction (VAF) mosaic variants without matching controls remains a major challenge in genomics, limited by technical noise, lack of benchmarks, and computational scalability. We present the DRAGEN mosaic caller, a hardware-accelerated approach identifying variants down to ∼1-2% VAF with low false-positive rates and hour-scale runtimes for mosaic SNV/indel detection from bulk sequencing. To support evaluation, we introduce a genome-wide low-VAF benchmark for variants between 1-10% VAF. Application to blood, sperm, and brain tissues revealed patterns, including mosaic hotspots and mutational signatures. The first analysis of HG002 blood showed that many "mosaic" variants defined from HG002 cell lines are likely culture-derived and not in vivo mutations. Importantly, DRAGEN also enables personalized assembly pangenome references to improve alignment and mosaic variant detection in complex regions. Together, this development makes routine low-VAF discovery feasible, opening new opportunities to study mosaic mutations in healthy and disease individuals.},
}

@article {pmid41674564,
year = {2025},
author = {Gu, L and Peng, C and Chen, A and Chen, K and Zheng, X and Yu, D and Wang, Z and Fang, L and Liu, GE and Zhao, P},
title = {Haplotype-resolved genome and pan-genome graphs reveal the impacts of structural variation on functional genome and feather colors in chickens.},
journal = {iMetaOmics},
volume = {2},
number = {3},
pages = {e70027},
pmid = {41674564},
issn = {2996-9514},
abstract = {Structural variation (SV) refers to a wide range of genetic variations that significantly affect genome biology and complex phenotypes. However, the population-level SV landscape and its functional impacts on chickens are largely unknown. Here, we generated haplotype-resolved genome assemblies for the Chinese Wenchang chicken and then integrated them with another 29 assemblies and 354 genome resequencing data to construct a pan-genome graph for SV genotyping. We detected 185,205 high-confidence SVs and found that one-third of them were derived from homology-based and transposable element (TE) insertion-based mutational mechanisms. By examining the ChickenGTEx resource, we discovered 1728 SVs associated with molecular phenotypes (e.g., gene expression and alternative splicing), including a 2.7-kb insertion in the exon of the EEF1A2 gene related to egg-laying rates, which showed a significant difference in frequency between broilers and layers. Additionally, we identified a lncRNA gene with a Variable Number of Tandem Repeats (VNTR)-mediated SV influencing white feathers in Wenchang chicken due to gene flow from white layers. Overall, our study provides a valuable resource for chicken genetics and genomics and sheds light on the SV landscape in chickens as well as its potential contributions to genome structure, gene regulation, and complex traits.},
}

@article {pmid41675550,
year = {2024},
author = {Wang, X and Lu, H and Zhao, Y and Zhang, Z and Li, J and Dong, Z and Hao, Y and Fang, L and Guan, X and Zhao, T and Hu, Y and Zhang, T},
title = {A super pan-genome map provides genomic insights into evolution of diploid cotton species.},
journal = {iMetaOmics},
volume = {1},
number = {1},
pages = {e15},
pmid = {41675550},
issn = {2996-9514},
abstract = {A high-quality super pan-genome was built using 22 representative diploid cottons species. Adaptive evolution among extant Gossypium species was investigated. Specific genes were enriched for different terms, revealing variations in characteristics of different cotton species. The 321 hotspot regions of structural variations (SVs), containing 90 genes associated with fiber initiation and/or elongation, were detected. A 444-bp deletion in the promoter sequence of GoNe that explained the lack of foliar nectary in G. gossypiodes (D6) and G. schwendimanii (D11) was identified.},
}

@article {pmid41673553,
year = {2026},
author = {Liu, X and Zhang, H and Zhou, X and Zuo, Y and Chen, G and Zhao, X and Yan, Y and Li, H and Zhang, M and Chen, C},
title = {Evolutionary and functional characterization of BBX genes in the barley pangenome.},
journal = {BMC plant biology},
volume = {},
number = {},
pages = {},
doi = {10.1186/s12870-026-08317-z},
pmid = {41673553},
issn = {1471-2229},
support = {KFKT202504//Open Research Projects of the State Key Laboratory of Wheat Improvement/ ; 2025XJQH16//Yibin University Research Projects/ ; H72313004//Yibin Agricultural Science and Technology Innovation Project/ ; 2025ZNSFSC1010//Sichuan Science and Technology Program/ ; 2023JJ008//Open Foundation of Key Laboratory of Wuliangye-flavor Liquor Solid-state Fermentation, China National Light Industry/ ; },
}

@article {pmid41668884,
year = {2026},
author = {Lee, SY and Choi, HJ and Lee, S and Choi, J and Kwak, JS and Kang, YJ and Hong, SC},
title = {Genome-based characterization of AHPND and non-AHPND Vibrio campbellii isolates from Republic of Korea.},
journal = {Frontiers in microbiology},
volume = {17},
number = {},
pages = {1724818},
pmid = {41668884},
issn = {1664-302X},
abstract = {With mounting evidence that Vibrio campbellii can act as a causative agent, acute hepatopancreatic necrosis disease (AHPND) represents a serious threat to global shrimp aquaculture. In this study, we present a comparative genomic analysis of 101 V. campbellii strains, including the recently isolated pathogenic and non-pathogenic strains, V. campbellii HJ-2023 and V. campbellii HJ-2023n, from the Republic of Korea. Whole-genome sequencing revealed that the pathogenic strain harbors three plasmids and carries the canonical AHPND toxin genes pirA and pirB, along with an expanded repertoire of virulence and secretion system genes. Pan-genome and insertion sequence analyses showed that pathogenic strains tend to cluster based on shared mobile genetic elements, particularly transposases located near toxin genes, underscoring the role of horizontal gene transfer in virulence acquisition. Although all strains displayed a broad distribution of antibiotic-resistance genes, pathogenicity did not consistently correlate with their presence. Similarly, carbohydrate-active enzyme (CAZyme) profiles were largely conserved, although certain enzymes, such as chitinases, may contribute accessory functions in host invasion. Notably, the AHPND-associated V. campbellii HJ-2023 strain contained multiple copies of key T6SS and T1SS genes, suggesting an increased potential for toxin delivery. These findings suggest that pathogenic potential in V. campbellii likely arises not only from the presence of toxins but also from the complex interplay of mobile elements, secretion systems, and genomic architecture. This study provides an essential genomic framework for understanding the emergence of AHPND in V. campbellii and offers insights to enhance molecular diagnostics, strengthen biosecurity, and improve disease control strategies in shrimp aquaculture.},
}

@article {pmid41668161,
year = {2026},
author = {Wang, H and Ou, X and Zhang, J and Yang, C and Zhang, Z and Kanwal, F and Zou, X and Yang, J and Wang, S},
title = {Pan-genome analysis reveals the evolutionary dynamics and functional divergence of the O-methyltransferase gene family in tomato.},
journal = {Journal of integrative plant biology},
volume = {},
number = {},
pages = {},
doi = {10.1111/jipb.70189},
pmid = {41668161},
issn = {1744-7909},
abstract = {O-Methyltransferases (OMTs) play crucial roles in plant defense, environmental adaptation, and quality formation by catalyzing the biosynthesis of diverse methylated metabolites. Although OMT (COMT and CCoAOMT) genes have been functionally characterized in various plant species, the evolutionary trajectory of the entire OMT gene family and the functional divergence of the CCoAOMT subfamily remain to be systematically elucidated. In this study, we performed pan-genome analysis of the OMT gene family in 61 tomato (Solanum spp.) accessions and conducted phylogenetic analysis across 20 plant species (from algae to angiosperms), identifying 2,882 OMT genes. Phylogenetic reconstruction revealed that all extant plant CCoAOMT genes evolved from a single ancestral lineage (Clade I) originating before the divergence of red and green algae. In tomato, 2,199 OMT genes were classified into 42 orthogroups: nine core, five soft-core, 22 dispensable, and six private orthogroups, with 52.4% classified as dispensable genes. OMT genes in the Solanum genus have predominantly undergone purifying selection. Among all COMT orthogroups, a single tandem duplicate cluster stands out as exclusively conserved. Members of this cluster have evolved a distinct catalytic role, as evidenced by the finding that SlCOMT2c exclusively catalyzes the formation of kaempferide via the 4'-O-methylation of kaempferol. Ion mobility spectrometry showed that SlAOMT, a member of the CCoAOMT-like subfamily, catalyzes the methylation of luteolin to produce two isomeric products identified as diosmetin and chrysoeriol while losing the canonical catalytic function of the CCoAOMT subfamily. In addition, we identified a potential gene regulatory network associated with methylated flavonoid biosynthesis. This study establishes an integrative framework for elucidating OMT evolution and provides analytical tools for identifying genes involved in isomeric methylated flavonoid biosynthesis, paving the way for studying adaptive evolution and specialized metabolic pathways in plants.},
}

@article {pmid41667795,
year = {2026},
author = {Zhao, X and Yu, J and Zhang, J and Sun, H and Wu, S and Zhao, J and Zhou, Y and Hammar, SA and Lin, YC and Zhang, Z and Huang, S and Dymerski, RT and Chen, F and Weng, Y and Grumet, R and Xu, Y and Fei, Z},
title = {Graph-based pangenome reveals structural variation dynamics during cucumber breeding.},
journal = {Nature genetics},
volume = {},
number = {},
pages = {},
pmid = {41667795},
issn = {1546-1718},
support = {2015-51181-24285//United States Department of Agriculture | National Institute of Food and Agriculture (NIFA)/ ; 2020-51181-32139//United States Department of Agriculture | National Institute of Food and Agriculture (NIFA)/ ; },
abstract = {Structural variants (SVs) represent an important yet underexplored component of plant genome diversity. Here we present a graph-based cucumber pangenome constructed from 39 reference-quality genomes, including 27 newly assembled and 12 previously published. The pangenome captures 171,892 high-confidence SVs, which were genotyped across 447 wild and cultivated accessions. Our analyses reveal that, during cucumber domestication, a substantial portion of mildly deleterious SNPs were retained, whereas SVs were consistently purged, highlighting their highly deleterious nature. During geographical expansion, a reduced SV burden and a younger age of SVs compared to SNPs were observed, suggesting stronger purifying selection acting on SVs. Introgressions from wild populations increased SV burden, potentially due to hitchhiking. Notably, incorporating SV burden into genomic prediction models improved prediction accuracy for several agronomically important traits. This study illuminates SV dynamics during cucumber domestication and range expansion and underscores the implications of SVs for future cucumber breeding.},
}

@article {pmid41664139,
year = {2026},
author = {Wang, X and Fu, J and Song, L and Wu, Q and Fang, Q and Zhang, Y and Deng, X and Xu, Q},
title = {Multi-omics analysis of somatic mutants reveals TCP7 allelically regulates multiple carotenogenic genes in citrus.},
journal = {Molecular horticulture},
volume = {6},
number = {1},
pages = {13},
pmid = {41664139},
issn = {2730-9401},
support = {2022YFF1003100//National Key Research and Development Program of China/ ; 31925034//National Natural Science Foundation of China/ ; 2022hsqd010//Foundation of Hubei Hongshan Laboratory/ ; 2021hszd016//Foundation of Hubei Hongshan Laboratory/ ; },
abstract = {Somatic mutations are widespread in all organisms and cause abundant phenotypic changes, constituting an important source of variation especially for clonally propagated plants. Somatic mutants can serve as a mutation-introducing method for exploring the regulatory mechanism of mutated trait formation in clonally propagated plants. Red-fleshed and orange-fleshed pomelo varieties derive from independent mutations of the wild-type white-fleshed Guanxi honey pomelo (Citrus grandis), offering an ideal system for dissecting core regulatory transcription factors behind the fruit color trait. Here, we performed a meta-analysis comprising genome, transcriptome, DNA methylome and chromatin accessibility assays of the two color mutants and their wild type, resulting in haplotype-scaled pan-genome. The chromatin openness analysis suggested that binding sites for TEOSINTE BRANCHED 1/CYCLOIDEA/PCF (TCP) transcription factors are significantly enriched in the differentially open regions, with different footprint patterns in the mutants and wild type. We identified CgTCP3, CgTCP7, and CgTCP20 as regulators of key carotenogenic genes including ZDS, BCH, and NCED2. Furthermore, CgTCP7 underwent positive selection in pomelo germplasm, with various alleles differentially affecting carotenogenic gene expression and modulating carotenoid accumulation. We therefore identified the core transcription factor genes responsible for color trait formation, providing resources for breeding varieties with diversified phenotypes.},
}

