@article {pmid40684816,
year = {2025},
author = {Zhao, H and Han, Z and Liu, S and Qi, X and Li, H and Wang, S},
title = {A proposed Lawsonella species with distinct functional features from L. clevelandensis revealed by metagenomics.},
journal = {Genomics},
volume = {117},
number = {5},
pages = {111089},
doi = {10.1016/j.ygeno.2025.111089},
pmid = {40684816},
issn = {1089-8646},
mesh = {Metagenomics ; *Genome, Bacterial ; Phylogeny ; RNA, Ribosomal, 16S/genetics ; Metagenome ; },
abstract = {The skin serves as a vital barrier, largely influenced by the commensal microbiota. Lawsonella clevelandensis, the currently recognized sole species in the genus Lawsonella, has gained increased attention as a cause of abscesses but is often overlooked due to its fastidious nature, which make its isolation and culture in the lab particularly challenging. Here, a comprehensive genomic investigation of Lawsonella was conducted using a cultivation-free metagenomic approach, focusing on 39 newly generated and 12 publicly available genomes. A novel species represented by 43 metagenome-assembled genomes (MAGs) was proposed based on mono-clade formation, 16S rDNA sequence similarity and genome-wide average nucleotide identity (ANI) values. All these MAGs were initially identified as L. clevelandensis A by GTDB-tk. Here, we designed them as 'Candidatus Lawsonella tjsk' sp. nov.. Distinct genomic characteristics between this newly proposed species and L. clevelandensis were observed. Significant fundamental functional differences between the two species were revealed by species-specific genes.},
}

Metagenomics
*Genome, Bacterial
Phylogeny
RNA, Ribosomal, 16S/genetics
Metagenome

@article {pmid40289066,
year = {2025},
author = {Dos Reis, JBA and Steindorff, AS and Lorenzi, AS and Pinho, DB and do Vale, HMM and Pappas, GJ},
title = {How genomics can help unravel the evolution of endophytic fungi.},
journal = {World journal of microbiology & biotechnology},
volume = {41},
number = {5},
pages = {153},
pmid = {40289066},
issn = {1573-0972},
support = {Funding code 001//Coordenação de Aperfeiçoamento de Pessoal de Nível Superior-Brasil (CAPES)/ ; No. DE-AC02-05CH11231//Office of Science of the U.S. Department of Energy/ ; FAPESC N.º: 1580/2024//Fundação de Amparo à Pesquisa e Inovação do Estado de Santa Catarina/ ; },
mesh = {*Endophytes/genetics/physiology ; *Fungi/genetics/classification/physiology ; *Genomics/methods ; Symbiosis ; *Plants/microbiology ; *Genome, Fungal ; *Evolution, Molecular ; Biological Evolution ; Secondary Metabolism ; },
abstract = {Endophytic fungi (EFs) form intimate associations with plants, residing within their tissues without causing apparent harm. Understanding the evolution of endophytic fungal genomes is essential for uncovering the mechanisms that drive their symbiotic relationships with host plants. This review explores the dynamic interactions between EFs and host plants, focusing on the evolutionary processes that shape their genomes. We highlighted key genomic adaptations promoting their endophytic lifestyle, including genes involved in plant cell wall degradation, secondary metabolite production, and stress tolerance. By combining genomic data with ecological and physiological information, this review provides a comprehensive understanding of the coevolutionary dynamics between EFs and host plants. Moreover, it provides insights that help elucidate the complex interdependencies governing their symbiotic interactions.},
}

*Endophytes/genetics/physiology
*Fungi/genetics/classification/physiology
*Genomics/methods
Symbiosis
*Plants/microbiology
*Genome, Fungal
*Evolution, Molecular
Biological Evolution
Secondary Metabolism

@article {pmid38336730,
year = {2024},
author = {Hu, Z and Zhou, L and Tao, X and Li, P and Zheng, X and Zhang, W and Tan, Z},
title = {Antimicrobial resistance survey and whole-genome analysis of nosocomial P. Aeruginosa isolated from eastern Province of China in 2016-2021.},
journal = {Annals of clinical microbiology and antimicrobials},
volume = {23},
number = {1},
pages = {12},
pmid = {38336730},
issn = {1476-0711},
support = {NAUSY-MS12//the Sanya Institute of Nanjing Agricultural University/ ; ZDYF2022XDNY236//Hainan Province Science and Technology Special Fund/ ; },
mesh = {Humans ; Aged ; Infant, Newborn ; Anti-Bacterial Agents/pharmacology/therapeutic use ; Pseudomonas aeruginosa/genetics ; *Cross Infection ; Drug Resistance, Bacterial/genetics ; Microbial Sensitivity Tests ; *Pseudomonas Infections/epidemiology/drug therapy ; Piperacillin/pharmacology ; Hospitals ; },
abstract = {BACKGROUND: Pseudomonas aeruginosa is a major Gram-negative pathogen that can exacerbate lung infections in the patients with cystic fibrosis, which can ultimately lead to death.

METHODS: From 2016 to 2021, 103 strains of P. aeruginosa were isolated from hospitals and 20 antibiotics were used for antimicrobial susceptibility determination. Using next-generation genome sequencing technology, these strains were sequenced and analyzed in terms of serotypes, ST types, and resistance genes for epidemiological investigation.

RESULTS: The age distribution of patients ranged from 10 days to 94 years with a median age of 69 years old. The strains were mainly isolated from sputum (72 strains, 69.9%) and blood (14 strains, 13.6%). The size of these genomes ranged from 6.2 Mb to 7.4 Mb, with a mean value of 6.5 Mb. In addition to eight antibiotics that show inherent resistance to P. aeruginosa, the sensitivity rates for colistin, amikacin, gentamicin, ceftazidime, piperacillin, piperacillin-tazobactam, ciprofloxacin, meropenem, aztreonam, imipenem, cefepime and levofloxacin were 100%, 95.15%, 86.41%, 72.82%, 71.84%, 69.90%, 55.34%, 52.43%, 50.49%, 50.49%, 49.51% and 47.57% respectively, and the carriage rate of MDR strains was 30.69% (31/101). Whole-genome analysis showed that a total of 50 ST types were identified, with ST244 (5/103) and ST1076 (4/103) having a more pronounced distribution advantage. Serotype predictions showed that O6 accounted for 29.13% (30/103), O11 for 23.30% (24/103), O2 for 18.45% (19/103), and O1 for 11.65% (12/103) of the highest proportions. Notably, we found a significantly higher proportion of ExoU in P. aeruginosa strains of serotype O11 than in other cytotoxic exoenzyme positive strains. In addition to this, a total of 47 crpP genes that mediate resistance to fluoroquinolones antibiotics were found distributed on 43 P. aeruginosa strains, and 10 new variants of CrpP were identified, named 1.33, 1.34, 1.35, 1.36, 1.37, 1.38, 1.39, 1.40, 1.41 and 7.1.

CONCLUSIONS: We investigated the antibiotic susceptibility of clinical isolates of P. aeruginosa and genomically enriched the diversity of P. aeruginosa for its prophylactic and therapeutic value.},
}

Humans
Aged
Infant, Newborn
Anti-Bacterial Agents/pharmacology/therapeutic use
Pseudomonas aeruginosa/genetics
*Cross Infection
Drug Resistance, Bacterial/genetics
Microbial Sensitivity Tests
*Pseudomonas Infections/epidemiology/drug therapy
Piperacillin/pharmacology
Hospitals

@article {pmid37629524,
year = {2023},
author = {Ruperao, P and Rangan, P and Shah, T and Thakur, V and Kalia, S and Mayes, S and Rathore, A},
title = {The Progression in Developing Genomic Resources for Crop Improvement.},
journal = {Life (Basel, Switzerland)},
volume = {13},
number = {8},
pages = {},
pmid = {37629524},
issn = {2075-1729},
support = {INV-037010/GATES/Bill & Melinda Gates Foundation/United States ; },
abstract = {Sequencing technologies have rapidly evolved over the past two decades, and new technologies are being continually developed and commercialized. The emerging sequencing technologies target generating more data with fewer inputs and at lower costs. This has also translated to an increase in the number and type of corresponding applications in genomics besides enhanced computational capacities (both hardware and software). Alongside the evolving DNA sequencing landscape, bioinformatics research teams have also evolved to accommodate the increasingly demanding techniques used to combine and interpret data, leading to many researchers moving from the lab to the computer. The rich history of DNA sequencing has paved the way for new insights and the development of new analysis methods. Understanding and learning from past technologies can help with the progress of future applications. This review focuses on the evolution of sequencing technologies, their significant enabling role in generating plant genome assemblies and downstream applications, and the parallel development of bioinformatics tools and skills, filling the gap in data analysis techniques.},
}

@article {pmid37461107,
year = {2023},
author = {Schmidt, M and Kutzner, A},
title = {MSV: a modular structural variant caller that reveals nested and complex rearrangements by unifying breakends inferred directly from reads.},
journal = {Genome biology},
volume = {24},
number = {1},
pages = {170},
pmid = {37461107},
issn = {1474-760X},
mesh = {*Software ; *Genomics ; Genome ; Computational Biology ; Sequence Analysis, DNA ; High-Throughput Nucleotide Sequencing ; },
abstract = {Structural variant (SV) calling belongs to the standard tools of modern bioinformatics for identifying and describing alterations in genomes. Initially, this work presents several complex genomic rearrangements that reveal conceptual ambiguities inherent to the representation via basic SV. We contextualize these ambiguities theoretically as well as practically and propose a graph-based approach for resolving them. For various yeast genomes, we practically compute adjacency matrices of our graph model and demonstrate that they provide highly accurate descriptions of one genome in terms of another. An open-source prototype implementation of our approach is available under the MIT license at https://github.com/ITBE-Lab/MA .},
}

*Software
*Genomics
Genome
Computational Biology
Sequence Analysis, DNA
High-Throughput Nucleotide Sequencing

@article {pmid37025151,
year = {2023},
author = {Wang, J and Hu, H and Liang, X and Tahir Ul Qamar, M and Zhang, Y and Zhao, J and Ren, H and Yan, X and Ding, B and Guo, J},
title = {High-quality genome assembly and comparative genomic profiling of yellowhorn (Xanthoceras sorbifolia) revealed environmental adaptation footprints and seed oil contents variations.},
journal = {Frontiers in plant science},
volume = {14},
number = {},
pages = {1147946},
pmid = {37025151},
issn = {1664-462X},
abstract = {Yellowhorn (Xanthoceras sorbifolia) is a species of deciduous tree that is native to Northern and Central China, including Loess Plateau. The yellowhorn tree is a hardy plant, tolerating a wide range of growing conditions, and is often grown for ornamental purposes in parks, gardens, and other landscaped areas. The seeds of yellowhorn are edible and contain rich oil and fatty acid contents, making it an ideal plant for oil production. However, the mechanism of its ability to adapt to extreme environments and the genetic basis of oil synthesis remains to be elucidated. In this study, we reported a high-quality and near gap-less yellowhorn genome assembly, containing the highest genome continuity with a contig N50 of 32.5 Mb. Comparative genomics analysis showed that 1,237 and 231 gene families under expansion and the yellowhorn-specific gene family NB-ARC were enriched in photosynthesis and root cap development, which may contribute to the environmental adaption and abiotic stress resistance of yellowhorn. A 3-ketoacyl-CoA thiolase (KAT) gene (Xso_LG02_00600) was identified under positive selection, which may be associated with variations of seed oil content among different yellowhorn cultivars. This study provided insights into environmental adaptation and seed oil content variations of yellowhorn to accelerate its genetic improvement.},
}

@article {pmid35699868,
year = {2023},
author = {Jalal, K and Khan, K and Hayat, A and Ahmad, D and Alotaibi, G and Uddin, R and Mashraqi, MM and Alzamami, A and Aurongzeb, M and Basharat, Z},
title = {Mining therapeutic targets from the antibiotic-resistant Campylobacter coli and virtual screening of natural product inhibitors against its riboflavin synthase.},
journal = {Molecular diversity},
volume = {27},
number = {2},
pages = {793-810},
pmid = {35699868},
issn = {1573-501X},
mesh = {Animals ; Humans ; *Anti-Bacterial Agents/pharmacology ; *Campylobacter coli ; Riboflavin Synthase ; },
abstract = {Campylobacter coli resides in the intestine of several commonly consumed animals, as well as water and soil. It leads to campylobacteriosis when humans eat raw/undercooked meat or come into contact with infected animals. A common manifestation of the infection is fever, nausea, headache, and diarrhea. Increasing antibiotic resistance is being observed in this pathogen. The increased incidence of C. coli infection, and post-infection complications like Guillain-Barré syndrome, make it an important pathogen. It is essential to find novel therapeutic targets and drugs against it, especially with the emergence of antibiotic-resistant strains. In the current study, genomes of 89 antibiotic-resistant strains of C. coli were downloaded from the PATRIC database. Potent drug targets (n = 36) were prioritized from the core genome (n = 1,337 genes) of this species. Riboflavin synthase was selected as a drug target and pharmacophore-based virtual screening was performed to predict its inhibitors from the NPASS (n = ~ 30,000 compounds) natural product library. The top three docked compounds (NPC115144, NPC307895, and NPC470462) were selected for dynamics simulation (for 50 ns) and ADMET profiling. These identified compounds appear safe for targeting this pathogen and can be further validated by experimental analysis before clinical trials.},
}

Animals
Humans
*Anti-Bacterial Agents/pharmacology
*Campylobacter coli
Riboflavin Synthase

@article {pmid35672841,
year = {2022},
author = {Sedaghatjoo, S and Mishra, B and Forster, MK and Becker, Y and Keilwagen, J and Killermann, B and Thines, M and Karlovsky, P and Maier, W},
title = {Comparative genomics reveals low levels of inter- and intraspecies diversity in the causal agents of dwarf and common bunt of wheat and hint at conspecificity of Tilletia caries and T. laevis.},
journal = {IMA fungus},
volume = {13},
number = {1},
pages = {11},
pmid = {35672841},
issn = {2210-6340},
support = {2812NA128//German Federal Ministry of Food and Agriculture (BMEL) based on a decision of the German Federal Parliament/ ; 2812NA017//German Federal Ministry of Food and Agriculture (BMEL) based on a decision of the German Federal Parliament/ ; },
abstract = {Tilletia caries and T. laevis, which are the causal agents of common bunt, as well as T. controversa, which causes dwarf bunt of wheat, threaten especially organic wheat farming. The three closely related fungal species differ in their teliospore morphology and partially in their physiology and infection biology. The gene content as well as intraspecies variation in these species and the genetic basis of their separation is unknown. We sequenced the genome of four T. caries, five T. controversa, and two T. laevis and extended this dataset with five publicly available ones. The genomes of the three species displayed microsynteny with up to 94.3% pairwise aligned regions excluding repetitive regions. The majority of functionally characterized genes involved in pathogenicity, life cycle, and infection of corn smut, Ustilago maydis, were found to be absent or poorly conserved in the draft genomes and the biosynthetic pathway for trimethylamine in Tilletia spp. could be different from bacteria. Overall, 75% of the identified protein-coding genes comprising 84% of the total predicted carbohydrate utilizing enzymes, 72.5% putatively secreted proteins, and 47.4% of effector-like proteins were conserved and shared across all 16 isolates. We predicted nine highly identical secondary metabolite biosynthesis gene clusters comprising in total 62 genes in all species and none were species-specific. Less than 0.1% of the protein-coding genes were species-specific and their function remained mostly unknown. Tilletia controversa had the highest intraspecies genetic variation, followed by T. caries and the lowest in T. laevis. Although the genomes of the three species are very similar, employing 241 single copy genes T. controversa was phylogenetically distinct from T. caries and T. laevis, however these two could not be resolved as individual monophyletic groups. This was in line with the genome-wide number of single nucleotide polymorphisms and small insertions and deletions. Despite the conspicuously different teliospore ornamentation of T. caries and T. laevis, a high degree of genomic identity and scarcity of species-specific genes indicate that the two species could be conspecific.},
}