@article {pmid41663438,
year = {2026},
author = {Ibrahim, MS and Fahmy, JA and Helal, MA and Hakim, FT and Sidarous, LR and Attallah, NE and Abouelhadid, S and Elhadidy, M and Badr, E},
title = {AntiPan: a genome-informed in silico pipeline for advancing subunit vaccine discovery against Staphylococcus aureus.},
journal = {Scientific reports},
volume = {16},
number = {1},
pages = {5396},
pmid = {41663438},
issn = {2045-2322},
support = {BVNCP8-10//Bactivac Catalyst Pump-Priming Projects grant/ ; BVNCP8-10//Bactivac Catalyst Pump-Priming Projects grant/ ; BVNCP8-10//Bactivac Catalyst Pump-Priming Projects grant/ ; 48072//Science, Technology & Innovation Funding Authority (STDF) One Health Research and Innovation Grant (OHRIG)/ ; 48072//Science, Technology & Innovation Funding Authority (STDF) One Health Research and Innovation Grant (OHRIG)/ ; },
mesh = {*Staphylococcus aureus/immunology/genetics ; *Vaccines, Subunit/immunology ; Molecular Docking Simulation ; Humans ; *Staphylococcal Vaccines/immunology/genetics ; *Genome, Bacterial ; *Staphylococcal Infections/prevention & control/immunology/microbiology ; Antigens, Bacterial/immunology/genetics ; Computer Simulation ; Vaccine Development ; Bacterial Proteins/immunology/genetics ; Vaccinology ; },
abstract = {Staphylococcus aureus (S. aureus) remains a major global health threat due to its multidrug resistance and immune evasion mechanisms. Despite numerous vaccine trials, no licensed vaccine is currently available for human use. Existing reverse vaccinology pipelines often neglect key host-pathogen immune interactions or rely on limited toolsets. This study introduces AntiPan, an enhanced in silico pipeline for identifying high-potential protein antigens for subunit vaccine design. AntiPan integrates five modules: pan-genome analysis, reverse vaccinology filters, protein assessment, immunoinformatics, and Toll-like receptors binding evaluation, while accounting for genomic diversity and immune evasion mechanisms. Using the genome of S. aureus isolated in Egypt, AntiPan identified 29 protective antigen candidates (PACs) implicated in host invasion, nutrient acquisition, and immune evasion. Ten PACs were shortlisted for future experimental validation, including IsdC, EbpS, SspB, EssA, TagH, SirA, EsxA, AmiA, HlgC, and HlgB. Molecular docking demonstrated that IsdC, AmiA, and TagH bind strongly and complementarily to the TLR1/TLR2 and TLR4/MD2 complexes, making them top vaccine candidates. Molecular dynamics simulations and MHC-epitope docking results further confirmed the immunogenicity potential of the top-ranked PACs. AntiPan is a command-line tool that provides an accessible, reproducible, and scalable platform for discovering bacterial vaccine targets. It applies to multidrug-resistant pathogens and is publicly available at: https://github.com/ComputationalBiologyLab/AntiPan .},
}

*Staphylococcus aureus/immunology/genetics
*Vaccines, Subunit/immunology
Molecular Docking Simulation
Humans
*Staphylococcal Vaccines/immunology/genetics
*Genome, Bacterial
*Staphylococcal Infections/prevention & control/immunology/microbiology
Antigens, Bacterial/immunology/genetics
Computer Simulation
Vaccine Development
Bacterial Proteins/immunology/genetics
Vaccinology

@article {pmid41661420,
year = {2026},
author = {Zhang, H and Feng, G and Feng, Y},
title = {Quinoa as a naturally stress-resistant crop: current status and future promises.},
journal = {Stress biology},
volume = {6},
number = {1},
pages = {12},
pmid = {41661420},
issn = {2731-0450},
support = {2022B02010-1//Science and Technology Department of Xinjiang Uygur Autonomous Region/ ; 2022YFF1003403-4//Key Technologies Research and Development Program/ ; 2021YFA1300401//Key Technologies Research and Development Program/ ; 32441015//National Natural Science Foundation of China/ ; },
abstract = {Quinoa (Chenopodium quinoa Willd.), a semi-domesticated halophyte originating in the Andean region, has emerged as a promising crop for exploiting marginal lands, valued for its exceptional nutritional profile and remarkable resilience to high salinity and drought. This review analyzes the current status and future potential of quinoa as a model halophytic crop. We begin by examining the physiological mechanisms that enable quinoa to thrive in marginal environments, which have been the subject of extensive study. Thanks to the advancement in high-throughput sequencing technology, genomic resources - including the recent development of high-quality reference genomes and a Chenopodium pangenome - are rapidly expanding. Sequence-based genetic mapping techniques hold the promise to dissect the molecular basis of complex traits in combination with the utility of functional genomics tools such as virus-induced gene silencing (VIGS) and stable genetic transformation. Ultimately, the application of modern breeding technologies, such as phenomics, genomic selection (GS), and CRISPR/Cas, will expedite the development of locally adapted, climate-resilient quinoa cultivars worldwide.},
}

@article {pmid41660079,
year = {2026},
author = {Oungbamnet, C and Hinwan, Y and Nithimongkolchai, N and Sawaswong, V and Chitcharoen, S and Faksri, K and Sirichoat, A},
title = {Whole-genome and pangenome insights into Mycobacterium colombiense clinical isolates from human infections.},
journal = {PeerJ},
volume = {14},
number = {},
pages = {e20716},
pmid = {41660079},
issn = {2167-8359},
mesh = {Humans ; Microbial Sensitivity Tests ; *Genome, Bacterial ; Whole Genome Sequencing ; Anti-Bacterial Agents/pharmacology ; Phylogeny ; Thailand ; *Mycobacterium avium Complex/genetics/drug effects/isolation & purification ; Drug Resistance, Bacterial/genetics ; Polymorphism, Single Nucleotide ; Virulence Factors/genetics ; },
abstract = {BACKGROUND: Nontuberculous mycobacteria are opportunistic pathogens which cause infections in various tissues, with the Mycobacterium avium complex (MAC) being a major cause of pulmonary diseases. Among MAC members, Mycobacterium colombiense is a clinically significant species with recognized pathogenic potential; however, studies on its genomic structure and genetic diversity remain limited.

METHODS: This study investigated the drug susceptibility profiles and performed whole-genome sequencing of 12 clinical M. colombiense isolates from the Clinical Microbiology Laboratory at Srinagarind Hospital, Khon Kaen University, Khon Kaen, Thailand.

RESULTS: Based on minimum inhibitory concentration values, moxifloxacin resistance was most prevalent (100%), followed by linezolid (90%), clarithromycin (30%), and amikacin (30%). The presence of antibiotic resistance genes and virulence factors, including ESX secretion systems and efflux pumps, highlights the bacterium's potential for immune evasion and survival under stress. Single nucleotide polymorphism-based phylogenetic analysis revealed a close genetic relatedness between the isolates. Pangenome analysis of 16 M. colombiense genomes (12 newly sequenced and four publicly available) identified 7,771 gene clusters, comprising 4,468 core genes, 1,834 accessory genes, and 1,469 unique genes, supporting a closed pangenome structure and indicating evolutionary conservation and low genetic variability among isolates.

CONCLUSIONS: This study provides valuable insight into the genomic diversity, antimicrobial resistance profiles, and virulence potential of M. colombiense isolates. These findings enhance understanding of the pathogen and may inform clinical management, targeted diagnostic development, and therapeutic strategies.},
}

Humans
Microbial Sensitivity Tests
*Genome, Bacterial
Whole Genome Sequencing
Anti-Bacterial Agents/pharmacology
Phylogeny
Thailand
*Mycobacterium avium Complex/genetics/drug effects/isolation & purification
Drug Resistance, Bacterial/genetics
Polymorphism, Single Nucleotide
Virulence Factors/genetics

@article {pmid41654659,
year = {2026},
author = {Damgaard, F and Jespersen, MG and Møller, JK and Coia, JE and Dessau, RB and Sydenham, TV and Strube, ML and Møller-Jensen, J and Justesen, US},
title = {Distinct prophage infections in colorectal cancer-associated Bacteroides fragilis.},
journal = {Communications medicine},
volume = {},
number = {},
pages = {},
doi = {10.1038/s43856-026-01403-1},
pmid = {41654659},
issn = {2730-664X},
abstract = {BACKGROUND: Colorectal cancer (CRC) patients exhibit distinct gut microbiota disruption, known as dysbiosis, which is believed to play a causative role in CRC. One of the key bacterial species implicated in CRC dysbiosis is Bacteroides fragilis, which presents a paradox as it is also present in most healthy individuals. This discrepancy underscores the need for analysis beyond species-level associations and to investigate intraspecies variation within B. fragilis.

METHODS: From a highly specific collection of B. fragilis isolates from CRC patients and controls, a pangenome-wide association study was conducted, identifying intraspecies genetic variations associated with CRC. The CRC association of these genetic variations were then validated in a metagenome sequencing cohort of faecal samples from 877 individuals, with and without CRC. To test group differences a mixed effects logistic regression with cohort as a random effect was performed for each genetic variation.

RESULTS: Here we show that CRC-associated B. fragilis isolates are infected with specific Caudoviricetes prophages, significantly more often than negative controls. The initial discovery was made in our highly specific isolate collection and then validated in an independent metagenome sequencing cohort, finding that CRC patients were twice as likely to have detectable levels of these phages (OR = 2.05, p = 2.522E-7, SE = 0.139).

CONCLUSIONS: To our knowledge, these findings mark the first link between one of the most implicated driver bacteria and phages in CRC and suggest a more complex role of phages in CRC dysbiosis than current models suggest and highlights the potential of phages as CRC biomarkers.},
}

@article {pmid41653238,
year = {2026},
author = {Sudharsan, R and Vanitha, A and Kannan, C and Jeevanantham, S and Reddy, NHS and Sowmya, P and Shankar, JG and Kesavan, M and Krishnamoorthy, R and Alshuniaber, MA and Osman, MA and Gatasheh, MK},
title = {Functional genomics and Pan-genome mining of endophytic Streptomyces rochei BBE1 reveal plant growth-promoting traits and biocontrol potential against banana Fusarium wilt.},
journal = {World journal of microbiology & biotechnology},
volume = {42},
number = {2},
pages = {78},
pmid = {41653238},
issn = {1573-0972},
}

@article {pmid41652681,
year = {2026},
author = {Hu, H and Wu, J and Sun, J and Wang, S and Liu, J and Dan, T},
title = {Comparative genomics reveals population structure and ecological adaptation in Lactobacillus helveticus.},
journal = {Food research international (Ottawa, Ont.)},
volume = {227},
number = {},
pages = {118266},
doi = {10.1016/j.foodres.2025.118266},
pmid = {41652681},
issn = {1873-7145},
mesh = {*Lactobacillus helveticus/genetics/classification ; Phylogeny ; *Genomics/methods ; *Genome, Bacterial ; *Adaptation, Physiological/genetics ; Evolution, Molecular ; },
abstract = {Lactobacillus helveticus (L. helveticus) is an important starter culture in fermented dairy production and is valued for its pronounced proteolytic activity. However, the genetic basis of its functional diversity and ecological adaptation warrants further investigation. This study presents a comparative genomic analysis of 284 L. helveticus isolated from diverse geographical regions and ecological niches. This investigation identified a core genome of 490 genes and a pan-genome encompassing 15,105 genes, revealing an open pan-genome structure for this species. Phylogenetic analysis classified the strains into six distinct evolutionary clades, indicating that their genetic evolution was likely driven by selective pressure associated with ecological niches. Statistically significant functional metabolic differences (P < 0.05) were observed among the different phylogenetic and ecological clades, whereas the intracellular peptidases were highly conserved. Assessment of angiotensin-converting enzyme (ACE) inhibitory activity among the strains revealed no significant differences across the phylogenetic clades. These findings demonstrate that L. helveticus has evolved evolutionary genomic mechanisms that facilitate its adaptation to diverse ecological environments. This study highlights the functional diversity of this species and provides a critical theoretical foundation for future industrial strain selection and development.},
}

*Lactobacillus helveticus/genetics/classification
Phylogeny
*Genomics/methods
*Genome, Bacterial
*Adaptation, Physiological/genetics
Evolution, Molecular

@article {pmid41649415,
year = {2026},
author = {Dzaraly, ND and Muthanna, AR and John, J and Masri, SN and Suhaili, Z and Sulaiman, N and A Rahman, NI and Tuan Soh, TS and Abdullah, FH and Biswas, S and Al-Obaidi, MMJ and Mohd Desa, MN},
title = {Comparative Whole Genome Sequencing of Seven Invasive Streptococcus pneumoniae Isolates from Malaysia Reveals Genetic Diversity, Recombination events, and Global Lineage Linkages.},
journal = {Journal of applied microbiology},
volume = {},
number = {},
pages = {},
doi = {10.1093/jambio/lxag040},
pmid = {41649415},
issn = {1365-2672},
abstract = {BACKGROUND: Streptococcus pneumoniae remains a major global health threat, causing diseases ranging from mild respiratory infections to severe conditions like pneumonia, sepsis, and meningitis. Although pneumococcal conjugate vaccines (PCVs) including PCV7, PCV10, and PCV13 have significantly reduced disease burden, especially in children, S. pneumoniae continues to exhibit high serotype and genetic diversity. Whole genome sequencing (WGS) analysis offers high-resolution insights into clonal lineages and multidrug-resistant strains. However, genomic data on Malaysian isolates remain limited.

METHODS: This study characterised the whole genome features and comparative profiles of seven invasive S. pneumoniae isolates from two tertiary hospitals in Malaysia. WGS analyses described serotype, sequence type (ST), antimicrobial resistance determinant genes, pan-genome structure, and recombination events.

RESULTS: The average genome size was ∼2.12 Mbp, with 1 988-2 205 coding sequences. WGS-based MLST identified five sequence types (ST236, ST320, ST386, ST671, ST695), with ST236 linked to serotypes 19A and 19F related to PMEN clones Taiwan19F-14 and CC271. Core genome analysis with 35 global reference strains revealed three major clades. Notably, isolates TSP95, SSP45, and SSP46 clustered closely with strains from South Korea, suggesting a long-term persistence of ST320 over a decade. Recombination analysis identified both shared and isolate-specific events, forming distinct phylogenetic clusters. Extensive shared recombination was observed in several isolates, while others displayed isolate-specific events, indicating ongoing genetic diversification.

CONCLUSION: These findings underscore the critical role of recombination in shaping pneumococcal population structure, evolution, and adaptation.},
}

@article {pmid41649278,
year = {2026},
author = {Selleri, E and Tarracchini, C and Petraro, S and Mancabelli, L and Milani, C and Turroni, F and Shao, Y and Browne, HP and Lawley, TD and van Sinderen, D and Ventura, M and Lugli, GA},
title = {Assessment of genome evolution in Bifidobacterium adolescentis indicates genetic adaptation to the human gut.},
journal = {mSystems},
volume = {},
number = {},
pages = {e0117325},
doi = {10.1128/msystems.01173-25},
pmid = {41649278},
issn = {2379-5077},
abstract = {UNLABELLED: Bifidobacterium adolescentis is one of the most frequently encountered bifidobacterial species present in the adult human gut microbiota, with a prevalence of approximately 60%. Despite its high prevalence, B. adolescentis has not been extensively studied and characterized, and our understanding of its physiological traits, genetic diversity, and potential interactions with other members of the human gut microbiota or with its host is therefore fragmentary. In the current study, a data set comprising 1,682 B. adolescentis genomes was compiled by combining publicly available data and metagenome assemblies from 131 projects to uncover the unique genetic characteristics of this species. A pangenome analysis of B. adolescentis identified 203 clusters of orthologous genes absent from the other five human-associated Bifidobacterium species, six of which were in silico predicted to encode functions unique to this taxon. Furthermore, 2,597 genes were predicted to have been acquired by horizontal gene transfer, including genes encoding extracellular structures involved in interaction with the host and other microorganisms, and phage defense mechanisms against bacteriophages. Detailed phylogenetic analysis revealed seven clusters within the B. adolescentis species, each partially associated with the origin of strain isolation, suggesting phylogenetic differentiation shaped by geographical strain origin. Moreover, a large-scale metagenomic analysis of over 10,000 human gut metagenomes from healthy adults revealed that B. adolescentis co-occurs with 36 putative beneficial commensals and butyrate-producing taxa, highlighting its role as a key bifidobacterial species involved in microbial networking within the adult human gut microbiota.

IMPORTANCE: To comprehensively explore the biodiversity within a microbial species, the reconstruction of a substantial number of genomes is essential. In this study, we successfully uncovered the genetic diversity of Bifidobacterium adolescentis by retrieving a large number of genomes from human gut metagenomic samples. The complete overview of the B. adolescentis pangenome enabled us to investigate the genetic features that distinguish this gut commensal from other bifidobacterial species residing in the human intestinal microbiota.},
}

@article {pmid41648402,
year = {2026},
author = {Versoza, CJ and Bales, KL and Jensen, JD and Pfeifer, SP},
title = {Characterizing the rates and patterns of de novo germline mutations in coppery titi monkeys (Plecturocebus cupreus).},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.64898/2026.01.15.699688},
pmid = {41648402},
issn = {2692-8205},
abstract = {Although recent advances in genomics have enabled the high-resolution study of whole genomes, our understanding of one of the key evolutionary processes, mutation, still remains limited. In primates specifically, studies have largely focused on humans and their closest evolutionary relatives, the great apes, as well as a handful of species of biomedical or conservation interest. Yet, as biological variation in mutation rates has been shown to vary across genomic regions, individuals, and species, a greater understanding of the underlying evolutionary dynamics at play will ultimately be illuminated by not only additional sampling across the Order, but also by a greater depth of sampling within-species. To address these needs, we here present the first population-scale genomic resources for a platyrrhine of considerable biomedical interest for both social behavior and neurobiology, the coppery titi monkey (Plecturocebus cupreus). Deep whole-genome sequencing of 15 parent-offspring trios, together with a computational de novo mutation detection pipeline based on pan-genome graphs, has provided a detailed picture of the sex-averaged mutation rate - 0.63 × 10 [-8] (95% CI: 0.43 × 10 [-8] - 0.90 × 10 [-8]) per site per generation - as well as the effects of both sex and parental age on underlying rates, demonstrating a significant paternal age effect. Coppery titi monkey males exhibit long reproductive lifespans, afforded by long-term pair bonding in the species' monogamous mating system, and our results have demonstrated that individuals reproducing later in life exhibit one of the strongest male mutation biases observed in any non-human primate studied to date. Taken together, this study thus provides an important piece of the puzzle for better comprehending the mutational landscape across primates.},
}

@article {pmid41648228,
year = {2026},
author = {Dockman, RL and Ottesen, EA},
title = {Niche specialization and cross-feeding interactions shaping gut microbial fiber degradation in a model omnivore.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.64898/2026.01.22.701066},
pmid = {41648228},
issn = {2692-8205},
abstract = {The gut microbiome plays an active role in host health, producing gut metabolites that influence host digestive and immune function while also mediating microbial crosstalk. Dietary fiber is a major source of important fermentation byproducts that are generally implicated in gut community stability and host wellbeing, but dissecting microbe-specific contributions to polysaccharide metabolism in the context of a complex gut community is challenging with conventional model organisms. Using the American cockroach (Periplaneta americana) as a model omnivore, we use chemically-defined synthetic diets to identify how complex gut microbial communities respond to two of the most abundant plant polysaccharides, xylan and cellulose. To do so, we fed cockroaches synthetic diets containing one of these fibers or a mix of both in differing ratios. Through both 16S rRNA gene profiling and RNA-seq, we show that mixed fibers enrich for organisms characteristic of the source fibers as well as additional organisms only enriched in mixed-fiber diets. Through an organism-centric pangenome approach, we identify the impact of these fibers on gut microbiome activity. We found that gut communities responded strongly to xylan, with Bacteroidota belonging to Bacteroides, Dysgonomonas, and Parabacteroides producing xylan-active CAZymes at high levels. Multiple groups of Bacillota also responded strongly to a xylan diet, but appeared to act as cross-feeding secondary degraders, producing primarily xylosidases and transcripts associated with xylose utilization. In contrast, cellulose diets were associated with higher transcriptional activity among Fibrobacterota, which are typically a minor component of the cockroach gut microbiome but were the primary producers of CAZymes associated with cellulose and cellobiose degradation. These experiments provide new insight into gut microbial metabolism of these complex plant polysaccharides. Further, they highlight the utility of the cockroach model and synthetic diets to answer fundamental questions about gut microbial responses to different polysaccharides alone and in combination.},
}

@article {pmid41648118,
year = {2026},
author = {Sanaullah, A and Brown, NK and Shakya, P and Deegutla, A and Naseri, A and Langmead, B and Zhi, D and Zhang, S},
title = {RLBWT-Based LCP Computation in Compressed Space for Terabase-Scale Pangenome Analysis.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.64898/2026.01.23.701410},
pmid = {41648118},
issn = {2692-8205},
abstract = {UNLABELLED: Lossless full text indexes are utilized in a myriad of applications in bioinformatics. The continuously decreasing cost of generating biological data has resulted in the need to build full text indexes on biological datasets of increasing size. Many compressed full text indexes have been developed to address this problem. In particular, run-length Burrows-Wheeler transform (RLBWT) based compressed full text indexes have seen wide development and adoption. However, the construction of these RLBWT-based compressed full text indexes is still computationally expensive, sometimes prohibitively so, even for current dataset sizes. Therefore, we present algorithms for the construction of RLBWT-based compressed full text indexes and their supporting data structures in compressed space. The algorithms have a space complexity of O (r) words and run in O (n) time for repetitive datasets, where r is the number of runs in the BWT, n is the length of the text, and repetitive datasets implies the average run length is at least log n . We provide the first algorithm to compute LCP-related information for repetitive datasets in optimal time and O (r) space, greatly reducing memory requirements. The key idea behind this algorithm is the utilization of r samples of the inverse suffix array at regular intervals. For example, on the Human Pangenome Reference Consortium Release 2 dataset, this reduces peak memory from 2,135 GiB to 170 GiB (12.6x reduction) compared to the previous best method (pfp-thresholds).

AVAILABILITY: The implementation is available at https://github.com/ucfcbb/TeraTools .