@article {pmid35564967,
year = {2022},
author = {Ud-Din, M and Albutti, A and Ullah, A and Ismail, S and Ahmad, S and Naz, A and Khurram, M and Haq, MU and Afsheen, Z and Bakri, YE and Salman, M and Shaker, B and Tahir Ul Qamar, M},
title = {Vaccinomics to Design a Multi-Epitopes Vaccine for Acinetobacter baumannii.},
journal = {International journal of environmental research and public health},
volume = {19},
number = {9},
pages = {},
pmid = {35564967},
issn = {1660-4601},
mesh = {*Acinetobacter baumannii/genetics ; Anti-Bacterial Agents ; Computational Biology/methods ; Epitopes, T-Lymphocyte ; Molecular Docking Simulation ; Vaccines, Subunit ; },
abstract = {Antibiotic resistance (AR) is the result of microbes' natural evolution to withstand the action of antibiotics used against them. AR is rising to a high level across the globe, and novel resistant strains are emerging and spreading very fast. Acinetobacter baumannii is a multidrug resistant Gram-negative bacteria, responsible for causing severe nosocomial infections that are treated with several broad spectrum antibiotics: carbapenems, β-lactam, aminoglycosides, tetracycline, gentamicin, impanel, piperacillin, and amikacin. The A. baumannii genome is superplastic to acquire new resistant mechanisms and, as there is no vaccine in the development process for this pathogen, the situation is more worrisome. This study was conducted to identify protective antigens from the core genome of the pathogen. Genomic data of fully sequenced strains of A. baumannii were retrieved from the national center for biotechnological information (NCBI) database and subjected to various genomics, immunoinformatics, proteomics, and biophysical analyses to identify potential vaccine antigens against A. baumannii. By doing so, four outer membrane proteins were prioritized: TonB-dependent siderphore receptor, OmpA family protein, type IV pilus biogenesis stability protein, and OprD family outer membrane porin. Immuoinformatics predicted B-cell and T-cell epitopes from all four proteins. The antigenic epitopes were linked to design a multi-epitopes vaccine construct using GPGPG linkers and adjuvant cholera toxin B subunit to boost the immune responses. A 3D model of the vaccine construct was built, loop refined, and considered for extensive error examination. Disulfide engineering was performed for the stability of the vaccine construct. Blind docking of the vaccine was conducted with host MHC-I, MHC-II, and toll-like receptors 4 (TLR-4) molecules. Molecular dynamic simulation was carried out to understand the vaccine-receptors dynamics and binding stability, as well as to evaluate the presentation of epitopes to the host immune system. Binding energies estimation was achieved to understand intermolecular interaction energies and validate docking and simulation studies. The results suggested that the designed vaccine construct has high potential to induce protective host immune responses and can be a good vaccine candidate for experimental in vivo and in vitro studies.},
}

*Acinetobacter baumannii/genetics
Anti-Bacterial Agents
Computational Biology/methods
Epitopes, T-Lymphocyte
Molecular Docking Simulation
Vaccines, Subunit

@article {pmid34773248,
year = {2022},
author = {Gann, ER and Truchon, AR and Papoulis, SE and Dyhrman, ST and Gobler, CJ and Wilhelm, SW},
title = {Aureococcus anophagefferens (Pelagophyceae) genomes improve evaluation of nutrient acquisition strategies involved in brown tide dynamics.},
journal = {Journal of phycology},
volume = {58},
number = {1},
pages = {146-160},
doi = {10.1111/jpy.13221},
pmid = {34773248},
issn = {1529-8817},
mesh = {Harmful Algal Bloom ; Nitrogen/metabolism ; Nutrients ; *Stramenopiles/genetics/metabolism ; },
abstract = {The pelagophyte Aureococcus anophagefferens causes harmful brown tide blooms in marine embayments on three continents. Aureococcus anophagefferens was the first harmful algal bloom species to have its genome sequenced, an advance that evidenced genes important for adaptation to environmental conditions that prevail during brown tides. To expand the genomic tools available for this species, genomes for four strains were assembled, including three newly sequenced strains and one assembled from publicly available data. These genomes ranged from 57.11 to 73.62 Mb, encoding 13,191-17,404 potential proteins. All strains shared ~90% of their encoded proteins as determined by homology searches and shared most functional orthologs as determined by KEGG, although each strain also possessed coding sequences with unique functions. Like the original reference genome, the genomes assembled in this study possessed genes hypothesized to be important in bloom proliferation, including genes involved in organic compound metabolism and growth at low light. Cross-strain informatics and culture experiments suggest that the utilization of purines is a potentially important source of organic nitrogen for brown tides. Analyses of metatranscriptomes from a brown tide event demonstrated that use of a single genome yielded a lower read mapping percentage (~30% of library reads) as compared to a database generated from all available genomes (~43%), suggesting novel information about bloom ecology can be gained from expanding genomic space. This work demonstrates the continued need to sequence ecologically relevant algae to understand the genomic potential and their ecology in the environment.},
}

Harmful Algal Bloom
Nitrogen/metabolism
Nutrients
*Stramenopiles/genetics/metabolism

@article {pmid34682706,
year = {2021},
author = {Ullah, A and Ahmad, S and Ismail, S and Afsheen, Z and Khurram, M and Tahir Ul Qamar, M and AlSuhaymi, N and Alsugoor, MH and Allemailem, KS},
title = {Towards A Novel Multi-Epitopes Chimeric Vaccine for Simulating Strong Immune Responses and Protection against Morganella morganii.},
journal = {International journal of environmental research and public health},
volume = {18},
number = {20},
pages = {},
pmid = {34682706},
issn = {1660-4601},
mesh = {Computational Biology ; Epitopes, T-Lymphocyte ; Immunity ; Molecular Docking Simulation ; *Morganella morganii/genetics ; *Vaccines ; },
abstract = {Morganella morganii is one of the main etiological agents of hospital-acquired infections and no licensed vaccine is available against the pathogen. Herein, we designed a multi-epitope-based vaccine against M. morganii. Predicted proteins from fully sequenced genomes of the pathogen were subjected to a core sequences analysis, followed by the prioritization of non-redundant, host non-homologous and extracellular, outer membrane and periplasmic membrane virulent proteins as vaccine targets. Five proteins (TonB-dependent siderophore receptor, serralysin family metalloprotease, type 1 fimbrial protein, flagellar hook protein (FlgE), and pilus periplasmic chaperone) were shortlisted for the epitope prediction. The predicted epitopes were checked for antigenicity, toxicity, solubility, and binding affinity with the DRB*0101 allele. The selected epitopes were linked with each other through GPGPG linkers and were joined with the cholera toxin B subunit (CTBS) to boost immune responses. The tertiary structure of the vaccine was modeled and blindly docked with MHC-I, MHC-II, and Toll-like receptors 4 (TLR4). Molecular dynamic simulations of 250 nanoseconds affirmed that the designed vaccine showed stable conformation with the receptors. Further, intermolecular binding free energies demonstrated the domination of both the van der Waals and electrostatic energies. Overall, the results of the current study might help experimentalists to develop a novel vaccine against M. morganii.},
}

Computational Biology
Epitopes, T-Lymphocyte
Immunity
Molecular Docking Simulation
*Morganella morganii/genetics
*Vaccines

@article {pmid34325069,
year = {2021},
author = {Haag, S and Häussler, S},
title = {Quo vadis clinical diagnostic microbiology?.},
journal = {Clinical microbiology and infection : the official publication of the European Society of Clinical Microbiology and Infectious Diseases},
volume = {27},
number = {11},
pages = {1562-1564},
doi = {10.1016/j.cmi.2021.07.013},
pmid = {34325069},
issn = {1469-0691},
}

@article {pmid32252628,
year = {2020},
author = {Grytten, I and Rand, KD and Nederbragt, AJ and Sandve, GK},
title = {Assessing graph-based read mappers against a baseline approach highlights strengths and weaknesses of current methods.},
journal = {BMC genomics},
volume = {21},
number = {1},
pages = {282},
pmid = {32252628},
issn = {1471-2164},
mesh = {Computational Biology/*methods ; Genome, Human ; High-Throughput Nucleotide Sequencing/methods ; Humans ; Sequence Alignment ; },
abstract = {BACKGROUND: Graph-based reference genomes have become popular as they allow read mapping and follow-up analyses in settings where the exact haplotypes underlying a high-throughput sequencing experiment are not precisely known. Two recent papers show that mapping to graph-based reference genomes can improve accuracy as compared to methods using linear references. Both of these methods index the sequences for most paths up to a certain length in the graph in order to enable direct mapping of reads containing common variants. However, the combinatorial explosion of possible paths through nearby variants also leads to a huge search space and an increased chance of false positive alignments to highly variable regions.

RESULTS: We here assess three prominent graph-based read mappers against a hybrid baseline approach that combines an initial path determination with a tuned linear read mapping method. We show, using a previously proposed benchmark, that this simple approach is able to improve overall accuracy of read-mapping to graph-based reference genomes.

CONCLUSIONS: Our method is implemented in a tool Two-step Graph Mapper, which is available at https://github.com/uio-bmi/two_step_graph_mapperalong with data and scripts for reproducing the experiments. Our method highlights characteristics of the current generation of graph-based read mappers and shows potential for improvement for future graph-based read mappers.},
}

Computational Biology/*methods
Genome, Human
High-Throughput Nucleotide Sequencing/methods
Humans
Sequence Alignment

@article {pmid32181686,
year = {2020},
author = {Mun, T and Kuhnle, A and Boucher, C and Gagie, T and Langmead, B and Manzini, G},
title = {Matching Reads to Many Genomes with the r-Index.},
journal = {Journal of computational biology : a journal of computational molecular cell biology},
volume = {27},
number = {4},
pages = {514-518},
pmid = {32181686},
issn = {1557-8666},
support = {R01 AI141810/AI/NIAID NIH HHS/United States ; R01 GM118568/GM/NIGMS NIH HHS/United States ; },
mesh = {Databases, Genetic ; Genome/*genetics ; *Genomics ; Humans ; Sequence Alignment/methods ; Sequence Analysis, DNA/*methods ; Software ; },
abstract = {The r-index is a tool for compressed indexing of genomic databases for exact pattern matching, which can be used to completely align reads that perfectly match some part of a genome in the database or to find seeds for reads that do not. This article shows how to download and install the programs ri-buildfasta and ri-align; how to call ri-buildfasta on an FASTA file to build an r-index for that file; and how to query that index with ri-align.},
}

Databases, Genetic
Genome/*genetics
*Genomics
Humans
Sequence Alignment/methods
Sequence Analysis, DNA/*methods
Software

@article {pmid31712258,
year = {2020},
author = {Busche, M and Pucker, B and Viehöver, P and Weisshaar, B and Stracke, R},
title = {Genome Sequencing of Musa acuminata Dwarf Cavendish Reveals a Duplication of a Large Segment of Chromosome 2.},
journal = {G3 (Bethesda, Md.)},
volume = {10},
number = {1},
pages = {37-42},
pmid = {31712258},
issn = {2160-1836},
mesh = {Aneuploidy ; *Chromosome Duplication ; Chromosomes, Plant/genetics ; Musa/*genetics ; },
abstract = {Different Musa species, subspecies, and cultivars are currently investigated to reveal their genomic diversity. Here, we compare the genome sequence of one of the commercially most important cultivars, Musa acuminata Dwarf Cavendish, against the Pahang reference genome assembly. Numerous small sequence variants were detected and the ploidy of the cultivar presented here was determined as triploid based on sequence variant frequencies. Illumina sequence data also revealed a duplication of a large segment on the long arm of chromosome 2 in the Dwarf Cavendish genome. Comparison against previously sequenced cultivars provided evidence that this duplication is unique to Dwarf Cavendish. Although no functional relevance of this duplication was identified, this example shows the potential of plants to tolerate such aneuploidies.},
}

Aneuploidy
*Chromosome Duplication
Chromosomes, Plant/genetics
Musa/*genetics

@article {pmid26254872,
year = {2015},
author = {Garza, DR and Dutilh, BE},
title = {From cultured to uncultured genome sequences: metagenomics and modeling microbial ecosystems.},
journal = {Cellular and molecular life sciences : CMLS},
volume = {72},
number = {22},
pages = {4287-4308},
pmid = {26254872},
issn = {1420-9071},
mesh = {Computer Simulation ; Ecosystem ; Genome, Microbial/*genetics ; Genome, Viral/*genetics ; High-Throughput Nucleotide Sequencing/*methods ; Metagenomics/*methods ; Microbial Consortia/genetics ; Microbiological Techniques/*methods ; Models, Theoretical ; Viruses/genetics ; },
abstract = {Microorganisms and the viruses that infect them are the most numerous biological entities on Earth and enclose its greatest biodiversity and genetic reservoir. With strength in their numbers, these microscopic organisms are major players in the cycles of energy and matter that sustain all life. Scientists have only scratched the surface of this vast microbial world through culture-dependent methods. Recent developments in generating metagenomes, large random samples of nucleic acid sequences isolated directly from the environment, are providing comprehensive portraits of the composition, structure, and functioning of microbial communities. Moreover, advances in metagenomic analysis have created the possibility of obtaining complete or nearly complete genome sequences from uncultured microorganisms, providing important means to study their biology, ecology, and evolution. Here we review some of the recent developments in the field of metagenomics, focusing on the discovery of genetic novelty and on methods for obtaining uncultured genome sequences, including through the recycling of previously published datasets. Moreover we discuss how metagenomics has become a core scientific tool to characterize eco-evolutionary patterns of microbial ecosystems, thus allowing us to simultaneously discover new microbes and study their natural communities. We conclude by discussing general guidelines and challenges for modeling the interactions between uncultured microorganisms and viruses based on the information contained in their genome sequences. These models will significantly advance our understanding of the functioning of microbial ecosystems and the roles of microbes in the environment.},
}

Computer Simulation
Ecosystem
Genome, Microbial/*genetics
Genome, Viral/*genetics
High-Throughput Nucleotide Sequencing/*methods
Metagenomics/*methods
Microbial Consortia/genetics
Microbiological Techniques/*methods
Models, Theoretical
Viruses/genetics

@article {pmid41240163,
year = {2025},
author = {Perez-Hernandez, C and Aldaroub, J and Barth, ZK and Aylward, FO},
title = {A novel lineage of large aquatic bacteriophages identified through metagenomics.},
journal = {Archives of virology},
volume = {170},
number = {12},
pages = {253},
pmid = {41240163},
issn = {1432-8798},
support = {#2141862//National Science Foundation/ ; },
mesh = {*Metagenomics ; *Bacteriophages/genetics/classification/isolation & purification ; *Genome, Viral ; Phylogeny ; },
abstract = {"Jumbo phages" are tailed phages with genome sizes >200 kbp and physical dimensions reaching up to 0.45 μm. Although jumbo phages represent only a small fraction of the isolated phages to date, metagenomic surveys have shown that they are broadly distributed in a wide range of environments. In this study, we surveyed metagenomic data from aquatic systems and identified 25 genomes from a heretofore-undescribed lineage of jumbo phages with genomes reaching up to 307 kbp. We refer to these phages as "moraphages", from the Gaelic word 'mór', for large. Moraphages represent a diverse lineage with inter-genome average amino acid identity (AAI) ranging from 39 to 95%, and our pan-genomic analysis identified only 26 viral orthologous groups (VOGs) found in at least 80% of the genomes. Our phylogenomic analysis suggests that moraphages are distant relatives of a recently described lineage of huge phages from marine sediment. Moraphages lack much of the genetic machinery found in other lineages of large phages, but they have a range of genes that may be used to take over host cellular machinery and subvert host defenses, such as glutamine synthetases, antitoxin genes, and chaperones. The predicted hosts of most moraphages are members of the phylum Bacteroidota, and some encode homologs of the chaperones DnaK and DnaJ that bear evidence of recent gene transfer from members of the order Flavobacteriales. Our work sheds light on the emerging diversity of large phages that are found across the biosphere.},
}

*Metagenomics
*Bacteriophages/genetics/classification/isolation & purification
*Genome, Viral
Phylogeny

@article {pmid41234744,
year = {2025},
author = {Chen, S and Wang, H and Ju, C and Zhang, P and Ren, Y and Chen, Y and Yi, X and Zhang, J and Zhang, S and Xiang, X},
title = {Rapid identification of Acinetobacter baumannii using novel specific molecular targets derived from pan-genome analysis and its clinical application.},
journal = {Frontiers in microbiology},
volume = {16},
number = {},
pages = {1669811},
pmid = {41234744},
issn = {1664-302X},
abstract = {Acinetobacter baumannii is a pathogen capable of causing severe hospital-acquired infections such as ventilator-associated pneumonia and bacteremia, accounting for over 80% of nosocomial infections. Current nucleic acid tests (NATs) for A. baumannii suffer from limitations in specificity and sensitivity due to reliance on suboptimal targets. Therefore, this study aimed to identify novel, highly specific molecular targets for A. baumannii NATs using pan-genome analysis. A total of 9 specific molecular targets for A. baumannii were screened from 642 genome sequences by pan-genome analysis: outO, ureE, rplY, bioF, menH_3, hemW, paaF_1, smpB and ppaX. These specific species targets have been verified by BLAST and PCR of non-target strains to have 100% specificity for A. baumannii. The specificity of the 9 target genes was verified by PCR, and 3 pairs of different PCR primers were designed for each target gene to determine the best sensitivity of PCR method for each target. Corresponding qPCR detection methods of 9 targets was also established and that of ureE was screened with the lowest detection limit of 10[-7] ng/μL. The qPCR method based on the ureE gene can achieve rapid, sensitive and accurate detection of A. baumannii in actual samples with interference from non-target bacteria. After verification of 23 samples, the qPCR method based on the mined target met the requirements in sensitivity, specificity and efficiency, and was consistent with the national verification method. ‌These results confirm that novel pan-genome targets with excellent generalizability among A. baumannii strains enhance detection accuracy in hospital environments, bringing hope for rapid clinical identification, timely interventions, and reduced mortality.},
}