SUPPLEMENTARY INFORMATION: Supplementary Material is available online at bioRxiv.},
}

@article {pmid41647261,
year = {2025},
author = {Yang, Q and Wang, P and Yang, X and Zhao, S and Zhang, Q and Yang, F and Liu, Z and Yu, B},
title = {Evolution and phylogenetic characteristics of the first Brucella canis strain isolated from a human patient in Yunnan Province, China.},
journal = {Frontiers in cellular and infection microbiology},
volume = {15},
number = {},
pages = {1743711},
pmid = {41647261},
issn = {2235-2988},
mesh = {*Phylogeny ; China ; *Brucella canis/genetics/classification/isolation & purification ; *Brucellosis/microbiology ; Humans ; Dogs ; Animals ; Genome, Bacterial ; Multilocus Sequence Typing ; Whole Genome Sequencing ; Polymorphism, Single Nucleotide ; *Evolution, Molecular ; },
abstract = {INTRODUCTION: Brucella canis is a zoonotic pathogen that infects both dogs and humans, yet its evolutionary and phylogenetic characteristics are poorly understood.

METHODS: Here, we comprehensively characterized an isolated strain of B. canis through integrated bacteriological, comparative genomic, and whole-genome sequencing-based core genome single-nucleotide polymorphism (WGS-cgSNP) analyses.

RESULTS: B. canis YN20042 was isolated from a febrile patient (38 °C) with sweating and fatigue. The culture exhibited rough, grayish white, sticky, and opaque colonies. The isolate was identified as Brucella strain by a BCSP-31 polymerase chain reaction (PCR) assay, which yielded an amplicon of the expected 223-bp size, and was classified as a B. canis strain by conventional biotyping. The patient reported frequent contact with dogs and livestock. The strain showed a 99.99% average nucleotide identity to the B. canis reference strain ATCC 23365 (GCA_000018525.1). An in silico multilocus sequence typing (MLST) analysis showed that the strain belonged to sequence type 21, which was consistent with its classification within B. canis. The genome of strain YN20042 exhibited strong synteny with the reference strain and showed no detectable structural variations. It harbored 12 predicted virulence factors encompassing 71 associated genes, although it notably lacked the wbpL gene but contained a Brucella suis mprF gene. A further analysis identified predicted mutations in key virulence genes (eryA, pagN, bmaC, cfa1, and cfa2) and predicted multiple horizontally acquired genes, collectively suggesting a complex evolutionary trajectory involving both gene variants and potential recombination events. A WGS-SNP analysis revealed that YN20042 clustered closely with strains isolated from Zhejiang and Beijing, indicating a high degree of genetic relatedness.

CONCLUSION: The first isolation of B. canis in the region expands the local spectrum of pathogenic Brucella and highlights the substantial infection risk for individuals with close dog and livestock contact. Enhanced surveillance, targeted screening of high-risk populations, and public health education are necessary to mitigate the risk of B. canis transmission.},
}

*Phylogeny
China
*Brucella canis/genetics/classification/isolation & purification
*Brucellosis/microbiology
Humans
Dogs
Animals
Genome, Bacterial
Multilocus Sequence Typing
Whole Genome Sequencing
Polymorphism, Single Nucleotide
*Evolution, Molecular

@article {pmid41646363,
year = {2026},
author = {Eskandar, P and Paten, B and Sirén, J},
title = {Lossless Pangenome Indexing Using Tag Arrays.},
journal = {Research square},
volume = {},
number = {},
pages = {},
doi = {10.21203/rs.3.rs-8233501/v1},
pmid = {41646363},
issn = {2693-5015},
abstract = {Pangenome graphs represent the genomic variation by encoding multiple haplotypes within a unified graph structure. However, efficient and lossless indexing of such structures remains challenging due to the scale and complexity of pangenomic data. We present a practical and scalable indexing framework based on tag arrays, which annotate positions in the Burrows--Wheeler transform (BWT) with graph coordinates. Our method extends the FM-index with a run-length compressed tag structure that enables efficient retrieval of all unique graph locations where a query pattern appears. We introduce a novel construction algorithm that combines unique $k$-mers, graph-based extensions, and haplotype traversal to compute the tag array in a memory-efficient manner. To support large genomes, we process each chromosome independently and then merge the results into a unified index using properties of the multi-string BWT and r-index. Our evaluation on the HPRC graphs demonstrates that the tag array structure compresses effectively, scales well with added haplotypes, and preserves accurate mapping information across diverse regions of the genome. This indexing method enables lossless and haplotype-aware querying in complex pangenomes and offers a practical indexing layer to develop scalable aligners and downstream graph-based analysis tools. The index additionally supports efficient one-to-all coordinate translation, enabling any interval on a haplotype to be mapped to its corresponding intervals across all other haplotypes in the graph.},
}

@article {pmid41643596,
year = {2026},
author = {Savin, M and Erler, T and Carlsen, L and Dengler, J and Hammerl, JA and Hoffmann, M and Knobloch, JK and Lübbert, C and Parcina, M and Schwanz, T and Zweigner, J and Mutters, NT},
title = {Cefiderocol-resistant Aeromonas with expanded Resistomes in German hospital wastewater: Phenotypic and genomic evidence from the environment-clinical Interface.},
journal = {The Science of the total environment},
volume = {1017},
number = {},
pages = {181478},
doi = {10.1016/j.scitotenv.2026.181478},
pmid = {41643596},
issn = {1879-1026},
abstract = {Hospital wastewater is a key interface between clinical and environmental reservoirs of antimicrobial resistance, fostering selection and horizontal gene transfer. Aeromonas spp. are aquatic opportunistic pathogens with highly plastic genomes and are increasingly recognized as potential intermediaries in resistance dissemination. We compared 72 cefiderocol-selected Aeromonas isolates recovered from untreated hospital wastewater collected at six tertiary care hospitals across Germany with 62 clinical isolates from patients with intestinal and extraintestinal infections, to characterize cefiderocol susceptibility, resistome composition, and genomic mobility features. Pangenome analysis revealed an open genome structure comprising 21,364 gene clusters, with a core genome of 2486 genes and a large cloud gene pool (15,612 clusters present in <15% of isolates), highlighting extensive genomic plasticity. Resistance phenotypes diverged markedly: cefiderocol-selected wastewater isolates exhibited high resistance rates to multiple clinically relevant agents - ciprofloxacin (93.1%), aztreonam (81.2%), and trimethoprim-sulfamethoxazole (38.9%), whereas clinical isolates remained largely susceptible overall (<10%). Under iron limitation, siderophore production increased in both cohorts; however, in the presence of cefiderocol it remained robust in wastewater isolates while being suppressed in clinical isolates. Comparative genomics showed that wastewater isolates carried substantially expanded resistomes (mean 13.8 ARGs; range 2-27) relative to clinical isolates (mean 2.6; range 1-11), including enrichment of clinically relevant β-lactamases and carbapenemases. This resistance burden coincided with a larger and more transmissible plasmidome and a high insertion sequence load. Notably, extensive plasmid-backbone homology was detected between Aeromonas and co-occurring cefiderocol-resistant Enterobacterales isolated from the same wastewater samples, highlighting interspecies gene flow at the hospital-environment interface. Together, these findings identify hospital wastewater as a reservoir and convergence point for highly resistant, mobilome-enriched Aeromonas subpopulations captured under cefiderocol selection, supporting Aeromonas as a One Health sentinel and emphasizing the value of wastewater-based surveillance for tracking mobile resistance determinants bridging environmental and clinical compartments.},
}

@article {pmid41643009,
year = {2026},
author = {Huang, Y and Zhang, Y and Zhang, Q and Zhuang, G and Li, C and Wang, B and Gao, R and Xu, Y and Qi, Y and Hua, X and Shi, H and Xu, Q and Yao, W and Liu, X and Qi, Y and Chen, B and Zhang, M and Ming, R and Tang, H and Zhang, J},
title = {Multiscale pangenome graphs empower the genomic dissection of mixed-ploidy sugarcane species.},
journal = {Science (New York, N.Y.)},
volume = {391},
number = {6785},
pages = {eadx1616},
doi = {10.1126/science.adx1616},
pmid = {41643009},
issn = {1095-9203},
mesh = {*Saccharum/genetics ; *Genome, Plant ; Polyploidy ; Haplotypes ; Genome-Wide Association Study ; Genomics/methods ; *Ploidies ; Chromosomes, Plant ; },
abstract = {The sugarcane genus Saccharum is characterized by complex genomes with diverse ploidy levels. We developed a multiscale graph-based pangenome representation, which integrates nine genome assemblies into a unified reference, representing modern cultivars and founding species. Each homo(eo)logous (encompasses both homologous and homeologous relationships) chromosome set retains 47 to 57 haplotypes and ~74,000 to 271,000 gene alleles. This framework enables multiomics exploration, encompassing homo(eo)log systems and epigenomic signatures. The pangenome facilitates population genomics analyses of 417 mixed-ploidy Saccharum accessions, revealing convergent selection and identifying the Andropogoneae TB1 homolog linked to tillering as a promising gene-editing target to boost cane yield. Additionally, the pangenome supports dosage-informed genome-wide association study, improving heritability estimates and identification of sugar or leaf-angle-associated loci, including SaIRX10 and SaBAK5. Our analytical framework establishes a foundation for graph-based genetic studies in sugarcane and other polyploid genomes.},
}

*Saccharum/genetics
*Genome, Plant
Polyploidy
Haplotypes
Genome-Wide Association Study
Genomics/methods
*Ploidies
Chromosomes, Plant

@article {pmid41642996,
year = {2026},
author = {Ma, W and Liu, Y and Wei, X and Zhang, X and Li, X and Liu, Z and Yuan, L and Li, G and Zhang, S and Yang, Q and Chang, X and Han, Z and Liang, H and Luan, Z and Wang, Q and Gu, Y and Wang, X and Zhao, X and Liu, Q and Sun, X and Liu, M and Feng, D and Lu, Y and Luo, S and Yang, L and Li, M and Allaby, R and Wang, K and Zhang, T and Shen, S and Van de Peer, Y and Hong, Y and Yuan, Y and Zhao, J},
title = {Gapless pangenome analyses reveal fast Brassica rapa subspeciation.},
journal = {Science (New York, N.Y.)},
volume = {391},
number = {6785},
pages = {eady7590},
doi = {10.1126/science.ady7590},
pmid = {41642996},
issn = {1095-9203},
mesh = {*Brassica rapa/genetics/classification/anatomy & histology ; *Genome, Plant ; Genes, Plant ; Centromere/genetics ; Plant Leaves/anatomy & histology/genetics/growth & development ; Genome-Wide Association Study ; Plant Proteins/genetics ; Telomere/genetics ; Plant Breeding ; Genetic Variation ; },
abstract = {Brassica rapa (Br) encompasses many morphotypes and subspecies, so it is a good model with which to investigate plant diversification and subspeciation. Here, we resequenced the genomes of 1720 Br accessions and de novo assembled 11 representative telomere-to-telomere gapless genomes for seven elite subspecies that underwent intensive morphotypification and developed distinct agronomic traits valued to agriculture. We identified 6992 unknown genes, 110 complete (peri)centromeres, and five new satellites associated with Br morphotypes and subspecies and Brassica species evolution. The pangenome, built on 11 gapless and 20 published genomes, reveals structural variations and gene diversities among Br subspecies. Pangenome-wide association studies uncovered that the gene BrLH1 controls leaf-head formation. We show that structural changes have occurred in satellites, (peri)centromeres, and genes, contributing to fast subspeciation and morphotypification during the short history of Br cultivation, providing invaluable resources for Brassica breeding.},
}

*Brassica rapa/genetics/classification/anatomy & histology
*Genome, Plant
Genes, Plant
Centromere/genetics
Plant Leaves/anatomy & histology/genetics/growth & development
Genome-Wide Association Study
Plant Proteins/genetics
Telomere/genetics
Plant Breeding
Genetic Variation

@article {pmid41642519,
year = {2026},
author = {Wu, Y and Jones, JDG and Lin, X},
title = {The Application of RenSeq for Pan-NLRome Analysis.},
journal = {Methods in molecular biology (Clifton, N.J.)},
volume = {3012},
number = {},
pages = {113-127},
pmid = {41642519},
issn = {1940-6029},
mesh = {Computational Biology/methods ; *Disease Resistance/genetics ; Gene Library ; High-Throughput Nucleotide Sequencing/methods ; Genes, Plant ; Genome, Plant ; Cloning, Molecular/methods ; *Plant Diseases/genetics ; Crops, Agricultural/genetics ; Triticum/genetics ; Plant Proteins/genetics ; Plant Breeding ; },
abstract = {Resistance gene enrichment sequencing (RenSeq) was developed in 2013. It has accelerated the cloning of plant NLR genes and has contributed to resistance breeding for multiple crop plants, such as potato, wheat, and rice. By combining with other strategies, many applications were developed, such as cDNA-RenSeq, dRenSeq, SMRT-RenSeq, RLP/KSeq, AgRenSeq, and MutRenSeq. These methods have been widely applied in different crops. In this protocol, we present a step-by-step guide for applying RenSeq in gene cloning and Pan-NLRome analysis. The protocol covers bait design, library preparation, target enrichment, and downstream bioinformatic analysis. This methodology can make RenSeq more accessible to researchers working with different crops and enhance our understanding of plant resistance genes in the age of pan-genome.},
}

Computational Biology/methods
*Disease Resistance/genetics
Gene Library
High-Throughput Nucleotide Sequencing/methods
Genes, Plant
Genome, Plant
Cloning, Molecular/methods
*Plant Diseases/genetics
Crops, Agricultural/genetics
Triticum/genetics
Plant Proteins/genetics
Plant Breeding

@article {pmid41642358,
year = {2026},
author = {Fang, C and Zhou, Z and Zhang, X and Xia, J and Liu, S and Li, J and Zhou, M},
title = {Epidemiological and Genomic Insights into Linezolid-Non-Susceptible Enterococci in Pediatric Patients.},
journal = {Current microbiology},
volume = {83},
number = {3},
pages = {155},
pmid = {41642358},
issn = {1432-0991},
support = {No. LTGC23H200006//Zhejiang Provincial Natural Science Foundation of China/ ; No. I23J0006//Key Program of The Independent Design Project of National Clinical Research Center for Child Health/ ; 2023C03028//"Pioneer" and "Leading Goose" R&D Program of Zhejiang Province/ ; },
mesh = {*Linezolid/pharmacology ; Humans ; *Gram-Positive Bacterial Infections/epidemiology/microbiology ; *Anti-Bacterial Agents/pharmacology ; Child ; Microbial Sensitivity Tests ; Genome, Bacterial ; *Enterococcus faecalis/genetics/drug effects/isolation & purification ; Multilocus Sequence Typing ; *Enterococcus/genetics/drug effects/isolation & purification/classification ; Genomics ; Child, Preschool ; China/epidemiology ; Drug Resistance, Multiple, Bacterial/genetics ; Infant ; },
abstract = {Enterococci are major opportunistic pathogens causing healthcare-associated infections in children. Linezolid, a WHO-designated critically important antibiotic for multidrug-resistant Gram-positive infections, is increasingly challenged by linezolid-non-susceptible enterococci (LNSE). Yet pediatric LNSE epidemiology and genomics data remain scarce, hindering targeted control. We analyzed 26 LNSE strains isolated from Children's Hospital, Zhejiang University School of Medicine (June 2020-July 2024) using MALDI-TOF MS, Vitek2 Compact, micro-broth dilution (for linezolid MIC), MLST, resistance/virulence gene detection, and pan-genome analysis (COG/KEGG annotation). Enterococcus faecalis (E. faecalis) dominated (23/26,88.5%) with ST16 as the major sequence type (ST) and four novel STs identified; all strains harbored optrA and fexA, with species-specific resistance/virulence gene profiles. The 23 E. faecalis strains exhibited an open pan-genome (b = 0.174725), indicating the possible existence of active horizontal gene transfer (HGT), with core, accessory, and unique genes showing distinct functional differentiation. These findings provide critical and robust empirical data to inform the development of targeted prevention and control strategies against LNSE in pediatric populations.},
}

*Linezolid/pharmacology
Humans
*Gram-Positive Bacterial Infections/epidemiology/microbiology
*Anti-Bacterial Agents/pharmacology
Child
Microbial Sensitivity Tests
Genome, Bacterial
*Enterococcus faecalis/genetics/drug effects/isolation & purification
Multilocus Sequence Typing
*Enterococcus/genetics/drug effects/isolation & purification/classification
Genomics
Child, Preschool
China/epidemiology
Drug Resistance, Multiple, Bacterial/genetics
Infant

@article {pmid41634489,
year = {2026},
author = {Araújo, MRB and Dos Santos, LS and Viana, MVC and Sousa, EG and Prates, FD and Perini, HF and da Silva, MV and da Silva Sousa, J and Brenig, B and Andrade, BS and Mattos-Guaraldi, AL and de Oliveira Sant'Anna, L and Ramos, JN and de Oliveira Vinhal, AL and de Castro Soares, S and Azevedo, V},
title = {Comparative genomics and molecular characterization of a multidrug-resistant Corynebacterium glucuronolyticum isolated for the first time from the human genitourinary tract in Latin America.},
journal = {Brazilian journal of microbiology : [publication of the Brazilian Society for Microbiology]},
volume = {57},
number = {1},
pages = {49},
pmid = {41634489},
issn = {1678-4405},
abstract = {UNLABELLED: Although Corynebacterium glucuronolyticum has been associated with human infections, its pathogenic potential remains poorly understood. Here, we describe the first case in Latin America of C. glucuronolyticum isolated from the human urogenital tract. The strain, designated IHP2022, was identified by MALDI-TOF MS (99% probability) and exhibited resistance to benzylpenicillin, clindamycin, and tetracycline, characterizing a multidrug-resistant (MDR) phenotype. Genomic analysis revealed a 2.88-Mb genome with 59.04% G + C content and no plasmids. Comparative genomic analysis, including 11 other publicly available genomes, demonstrated high genetic diversity and positioned IHP2022 close to strain p3-SID752 from the USA, suggesting a broad geographical distribution. The genome harbored multiple virulence and resistance genes, as well as a Type I-E CRISPR-Cas system. Functional annotation and pangenome analysis identified 4,027 gene families categorized into core, shell, and cloud components. By integrating phenotypic and genomic data, this study provides the first in-depth characterization of an MDR C. glucuronolyticum strain minimizing current knowledge gaps and contributing to a better understanding of its pathogenic potential.

SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1007/s42770-025-01822-7.},
}

@article {pmid41636756,
year = {2026},
author = {Park, S and Lee, H and Yook, S and Baek, C and Kim, J and Kwak, S and Na, T and Seo, T},
title = {Oceanimonas aquatica sp. nov. and Arenibacter flavimaris sp. nov., isolated from seawater.},
journal = {International journal of systematic and evolutionary microbiology},
volume = {76},
number = {2},
pages = {},
doi = {10.1099/ijsem.0.007054},
pmid = {41636756},
issn = {1466-5034},
mesh = {RNA, Ribosomal, 16S/genetics ; *Seawater/microbiology ; *Phylogeny ; DNA, Bacterial/genetics ; Bacterial Typing Techniques ; Republic of Korea ; Base Composition ; Sequence Analysis, DNA ; Nucleic Acid Hybridization ; Fatty Acids/chemistry ; Genome, Bacterial ; },
abstract = {The novel strains CHS3-5[T] and M-2[T] were isolated from seawater collected near Suaeda japonica colonies on Seongmodo Island, Republic of Korea. Strain CHS3-5[T] was Gram-stain-negative, motile with flagella, rod-shaped, strictly aerobic and formed circular, convex, ivory-coloured colonies, while strain M-2[T] was Gram-stain-negative, motile by gliding, rod-shaped, strictly aerobic and formed circular, raised, dark yellow colonies. Based on 16S rRNA and draft genome analyses, strains CHS3-5[T] and M-2[T] were identified as members of the Oceanimonas and Arenibacter genera, respectively. Strain CHS3-5[T] grew at temperatures of 10-40 °C, pH 4.0-10.0 and in the presence of 2.0-11.0% NaCl, with optimal growth at 30 °C, pH 7.0 and 3.0% NaCl. Strain M-2[T] grew at temperatures of 15-40 °C, pH 6.0-9.0 and in the presence of 2.0-4.0% NaCl, with optimal growth at 30 °C, pH 7.0 and 3.0% NaCl. Both novel strains showed low genomic relatedness to their respective type species. The average nucleotide identity and digital DNA-DNA hybridization values were 84.5-85.7% and 26.5-34.7% for strain CHS3-5[T] and 76.6-85.9% and 18.6-30.3% for strain M-2[T], respectively, supporting their classification as novel species. We propose the names Oceanimonas aquatica sp. nov. (type strain CHS3-5[T]=KACC 23248[T]=TBRC 17651[T]) and Arenibacter flavimaris sp. nov. (type strain M-2[T]=KACC 23249[T]=TBRC 17650[T]) for these strains.},
}

RNA, Ribosomal, 16S/genetics
*Seawater/microbiology
*Phylogeny
DNA, Bacterial/genetics
Bacterial Typing Techniques
Republic of Korea
Base Composition
Sequence Analysis, DNA
Nucleic Acid Hybridization
Fatty Acids/chemistry
Genome, Bacterial

@article {pmid41636541,
year = {2026},
author = {Treen, RZ and Gonzalez-Juarrero, M and Jackson, M and Lapierre, P and Kremer, L and Ghosh, P and Ojha, AK},
title = {Mycobacterium abscessus research: learning from challenges.},
journal = {Journal of bacteriology},
volume = {},
number = {},
pages = {e0043625},
doi = {10.1128/jb.00436-25},
pmid = {41636541},
issn = {1098-5530},
abstract = {Mycobacterium abscessus (Mab), a rapidly growing mycobacterial species with intrinsic and acquired resistance to multiple antibiotics, is an emerging public health concern. The rise in clinical cases of treatment-refractory infections of M. abscessus has propelled its research toward novel therapeutic approaches. The number of publications entitled "Mycobacterium abscessus" has increased by ~300% over the last decade, of which the majority of studies exploring the fundamental biology and pathogenesis of Mab have used the reference strain ATCC19977. However, whole-genome sequence analyses, combined with transposon-seq based functional genomics, reveal an open pan-genome with significant variations in the essential genes across ATCC19977 and clinical isolates. These new discoveries demand a careful selection of strains and growth conditions in experimental design. In this minireview, we discuss these challenges and propose a framework for future M. abscessus studies in silico, including a new web-based resource for pangenome analysis, in vitro, and in animal models.},
}