@article {pmid41231250,
year = {2025},
author = {Jung, H and Kim, YR and Cho, E and Lee, JS and Yoon, JH and Sukhoom, A and Kim, W},
title = {Description of Albimonas marina sp. nov., isolated from sea sand on the Yellow Sea Coast.},
journal = {Current microbiology},
volume = {83},
number = {1},
pages = {20},
pmid = {41231250},
issn = {1432-0991},
mesh = {Phylogeny ; RNA, Ribosomal, 16S/genetics ; Base Composition ; DNA, Bacterial/genetics ; Fatty Acids/analysis/chemistry ; *Sand/microbiology ; *Seawater/microbiology ; Republic of Korea ; Bacterial Typing Techniques ; Nucleic Acid Hybridization ; Sequence Analysis, DNA ; Genome, Bacterial ; Seashore ; },
abstract = {A Gram-stain-negative, anaerobic, short rod-shaped bacterium, designated as CAU 1670[T], was isolated from a sea sand sample collected from Masiran Beach, Republic of Korea. Optimal growth conditions for the bacterium were identified as growth media containing 0-3% (w/v) NaCl at 30 °C and pH 5.5. Strain CAU 1670[T] exhibited high 16S rRNA gene sequence similarity with Albimonas pacifica CGMCC 1.11030[T] (97.8% similarity) and Albimonas donghaensis DSM 17,890[T] (94.8% similarity). The phylogeny tree based on the 16 S rRNA gene and core housekeeping gene sequences showed that strain CAU 1670[T] belonged to the genus Albimonas. The major fatty acids included summed feature 8 (C18:1 ω7c and/or C18:1 ω6c), and the predominant respiratory quinone was Q-10. The G + C content of the type strain genome was 72.6%. The average nucleotide identity and digital DNA-DNA hybridization values between strain CAU 1670[T] and reference strains were 78.5-86.4% and 22.1-31.0%, respectively. Pan-genome analysis demonstrated that strain CAU 1670[T] and reference strains shared 2,010 core genes. Based on phenotypic, phylogenetic, and chemotaxonomic characteristics, strain CAU 1670[T] represents a novel species within the genus Albimonas, for which the name Albimonas marina sp. nov. is proposed. The type strain is CAU 1670[T] (= KCTC 92734[T]; = MCCC 1K08481[T]).},
}

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

@article {pmid41231018,
year = {2025},
author = {Mendonça-Santos, T and Abrahão, J and Del-Bem, L-E},
title = {Integrative genomic analyses support the division of the extended Asfarviridae clade into multiple viral families.},
journal = {Journal of virology},
volume = {},
number = {},
pages = {e0133725},
doi = {10.1128/jvi.01337-25},
pmid = {41231018},
issn = {1098-5514},
abstract = {Giant viruses continue to challenge our understanding of virology, blurring boundaries of what a virus can be. The so-called "extended Asfarviridae"- such as African swine fever virus, faustovirus, kaumoebavirus, pacmanvirus, and AbALV-has long puzzled taxonomists. By integrating comparative genomics, pangenomics, and phylogenomics, we show these lineages are deeply divergent, forming multiple families rather than one. This work underscores the huge unexplored diversity of giant viruses and demonstrates the value of integrative genomic analyses for proper taxonomic delineation.},
}

@article {pmid41227682,
year = {2025},
author = {Phayakka, P and Vongkamjan, K and Khrongsee, P and Subramaniam, K and Mordmueng, A and Pelyuntha, W},
title = {Detection, Genomic Characterization, and Antibiotic Susceptibility of Salmonella Anatum SPBM3 Isolated from Plant-Based Meat.},
journal = {Foods (Basel, Switzerland)},
volume = {14},
number = {21},
pages = {},
pmid = {41227682},
issn = {2304-8158},
support = {WU67272//Walailak University/ ; },
abstract = {Plant-based meat (PBM) products have rapidly grown in popularity due to increasing consumer demand for sustainable, ethical, and health-oriented food alternatives. However, these novel products may pose microbiological risks similar to traditional meats, including contamination by Salmonella spp. In this study, PBM samples (n = 63), including raw products (ground pork, mushroom, and burger) and cooked products (chicken tender, chicken breast, nugget, and beef), were collected from local retail markets in Bangkok, Thailand. The prevalence of Salmonella spp. was assessed by calculating the proportion of confirmed positive samples relative to the total number of PBM products tested. Additionally, the genomic characteristics and antibiotic susceptibility of Salmonella isolated from PBM were also investigated. From the result, Salmonella enterica was detected in 2.44% (1/41) of raw PBM samples, whereas no contamination was observed in cooked PBM products (0/22). Serovar identification revealed the isolate to be S. Anatum. Whole genome sequencing (WGS) analysis revealed the genome of S. Anatum SPBM3 consisted of 4,726,256 base pairs with 52.15% GC content, encoding 4717 coding sequences (CDS). Pangenomic analyses placed S. Anatum SPBM3 within a distinct sub-cluster closely related to pathogenic Salmonella strains previously reported, confirming its identity as part of the S. enterica lineage. The genome harbored 67 antimicrobial resistance genes, 5 prophage elements, and 305 key virulence determinants. Phenotypically, the isolate exhibited susceptibility to most tested antibiotics but showed intermediate resistance to streptomycin, ciprofloxacin, and colistin. Our findings highlight the potential microbial risks associated with PBM products and emphasize the importance of genomic surveillance to ensure food safety and public health protection as dietary preferences evolve toward non-traditional food matrices.},
}

@article {pmid41226516,
year = {2025},
author = {Sum, DKC and Chong, YY and Tan, JL},
title = {Comparative Analyses Suggest Genome Stability and Plasticity in Stenotrophomonas maltophilia.},
journal = {International journal of molecular sciences},
volume = {26},
number = {21},
pages = {},
doi = {10.3390/ijms262110477},
pmid = {41226516},
issn = {1422-0067},
mesh = {*Stenotrophomonas maltophilia/genetics/pathogenicity ; *Genome, Bacterial ; *Genomic Instability ; Gene Transfer, Horizontal ; Interspersed Repetitive Sequences ; Evolution, Molecular ; Virulence/genetics ; Phylogeny ; Linkage Disequilibrium ; },
abstract = {Stenotrophomonas maltophilia (S. maltophilia) is a multidrug-resistant opportunistic pathogen. There are an increasing number of case reports on S. maltophilia infections in recent years, and the species is becoming a public health concern. Many studies have focused on profiling and pangenome of the species, particularly on their antibiotic resistance and virulence genes. However, there is a lack of studies on mobile genetic elements (MGEs), a subset of pangenome that significantly contributes to the diversity, stability, and plasticity of a population. In this study, 20 genomes of S. maltophilia were downloaded from the NCBI Genome database. The genomes were subjected to profiling of MGEs, their impact on the population structures, and the evaluation of evolutionary trends of the core genomes. The cataloguing of MGEs indicated active horizontal gene transfer events in the S. maltophilia's population. Multiple virulence and drug resistance genes were predicted within and outside of the MGEs. We observed multiple chromosomal rearrangements in the genomes, most likely caused by MGEs, affecting up to approximately 50% of a single genome sequence. A high number of linkage disequilibrium sites were also predicted in the core genomes. This study provides insights into stability in the core and plasticity in the accessory regions in the S. maltophilia population.},
}

*Stenotrophomonas maltophilia/genetics/pathogenicity
*Genome, Bacterial
*Genomic Instability
Gene Transfer, Horizontal
Interspersed Repetitive Sequences
Evolution, Molecular
Virulence/genetics
Phylogeny
Linkage Disequilibrium

@article {pmid41159561,
year = {2025},
author = {Romero Picazo, D and Muccino, F and Kwasigroch, P and Hartmann, L and Hülter, NF and Dagan, T},
title = {Evolution of the Plant-Associated Pantoea was Accompanied by Plasmid Domestication Events.},
journal = {Molecular biology and evolution},
volume = {42},
number = {11},
pages = {},
pmid = {41159561},
issn = {1537-1719},
mesh = {*Pantoea/genetics ; *Plasmids/genetics ; *Evolution, Molecular ; Phylogeny ; Domestication ; Plants/microbiology ; },
abstract = {Plasmids are important drivers of evolutionary transformations and ecological adaptation in prokaryotes. Plasmids supplying the host with beneficial functions may become domesticated and gain a stable inheritance within the host lineage. Domesticated plasmids may comprise core genes that are present in all taxon members. The origin of plasmid core genes remains poorly understood and alternative scenarios entailing gene translocation or genetic redundancy are debated. Studying plasmid evolution in the plant-associated Pantoea, we show that the large Pantoea plasmids (LPP-1 and LPP-2) are domesticated. We infer that the LPP-1 was acquired in the ancestor of plant-associated Pantoea species. The LPP-2 acquisition is traced to the ancestor of plant growth-promoting species. We show that both plasmids are vertically inherited and the LPP-1 replication is furthermore coordinated with chromosome replication. Both plasmids harbor core gene families at the genus (LPP-1) or species (LPP-2) level. Using phylogenomics we infer a deep divergence between plasmid and chromosomal core genes, indicating rare gene translocation between the replicons. Our results suggest that the LPP-1 and LPP-2 acquisition introduced genetic redundancy with chromosomal genes, that was followed by successive waves of differential gene loss. The domestication of both plasmids likely contributed to species divergence in Pantoea.},
}

*Pantoea/genetics
*Plasmids/genetics
*Evolution, Molecular
Phylogeny
Domestication
Plants/microbiology

@article {pmid41224755,
year = {2025},
author = {Gupta, S and Almeida, A},
title = {Integration of metagenome-assembled genomes with clinical isolates expands the genomic landscape of gut-associated Klebsiella pneumoniae.},
journal = {Nature communications},
volume = {16},
number = {1},
pages = {9959},
pmid = {41224755},
issn = {2041-1723},
support = {MR/W016184/1//RCUK | Medical Research Council (MRC)/ ; },
abstract = {Klebsiella pneumoniae is an opportunistic pathogen causing diseases ranging from gastrointestinal disorders to severe liver abscesses. While clinical isolates of K. pneumoniae have been extensively studied, less is known about asymptomatic variants colonizing the human gut across diverse populations. Developments in genome-resolved metagenomics have offered unprecedented access to metagenome-assembled genomes (MAGs), expanding the known bacterial diversity within the gut microbiome. Here we analysed 656 human gut-derived K. pneumoniae genomes (317 MAGs, 339 isolates) from 29 countries to investigate the population structure and genomic landscape of gut-associated lineages. Over 60% of MAGs were found to belong to new sequence types, highlighting a large uncharacterized diversity of K. pneumoniae missing among sequenced clinical isolates. In particular, integrating MAGs nearly doubled gut-associated K. pneumoniae phylogenetic diversity, and uncovered 86 MAGs with >0.5% genomic distance compared to 20,792 Klebsiella isolate genomes from various sources. Pan-genome analyses identified 214 genes exclusively detected among MAGs, with 107 predicted to encode putative virulence factors. Notably, combining MAGs and isolates revealed genomic signatures linked to health and disease and more accurately classified disease and carriage states compared to isolates alone. These findings showcase the value of metagenomics to understand pathogen evolution and diversity with implications for public health surveillance strategies.},
}

@article {pmid41223054,
year = {2025},
author = {Liu, Z and Li, M and Wang, Y and Li, T and Li, W and Xing, L and Du, H and He, Q},
title = {Genomic insights into karyotype evolution and adaptive mechanisms in Polygonaceae species.},
journal = {Cell reports},
volume = {44},
number = {11},
pages = {116558},
doi = {10.1016/j.celrep.2025.116558},
pmid = {41223054},
issn = {2211-1247},
abstract = {Polygonaceae, with ecological versatility and global distribution, is an ideal system for investigating plant adaptation. However, the genomic mechanisms underlying its karyotype evolution and environmental resilience remain unclear. We herein present chromosome-level genomes of 11 species from 10 Polygonaceae genera. Our analyses reveal that Gypsy retrotransposons are key drivers of genome size variations in Polygonaceae. We reconstructed a Polygonaceae ancestral karyotype comprising 28 proto-chromosomes and elucidated evolutionary trajectories via extensive chromosomal rearrangements. Furthermore, we constructed a cross-genus super pan-genome for Polygonaceae, identifying 80,055 gene families, of which 9,845 (12.30%) are core gene families. Private genes are found to contribute significantly to interspecific differences in adaptability. Notably, gene copy number variations are identified as a critical factor influencing adaptations to diverse niches involving species-specific increases in metabolic pathways. This study provides a genomic framework for Polygonaceae karyotype plasticity and adaptive innovation, offering insights into plant evolution under environmental challenges.},
}

@article {pmid41221579,
year = {2025},
author = {Narechania, A and Gopalakrishnan, S and Gilbert, MTP},
title = {What We Talk About When We Talk About Microbial Species.},
journal = {Molecular ecology},
volume = {},
number = {},
pages = {e70171},
doi = {10.1111/mec.70171},
pmid = {41221579},
issn = {1365-294X},
abstract = {Genome annotation, alignment and phylogenetics are at the centre of most studies in evolutionary genomics. These techniques function best when rooted in prior work. Genes are mined from new genomes using evidence from old gene models. These genomes are aligned to well-worn references to create matrices for tree reconstruction. Trees are often populated with well-characterised genomes to add context to the newly sequenced. Genome inference traces a line back to model organisms, yoking the analysis of new genomes to layers of previous knowledge. Here, we present an alternative approach that uses unannotated and unaligned sequence to understand the information diversity of sequence ensembles. Any set of genomes can comprise our sequence ensemble. In a pandemic context, a sequence ensemble might be clinically isolated strains from one day. In a systematic context, a sequence ensemble could be the pangenome available for a clade. The normal bioinformatics playbook would have us align. But we instead compress. A sequence ensemble that compresses easily contains lower information diversity. For pandemics, we can use curves of information diversity to trace genomic novelty and monitor selective sweeps in new strains. For systematics, we can calculate compressibility quickly across all known bacterial taxa, levelling the criteria for species across clades. If we tolerate data loss, we can go one step further and capture structural evolution as we compress. Our approach sacrifices a lot. We skip many of the products of modern bioinformatics like variation anchored to known genes or genome alignment to prescribed references or pangenome graphs. But we gain speed, breadth and the ability to rapidly respond to novelty.},
}

@article {pmid41219210,
year = {2025},
author = {Gaccione, L and Toppino, L and Bolger, M and Schmidt, M and Tassone, MR and Sulli, M and Idahl, E and Alonso, D and Aprea, G and Ferrante, P and Lefebvre, V and Boyaci, HF and Schafleitner, R and Gattolin, S and Finkers, R and Brouwer, M and Bovy, A and Prohens, J and Portis, E and Lanteri, S and Rotino, GL and Giuliano, G and Usadel, B and Barchi, L},
title = {Graph-based pangenomes and pan-phenome provide a cornerstone for eggplant biology and breeding.},
journal = {Nature communications},
volume = {16},
number = {1},
pages = {9919},
pmid = {41219210},
issn = {2041-1723},
support = {677379//EC | Horizon 2020 Framework Programme (EU Framework Programme for Research and Innovation H2020)/ ; 101094738//EC | Horizon 2020 Framework Programme (EU Framework Programme for Research and Innovation H2020)/ ; 677379//EC | Horizon 2020 Framework Programme (EU Framework Programme for Research and Innovation H2020)/ ; 101094738//EC | Horizon 2020 Framework Programme (EU Framework Programme for Research and Innovation H2020)/ ; },
abstract = {Eggplant (Solanum melongena L.) is a major Solanaceous crop of Asian origin, but genomic resources remain limited compared to related species. Here, a core collection of 368 accessions spanning global diversity of S. melongena and wild relatives is phenotyped for agronomic, disease resistance and fruit metabolomic traits and resequenced. Additionally, 40 chromosome-level assemblies of S. melongena, its progenitor S. insanum and the allied species S. incanum enable the construction of two graph-based pangenomes, capturing broad genetic variation. We demonstrate the power of these datasets by identifying major loci controlling prickliness and resistance to Fusarium oxysporum f. sp. melongenae, driven by SVs affecting the LONELY GUY 3 gene and a resistance gene cluster, respectively, as well as a mutation in a GDSL-like esterase/lipase gene altering the levels of dicaffeoyl-quinic acids. These findings provide a cornerstone for pangenome-assisted breeding, enabling detailed analyses of genetic diversity, domestication history, and trait evolution in eggplant.},
}