@article {pmid41632591,
year = {2026},
author = {Downing, T},
title = {Approaches to Studying Virus Pangenome Variation Graphs.},
journal = {Genomics, proteomics & bioinformatics},
volume = {},
number = {},
pages = {},
doi = {10.1093/gpbjnl/qzag003},
pmid = {41632591},
issn = {2210-3244},
abstract = {Pangenome variation graphs (PVGs) allow for the representation of genetic diversity in a more nuanced way than traditional reference-based approaches. Here I focus on how PVGs are a powerful tool for studying genetic variation in viruses, offering insights into the complexities of viral quasispecies, mutation rates, and population dynamics. PVGs originated in human genomics and hold great promise for viral genomics. Previous work has been constrained by small sample sizes and gene-centric methods, whereas PVGs enable a more comprehensive approach to studying viral diversity. Large viral genome collections should be used to make PVGs, which offer significant advantages. Here, I outline accessible tools to achieve their construction. This spans PVG construction, PVG file formats, PVG manipulation and analysis, PVG visualisation, measuring PVG openness, and mapping reads to PVGs. Additionally, the development of PVG-specific formats for mutation representation and personalised PVGs that reflect specific research questions will further enhance PVG applications. Challenges remain, particularly in managing nested variants, optimising error detection, optimising k-mer/minimizer-based approaches for AT-rich genomes, incorporating long read sequencing data, and scalable visualisation approaches. Nevertheless, PVGs offer a new opportunity for viral population genomics, and a testing ground for tool development prior to application to larger eukaryotic genomes. These advances will enable more accurate and comprehensive detection of viral mutations, contributing to a deeper understanding of viral evolution and genotype-phenotype associations.},
}

@article {pmid41631370,
year = {2026},
author = {Droc, G and Giraud, D and Belser, C and Labadie, K and Duprat, S and Cruaud, C and Istace, B and Menezes, FDS and Mario de Andrade Silva, E and Curk, F and Costantino, G and Soriano, A and Mournet, P and Dereeper, A and Miranda, M and Marchi, E and Santoni, S and Santana Silva, RJ and Sidibe-Bocs, S and Luro, F and Choisne, N and Maumus, F and Hufnagel, B and Micheli, F and Wincker, P and Aury, JM and Lemainque, A and Ollitrault, P},
title = {A Super-Pangenome for Cultivated Citrus Reveals Evolutive Features During the Allopatric Phase of Their Reticulate Evolution.},
journal = {Plant biotechnology journal},
volume = {},
number = {},
pages = {},
doi = {10.1111/pbi.70553},
pmid = {41631370},
issn = {1467-7652},
support = {ANR-10-INBS-09-08//Agence Nationale de la Recherche/ ; //Commissariat à l'Énergie Atomique et aux Énergies Alternatives/ ; //Genoscope - Centre National de Séquençage/ ; //Centre de Coopération Internationale en Recherche Agronomique pour le Développement/ ; },
abstract = {The main genetic diversity observed in cultivated citrus results from a reticulate evolution involving four ancestral taxa whose radiation occurred in allopatry. In such context, GWAS analysis, genome diversity and transcriptomic studies will be significantly enhanced through pangenome approaches. We report the implementation of a super-pangenome for cultivated citrus, established with de novo assemblies of C. medica, C. reticulata and C. micrantha, released for the first time alongside a published chromosome-scale assembly of C. maxima. Repetitive element annotation revealed that half of each genome consisted of transposable elements or DNA-satellites. The new genome assemblies display strong synteny and collinearity, while discrepancies are observed with the C. maxima assembly. Resequencing information from 55 accessions helped to explore the intra- and interspecific diversity of the ancestral taxa and their relationships with horticultural groups. Diagnostic SNPs of the ancestral taxa revealed interspecific introgressions in several representative accessions of C. reticulata, C. maxima and C. medica as well as insights into the origin and phylogenomic structures of horticultural groups. PAV analysis revealed a gene whose absence or presence was specific to one of the ancestral taxa. Diagnostic PAV analysis uncovered a large chloroplastic introgression in C. medica chromosome 4. The analysis of the functional enrichment and species-specific adaptations in the citrus super-pangenome revealed distinct functional specialisations. This highlights the evolutionary paths that have shaped species, contributing to the diversity in the citrus super-pangenome while maintaining a shared foundation of essential biological processes. We established a Genome Hub, offering a platform for continuous genomic research.},
}

@article {pmid41627508,
year = {2026},
author = {Orozco-Ochoa, AK and Quiñones, B and Lee, BG and González-Gómez, JP and Lira-Morales, JD and Castro-Del Campo, N and Valdez-Torres, JB and Chaidez-Quiroz, C},
title = {Pangenomics of high-risk international clones in Acinetobacter baumannii identifies distinctive virulence and antimicrobial resistance profiles.},
journal = {Archives of microbiology},
volume = {208},
number = {4},
pages = {173},
pmid = {41627508},
issn = {1432-072X},
support = {2030-42000-055-00D//United States Department of Agriculture (USDA), Agricultural Research Service (ARS), CRIS/ ; Ciencia de Frontera 2023//Ciencia de Frontera 2023/ ; },
mesh = {*Acinetobacter baumannii/genetics/drug effects/pathogenicity/classification/isolation & purification ; *Acinetobacter Infections/microbiology/epidemiology ; Humans ; *Virulence Factors/genetics ; Virulence/genetics ; Anti-Bacterial Agents/pharmacology ; *Drug Resistance, Multiple, Bacterial/genetics ; Mexico/epidemiology ; Phylogeny ; Genome, Bacterial ; Microbial Sensitivity Tests ; Bacterial Proteins/genetics ; Genomics ; },
abstract = {The bacterial pathogen Acinetobacter baumannii is an opportunistic and nosocomial causative agent of multidrug resistant infections worldwide. The present study conducted comparative genomic analyses to identify relevant pathogenicity traits in A. baumannii strains from diverse clinical samples and geographical regions in Mexico. Pangenome analysis clustered the strains into four phylogenomic clades, comprising various international clones. Clades I and II strains, predominantly from blood and respiratory infections in the Central region, were significantly associated with the Latin American IC5 clone (P = 0.0002), whereas clade III strains, primarily from diverse samples in the Northwestern region, were significantly associated with the European IC2 clone (P = 0.0030). Virulence determinants implicated in adhesion (ompA, omp38), biofilm formation (pgaA-D, csuA/BABCDE), motility (pil, fim), regulatory systems (bfmRS, barAB, abaR/abaI), iron acquisition (bas, bau), and efflux pump-delivery systems (adeFGH) were identified among the A. baumannii strains, representing all clades and geographical regions. Analysis of intrinsic and acquired antimicrobial resistance revealed that clades I and II strains were significantly correlated with resistance to β-lactamases (blaADC-6, blaOXA-239, blaOXA-65), sulfonamides (sul2), and chloramphenicol (cmlB1) (P = 0.0001). Interestingly, clade III strains, predominantly from the agricultural Northwestern region, exhibited a significant association of broader resistance genes against aminoglycosides (aac(6')-Ib', aph(3')-Ia, armA, aadA), β-lactamases (blaTEM-4, blaADC-25, blaOXA-66), sulfonamides (sul1), tetracyclines (tetA), and macrolides (mphD, msrE) (P = 0.0001). Subsequent characterization of mobile genetic elements indicated genetic plasticity and potential transfer of antimicrobial resistance. Collectively, this fundamental information would enable the improvement of epidemiological surveillance and intervention strategies for A. baumannii.},
}

*Acinetobacter baumannii/genetics/drug effects/pathogenicity/classification/isolation & purification
*Acinetobacter Infections/microbiology/epidemiology
Humans
*Virulence Factors/genetics
Virulence/genetics
Anti-Bacterial Agents/pharmacology
*Drug Resistance, Multiple, Bacterial/genetics
Mexico/epidemiology
Phylogeny
Genome, Bacterial
Microbial Sensitivity Tests
Bacterial Proteins/genetics
Genomics

@article {pmid41627425,
year = {2026},
author = {Unlu Celebi, S and Yalcin, S and Kurt Azap, O and Uskudar Guclu, A},
title = {Genomic insights into the genetic diversity, resistance determinants, and plasmid content of carbapenem-resistant Acinetobacter baumannii clinical isolates.},
journal = {Archives of microbiology},
volume = {208},
number = {4},
pages = {169},
pmid = {41627425},
issn = {1432-072X},
support = {DA24/22//Baskent Üniversitesi/ ; },
mesh = {*Acinetobacter baumannii/genetics/drug effects/isolation & purification/classification ; *Plasmids/genetics ; *Carbapenems/pharmacology ; Humans ; *Anti-Bacterial Agents/pharmacology ; *Genetic Variation ; *Acinetobacter Infections/microbiology ; Microbial Sensitivity Tests ; Genome, Bacterial ; *Drug Resistance, Multiple, Bacterial/genetics ; Multilocus Sequence Typing ; Whole Genome Sequencing ; Electrophoresis, Gel, Pulsed-Field ; Bacterial Proteins/genetics ; },
abstract = {Carbapenem-resistant Acinetobacter baumannii (CRAB) is a critical nosocomial pathogen with limited therapeutic options. This study aimed to describe clonal relationships among CRAB isolates and genomic insights from representative clusters. A total of 128 non-duplicate CRAB isolates were included in the study. Pulsed-field gel electrophoresis (PFGE) was used to assess clonal relationships and as a preliminary clustering tool for isolate selection. Twelve representative isolates from distinct PFGE clusters were selected for whole-genome sequencing using Oxford Nanopore. Genome assembly, annotation, and comparative analyses were performed using Flye, Prokka, and Roary, respectively. Antimicrobial resistance (AMR) genes, plasmids, insertion sequences, integrons and prophages were identified using the CARD, MOB-suite, ISEscan, IntegronFinder, and PHASTEST tools, respectively. Multilocus sequence typing (MLST) and pangenome analyses were conducted to determine genetic diversity and relatedness among the CRAB isolates. Antibiotic susceptibility testing revealed an extensively drug-resistant phenotype, colistin resistance rate was 23.4%. Mutations in lpxC, lpxD, pmrB, and lpxA were identified in colistin-resistant isolates, suggesting a possible role. Most isolates belonged to the globally disseminated clone ST2Pasteur, while others were classified as ST636 and ST78. Genomic comparisons identified diverse resistance genes, mobile genetic elements, plasmids, integrons, and virulence factors. Pangenome analysis uncovered a considerable genomic diversity, with 2700 core genes (42.5%) and 3649 accessory genes (57.5%), including 1864 strain-specific (cloud) genes (29.4%) among the isolates. Overall, our findings demonstrate the complex genomic architecture of CRAB and highlight the potential role of genomic surveillance in local infection control.},
}

*Acinetobacter baumannii/genetics/drug effects/isolation & purification/classification
*Plasmids/genetics
*Carbapenems/pharmacology
Humans
*Anti-Bacterial Agents/pharmacology
*Genetic Variation
*Acinetobacter Infections/microbiology
Microbial Sensitivity Tests
Genome, Bacterial
*Drug Resistance, Multiple, Bacterial/genetics
Multilocus Sequence Typing
Whole Genome Sequencing
Electrophoresis, Gel, Pulsed-Field
Bacterial Proteins/genetics