@article {pmid41217162,
year = {2025},
author = {Liu, J-p and Zhou, Q and Zhang, C and Wu, Y and Ma, X-j and Qi, R},
title = {Pan-genome classification of the virulence spectrum of Bartonella and the variation of heme-binding protein virulence factor in isolates from the Tibetan Plateau.},
journal = {Microbiology spectrum},
volume = {},
number = {},
pages = {e0046525},
doi = {10.1128/spectrum.00465-25},
pmid = {41217162},
issn = {2165-0497},
abstract = {This study classifies Bartonella species based on virulence factors and explores the genomic characteristics of Bartonella isolates from the Qinghai-Tibet Plateau to understand their ecological adaptations. PCR detection and isolation culture of Bartonella were performed on 50 captured pikas in their habitats on the Qinghai-Tibet Plateau. The Qinghai-Tibet isolates were identified through gltA and rpoB phylogenetic analysis, ANI analysis, and single-copy homologous gene phylogeny. Reference genomes of Bartonella species were analyzed for virulence classification via pan-genome and virulence factor comparisons. Bartonella species were categorized into five virulence groups, including a high-virulence group containing Bartonella henselae, B. quintana, B. kosoyi, B. koehlerae, and B. tribocorum. B. bacilliformis lacked Trw and VirB/VirD4, while the copy number of flagella was significantly higher. Bartonella grahamii infected up to 12% of plateau pikas from the Qinghai-Tibet Plateau. B. grahamii plateau isolate had the most unique genes (5.6%), with 65.06% of them unknown in function, followed by replication, recombination, and repair (11.64%), and amino acid transport and metabolism (5.48%). The heme-binding protein virulence factor in B. grahamii plateau isolate exhibited 14 amino acid mutations, leading to changes in the protein-binding sites. Bartonella can be classified into five virulence groups. In the high-virulence group, the less common B. tribocorum and B. kosoyi are included. Trw and VirB/VirD4 gradually replaced ancestral flagella genes in Bartonella evolution. The isolated strains have more unique genes due to plateau pikas' unique physiological traits, which may be connected to adaptation to the high-altitude host environment.IMPORTANCEBartonella species are emerging zoonotic pathogens capable of infecting a wide range of mammals, including humans. Understanding their virulence and evolution is critical for assessing potential public health risks. This study classifies Bartonella species based on virulence factors, revealing species with potential human pathogenicity. The Qinghai-Tibet Plateau, with its extreme environment, may drive bacterial adaptation. By analyzing Bartonella isolates from plateau pikas, we identified unique genes and virulence factor variations, providing insights into bacterial evolution in high-altitude hosts. Our findings highlight the significance of pan-genome analysis in identifying pathogenic traits and evaluating zoonotic risks. This study enhances our understanding of Bartonella adaptation, aiding in the clinical identification and characterization of highly pathogenic strains.},
}

@article {pmid41214748,
year = {2025},
author = {Afsharyan, NP and Golicz, AA and Snowdon, RJ},
title = {Pangenomic structural variant patterns reflect evolutionary diversification in Brassica napus.},
journal = {Genome biology},
volume = {26},
number = {1},
pages = {381},
pmid = {41214748},
issn = {1474-760X},
support = {SN 14/27-1//Deutsche Forschungsgemeinschaft/ ; },
abstract = {BACKGROUND: Understanding genetic diversity is crucial for enhancing crop productivity. This study explores species-wide genome structural variation (SV) and its role in intraspecific and ecogeographical diversification of Brassica napus, a recently evolved, globally important allopolyploid crop.

RESULTS: We perform whole-genome long-read DNA-sequencing and construct reference-guided genome assemblies for 94 accessions, including winter-type, spring-type, and East Asian oilseed, along with kale forms and swedes/rutabagas. We investigate pangenomic patterns of SVs and determine pangenome-wide distributions and frequencies of inversions, gene presence-absence variants, and collective SVs including insertions and deletions. Results reveal pangenome-wide patterns for insertions, deletions, inversions, and large chromosomal deletions/duplications, reflecting evolutionary diversification across morphotypes and ecotypes. Collective SVs are unevenly distributed and biased toward subgenome A, with asymmetrical selection pattern favoring subgenome C. Selection signatures for inversions exhibit no subgenome asymmetry; however, increased selection signal strength and frequency are detected in paracentric chromosome regions, highlighting evolutionary significance. Analysis of the candidate loci under selection identifies regions for collective SVs and inversions, harboring genes for organ formation, cell division and expansion in swede, and stress responses in East Asian oilseed rape. Large chromosomal duplications and deletions distinguish swede from oilseed rape, particularly in subgenome C, including copy-number variation in flowering-time genes BnFLC.C09 and BnATX2.C08, and cell wall development gene BnCEL2.C08.

CONCLUSIONS: These findings underscore functional and evolutionary significance of pangenomic SV formation during Brassica napus diversification. Information on SV patterns with putative functional relevance provides breeding insights, particularly for developing molecular markers to optimize performance of Brassica napus and other Brassica crops.},
}

@article {pmid41213900,
year = {2025},
author = {Bu, C and Zhang, H and Zhang, F and Liang, W and Gao, H and Zhao, J and Lv, F and Xue, R and Liu, Q and Zhang, Z and Jin, Z and Xiao, J},
title = {PGAP2: A comprehensive toolkit for prokaryotic pan-genome analysis based on fine-grained feature networks.},
journal = {Nature communications},
volume = {16},
number = {1},
pages = {9865},
pmid = {41213900},
issn = {2041-1723},
support = {32170669//National Natural Science Foundation of China (National Science Foundation of China)/ ; },
abstract = {Pan-genome analysis is a crucial method for studying genomic dynamics. By creating pan-genome maps for prokaryotic organisms, we can gain valuable insights into their genetic diversity and ecological adaptability. However, current analytical methods often struggle to balance accuracy and computational efficiency, and they tend to provide primarily qualitative results. This study introduces PGAP2, an integrated software package that simplifies various processes, including data quality control, pan-genome analysis, and result visualization. PGAP2 facilitates the rapid and accurate identification of orthologous and paralogous genes by employing fine-grained feature analysis within constrained regions. Our systematic evaluation with simulated and gold-standard datasets demonstrates that PGAP2 is more precise, robust, and scalable than state-of-the-art tools for large-scale pan-genome data. Furthermore, PGAP2 introduces four quantitative parameters derived from the distances between or within clusters, enabling detailed characterization of homology clusters. Finally, we validate our quantitative findings by applying PGAP2 to construct a pan-genomic profile of 2794 zoonotic Streptococcus suis strains. This analysis offers new insights into the genetic diversity of S. suis, thereby enhancing our understanding of its genomic structure. PGAP2 is freely available at https://github.com/bucongfan/PGAP2 .},
}

@article {pmid41213172,
year = {2025},
author = {Li, H and Xu, Y and Li, G and Zhang, H and Cui, J and Qiu, Y and Lin, Z and Ji, R and Xu, G and Luo, W and Tang, H and Qiu, S},
title = {Comparative Genomic Analysis of the Obligate Pathogen "Candidatus Phytoplasma australasiaticum" SPWBPT2024.},
journal = {Phytopathology},
volume = {},
number = {},
pages = {},
doi = {10.1094/PHYTO-04-25-0144-R},
pmid = {41213172},
issn = {0031-949X},
abstract = {Sweet potato witches' broom disease caused by phytoplasmas threatens crop productivity in Fujian, China. Here we report a complete phytoplasma genome consisting of a single circular chromosome (680,179 bp with a G+C content of 29.44%) via the next-generation sequencing of sweet potato witches' broom-infected samples. A total of 730 genes were predicted, while two 16S rRNAs were revealed to be identical to sequences in 'Candidatus Phytoplasma australasiaticum'. Following the latest guidelines for the description of phytoplasma species, we have named the strain Candidatus Phytoplasma australasiaticum SPWBPT2024. The genome contained 33 transporters, 35 putative effectors (including SAP11 and SAP54 with multiple copies), and two potential mobile units. Analyses of published peanut and sweet potato phytoplasma genomes revealed the similarities between their effectors and the effectors in this phytoplasma genome. A motif analysis was performed to clarify the difference between the two SAP54 copies in the obtained phytoplasma genome as well as the trends in conserved motifs in other strains. In addition, metabolic pathway-related genes in three genomes were examined, revealing deficiencies in the glycolysis and pyrimidine synthesis pathways. A pan-genome analysis has revealed that the phytoplasma genome is an open genome. To gain further insights into whole-cell metabolic processes, we reconstructed draft genome-scale metabolic models (GEMs) of the genome. This study provides valuable genomic insights into this phytoplasma, characterising conserved and strain-specific SAP effectors, as well as distinct metabolic deficiencies that may help advance research to combat phytoplasma infections, including accurate diagnostics, vector transmission control and antimicrobial interventions.},
}

@article {pmid41212599,
year = {2025},
author = {Acha Alarcon, L and Seguí, G and Piñeiro-Iglesias, B and Svetlicic, E and Kondori, N and Gomila, M and Moore, ERB and Karlsson, R},
title = {Identification of Streptococcus pneumoniae-Specific Proteins by Surface-Shaving Proteomics.},
journal = {Journal of proteome research},
volume = {},
number = {},
pages = {},
doi = {10.1021/acs.jproteome.5c00716},
pmid = {41212599},
issn = {1535-3907},
abstract = {Streptococcus pneumoniae (pneumococcus) is a prominent cause of bacterial pneumonia, meningitis, and septicemia, causing high morbidity and high mortality, particularly in children and the elderly. In this study, proteomics- and genomics-based approaches were used for the identification of pneumococcal protein and peptide biomarkers of S. pneumoniae for diagnostics and prospective targets for treatment. Through a pan-genome analysis, 11 S. pneumoniae strains, demonstrating genetic variation within the species, were selected for proteomic characterization. Mass spectrometry-based proteomics, in combination with bacterial surface-shaving, were used to study the cell-surface proteome of S. pneumoniae. The data obtained from three biological replicates per strain were analyzed to identify and rank the proteins and peptides according to their presence in the strains, as well as their presence in all available S. pneumoniae proteomes (8,892) archived in public databases. Several highly ranked proteins have been described as "species-specific" for S. pneumoniae and as surface-associated virulence factors or demonstrate highly antigenic properties. Proteins (34) previously not recognized as S. pneumoniae-specific were proposed to be novel biomarkers, demonstrating high degrees of prevalence in all analyzed proteomes, with little or no sequence similarities to closely related species but common among the genetically diverse strains included in this study.},
}

@article {pmid41205224,
year = {2025},
author = {Brose, J and Martin, D and Wang, YW and Wood, JC and Vaillancourt, B and Hamilton, JP and Buell, CR},
title = {An allelic resolution gene atlas for tetraploid potato provides insights into tuberization and stress resilience.},
journal = {The Plant journal : for cell and molecular biology},
volume = {124},
number = {3},
pages = {e70557},
doi = {10.1111/tpj.70557},
pmid = {41205224},
issn = {1365-313X},
support = {IOS-2140176//National Science Foundation/ ; 5T32GM142623/NH/NIH HHS/United States ; //University of Georgia/ ; //Georgia Research Alliance/ ; //Georgia Seed Development/ ; },
abstract = {Tubers are modified underground stems that enable asexual, clonal reproduction and serve as a mechanism for overwintering and avoidance of herbivory. Potato (Solanum tuberosum L.) is cultivated for its tubers, which serve as a major crop. Genes responsible for tuber initiation and disease resistance have been characterized in potato including StSP6A, a homolog of flowering time, that functions as a tuberigen, the equivalent of a florigen. To elucidate additional molecular and genetic mechanisms underlying potato biology including tuber initiation, tuber development, and stress responses, we generated a developmental and abiotic/biotic-stress gene expression atlas from 34 tissues and treatments of the tetraploid potato cultivar, Atlantic. Using the haplotype-phased tetraploid Atlantic genome assembly and expression abundances of 129 218 genes, we constructed gene coexpression modules that represent networks associated with distinct developmental stages as well as stress responses. Functional annotations were given to modules and used to identify genes involved in tuberization and stress resilience. Structural variation from a pan-genomic analysis across four cultivated potato genome assemblies as well as domestication and wild introgression data allowed for deeper insights into the modules to identify key genes involved in tuberization and stress responses. This study underscores the importance of transcriptional regulation in tuberization and provides a comprehensive framework for future research on potato development and improvement.},
}

@article {pmid41204087,
year = {2025},
author = {Chugh, K and Xuan, Z},
title = {Revealing the spectrum of extended-core gene variation in the Escherichia coli pan-genome.},
journal = {BMC genomics},
volume = {26},
number = {1},
pages = {1013},
pmid = {41204087},
issn = {1471-2164},
}

@article {pmid41203424,
year = {2025},
author = {Shivakumar, VS and Langmead, B},
title = {Partitioned Multi-MUM finding for scalable pangenomics with MumemtoM.},
journal = {Genome research},
volume = {},
number = {},
pages = {},
doi = {10.1101/gr.280940.125},
pmid = {41203424},
issn = {1549-5469},
abstract = {Pangenome collections are growing to hundreds of high-quality genomes. This necessitates scalable methods for constructing pangenome alignments that can incorporate newly-sequenced assemblies. We previously developed Mumemto, which computes maximal unique matches (multi-MUMs) across pangenomes using compressed indexing. In this work, we introduce MumemtoM (Mumemto Merge), comprising two new partitioning and merging strategies. Both strategies enable highly parallel, memory efficient, and updateable computation of multi-MUMs. One of the strategies, called string-based merging, is also capable of conducting the merges in a way that follows the shape of a phylogenetic tree, naturally yielding the multi-MUM for the tree's internal nodes as well as the root. With these strategies, Mumemto now scales to 474 human haplotypes, the only multi-MUM method able to do so. It also introduces a time-memory tradeoff that allows Mumemto to be tailored to more scenarios, including in resource-limited settings.},
}

@article {pmid41202851,
year = {2025},
author = {Hoffmann, N and Besson, A and Hitte, C and Plassais, J and Derrien, T},
title = {Long Noncoding RNAs in Dogs: Comparative Insights Across Species and Breeds.},
journal = {Annual review of animal biosciences},
volume = {},
number = {},
pages = {},
doi = {10.1146/annurev-animal-030424-073201},
pmid = {41202851},
issn = {2165-8110},
abstract = {Long noncoding RNAs (lncRNAs) have emerged as key regulators of gene expression, yet their annotation and functional characterization remain challenging, especially in nonclassical model organisms. In this review, we explore the landscape of lncRNAs in dogs (Canis lupus familiaris) and other species, highlighting recent advances in genome assemblies, transcriptomic resources, and computational tools for lncRNA discovery. We discuss the advantages of the canine system for studying genotype-phenotype relationships, including its rich breed diversity, well-characterized diseases, and simplified genetic architecture. We describe how both short- and long-read RNA-sequencing technologies, in combination with curated reference annotations from Ensembl and RefSeq, have enabled the detection of thousands of novel canine lncRNAs. However, we also point out discrepancies across assemblies and annotation strategies, which underscore the importance of integrating multi-omic data and refining computational pipelines. Using comparative genomics, we illustrate lncRNA conservation across dog breeds and species and review emerging examples of phenotype-associated or differentially expressed lncRNAs. Finally, we argue for a transition toward pangenome and pan-transcriptome approaches, which can better capture transcript diversity and structural variation across breeds. Such frameworks will be essential for the future functional annotation of lncRNAs and their application to both veterinary and human biomedical research.},
}