@article {pmid41628479,
year = {2026},
author = {Cole, B and Zhang, W and Shi, J and Wang, H and Baker, C and Varoquaux, N and Hollingsworth, J and Hutmacher, R and Dahlberg, J and Pierroz, G and Barry, KW and Singan, V and Yoshinaga, Y and Daum, C and Zane, M and Blow, M and O'Malley, R and Shu, S and Jenkins, JW and Lovell, JT and Schmutz, J and Taylor, JW and Coleman-Derr, D and Visel, A and Lemaux, PG and Purdom, E and Vogel, JP},
title = {Multi-season analysis reveals hundreds of drought-responsive genes in sorghum.},
journal = {The Plant journal : for cell and molecular biology},
volume = {125},
number = {3},
pages = {e70657},
doi = {10.1111/tpj.70657},
pmid = {41628479},
issn = {1365-313X},
support = {DE-SC0014081//U.S. Department of Energy/ ; //U.S. Department of Energy Joint Genome Institute/ ; },
mesh = {*Sorghum/genetics/physiology ; *Droughts ; Gene Expression Regulation, Plant ; Gene Expression Profiling ; Transcriptome ; Genotype ; Seasons ; Genes, Plant ; Plant Leaves/genetics/physiology ; Stress, Physiological/genetics ; Plant Roots/genetics/physiology ; Plant Proteins/genetics/metabolism ; },
abstract = {Persistent drought affects global crop production and is becoming more severe in many parts of the world in recent decades. Deciphering how plants respond to drought will facilitate the development of flexible mitigation strategies. Sorghum bicolor L. Moench (sorghum), a major cereal crop and an emerging bioenergy crop, exhibits remarkable resilience to drought. To better understand the molecular traits that underlie sorghum's remarkable drought tolerance, we undertook a large-scale sorghum gene expression profiling effort, totaling nearly 1500 transcriptome profiles, across a 3-year field study with replicated plots in California's Central Valley. This study included time-resolved gene expression data from roots and leaves of two sorghum genotypes, BTx642 and RTx430, with different pre-flowering and post-flowering drought-tolerance adaptations under control and drought conditions. Quantification of genotype-specific drought tolerance effects was enabled by de novo sequencing, assembly, and annotation of both BTx642 and RTx430 genomes. These reference-quality genomes were used to construct a pangene set for characterizing conserved and genotype-specific expression. By integrating time-resolved transcriptomic responses to drought in the field across three consecutive years, we identified a set of 726 drought-responsive genes that responded similarly in all 3 years of our field study. Functional enrichment analysis identified abiotic stress, secondary cell wall-related processes and metabolism as particularly affected under both types of drought stress. We also found that some glyoxylate cycle pathway genes, including malate synthase and isocitrate lyase, are differentially regulated particularly during post-flowering drought stress, implicating this pathway as potentially important for drought responsiveness. This expansive dataset represents a unique resource for sorghum and drought research communities and provides a methodological framework for the integration of multi-faceted time-resolved transcriptomic datasets.},
}

*Sorghum/genetics/physiology
*Droughts
Gene Expression Regulation, Plant
Gene Expression Profiling
Transcriptome
Genotype
Seasons
Genes, Plant
Plant Leaves/genetics/physiology
Stress, Physiological/genetics
Plant Roots/genetics/physiology
Plant Proteins/genetics/metabolism

@article {pmid41626333,
year = {2025},
author = {Nan, H and Chen, X and Zhang, J and Zou, M and Shang, E and Guo, X and Kou, K},
title = {Dualistic MADS-box evolution forged legume diversity post-WGD.},
journal = {Frontiers in plant science},
volume = {16},
number = {},
pages = {1740598},
pmid = {41626333},
issn = {1664-462X},
abstract = {The MADS-box gene family plays a central role in plant development and adaptation, yet its evolutionary history in legumes is remarkably complex. In this study, we performed a pangenomic analysis across 52 legume species, identifying 4,872 MADS-box genes and reconstructing their phylogeny into 16 subfamilies. Our analysis uncovered a pervasive dualistic evolutionary model driven by distinct duplication mechanisms. Structurally, the genes fall into two categories: the compact, intron-poor Type I and the complex, intron-rich Type II. We demonstrate that whole-genome duplication (WGD) serves as the major driver (42.2%) behind the expansion of the conserved core genome, which includes key floral regulators such as the "ABCDE model" genes. These WGD-derived genes are under strong purifying selection, thereby ensuring developmental stability. In contrast, small-scale duplication (SSD) fuels the expansion of the dynamic periphery, primarily composed of Type I genes and stress-responsive clades, which evolve under relaxed selection and promote lineage-specific innovation-as strikingly exemplified by the massive tandem expansion of the SVP subfamily in Prosopis. Pangenome analysis confirmed that WGD-derived genes were enriched in the conserved core genome, underpinning essential functions, whereas SSD-derived genes dominated the variable genome and acted as a source of genetic novelty. Transcriptome analysis in soybean identified four organ-specific expression modules, predominantly comprising Type II core genes. Under biotic and abiotic stress, WGD-derived gene pairs exhibited prominent asymmetric expression. The expression divergence was validated by qRT-PCR. Overall, our findings establish a unified framework for MADS-box gene evolution in legumes, illustrating how divergent duplication mechanisms and selective pressures have collectively shaped a gene family critical to both evolutionary innovation and developmental stability.},
}

@article {pmid41625147,
year = {2026},
author = {Brůna, T and Sreedasyam, A and Harder, AM and Lovell, JT},
title = {Evolutionary and methodological considerations when interpreting gene presence-absence variation in pangenomes.},
journal = {NAR genomics and bioinformatics},
volume = {8},
number = {1},
pages = {lqag011},
pmid = {41625147},
issn = {2631-9268},
mesh = {*Genome, Plant ; Molecular Sequence Annotation ; *Evolution, Molecular ; *Glycine max/genetics ; *Gossypium/genetics ; *Genetic Variation ; *Genomics/methods ; },
abstract = {While graph-based pangenomes have become a standard and interoperable foundation for comparisons across multiple reference genomes, integrating protein-coding gene annotations across pangenomes in a single 'pangene set' remains challenging, both because of methodological inconsistency and biological presence-absence variation (PAV). Here, we review and experimentally evaluate the root of genome annotation and pangene set inconsistency using two polyploid plant pangenomes: cotton and soybean, which were chosen because of their existing diverse high-quality genomic resources and the known importance of gene PAV in their respective breeding programs. We first demonstrate that building pangene sets across different genome resources is highly error prone: PAV calculated directly from the genome annotations hosted on public repositories recapitulates structure in annotation methods and not biological sequence differences. Re-annotation of all genomes with a single identical pipeline largely resolves the broadest stroke issues; however, substantial challenges remain, including a surprisingly common case where exactly identical sequences have different gene model structural annotations. Combined, these results clearly show that pangenome gene model annotations must be carefully integrated before any biological inference can be made regarding sequence evolution, gene copy-number, or PAV.},
}

*Genome, Plant
Molecular Sequence Annotation
*Evolution, Molecular
*Glycine max/genetics
*Gossypium/genetics
*Genetic Variation
*Genomics/methods

@article {pmid41624418,
year = {2026},
author = {Yu, C and Li, W and Jiang, Y and Yang, Q and Gan, G and Cai, L and Li, W and Wang, Y},
title = {Graph pan-genome advances genetic discoveries and the improvement of eggplant.},
journal = {Horticulture research},
volume = {13},
number = {1},
pages = {uhaf248},
pmid = {41624418},
issn = {2662-6810},
abstract = {Eggplant is one of the most important solanaceous vegetable crops worldwide. To explore its genomic diversity, we assembled two T2T-level reference genomes from the African eggplant 'Y11' (Solanum aethiopicum L.) and the cultivated variety 'Gui5' (Solanum melongena L.) with genome sizes of 1.10 and 1.13 Gb, respectively. The contigs N50 lengths are 94.2 and 93.9 Mb, with annotations of 37 324 and 40 300 protein-coding genes correspondingly. We also sequenced 238 germplasms, primarily local and cultivated varieties from China, Southeast Asia, Europe, and Africa, identifying 7 853 531 high-quality single nucleotide polymorphisms. Phylogenetic trees and population structures suggest that the domestication of Chinese eggplants occurred later than in Southeast Asia and subsequently diverged into northern and southern groups within China, evolving relatively independently with limited genetic flow between these two groups. Their diversity is significantly lower than that of Southeast Asia and Europe. By selecting 22 representative accessions and four chromosome-level genomes, we constructed an Asian-representative eggplant pan-genome, assembling 463.94 Mb of nonreference sequences. Of these sequences, 38.3% are core genes, 46.9% are dispensable genes, and 14.9% are unique genes. Presence/absence variation genes were found to be highly associated with stress resistance in eggplants. Genome-wide association studies identified 946 SNPs and 9605 genes significantly associated with 10 important traits. Notably, genes involved in zeatin biosynthesis closely linked to plant auxins significantly impact fruit size and shape attributes, playing a crucial role in eggplant yield. This high-quality reference genome alongside the pan-genome will provide valuable insights into eggplant breeding advancement.},
}

@article {pmid41621535,
year = {2026},
author = {Liao, X and Xi, Y and Liao, B and Xiao, S and Guo, S and Hu, H and Huang, Z and Dou, D and Chen, S and Xu, J},
title = {Chromosome-level genome of wild-simulated Panax ginseng identifies SNP markers for germplasm and medicinal quality evaluation.},
journal = {Journal of advanced research},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.jare.2026.01.062},
pmid = {41621535},
issn = {2090-1224},
abstract = {INTRODUCTION: Panax ginseng C. A. Mey., a precious traditional medicinal herb, demonstrates diverse pharmacological activities, including immunomodulation and anti-fatigue effects. However, prolonged cultivation has led to germplasm admixture and cultivar degeneration, resulting in inconsistent quality that severely compromises its medicinal value and industrial standardization. Therefore, establishing accurate and efficient germplasm evaluation tools is critical for ensuring the quality of P. ginseng medicinal materials.

OBJECTIVES: To integrate whole-genome sequencing and chemical fingerprinting for ginseng germplasm identification and quality consistency assessment.

METHODS: Chromosome-level genomes of ginseng from Jilin (JA) and Liaoning (FC) were assembled using PacBio HiFi, Illumina, and Hi-C technologies. Gene family identification and phylogenetic analysis were performed across 13 representative species. Using the JA genome as the reference, we constructed a pan-genome incorporating 7 ginseng genomes to dissect gene repertoire composition and structural variation distribution across ginseng populations. Population structure analysis with 76 individual ginseng samples revealed genetic diversity, and its integration with HPLC chemical fingerprints provided a joint assessment of quality consistency.

RESULTS: We assembled two chromosome-level genomes and, through comparative genomics, revealed significant expansion of ginsenoside biosynthesis-related gene families and subgenome divergence. The core gene set accounted for 54.1% of the pan-genome, indicating high genetic conservation. SNP distribution patterns from population resequencing enabled the development of germplasm-specific molecular markers and a genetic-chemical integrated evaluation model.

CONCLUSION: The molecular marker system and genetic-chemical joint assessment developed here provide reliable novel tools for germplasm identification and quality control, advancing standardization in the ginseng industry.},
}

@article {pmid41621533,
year = {2026},
author = {Yang, YH and Yao, CY and Lin, MJ and Huang, KT and Lin, YH and Huang, YH and Chiu, IH and Lai, SK and Chen, CY and Yang, YC and Hsu, CL and Hsu, JS and Chen, CY and Chen, PL},
title = {Unmasking human T cell receptor germline diversity: 335 novel alleles identified in 47 Pangenome reference individuals using the gAIRR Suite.},
journal = {Journal of advanced research},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.jare.2026.01.053},
pmid = {41621533},
issn = {2090-1224},
abstract = {INTRODUCTION: The adaptive immune receptor repertoire (AIRR), also referred to as expressed AIRR (exprAIRR) for clarity, comprises V(D)J-recombined T cell receptors (TR) and immunoglobulins (IG), and is central to adaptive immunity. Accurate exprAIRR profiling depends on a comprehensive and population-representative germline gene set encoding AIRR (gAIRR). In addition to serving as the reference for AIRR-seq, gAIRR alleles themselves are increasingly recognized as contributors to immune-related phenotypes, including disease susceptibility, variable vaccine responsiveness, and adverse immune events OBJECTIVES: Current germline TR references form an essential foundation, but based on scientific inference, likely represent only a portion of true human diversity. Some alleles lack flanking genomic information, and several populations remain underrepresented-constraints rooted in earlier sequencing methodologies. This study aims to substantially expand these references by resolving full-length TR alleles and their flanking regions across ancestrally diverse individuals.

METHODS: We analyzed 47 high-quality, phased diploid genomes from the Human Pangenome Reference Consortium (HPRC) using the gAIRR Suite. All novel alleles were crosschecked using two orthogonal pipelines: gAIRR-annotate (assembly-based annotation) and gAIRR-seq/gAIRR-call (targeted short-read sequencing and genotyping).