@article {pmid41201653,
year = {2025},
author = {Krusenbaum, L and Wissuwa, M},
title = {Low-call-rate SNPs and presence-absence variation identified in the rice pan-genome can improve genomic prediction of rice gene bank accessions.},
journal = {TAG. Theoretical and applied genetics. Theoretische und angewandte Genetik},
volume = {138},
number = {12},
pages = {295},
pmid = {41201653},
issn = {1432-2242},
support = {EXC-2070 - 390732324//Deutsche Forschungsgemeinschaft/ ; },
mesh = {*Oryza/genetics ; *Polymorphism, Single Nucleotide ; *Genome, Plant ; Phenotype ; *Genomics ; Genotype ; Plant Breeding ; },
abstract = {Substantial improvements in genomic prediction accuracy for rice gene bank accessions were achieved by incorporating SNPs of low call rate identified in a recently published rice pan-genome. Introduction of useful genetic variation to breeding populations is a key factor in achieving genetic gain in crop breeding. However, identifying donors from genetic diversity stored in gene banks requires extensive phenotyping, which is not feasible for many traits of interest. Genomic prediction (GP) of phenotypic values has been proposed to overcome this phenotyping bottleneck. A key challenge for GP is the identification of appropriate markers representative of genetic variation causal for phenotypes. Here we report on utilizing single nucleotide polymorphisms (SNPs) from the core and dispensable genomes of a rice pan-genome resource comprising 16 reference sequences. Using a published pan-genome graph, we identified SNPs within structural variations of the dispensable genome. In this SNP set, SNPs of low call rate (CR) were common. Presence-absence variation (PAV) of these SNPs was associated with subpopulation structure, indicating that SNP absence reflects on underlying sequence PAV rather than being solely due to technical errors in SNP detection. To incorporate these SNPs in GP models, we employed modified encoding, retaining information of PAV and nucleotide variation by one-hot encoding (OHE). Adding these to SNP matrices increased prediction accuracies of GP for some traits and subpopulations. Improvements could largely be attributed to the inclusion of PAV. Our results show that the traditional approach of applying strict CR filters to SNPs located in the dispensable genome disregards potentially valuable genetic information not in linkage with SNPs of high CR. The proposed strategy provides a straightforward way to enhance GP performance in rice gene bank accessions.},
}

*Oryza/genetics
*Polymorphism, Single Nucleotide
*Genome, Plant
Phenotype
*Genomics
Genotype
Plant Breeding

@article {pmid41199348,
year = {2025},
author = {Ghozlane, A and Thirion, F and Plaza Oñate, F and Gauthier, F and Le Chatelier, E and Annamalé, A and Almeida, M and Ehrlich, SD and Pons, N},
title = {Accurate profiling of microbial communities for shotgun metagenomic sequencing with Meteor2.},
journal = {Microbiome},
volume = {13},
number = {1},
pages = {227},
pmid = {41199348},
issn = {2049-2618},
support = {ANR-11-DPBS-0001//Metagenopolis/ ; },
abstract = {BACKGROUND: The characterization of complex microbial communities is a critical challenge in microbiome research, as it is essential for understanding the intricate relationships between microorganisms and their environments. Metagenomic profiling has advanced into a multifaceted approach, combining taxonomic, functional, and strain-level profiling (TFSP) of microbial communities. Here, we present Meteor2, a tool that leverages compact, environment-specific microbial gene catalogues to deliver comprehensive TFSP insights from metagenomic samples.

RESULTS: Meteor2 currently supports 10 ecosystems, gathering 63,494,365 microbial genes clustered into 11,653 metagenomic species pangenomes (MSPs). These genes are extensively annotated for KEGG orthology, carbohydrate-active enzymes (CAZymes) and antibiotic-resistant genes (ARGs). In benchmark tests, Meteor2 demonstrated strong performance in TFSP, particularly excelling in detecting low-abundance species. When applied to shallow-sequenced datasets, Meteor2 improved species detection sensitivity by at least 45% for both human and mouse gut microbiota simulations compared to MetaPhlAn4 or sylph. For functional profiling, Meteor2 improved abundance estimation accuracy by at least 35% compared to HUMAnN3 (based on Bray-Curtis dissimilarity). Additionally, Meteor2 tracked more strain pairs than StrainPhlAn, capturing an additional 9.8% on the human dataset and 19.4% on the mouse dataset. Furthermore, in its fast configuration, Meteor2 emerges as one of the fastest available tools for profiling, requiring only 2.3 min for taxonomic analysis and 10 min for strain-level analysis against the human microbial gene catalogue when processing 10 M paired reads - operating within a modest 5 GB RAM footprint. We further validated Meteor2 using a published faecal microbiota transplantation (FMT) dataset, demonstrating its ability to deliver an extensive and actionable metagenomic analysis. The unified database design also simplifies the integration of TFSP outputs, making it straightforward for researchers to interpret and compare results.

CONCLUSIONS: These results highlight Meteor2 as a robust and versatile tool for advancing microbiome research and applications. As an open-source, easy-to-install, and accurate analysis platform, Meteor2 is highly accessible to researchers, facilitating the exploration of complex microbial ecosystems.},
}

@article {pmid41199203,
year = {2025},
author = {Demenou, BB and Ndar, A and Pineau, CP and Hinsinger, DD and Marande, W and Hourcade, D and Faivre-Rampant, P},
title = {Chromosome-scale assembly of European flax (Linum usitatissimum L.) genotypes and pangenomic analysis provide genomic tools to improve breeding.},
journal = {BMC genomics},
volume = {26},
number = {1},
pages = {1008},
pmid = {41199203},
issn = {1471-2164},
support = {GenoFLAX project//CIPALIN (France)/ ; GenoFLAX project//"Filière Lin fibre", Arvalis Institute/ ; GenoFLAX project//Linéa/ ; GenoFLAX project//INRae and CIPALIN (France)/ ; GenoFLAX project//"Filière Lin Fibre", Arvalis Institute/ ; GenoFLAX project//INRAe and CIPALIN (France)/ ; },
}

@article {pmid41190272,
year = {2025},
author = {Negrete-Paz, AM and Vázquez-Marrufo, G and Vázquez-Garcidueñas, MS},
title = {Beyond H37Rv: Mycobacterium tuberculosis pangenome structure and applications.},
journal = {Frontiers in microbiology},
volume = {16},
number = {},
pages = {1695567},
pmid = {41190272},
issn = {1664-302X},
abstract = {Mycobacterium tuberculosis (Mtb) is among the most successful bacterial pathogens, with multidrug-resistant strains posing significant challenges to global tuberculosis control. Traditional single-genome analyses, while essential for identifying strain-specific mutations, are limited in capturing the full spectrum of genetic diversity related to virulence, drug susceptibility, and transmission dynamics. Pangenomics examines the complete gene repertoire across all sequenced representatives of a species and addresses these limitations by enabling comprehensive, species-wide assessments of genetic variation. In this review, we summarize current knowledge of the Mtb pangenome, focusing on structural organization, methodological frameworks, and clinical applications. The Mtb pangenome exhibits a highly conserved genetic structure, with core genome estimates ranging from 1,166 to 3,767 genes, depending on the analytical thresholds and methodological approaches. Significant controversy regarding its classification as open or closed arises primarily from differences in computational pipelines (Roary, BPGA, Panaroo), core genome inclusion criteria (95%-100% presence), and dataset composition rather than fundamental biological disagreement. Despite these methodological challenges, pangenomic applications have demonstrated transformative potential in molecular epidemiology, drug resistance prediction, and virulence profiling. This perspective underscores a shift toward diversity-inclusive approaches, with integration of machine learning and standardization of analytical protocols identified as key priorities for future tuberculosis research and therapeutic innovation.},
}

@article {pmid41183489,
year = {2025},
author = {Chen, Z and Cui, M},
title = {Comparative genomics reveals antimicrobial resistance and population structure of chicken-associated Salmonella enterica serotype Typhimurium in the United States.},
journal = {Letters in applied microbiology},
volume = {},
number = {},
pages = {},
doi = {10.1093/lambio/ovaf127},
pmid = {41183489},
issn = {1472-765X},
abstract = {Salmonella enterica serotype Typhimurium is a leading cause of foodborne outbreaks linked to chickens in the United States. To investigate the genomic landscape of antimicrobial resistance (AMR) in this population, 1 048 chicken-associated S. Typhimurium genomes collected nationwide were analyzed. Overall, 84.5% of isolates carried at least one AMR determinant, and 34.3% displayed multidrug resistance (MDR). Sulfonamide and tetracycline resistance were most prevalent (1.03 and 1.01 AMR determinant per isolate, respectively). ARG co-occurrence analysis identified strong associations among tet(A), sul1, sul2, aac(3)-VIa, and aadA1, with blaCMY-2 emerging within an expanding co-resistance cluster. ARG-plasmid replicon association analysis indicated significant positive links between sul2 and tet(A) with IncC and ColRNAI. Machine learning-driven association rule mining demonstrated that integron carriage perfectly predicted MDR, and their absence in both non-AMR and AMR but non-MDR isolates underscores their pivotal role as the defining marker of MDR. We observed a pan-genome pattern with 3 855 core and 9 549 accessory genes, reflecting both genomic conservation and diversity. Whole-genome phylogenetic analysis revealed two major clades, with sequence type 19 comprising 99.0% of the isolates. This research provides a comprehensive genomic characterization of chicken-associated S. Typhimurium in the United States, highlighting key AMR mechanisms relevant for food safety and public health.},
}

@article {pmid41180027,
year = {2025},
author = {Zhao, RP and Luo, YH and Xie, WZ and Zhou, ZW and Qian, YQ and Yuan, SL and Li, DA and Li, J and Lu, K and Zhang, X and Song, JM and Chen, LL},
title = {RAGA: a reference-assisted genome assembly tool for efficient population-scale assembly.},
journal = {Horticulture research},
volume = {12},
number = {11},
pages = {uhaf207},
pmid = {41180027},
issn = {2662-6810},
abstract = {High-quality reference genomes at the population scale are fundamental for advancing pan-genomic research. However, high-quality genome assembly at the population scale is costly and time-consuming. To overcome these limitations, we developed Reference-Assisted Genome Assembly (RAGA), a hybrid computational tool that combines de novo and reference-based assembly approaches. RAGA efficiently employs existing reference genomes from the same or closely related species in combination with PacBio HiFi reads to produce high-quality alternative long sequences. These sequences can be integrated with de novo assemblies to improve assembly quality across population-scale datasets. The performance of RAGA across various plant genomes demonstrated its ability to reduce the number of contigs, decrease gaps, and correct genome assembly errors. The implementation of RAGA (available at https://github.com/wzxie/RAGA) significantly streamlines population-scale genome assembly workflows, providing a robust foundation for comprehensive pan-genomic investigations. This tool represents a substantial advancement in making large-scale genomic studies more accessible and efficient.},
}

@article {pmid41180022,
year = {2025},
author = {Huang, M and Zheng, P and Li, N and Chen, Q and Liu, Y and Huang, B and Tao, X and Yu, J and Xu, S},
title = {Evolutionary dynamics and functional divergence of the UDP-glycosyltransferases gene family revealed by a pangenome-wide analysis in tomato.},
journal = {Horticulture research},
volume = {12},
number = {11},
pages = {uhaf204},
pmid = {41180022},
issn = {2662-6810},
abstract = {UDP-dependent glycosyltransferases (UGTs) play a critical role in producing glycosylated metabolites that mediate plant-environment interactions. Recent studies have examined the role of UGT genes across various plant genomes. However, the evolutionary history and functional divergence of the UGT pan-gene family in the genus Solanum have not yet been explored. This study integrated data from 61 tomatoes and 9 representative genomes, ranging from algae to angiosperms, to identify 12 073 genes. The phylogeny of the UGT gene family reveals a clear evolutionary trajectory from unicellular algae to ferns, mosses, gymnosperms, and angiosperms. The study identified a significant number of tomato-specific UGT genes and explored the expansions of UGT73 and UGT85 subfamilies. The entire UGT genes (10 769) in tomato were classified into 118 orthologous gene groups, including 58 core, 31 softcore, 10 dispensable, 19 private orthologous gene groups, and the core groups contained 7811 genes, representing 72.53% of the total UGT genes. Analysis of gene family expansion revealed that whole-genome triplication and tandem duplication events play significant roles in the expansion of the UGT gene family. Selection pressure analysis revealed that the UGT genes experienced purifying selection in the genus Solanum. Additionally, expression profiles of some UGT genes in different tissues demonstrated expression divergence of multicopy genes across different UGT subfamilies due to the increase in gene dosage. Subcellular localization prediction revealed that most genes are localized in the chloroplast. These findings provide critical insights into the evolution and function of the UGT genes in tomato, laying a foundation for further exploration in adaptive evolution.},
}

@article {pmid41179999,
year = {2023},
author = {Hong, A and Oliva, M and Köppl, D and Bannai, H and Boucher, C and Gagie, T},
title = {Acceleration of FM-index Queries Through Prefix-free Parsing.},
journal = {Algorithms in bioinformatics : ... International Workshop, WABI ..., proceedings. WABI (Workshop)},
volume = {273},
number = {},
pages = {},
pmid = {41179999},
abstract = {FM-indexes are a crucial data structure in DNA alignment, for example, but searching with them usually takes at least one random access per character in the query pattern. Ferragina and Fischer [5] observed in 2007 that word-based indexes often use fewer random accesses than character-based indexes, and thus support faster searches. Since DNA lacks natural word-boundaries, however, it is necessary to parse it somehow before applying word-based FM-indexing. Last year, Deng et al. [3] proposed parsing genomic data by induced suffix sorting, and showed the resulting word-based FM-indexes support faster counting queries than standard FM-indexes when patterns are a few thousand characters or longer. In this paper we show that using prefix-free parsing-which takes parameters that let us tune the average length of the phrases-instead of induced suffix sorting, gives a significant speedup for patterns of only a few hundred characters. We implement our method and demonstrate it is between 3 and 18 times faster than competing methods on queries to GRCh38. And was consistently faster on queries made to 25,000, 50,000 and 100,000 SARS-CoV-2 genomes. Hence, it is very clear that our method accelerates the performance of count over all state-of-the-art methods with a minor increase in the memory. The source code for PFP-FM is available at https://github.com/marco-oliva/afm.},
}

@article {pmid41176227,
year = {2025},
author = {Tigabu, A and Willcox, MDP and Stapleton, F},
title = {Phenotypic and Genotypic Profiling of Antimicrobial Resistance Genes and Virulence Factors in Pseudomonas aeruginosa Isolates from Keratitis Patients.},
journal = {The ocular surface},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.jtos.2025.10.011},
pmid = {41176227},
issn = {1937-5913},
abstract = {BACKGROUND: Pseudomonas aeruginosa (P. aeruginosa) is a major cause of ocular infections, exhibiting resistance to many antimicrobial agents and the ability to acquire further resistance through mutations and horizontal gene transfer. It employs a range of virulence factors to invade ocular tissues, leading to complications such as corneal scarring and perforation. Alarmingly, multidrug-resistant P. aeruginosa isolates are increasing worldwide. For instance, a recent outbreak in the United States of America (USA) involving an extensively drug-resistant P. aeruginosa PA1270 strain resulted in four deaths, four eye removals, and 14 cases of vision loss. A comprehensive understanding of the antibiotic resistance and virulence mechanisms of P. aeruginosa is essential for the effective management of corneal infections.

METHODS: Whole-genome sequencing data from 70 P. aeruginosa isolates collected from corneal samples were retrieved from the National Center for Biotechnology Information (NCBI) database and annotated using Prokka 1.14.6. Unique genes identified in these datasets were analyzed against the Comprehensive Antibiotic Resistance Database (CARD) to determine antimicrobial resistance profiles. The presence of acquired resistance genes and virulence factors were assessed using ResFinder and the Virulence Factor Database (VFDB), respectively. Roary v3.13.0 was used for pangenome analysis, while Snippy v4.6.0 was employed for whole-genome variant analysis. Furthermore, mobile genetic elements (MGEs) and pathogenicity islands (PIs) were identified using MobileElementFinder v1.0.3 and IslandViewer 4, respectively. In parallel, phenotypic characterization, including determination of minimum inhibitory concentrations (MICs) for selected antimicrobial agents, was performed using the broth microdilution method. Additionally, a crystal violet assay was conducted to evaluate the biofilm-forming ability of P. aeruginosa.

RESULTS: The corneal P. aeruginosa harboured numerous AMR genes against various classes of antibiotics. Notably, the most prevalent acquired resistance genes across all keratitis P. aeruginosa strains were β-lactams blaPAO, and blaOXA, aminoglycoside aph(3')-IIb, chloramphenicol catB7, and fosfomycin fosA. P. aeruginosa keratitis isolates harbored more core and cloud genes than environmental and cystic fibrosis (CF) strains. A significant difference in ciprofloxacin resistance gene crpP was observed between the keratitis and CF isolates. Additionally, a considerable number of insertion sequences (ISPa1, ISPa6, ISPa32) and transposons (Tn4661, Tn6082, Tn5563) were identified. Phenotypic characterization of antimicrobial resistance (AMR) revealed that gentamicin were the most effective antibiotics against corneal P. aeruginosa isolates. However, 68.9% of the isolates exhibited resistance to imipenem. Surprisingly, 26.7% of the P. aeruginosa strains were classified as MDR, all of them originating from India. Furthermore, 61.8% of the corneal P. aeruginosa isolates were strong biofilm producers, with all MDR strains identified as strong biofilm formers.

CONCLUSIONS: Genotypic analysis revealed key resistance mechanisms, including antibiotic efflux, inactivation, and target alteration, as well as several structural and secreted virulence factors. Whilst MDR and extensively drug-resistant (XDR) strains were identified among the keratitis P. aeruginosa isolates, most isolates in this study were susceptible to gentamicin. These findings offer valuable insights for developing targeted therapeutic strategies that, when used in combination with antibiotics, may improve treatment outcomes and help mitigate the emergence of resistance.},
}

@article {pmid41174887,
year = {2025},
author = {Gao, C and Liu, X and Zhao, B and Feng, H and Huang, L},
title = {High-Quality Genome Assembly of Diplocarpon coronariae Unveils LTR Retrotransposon-Driven Structural Dynamics in Fungi Evolution.},
journal = {Molecular ecology resources},
volume = {},
number = {},
pages = {e70070},
doi = {10.1111/1755-0998.70070},
pmid = {41174887},
issn = {1755-0998},
support = {2020zdzx03-03-01//Key Science and Technology Special Projects of Shaanxi Province/ ; },
abstract = {Long terminal repeat retrotransposons (LTR-RTs) are recognised as a significant evolutionary force capable of shaping the structure and function of the genomes in eukaryotes, including animals, plants, and fungi. However, much remains largely unknown about how LTR-RTs influence the evolution of fungi at the chromosomal level. Here, we assembled the genome of an important plant pathogenic fungus, Diplocarpon coronariae (strain XN1), at the chromosomal level and obtained high-precision, full-length transcriptome annotations through transcriptome evidence and manual curation. Using high-quality genomes and gene annotations, we identified the two-speed genome and constructed a pan-genome graph of D. coronariae. Through comparative genomics, we discovered that LTR-RTs contributed to sequence and structural evolution among different strains of D. coronariae. Based on gene families constructed from the genomes of multiple species within Leotiomycetes, LTR-RTs were found to be involved in the formation of species-specific gene families as well as the expansion of gene families. Furthermore, through interspecies comparative genomics analysis, we identified a young chromosome, Chr15, specifically present in D. coronariae XN1. Chr15 likely originated from conserved topologically associating domains (TADs) and gradually expanded with the burst insertion of LTR-RTs, forming a completely new chromosome. This study provides new insights into the complexity and formation mechanisms of LTR retrotransposon-driven chromosomal and genomic structural evolution in fungi.},
}

@article {pmid41174464,
year = {2025},
author = {Lamrabet, M and Missbah El Idrissi, M},
title = {Comparative genomic analysis of native Bradyrhizobium spp. nodulating Retama dasycarpa in Moroccan semi-arid ecosystems: insights into symbiotic diversity and environmental adaptation.},
journal = {BMC genomics},
volume = {26},
number = {1},
pages = {984},
pmid = {41174464},
issn = {1471-2164},
mesh = {*Bradyrhizobium/genetics/classification/physiology ; *Symbiosis/genetics ; *Fabaceae/microbiology ; Phylogeny ; Morocco ; *Genomics/methods ; Nitrogen Fixation/genetics ; *Genome, Bacterial ; *Ecosystem ; *Adaptation, Physiological/genetics ; Root Nodules, Plant/microbiology ; Plant Root Nodulation/genetics ; },
abstract = {BACKGROUND: Retama dasycarpa, a drought-resistant legume endemic to Morocco's High Atlas Mountains, thrives in harsh conditions due to its association with nitrogen-fixing Bradyrhizobium strains. Despite the ecological significance of this symbiosis, the genetic diversity, symbiotic mechanisms, and stress adaptation strategies of these microsymbionts remain poorly understood. In this study we employed a comparative genomic approach to elucidate the genomic and functional traits of five strains isolated from R. dasycarpa nodules, with a focus on their symbiotic and stress-responsive gene repertoires.

RESULTS: Phylogenomic analysis revealed that four of the five strains likely represent novel Bradyrhizobium species, as indicated by average nucleotide identity (ANI) and digital DNA-DNA hybridization (dDDH) values below species delineation thresholds. Genomic comparisons identified core symbiotic genes, including nod, nif, and fix genes, essential for nodulation and nitrogen fixation. Interestingly, strain RDT46 lacked canonical nod genes but retained a minimal Type III Secretion System (T3SS), suggesting alternative symbiotic pathways. Pangenome analysis of 56 Bradyrhizobium genomes highlighted an open pangenome with extensive accessory gene content, reflecting adaptive versatility. Stress adaptation genes, such as those involved in osmoprotectant synthesis, oxidative stress response, and heat shock, were conserved across the five strains, underscoring their resilience to semi-arid conditions.

CONCLUSIONS: This study uncovers previously unknown genomic diversity in R. dasycarpa-associated Bradyrhizobim spp., including evidence for non-canonical symbiosis mechanisms. The strains' genetic toolkit for stress tolerance highlights their potential as inoculants for revegetation of degraded semi-arid lands.},
}

*Bradyrhizobium/genetics/classification/physiology
*Symbiosis/genetics
*Fabaceae/microbiology
Phylogeny
Morocco
*Genomics/methods
Nitrogen Fixation/genetics
*Genome, Bacterial
*Ecosystem
*Adaptation, Physiological/genetics
Root Nodules, Plant/microbiology
Plant Root Nodulation/genetics

@article {pmid41174429,
year = {2025},
author = {Chen, J and Peng, J and Liu, Y and Fu, L and Duan, X and Xu, Z and Zhang, J and Li, Y and Zhao, Y and Guo, L},
title = {Mobile genetic elements potentially drive adaptive evolution of pork-derived multidrug-resistant Salmonella Derby ST40 lineages: An integrated analysis.},
journal = {Food research international (Ottawa, Ont.)},
volume = {221},
number = {Pt 2},
pages = {117352},
doi = {10.1016/j.foodres.2025.117352},
pmid = {41174429},
issn = {1873-7145},
mesh = {*Drug Resistance, Multiple, Bacterial/genetics ; Animals ; Swine ; Phylogeny ; *Salmonella/genetics/drug effects/classification/isolation & purification ; *Interspersed Repetitive Sequences/genetics ; Humans ; Food Microbiology ; Anti-Bacterial Agents/pharmacology ; *Pork Meat/microbiology ; Evolution, Molecular ; Microbial Sensitivity Tests ; China ; },
abstract = {Salmonella Derby (S. Derby) is transmitted to humans through contaminated pork products. S. Derby ST40, with multidrug resistance (MDR) and extensive drug resistance, poses major food safety and public health challenges. By integrating antimicrobial susceptibility testing, phylogenetic analysis, phylogeographic reconstruction, pan-genomics, and pan-genome-wide association study, we investigated adaptive evolution and transmission dynamics of antibiotic resistance in S. Derby ST40 (71 isolates from livestock and 1572 global isolates from humans, food, and environment). Globally, S. Derby ST40 strains (69.36 % pork-derived) were divided into six clades. blaOXA-1-carrying MDR Clade VI evolved in China from Clade II Clade VI carried about 19 resistance genes; its MDR primarily resulted from combined effects of resistance genes in chromosomal MDR regions and mobile genetic elements (MGEs), accumulating via horizontal gene transfer. S. Derby ST40 accessory genes contained abundant recombinases associated with MGEs and resistance genes. Pork-derived MGEs and chromosomal MDR variable regions may drive Clade VI's evolution. Molecular clock analysis indicated that S. Derby ST40 originated in the United States in 1939, and Clade VI diverged from Clade II in China around 1979. Clade VI engaged in global antimicrobial resistance network via intercontinental transmission; China emerged as a main transmission hub in the 21st century. Globally circulating pork- and poultry-derived strains demonstrate more resistance genes than human-derived strains, indicating that animal husbandry and animal food production chains are resistance gene reservoirs. Strengthening antibiotic regulation in livestock farming may curb resistance gene dissemination within food chains, and a One Health governance framework may prevent and control cross-border MDR bacterial transmission.},
}

*Drug Resistance, Multiple, Bacterial/genetics
Animals
Swine
Phylogeny
*Salmonella/genetics/drug effects/classification/isolation & purification
*Interspersed Repetitive Sequences/genetics
Humans
Food Microbiology
Anti-Bacterial Agents/pharmacology
*Pork Meat/microbiology
Evolution, Molecular
Microbial Sensitivity Tests
China

@article {pmid41168819,
year = {2025},
author = {Viora-Dupont, E and Delanne, J and Garde, A and Nambot, S and Colin, E and Bournez, M and Fauconnier-Fatus, C and Racine, C and Simao De Souza, C and Bernard, C and Maurer, A and Espitalier, A and Binquet, C and Bouctot, M and Humbert, ML and Briffaut, AS and Darmency, V and Plumet, P and Cotinaud-Ricou, A and Relin, N and Callier, P and Mosca-Boidron, AL and Marle, N and Tran Mau-Them, F and Denommé-Pichon, AS and Safraou, H and Vitobello, A and Philippe, C and Duffourd, Y and Bruel, AL and Thauvin-Robinet, C and Faivre, L},
title = {Exome sequencing in severe non-syndromic specific learning and language disorders in a French cohort.},
journal = {Molecular autism},
volume = {16},
number = {1},
pages = {54},
pmid = {41168819},
issn = {2040-2392},
abstract = {BACKGROUND: Specific learning disorders (SLDs) affect approximately 5% of school-age children. In France, genetic investigations of complex non-syndromic SLD cases include chromosomal microarray analysis and fragile X syndrome testing. However, the examples of genes being described in intellectual disability or autism spectrum disorder and also reported in patients with complex and severe SLDs are multiplying. International efforts using exome sequencing have identified monogenic diseases that explain severe SLDs in some instances. The aim of our study was to investigate the value of exome sequencing in children with SLDs without intellectual disability and autism spectrum disorder.

METHODS: We initiated a prospective study using exome sequencing in patients with well-documented, severe SLD.

RESULTS: Analysis of 82 patients revealed pathogenic/likely pathogenic variants in 11 (13.4%) patients (ADNP, BRAF, CREBBP, KCNN2, KIF1A, RERE, SCN8A, SET, SMARCC2 (x2), TRIO). In addition, 38 variants of uncertain significance in candidate genes for severe neurodevelopmental disorders (NDDs) or in genes of unknown significance that could contribute to the phenotype were identified in 30 patients.

LIMITATIONS: The study of 82 patients does not provide sufficient statistical power to conclude that exome testing adds value over chromosomal microarray analysis, or to determine which patient profiles are more likely to benefit from genetic testing. Studies with larger patient numbers are needed to increase statistical power.

CONCLUSIONS: This study confirms the involvement of NDD genes in milder phenotypes and suggests the potential of exome sequencing for diagnosing severe SLDs. Further research on larger samples is required to determine which SLDs are most likely to benefit from pangenomic explorations and to clarify the implication of candidate variants.},
}

@article {pmid41171631,
year = {2025},
author = {Rodrigues, JA and Vasco, KA and Blankenship, HM and Cha, W and Mukherjee, S and Sloup, RE and Carbonell, SL and Soehnlen, MK and Manning, SD},
title = {Evidence of diversification and geographic separation in a lineage of Campylobacter jejuni co-circulating in cattle and humans.},
journal = {Microbial genomics},
volume = {11},
number = {10},
pages = {},
doi = {10.1099/mgen.0.001553},
pmid = {41171631},
issn = {2057-5858},
mesh = {Animals ; Cattle ; *Campylobacter jejuni/genetics/classification/isolation & purification/pathogenicity ; Humans ; *Campylobacter Infections/microbiology/veterinary/epidemiology ; Phylogeny ; Multilocus Sequence Typing ; Genome, Bacterial ; Polymorphism, Single Nucleotide ; *Cattle Diseases/microbiology ; Michigan ; },
abstract = {Campylobacter jejuni, a leading cause of gastroenteritis, is acquired by consuming contaminated food products or via direct contact with animal reservoirs like cattle and poultry. Prior studies have identified specific C. jejuni lineages such as sequence type (ST)-982 and ST-61, to be associated with cattle, while others are linked to chickens and other animal sources. Since cattle-associated lineages were more commonly resistant to tetracycline and detected in patients with a history of cattle contact, we performed comparative genomics on 61 cattle- and 175 human-derived strains collected during an overlapping time period in Michigan. Pangenome analyses and a core-gene phylogeny revealed a high degree of genomic similarity among cattle-associated lineages regardless of strain source, while a machine learning approach predicted that the ST-982 human strains originated from cattle. Further characterization of these closely related strains using high-quality SNP clustering demonstrated that the human and cattle strains differed by >260 SNPs. The cattle genomes also have less unique genes with fewer accessory and virulence genes than the human genomes, providing evidence for diversification within and adaptation to the cattle host. Comparing the core-gene MLST (cgMLST) profiles to those from 723 published ST-982 genomes identified multiple sequence clusters that varied in frequency by US region. Together, these data illustrate that genetically similar ST-982 strains are co-circulating in cattle and humans. They also suggest that clonal expansion of cattle-associated lineages may contribute to regional differences in genotype distributions and antibiotic resistance frequencies, which likely occur due to varying selective pressures present in each region.},
}

Animals
Cattle
*Campylobacter jejuni/genetics/classification/isolation & purification/pathogenicity
Humans
*Campylobacter Infections/microbiology/veterinary/epidemiology
Phylogeny
Multilocus Sequence Typing
Genome, Bacterial
Polymorphism, Single Nucleotide
*Cattle Diseases/microbiology
Michigan

@article {pmid41169709,
year = {2025},
author = {Gavriilidou, A and Stamatakis, A and Kupczok, A and Bista, I and Jiggins, CD and Fernández, R and Skourtanioti, E and Amoutzias, G and Delneri, D and Kyrpides, N and Nikolaou, C and Pittis, AA and Manousaki, T and Vakirlis, N},
title = {Advances and challenges in understanding evolution through genome comparison: meeting report of the European Molecular Biology Organization (EMBO) lecture course "Evolutionary and Comparative Genomics".},
journal = {Bioinformatics advances},
volume = {5},
number = {1},
pages = {vbaf223},
pmid = {41169709},
issn = {2635-0041},
abstract = {This perspective outlines emerging trends, key challenges, and future opportunities in evolutionary and comparative genomics. Our starting point are the topics presented at the 2024 EMBO Early Career Lecture Course "Evolutionary and Comparative Genomics", which highlighted recent conceptual and methodological advances in areas ranging from microbial pangenomes, protein evolution, hybrid speciation, novel gene origination and transposon dynamics. Here, we emphasize the role of computational and molecular approaches, providing a forward-looking view on where the field is headed and how it is being reshaped by new technologies and approaches.},
}

@article {pmid41168433,
year = {2025},
author = {Moosman, OW and Kelley, JL and Bogan, SN},
title = {Mitigating assembly and switch errors in phased genomes of polar fishes reveals haplotype diversity in copy number of antifreeze protein genes.},
journal = {Heredity},
volume = {},
number = {},
pages = {},
pmid = {41168433},
issn = {1365-2540},
support = {OPP-2312253//NSF | Directorate for Geosciences (GEO)/ ; },
abstract = {Phased genomes and pangenomes are enhancing our understanding of genetic variation. Accurate phasing and assembly in repetitive regions of the genome remain challenging, however. Addressing this obstacle is crucial for studying structural genomic variation, such as copy number variations (CNVs) common to repetitive regions. Polar fishes, for example, evolved repetitive tandem arrays of antifreeze protein (AFP) genes that facilitate adaptation to freezing and expanded in copy number in colder environments. AFP CNVs remain poorly characterized in polar fishes and may be illuminated by haplotype-aware approaches. We performed long-read sequencing for two polar fishes in the suborder Zoarcoidei and leveraged additional published long-read data to assemble phased genomes. We developed a workflow to measure haplotype diversity in CNV while controlling for misassembly and switch errors-a change from one parental haplotype to another in a contiguous assembly. We present gfa_parser, which computes and extracts all possible contiguous sequences for phased or primary assemblies from graphical fragment assembly (GFA) files, and switch_error_screen, which flags potential switch errors. gfa_parser revealed that assembly uncertainty was ubiquitous across AFP array haplotypes and that standard processing of graphical fragment assemblies can bias measurement of haplotype CNVs. We detected no switch errors in AFP arrays. After controlling for misassembly and switch error, we detected haplotype diversity of AFP CNVs in all studied polar Zoarcoidei species and in 60% of AFP arrays. Intraindividual haplotype diversity spanned differences of 3-16 copies. Our workflow revealed intraspecific genomic diversity in zoarcoids that likely fueled the evolution of AFP copy number across temperature.},
}