RESULTS: We identified 335 novel TR alleles-305 TRV and 30 TRJ-representing 91.6% and 30.9% increases over IMGT records (v3.1.41; accessed 2025-04-19), respectively. Many novel alleles occurred at substantial frequencies, particularly among individuals of African ancestry. We further established a comprehensive flanking sequence database, including recombination signal sequences (RSS), and documented allele-specific variations in these regions. Functional annotation showed that several novel alleles exhibit altered coding potential, including transitions to pseudogene or open reading frames (ORFs) status.

CONCLUSION: This study significantly expands the known landscape of human TR germline diversity and provides a rigorously validated, population-diverse resource comprising novel alleles, flanking sequences, RSS profiles, and supporting analytical tools. These improved gAIRR references are essential for accurate germline genotyping and exprAIRR profiling, and will enable improved detection of immunogenetic associations. Our findings advance precision immunogenomics and support the development of ancestry-independent yet diversity-comprehensive genotyping, vaccines, and immunotherapies.},
}

@article {pmid41617692,
year = {2026},
author = {Yang, L and Gao, Y and Kuhn, KL and Bhowmik, N and Li, W and Zanton, G and Fang, L and Cole, JB and Li, C and Baldwin Vi, RL and Van Tassell, CP and Rosen, BD and Ma, L and Smith, TPL and Liu, GE},
title = {Phased-assembly-driven pangenome graphs for structural variant genotyping and complex trait mapping in dairy cattle.},
journal = {Nature communications},
volume = {},
number = {},
pages = {},
doi = {10.1038/s41467-026-68807-4},
pmid = {41617692},
issn = {2041-1723},
abstract = {Structural variants are an underexplored source of genetic diversity. As part of the FarmGTEx Project, here we report a Holstein breed-specific pangenome graph (H20D) using Minigraph-Cactus and 40 phased haploid assemblies from 20 cows. H20D outperforms both assembly- and read-based long-read callers, and far exceeds short-read approaches, identifying over 10,000 additional structural variants per sample. It also significantly improves structural variant detection and genotyping relative to graphs built across breeds or from fewer/unphased assemblies, with particular advantages in complex regions. Using H20D, we genotype variants in 173 cattle and performed a GWAS, where a larger fraction of structural variants than SNPs reach genome-wide significance, implicating them as potential causal variants. Together, these results demonstrate the power of phased, within-breed pangenome graphs for accurate SV genotyping and trait mapping in dairy cattle.},
}

@article {pmid41616024,
year = {2026},
author = {Miao, J and Li, D},
title = {TEvarSim: A genome simulator for transposable element (TE) variants.},
journal = {PLoS computational biology},
volume = {22},
number = {1},
pages = {e1013933},
doi = {10.1371/journal.pcbi.1013933},
pmid = {41616024},
issn = {1553-7358},
abstract = {Transposable element (TE) variants, the presence or absence of TE sequences such as LINE-1, Alu, SVA, and endogenous retroviruses, are a major source of genomic diversity and play critical roles in human health, evolution, and disease. As interest in TE variants grows, developing related methods and tools for detection has become increasingly important. However, rigorous benchmarking of TE variant detection methods remains limited due to the lack of accurate and scalable TE variant simulation platforms and the absence of reliable ground truth data. Here, we developed TEvarSim, a novel TE variant simulator that generates TE-containing genomic data in multiple formats, including genomes, short- and long-read sequencing data, and VCF files. TEvarSim supports both random and real-world TE insertions and deletions, including variants derived from pangenome graphs. It can rapidly simulate hundreds to thousands of synthetic chromosomes or genomes and model natural variation at the haplotype, individual, and population levels, making it well suited for large-scale studies. In addition, TEvarSim can directly compare simulated VCF files with TEs reported by TE detection tools, streamlining the benchmarking of TE genotyping methods. TEvarSim provides an all-in-one toolkit for simulating, evaluating, and improving TE variant detection, advancing our ability to accurately study TEs in health and disease in various species.},
}

@article {pmid41614785,
year = {2025},
author = {Wang, Z and Wang, J and Wang, Z and Liu, H and Wang, H and Wang, Q and Li, N},
title = {Genome-Wide Identification of Mitochondrial Calcium Uniporter Family Genes in the Tomato Genus and Expression Profilings Under Salt Stress.},
journal = {Current issues in molecular biology},
volume = {47},
number = {12},
pages = {},
doi = {10.3390/cimb47121021},
pmid = {41614785},
issn = {1467-3045},
support = {xjnkywdzc-2025001-10//Academy of Agricultural Sciences of Xinjiang Uygur Autonomous Region/ ; },
abstract = {The mitochondrial calcium uniporter (MCU) is a key channel controlling mitochondrial Ca[2+] homeostasis, yet its role in plant stress responses remains unclear. Using the tomato pan-genome, this study identified 66 MCU genes across 12 tomato species and grouped them into two distinct evolutionary subfamilies. Phylogenetic, collinearity, and selection pressure analyses revealed that MCU genes are evolutionarily conserved and have undergone strong purifying selection. In addition, one MCU gene located on chromosome 6 appears to have originated before the divergence of monocots and dicots, indicating an ancient evolutionary trajectory. Gene structure and conserved motif analyses confirmed their structural conservation, while promoter cis-element analysis suggested that MCU genes are widely involved in light and hormone responsiveness. Expression profiling under salt stress showed that multiple MCU genes are differentially regulated in a time-dependent manner: SolycMCU1 and SolycMCU2 respond rapidly at early stages, whereas SolycMCU5 and SolycMCU6 are upregulated during middle and late phases. These results highlight the functional diversification of MCU genes in tomato under salt stress. This study provides the first comprehensive evolutionary and functional analysis of the tomato MCU gene family, offering insights into their stress-regulatory mechanisms and potential use in breeding salt-tolerant tomatoes.},
}

@article {pmid41612190,
year = {2026},
author = {Ontano, A and Sim, SB and Jenkins, J and Geib, SM and Childers, AK and Scheffler, B and Vaughn, J},
title = {Independent centromeric expansions define giant hornet genomes.},
journal = {BMC genomics},
volume = {},
number = {},
pages = {},
doi = {10.1186/s12864-025-12512-x},
pmid = {41612190},
issn = {1471-2164},
support = {8042-30500-002-000-D//Agricultural Research Service/ ; 6066-21310-006-000-D//Agricultural Research Service/ ; 8042-21000-291-046-I//Animal and Plant Health Inspection Service/ ; },
}

@article {pmid41605290,
year = {2026},
author = {Shi, L and Zhang, M and Zheng, R and Kwok, LY and Zhang, W},
title = {Comparative genomics reveals two major lineages of Bifidobacterium adolescentis in the human gut, driven by divergent adaptation in China and the United States.},
journal = {Journal of advanced research},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.jare.2026.01.071},
pmid = {41605290},
issn = {2090-1224},
abstract = {INTRODUCTION: Bifidobacterium adolescentis is a key beneficial member of the human gut microbiota, but its genomic diversity and evolutionary drivers across human populations remain poorly characterized.

OBJECTIVES: Understanding genomic functional heterogeneity and evolutionary patterns in human gut-derived B. adolescentis.

METHODS: We performed a comparative genomic analysis of 395B. adolescentis, mainly from China (n = 169) and the U.S. (n = 146), with smaller sets from Australia, Italy, and the United Kingdom, to investigate functional heterogeneity and evolutionary mechanisms. Our analysis integrated core and pan-genome architecture, phylogenomics, single nucleotide polymorphism (SNP)-based population structure, carbohydrate-active enzyme profiles, CRISPR-Cas systems, antibiotic resistance genes, and recombination dynamics.

RESULTS: The pan-genome was open and highly plastic. Phylogenetic reconstruction identified two major clades with strong geographic stratification: Chinese isolates predominantly clustered in Clade B, while U.S. isolates grouped in Clade A. Functional annotation showed regional specialization in carbohydrate-active enzymes, with Chinese isolates enriched in glycosyltransferase families and U.S. isolates in carbohydrate-binding module and carboxylesterase families, likely reflecting dietary adaptations. Genomic islands were hotspots for horizontal gene transfer, harboring region-specific carbohydrate-active enzymes and antibiotic resistance genes such as tet(W/32/O) and ermX, which were frequently located in Chinese isolates. Recombination was found to be the primary driver of genetic diversity, with recombination-to-mutation ratios approaching and exceeding 3.0 in Chinese and U.S. isolates. Linkage disequilibrium decay further supported higher recombination rates in these populations.

CONCLUSION: B. adolescentis has diverged into two major genomic lineages, primarily associated with isolates from China and the U.S. This divergence reflects adaptation to distinct host-associated ecological factors, such as diet, antibiotic exposure, and lifestyle, and is predominantly driven by extensive homologous recombination rather than point mutations. These findings highlight how regional selective pressures shape the genomic and functional landscape of this key gut symbiont.},
}

@article {pmid41599631,
year = {2025},
author = {Allemailem, KS},
title = {Pangenome-Guided Reverse Vaccinology and Immunoinformatics Approach for Rational Design of a Multi-Epitope Subunit Vaccine Candidate Against the Multidrug-Resistant Pathogen Chromobacterium violaceum: A Computational Immunopharmacology Perspective.},
journal = {Pharmaceuticals (Basel, Switzerland)},
volume = {19},
number = {1},
pages = {},
doi = {10.3390/ph19010029},
pmid = {41599631},
issn = {1424-8247},
support = {QU-APC-2025//Deanship of Graduate Studies and Scientific Research at Qassim University/ ; },
abstract = {Background: Chromobacterium violaceum is an emerging multidrug-resistant (MDR) Gram-negative bacterium associated with severe septicemia, abscess formation, and high mortality, particularly in immunocompromised individuals. Increasing antimicrobial resistance and the absence of approved vaccines underscore the urgent need for alternative preventive strategies. Traditional vaccine approaches are often inadequate against genetically diverse MDR pathogens, prompting the use of computational immunology and reverse vaccinology for vaccine design. Objectives: This study aimed to design and characterize a novel multi-epitope subunit vaccine (MEV) candidate against C. violaceum using a comprehensive pangenome-guided subtractive proteomics and immunoinformatics pipeline to identify conserved antigenic targets capable of eliciting strong immune responses. Methods: Comparative genomic analysis across eight C. violaceum strains identified 3144 core genes. Subtractive proteomics filtering yielded two essential, non-homologous, surface-accessible, and antigenic proteins-penicillin-binding protein 1A (Pbp1A) and organic solvent tolerance protein (LptD)-as vaccine targets. Cytotoxic T-lymphocyte (CTL), helper T-lymphocyte (HTL), and B-cell epitopes were predicted and integrated into a 272-amino-acid MEV construct adjuvanted with human β-defensin-4A using optimal linkers. The construct was evaluated through structural modeling, molecular docking with TLR4, molecular dynamics simulation, immune simulation, and in silico cloning into the pET-28a(+) vector. Results: The MEV construct exhibited strong antigenicity, non-allergenicity, and non-toxicity, with stable tertiary structure and favorable physicochemical properties. Docking and dynamics simulations demonstrated high binding affinity and stability with TLR4 (ΔG = -16.2 kcal/mol), while immune simulations predicted durable humoral and cellular immune responses with broad population coverage (≈89%). Codon optimization confirmed high expression potential in E. coli K12. Conclusions: The pangenome-guided immunoinformatics approach enabled the identification of conserved antigenic proteins and rational design of a promising multi-epitope vaccine candidate against MDR C. violaceum. The construct exhibits favorable immunogenic and structural features, supporting its potential for experimental validation and future development as a preventive immunotherapeutic against emerging MDR pathogens.},
}