@article {pmid41162711,
year = {2025},
author = {Avni, R and Kamal, N and Bitz, L and Jellen, EN and Bekele, WA and Angessa, TT and Auvinen, P and Bitz, O and Boyle, B and Canales, FJ and Carlson, CH and Chapman, B and Chawla, HS and Chen, Y and Copetti, D and Correia de Lemos, S and Dang, V and Eichten, SR and Klos, KE and Fenn, AM and Fiebig, A and Fu, YB and Gundlach, H and Gupta, R and Haberer, G and He, T and Herrmann, MH and Himmelbach, A and Howarth, CJ and Hu, H and Isidro Y Sánchez, J and Itaya, A and Jannink, JL and Jia, Y and Kaur, R and Knauft, M and Langdon, T and Lux, T and Marmon, S and Marosi, V and Mayer, KFX and Michel, S and Nandety, RS and Nilsen, KT and Paczos-Grzęda, E and Pasha, A and Prats, E and Provart, NJ and Ravagnani, A and Reid, RW and Schlueter, JA and Schulman, AH and Sen, TZ and Singh, J and Singh, M and Sirijovski, N and Stein, N and Studer, B and Viitala, S and Vronces, S and Walkowiak, S and Wang, P and Waters, AJ and Wight, CP and Yan, W and Yao, E and Zhang, XQ and Zhou, G and Zhou, Z and Tinker, NA and Fiedler, JD and Li, C and Maughan, PJ and Spannagl, M and Mascher, M},
title = {A pangenome and pantranscriptome of hexaploid oat.},
journal = {Nature},
volume = {},
number = {},
pages = {},
pmid = {41162711},
issn = {1476-4687},
abstract = {Oat grain is a traditional human food that is rich in dietary fibre and contributes to improved human health[1,2]. Interest in the crop has surged in recent years owing to its use as the basis for plant-based milk analogues[3]. Oat is an allohexaploid with a large, repeat-rich genome that was shaped by subgenome exchanges over evolutionary timescales[4]. In contrast to many other cereal species, genomic research in oat is still at an early stage, and surveys of structural genome diversity and gene expression variability are scarce. Here we present annotated chromosome-scale sequence assemblies of 33 wild and domesticated oat lines, along with an atlas of gene expression across 6 tissues of different developmental stages in 23 of these lines. We construct an atlas of gene-expression diversity across subgenomes, accessions and tissues. Gene loss in the hexaploid is accompanied by compensatory upregulation of the remaining homeologues, but this process is constrained by subgenome divergence. Chromosomal rearrangements have substantially affected recent oat breeding. A large pericentric inversion associated with early flowering explains distorted segregation on chromosome 7D and a homeologous sequence exchange between chromosomes 2A and 2C in a semi-dwarf mutant has risen to prominence in Australian elite varieties. The oat pangenome will promote the adoption of genomic approaches to understanding the evolution and adaptation of domesticated oats and will accelerate their improvement.},
}

@article {pmid41162683,
year = {2025},
author = {Lin, Y and He, J and Zhang, Q and Li, Y and Ke, J and Lin, C and Yao, B and Zhang, C and Tan, N},
title = {Aerococcus christensenii: an emerging pathogen associated with infections and bacteremia in pregnancy-genomic insights and pathogenicity evaluation.},
journal = {Functional & integrative genomics},
volume = {25},
number = {1},
pages = {229},
pmid = {41162683},
issn = {1438-7948},
support = {868-000001033222//The Scientific Foundation for Youth Scholars of Shenzhen University/ ; 868-000001033222//The Scientific Foundation for Youth Scholars of Shenzhen University/ ; 868-000001033222//The Scientific Foundation for Youth Scholars of Shenzhen University/ ; },
mesh = {Female ; Pregnancy ; Humans ; *Bacteremia/microbiology ; Animals ; *Aerococcus/genetics/pathogenicity/drug effects/isolation & purification ; Mice ; *Genome, Bacterial ; *Gram-Positive Bacterial Infections/microbiology ; Virulence/genetics ; *Pregnancy Complications, Infectious/microbiology ; Virulence Factors/genetics ; },
abstract = {Aerococcus christensenii (A. christensenii) is a symbiotic bacterium that primarily colonizes the vagina. Infections caused by A. christensenii are rare but can also pose a significant health threat. In this study, two rare cases of A. christensenii bacteremia in pregnant women complicated with chorioamnionitis were investigated; and two strains KSW23 and KWL24, which were isolated from blood samples, were analyzed for their genomic characteristics and pathogenic potential. Whole-genome sequencing revealed that the genome sizes of KSW23 and KWL24 were approximately 1.6 Mb, and predicted multiple genes associated with pathogenicity (tuf, eno, plr/gapA, galU, galE, groEL, gndA, sugC, lplA1, mgtB, clpC, clpP, and lmb), antibiotic resistance (ermB and tet(M)), and mobile genetic elements (plasmid replicon repUS43 and transposon Tn6009). Correspondingly, these strains showed multidrug resistance to Macrolides, Lincosamides, and Tetracyclines. Pangenome analysis revealed close evolutionary relationships and significant genomic conservation between these two strains and the previously isolated strains, especially with respect to genes related to pathogenicity and antibiotic resistance. Notably, a mouse bacteremia model confirmed the pathogenicity and virulence of A. christensenii strains KSW23 and KWL24, which induced bacteremia and mortality, but not as strongly as Staphylococcus aureus (S. aureus) strain ATCC25923. Additionally, A. christensenii exhibited a robust survival ability in human blood comparable to those observed in S. aureus strain ATCC25923. To our knowledge, this study is the first genomic research on A. christensenii, and confirms the species' bloodstream invasive capacity and pathogenicity based on genomic studies and experimental validation. These findings underscore its role as a pathogen in the ascending genital tract in the obstetric population.},
}

Female
Pregnancy
Humans
*Bacteremia/microbiology
Animals
*Aerococcus/genetics/pathogenicity/drug effects/isolation & purification
Mice
*Genome, Bacterial
*Gram-Positive Bacterial Infections/microbiology
Virulence/genetics
*Pregnancy Complications, Infectious/microbiology
Virulence Factors/genetics

@article {pmid41152942,
year = {2025},
author = {Stalder, L and Maurhofer, M and Croll, D},
title = {High-resolution profiling of bacterial and fungal communities using pangenome-informed taxon-specific long-read amplicons.},
journal = {Microbiome},
volume = {13},
number = {1},
pages = {219},
pmid = {41152942},
issn = {2049-2618},
support = {177052//Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung/ ; 177052//Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung/ ; },
mesh = {Phylogeny ; *Microbiota/genetics ; *High-Throughput Nucleotide Sequencing/methods ; *Triticum/microbiology ; *Bacteria/classification/genetics ; Pseudomonas/genetics/classification/isolation & purification ; RNA, Ribosomal, 16S/genetics ; *Ascomycota/genetics/classification/isolation & purification ; *Fungi/classification/genetics/isolation & purification ; Sequence Analysis, DNA/methods ; *Mycobiome ; },
abstract = {BACKGROUND: High-throughput sequencing technologies have greatly advanced our understanding of microbiomes, but resolving microbial communities at species and strain levels remains challenging.

RESULTS: We developed and validated a pipeline for designing, multiplexing, and sequencing highly polymorphic taxon-specific long-read amplicons. We focused on the wheat microbiome as a proof-of-principle and demonstrate strain-level resolution for the wheat-associated Pseudomonas microbiome and the ubiquitous fungal pathogen Zymoseptoria tritici. We achieved an order of magnitude higher phylogenetic resolution compared to existing ribosomal amplicons. The designed amplicons accurately capture species and strain diversity outperforming full-length 16S and ITS amplicons. Furthermore, we tracked microbial communities in the wheat phyllosphere across time and space to establish fine-grained species and strain-specific dynamics. To expand the utility of our approach, we generated pangenome-informed amplicon templates for additional key bacterial and fungal genera.

CONCLUSIONS: Pangenome-informed microbiome profiling enables the tracking of microbial community dynamics in complex environments and overcomes limitations in phylogenetic resolution. Video Abstract.},
}

Phylogeny
*Microbiota/genetics
*High-Throughput Nucleotide Sequencing/methods
*Triticum/microbiology
*Bacteria/classification/genetics
Pseudomonas/genetics/classification/isolation & purification
RNA, Ribosomal, 16S/genetics
*Ascomycota/genetics/classification/isolation & purification
*Fungi/classification/genetics/isolation & purification
Sequence Analysis, DNA/methods
*Mycobiome

@article {pmid41152715,
year = {2025},
author = {Li, CJ and Zhang, J and Su, J and Yu, LY and Chen, HH and Zhang, YQ},
title = {Genomic insights into Gordonia diversity: proposal of three novel species (Gordonia. altitudinis sp. nov., Gordonia. ligustrum sp. nov., and Gordonia. pistacia sp. nov.) with distinct environmental and biomedical traits.},
journal = {BMC microbiology},
volume = {25},
number = {1},
pages = {692},
pmid = {41152715},
issn = {1471-2180},
support = {32170021//National Natural Science Foundation of China/ ; },
mesh = {Phylogeny ; RNA, Ribosomal, 16S/genetics ; Soil Microbiology ; *Genome, Bacterial ; DNA, Bacterial/genetics ; Nucleic Acid Hybridization ; *Actinobacteria/classification/genetics ; Genomics ; Sequence Analysis, DNA ; Bacterial Typing Techniques ; },
abstract = {BACKGROUND: Rare actinomycetes, particularly Gordoni spp., are emerging as critical sources of bioactive metabolites and opportunistic pathogens.

RESULTS: In this study, we isolated three novel Gordonia strains from soil samples and characterized their taxonomic status using a polyphasic taxonomic approach. Phylogenetic analysis of 16S rRNA genes and whole-genome comparisons indicated that strains CPCC 205333[ T], CPCC 205515[ T], and CPCC 206044[ T] represent three distinct novel species. The overall genome relatedness indices of average nucleotide identity (ANI) and digital DNA-DNA hybridization (dDDH) between these studied strains and their related type strains of the genus Gordonia were all below the established thresholds for species delineation, confirming the classification of these three as novel species, for which we propose the names Gordonia altitudinis sp. nov., Gordonia ligustrum sp. nov., and Gordonia pistacia sp. nov., respectively. Functional annotation revealed their ecological versatility, with Gordonia spp. contributing significantly to soil microbiome functionality through plant growth-promoting traits (e.g., nitrogen fixation, siderophore production) and biosynthetic gene clusters (BGCs), while also harboring virulence factors. Pan-genomic analysis of 225 Gordonia strains delineated an open gene pool (α = 0.82; 22% fluidity), reflecting adaptive plasticity. Core genomes were enriched in conserved metabolic pathways, whereas accessory and strain-specific genes showed niche-driven functional diversification, suggesting ecological specialization.

CONCLUSION: These findings expand the genomic and functional understanding of Gordonia, highlighting its dual role in environmental resilience and pathogenicity, with potential applications in biotechnology and microbiome engineering.},
}

Phylogeny
RNA, Ribosomal, 16S/genetics
Soil Microbiology
*Genome, Bacterial
DNA, Bacterial/genetics
Nucleic Acid Hybridization
*Actinobacteria/classification/genetics
Genomics
Sequence Analysis, DNA
Bacterial Typing Techniques

@article {pmid41152006,
year = {2025},
author = {McInerney, JO},
title = {Classifying Convergences in the Light of Horizontal Gene Transfer: Epaktovars and Xenotypes.},
journal = {Molecular biology and evolution},
volume = {},
number = {},
pages = {},
doi = {10.1093/molbev/msaf279},
pmid = {41152006},
issn = {1537-1719},
abstract = {The classification of living systems presents significant challenges due to the prevalence of gene transfer between genomes. Traditional taxonomic systems have been designed to describe tree-like evolution and consequently struggle to accommodate network-like evolutionary patterns. In this perspective, I consolidate and clarify terminology for describing organisms whose evolutionary history has not been strictly tree-like. I introduce two complementary concepts: epaktovars - groups (>=2) of organisms exhibiting convergent phenotypes through independent acquisition of similar functions, whether via horizontal gene transfer or independent evolution of analogous solutions; and xenotypes - organisms that share homologous genes acquired through horizontal gene transfer, regardless of whether these shared genes produce similar or different phenotypes. The epaktovar concept mirrors the previously established concept of epaktologs (independent assembly of similar protein domain architectures), while xenotypes extends the concept of xenologs (horizontally transferred homologous genes) to the genome level. Recent research on homoplastic patterns in pangenome evolution enhances our understanding of these phenomena. These concepts also have important applications in synthetic biology and de-extinction efforts, where genetically modified organisms and reconstructed extinct species can be understood as xenotypes and epaktovars of their genetic donors, providing a framework for classifying organisms whose genetic composition has been shaped by human intervention rather than natural evolutionary processes. These terms collectively provide a framework for describing both phenotypic convergence arising through any evolutionary mechanism and shared genetic material resulting specifically from gene transfer across diverse lineages.},
}

@article {pmid41151379,
year = {2025},
author = {Quadrana, L and Henderson, IR},
title = {The natural history of transposons in plant pangenomes and panepigenomes.},
journal = {Current opinion in plant biology},
volume = {88},
number = {},
pages = {102818},
doi = {10.1016/j.pbi.2025.102818},
pmid = {41151379},
issn = {1879-0356},
abstract = {Transposons are DNA sequences capable of self-mobilization, which occupy large fractions of plant genomes. Due to their repetitive nature, complete maps of transposon diversity have been challenging to obtain. The advent of long-read sequencing now provides high-quality pangenomic assemblies, revealing transposon diversity within and between species. Transposons are major targets of epigenetic and post-transcriptional silencing, which provide the capacity for cryptic transmission, and facilitate environmental and developmental regulation. Transposon distributions are highly structured along plant chromosomes and we examine genomic niches that specific families are adapted to occupy. Here, we review new insights into transposon core and accessory proteins, and how these can regulate activity in vivo. Finally, we consider the role of transposons in host genome adaptation and evolution, as well as how they are selected on their own terms.},
}

@article {pmid41146324,
year = {2025},
author = {Campos-Dominguez, L and Castanera, R and Grover, CE and Wendel, JF and Casacuberta, JM},
title = {Differential LTR-retrotransposon dynamics across polyploidization, speciation, domestication, and improvement of cotton (Gossypium).},
journal = {Genome biology},
volume = {26},
number = {1},
pages = {369},
pmid = {41146324},
issn = {1474-760X},
support = {PID2022-143167NB-100//Ministerio de Ciencia e Innovación/ ; },
mesh = {*Gossypium/genetics ; *Retroelements ; *Terminal Repeat Sequences ; *Domestication ; *Polyploidy ; Genome, Plant ; Evolution, Molecular ; *Genetic Speciation ; Phylogeny ; },
abstract = {BACKGROUND: Transposable elements are major components of plant genomes and major drivers of plant genome evolution. The cotton genus (Gossypium) is an excellent evolutionary model for polyploidization, speciation, domestication, and crop improvement. Here, we implement genome and pangenome analyses to study in detail the dynamics of LTR-retrotransposons during the cotton evolution.

RESULTS: We show that some LTR-retrotransposon lineages amplified in tetraploid cotton compared to their diploid progenitors, whereas others stayed stable or amplified but were removed through solo-LTR formation. Using species-level pangenomes we show that only a few lineages (CRM, Tekay, Ivana, and Tork) remained active after polyploidization and are still transposing. Tekay and CRM elements have re-shaped the centromeric and pericentromeric regions of tetraploid cottons in a subgenome specific manner, through new insertions but also selective eliminations through solo-LTR formation. On the other hand, Ivana and Tork have actively inserted within or close to genes affecting their expression. Finally, population-level analyses using the two pangenomes and data from 283 and 223 varieties of G. hirsutum and G. barbadense reveal changes in Transposon Insertion Polymorphism frequencies accompanying domestication and improvement of both species, suggesting the possibility of selection on linked regions.

CONCLUSIONS: Our findings reveal that LTR-retrotransposon lineages followed differential dynamics during cotton evolution, displaying differences among species and the two coresident genomes of allopolyploid cotton. A handful of the LTR-retrotransposon lineages that expanded after polyploidization helped shape the genomes of both G. hirsutum and G. barbadense, impacting their centromere and pericentromeric regions as well as protein-coding genes.},
}

*Gossypium/genetics
*Retroelements
*Terminal Repeat Sequences
*Domestication
*Polyploidy
Genome, Plant
Evolution, Molecular
*Genetic Speciation
Phylogeny

@article {pmid41145869,
year = {2025},
author = {Yang, S and Wang, Y and Huang, Q and Wang, M and Wang, S and Fu, X and Zhu, C and Cheng, J and Liu, S and Yang, Z and Yang, N and Yan, J and Yang, X and Qin, F},
title = {A pangenome of maize provides genetic insights into drought resistance.},
journal = {Nature genetics},
volume = {},
number = {},
pages = {},
pmid = {41145869},
issn = {1546-1718},
support = {2019M660867//China Postdoctoral Science Foundation/ ; },
abstract = {Drought poses a severe threat to the stability of crop yields. It is crucial to identify genetic resources and decipher the molecular mechanisms underlying drought resistance in crops. Here we generated high-quality genome assemblies of 25 maize germplasms exhibiting substantial variation in drought resistance. Combined with 31 additional maize genome sequences, a comprehensive pangenome analysis was performed. Rare allelic variations and extensive regulatory diversity were revealed in abscisic acid-related or drought-related genes, which may contribute to the diversity in drought resistance among germplasms. Furthermore, we identified three genes, ZmUGE2, ZmSIL2 and ZmASI3, that enhance maize drought resistance by strengthening mechanical support of the cell wall, regulating stress-responsive gene expression and coordinating male and female inflorescence development, respectively. Thus, this study provides valuable insight into the genetic control of drought resistance in maize at different growing stages. The expanded maize pangenome information serves as a valuable resource for maize genomic research.},
}

@article {pmid41144276,
year = {2025},
author = {Kaestli, M and Gibb, K and Hedges, CE and Padovan, A},
title = {High genomic diversity of Vibrio parahaemolyticus from underexplored tropical northern Australia: a baseline for future surveillance.},
journal = {Microbial genomics},
volume = {11},
number = {10},
pages = {},
doi = {10.1099/mgen.0.001536},
pmid = {41144276},
issn = {2057-5858},
mesh = {*Vibrio parahaemolyticus/genetics/isolation & purification/classification/pathogenicity ; Australia/epidemiology ; Humans ; Phylogeny ; *Vibrio Infections/microbiology/epidemiology ; Genome, Bacterial ; *Genetic Variation ; Genomic Islands ; Tropical Climate ; Genomics ; },
abstract = {Vibrio parahaemolyticus is an autochthonous marine bacterium that causes gastroenteritis after ingestion of raw or undercooked seafood and, less frequently, wound and tissue infections. Genomic information from northern Australia is scarce, and most sequences to date stem from foodborne outbreaks in southern states. We analysed 24 environmental and 5 clinical isolates (4 wound and 1 gastrointestinal case) collected in the wet-dry tropics from northern Australia and placed them alongside 48 representative public genomes. Core-genome phylogeny showed that the northern Australian strains sit within the broad VppAsia lineage and intermix with Asian and South American isolates, reflecting the limited geographic structuring in the marine environment. A gastrointestinal isolate (RDH3, ST-2901) harboured the trh2-positive VPaI-β pathogenicity island (including vtrAB and hlyDBAC genes) and displayed an A187S change in the TRH2 toxin which was absent in the other TRH-1/-2 sequences of the isolates analysed in this study. Wound isolates lacked tdh and trh genes, suggesting that the species' intrinsic virulome may suffice for tissue colonization; notably, one wound strain carried a plasmid with a Vibrio alginolyticus pilT copy linked to twitching motility which has been associated with wound infections. It remains to be determined whether this additional pilT copy, beyond the core genome copies, confers a selective advantage for tissue colonization. Plasmid diversity amongst clinical isolates and a diseased aquaculture fish, including a putative chimaera plasmid in the gastrointestinal isolate, underscores the role of mobile elements as reservoirs allowing adaptability to changing environments. Our findings expand the Australian genomic catalogue beyond outbreak strains, reveal extensive accessory-genome variability in tropical waters and underscore the need for One-Health surveillance frameworks that monitor virulence and resistance markers beyond the canonical hemolysin genes.},
}

*Vibrio parahaemolyticus/genetics/isolation & purification/classification/pathogenicity
Australia/epidemiology
Humans
Phylogeny
*Vibrio Infections/microbiology/epidemiology
Genome, Bacterial
*Genetic Variation
Genomic Islands
Tropical Climate
Genomics

@article {pmid41143262,
year = {2025},
author = {Oh, JH and Jeong, H and Kim, M and Cho, M and Kim, E},
title = {Transcriptome and methane emission dataset of indica and japonica rice cultivars (93-11, Milyang352, Milyang392) at tillering and heading stages.},
journal = {Data in brief},
volume = {62},
number = {},
pages = {112027},
pmid = {41143262},
issn = {2352-3409},
abstract = {This dataset comprises transcriptome profiles and methane emission measurements collected from roots and stems (including leaves) of three rice cultivars: Indica 93-11, Japonica Milyang352, and Milyang392 (an anther-culture line derived from 93-11 × Milyang352 with a high Indica gene proportion). Notably, Milyang392 exhibited the lowest methane emission among the three cultivars, highlighting its potential for climate-resilient breeding. Samples were collected at the tillering stage (June 28 and July 12, 2022) and heading stage (July 26 and August 11, 2022), with three biological replicates per condition, totaling 72 samples. RNA-Seq data were generated using the Illumina HiSeq platform (paired-end, 150 bp), and low-quality reads (Phred < 20, length < 50 bp) were filtered using Trimmomatic and BBDuk. Reads were aligned to the Oryza sativa pan-genome (TGSRICEPAN) using HISAT2, and gene-level read counts were computed using HTSeq. Differentially expressed genes (DEGs) were identified using DESeq2 with thresholds of |log2 fold change| ≥ 1 and adjusted p-value < 0.05. Maximum detected DEGs were 19,267 (root) and 17,165 (stem). Methane emissions were measured using gas chromatography (GC, Agilent 7890B) from the same biological replicates, showing the highest emission in 93-11 (15.2 mg/m[2]/h), followed by Milyang352 (12.8 mg/m[2]/h) and Milyang392 (9.5 mg/m[2]/h). These values correspond to 2.00 ± 0.12 kg/ha for 93-11, 1.57 ± 0.06 kg/ha for Milyang352, and 1.17 ± 0.01 kg/ha for Milyang392. The dataset is useful for studies of methane-related gene expression, rice metabolic pathways, and climate-resilient crop breeding, providing a valuable resource for machine learning applications and understanding genotype-specific responses.},
}

@article {pmid41140409,
year = {2025},
author = {Huang, L and Zhou, L and Zhang, N and Zhou, W and Xu, B and Hong, J and Zhang, W and Zhang, Y and Xu, K and Bao, C and Jiang, H and Tan, Z and Li, J},
title = {Limited genomic diversity and convergent adaptation of Brucella melitensis isolated from human in East China, from 2011 to 2024.},
journal = {Frontiers in microbiology},
volume = {16},
number = {},
pages = {1663555},
pmid = {41140409},
issn = {1664-302X},
abstract = {OBJECTIVE: This study aimed to investigate the genomic epidemiology of Brucella melitensis in Jiangsu Province, a typical low-endemic region in East China where the incidence of human brucellosis has been increasing in recent years. Accordingly, a molecular epidemiological study was conducted on the 2,552 reported brucellosis patients in Jiangsu province, from 2011 to 2024.

METHODS: All B. melitensis isolated from these patients were sequenced using next-generation sequencing (NGS), and 515 strains met the criteria for subsequent analysis. Core genome multi-locus sequence typing (cgMLST), pan-genome analysis and core genome single nucleotide polymorphism (cgSNP) were utilized to analyze genomic characteristics and establish the epidemiological linkages among global strains.

RESULTS: Among 515 isolates, 439 (85.24%) and 505 (98.06%) were identified as B. melitensis biovar 3 and sequence type 8(ST8), respectively. cgMLST further classified them into 28 core gene sequence types (cgSTs), including four novel genotypes (cgST1586-cgST1589) discovered in this study, whose identification expands the global cgMLST database and provides new markers for epidemiological surveillance. According to the cgSNP-based phylogenetic analysis, two distinct clades were persistently circulating within Jiangsu Province. One clade demonstrated significant genetic clustering with the Middle East strains, the other clade was closely linked to the hyper-endemic regions in China. Pan-genome analysis revealed their high homology, with core proteins primarily involved in amino acid transport and metabolism. Over the past 14 years, these isolates have exhibited limited genetic diversity and may be evolving toward a genotype that is better adapted to the host and environment.

CONCLUSION: The human brucellosis in Jiangsu is mainly attributed to imported infections through various patterns, which is consistent with the typical epidemiology characteristics observed in low-endemic regions. The identification of four novel cgSTs and evidence of genomic evolutionary changes provide important insights to strengthen surveillance and guide targeted control strategies for brucellosis in East China.},
}

@article {pmid41134096,
year = {2025},
author = {Lu, T and Jiang, S and Liu, X and Lu, Z and Sadaqat, M and Chen, C and Zuo, X and Tahir Ul Qamar, M},
title = {Pan-genome analysis and functional characterisation of the terpene synthase (TPS) gene family in five varieties of yellowhorn (Xanthoceras sorbifolium).},
journal = {Functional plant biology : FPB},
volume = {52},
number = {10},
pages = {},
doi = {10.1071/FP24349},
pmid = {41134096},
issn = {1445-4416},
mesh = {*Alkyl and Aryl Transferases/genetics/metabolism ; Phylogeny ; *Multigene Family ; *Genome, Plant/genetics ; *Sapindaceae/genetics/enzymology ; *Plant Proteins/genetics/metabolism ; Gene Expression Regulation, Plant ; Stress, Physiological/genetics ; },
abstract = {The terpene synthase (TPS) gene family is integral to the biosynthesis of terpenoids, which are vital for plant defence, development, and interaction with the environment. Yellowhorn (Xanthoceras sorbifolium) has gained attention for its bioactive compounds, particularly terpenoids, which have applications in pharmaceuticals, biofuels, and cosmetics. This study provides a comprehensive pan-genome-wide analysis of the TPS gene family across five yellowhorn varieties (Xg11, Xzs4, Xwf8, Xjg, and Xzg2). A total of 257 TPS genes were identified and characterised, showing diversity in their evolutionary patterns. Phylogenetic analysis revealed distinct clades corresponding to functional classes of TPS genes. Conserved domains and motifs of these genes were analysed to highlight their structural characteristics. Furthermore, expression profiling under abiotic stresses, including cold and drought, was conducted, revealing the roles of specific TPS genes in stress tolerance. Tissue-specific expression analysis demonstrated the involvement of TPS genes in key physiological processes across different plant organs. This research advances our understanding of the TPS gene family in yellowhorn, with implications for improving crop resilience and biotechnological applications.},
}

*Alkyl and Aryl Transferases/genetics/metabolism
Phylogeny
*Multigene Family
*Genome, Plant/genetics
*Sapindaceae/genetics/enzymology
*Plant Proteins/genetics/metabolism
Gene Expression Regulation, Plant
Stress, Physiological/genetics

@article {pmid41133102,
year = {2025},
author = {Shi, Y and Liu, L and Wu, J and Gao, M and Sheng, K and Hou, W and Li, X and Wang, H},
title = {Whole-genome sequencing and analysis of a novel strain Streptococcus oralis CRC211 from colorectal tumor.},
journal = {Microbiome research reports},
volume = {4},
number = {3},
pages = {33},
pmid = {41133102},
issn = {2771-5965},
abstract = {Aim: This study provides a comprehensive genomic characterization of Streptococcus oralis CRC211, a novel bacterial strain isolated from colorectal tumor tissue. Methods: Whole-genome sequencing and comparative genomic analyses were performed. Results: The high-quality assembled genome (15.03 Mb, 40.94% guanine-cytosine content) contains 2 prophage regions spanning 160.5 kb, which may facilitate the horizontal transfer of virulence genes. Functional annotation identified 3,674 genes, with significant enrichment in metabolic pathways (amino acid and carbohydrate metabolism) and virulence factors (116 genes in Virulence Factors Batabase), including adhesins and biofilm-associated proteins that likely promote tumor colonization. Comparative genomic analysis revealed that CRC211 shares 92.29% average nucleotide identity with reference Streptococcus oralis strains, while pan-genome analysis demonstrated an open genome structure with 1,222 conserved core genes. In addition, the strain also carries 75 antimicrobial resistance genes, underscoring its potential clinical relevance. Notably, the genomic profile indicates adaptations for nutrient acquisition and immune evasion in the tumor microenvironment. Conclusion: These findings establish CRC211 as a colorectal cancer (CRC)-associated strain with distinct genomic features that may contribute to tumor progression. The study provides critical insights into its possible oncogenic mechanisms and highlights potential applications in mic ases,indels - changerobiota-based diagnostics or therapeutics for colorectal cancer.},
}

@article {pmid41132938,
year = {2025},
author = {Wang, J and Zhou, Q and Liu, Y and Li, R and Lan, L and Zhao, J and Yang, Z and Jia, Y and Hu, H},
title = {Editorial: Exploring structural variants in plant pangenomics: innovations and applications.},
journal = {Frontiers in plant science},
volume = {16},
number = {},
pages = {1700222},
pmid = {41132938},
issn = {1664-462X},
}

@article {pmid41132369,
year = {2025},
author = {Huang, Z and Ren, Q and Du, X and Cao, S and Li, Y},
title = {Epidemiological and comparative genomic analysis of pathogenic Glaesserella parasuis from livestock agriculture in Shandong, China.},
journal = {Frontiers in microbiology},
volume = {16},
number = {},
pages = {1698342},
pmid = {41132369},
issn = {1664-302X},
abstract = {Glaesserella parasuis (G. parasuis) is the causative agent of Glässer's disease, posing a significant economic threat to the livestock agriculture. The present study aimed to investigate the prevalence of G. parasuis in six regions of Shandong Province, China, from June 2023 to November 2024, and to analyze the whole genome of G. parasuis isolates using whole genome sequencing (WGS). This study conducted a comprehensive analysis of the isolates, encompassing antibiotic resistance profiling, virulence gene detection, multilocus sequence typing (MLST), prophage detection, and pan-genome analysis. The prevalence of G. parasuis ranged from 10.8 to 26.5% across different cities in Shandong Province, exhibiting significant seasonal variation (p < 0.01). Among the 45 isolates, serovar 4 accounted for the highest proportion (40%). Antibiotic resistance testing revealed that 55.6% of isolates demonstrated multidrug-resistance (MDR). WGS analysis revealed that 18 distinct sequence types (STs) were identified across the 45 isolates, including 13 newly discovered STs. Notably, all isolates possessed complete prophage sequences. Pan-genome and phylogenetic analysis of 145 G. parasuis strains indicated that G. parasuis possesses an open pan-genome with genetic diversity. In summary, these data enhance our understanding of the molecular characteristics and epidemiological risks of G. parasuis in Shandong Province, China, particularly regarding livestock agriculture.},
}

@article {pmid41131485,
year = {2025},
author = {Sorin, V and Naji, MM and Birbes, C and Grohs, C and Escouflaire, C and Fritz, S and Eché, C and Marcuzzo, C and Suin, A and Donnadieu, C and Gaspin, C and Iampietro, C and Milan, D and Drouilhet, L and Tosser-Klopp, G and Boichard, D and Klopp, C and Sanchez, MP and Boussaha, M},
title = {Application of a French cattle pangenome, from structural variant discovery to association studies on key phenotypes.},
journal = {Genetics, selection, evolution : GSE},
volume = {57},
number = {1},
pages = {61},
pmid = {41131485},
issn = {1297-9686},
abstract = {BACKGROUND: The current cattle reference genome assembly, a pseudo-linear sequence produced using sequences from a single Hereford cow, represents a limitation when performing genetic studies, especially when investigating the whole spectrum of genetic variations within the species. Detecting structural variations (SVs) poses significant challenges when relying solely on conventional methods of sequencing read mapping to the current bovine genome assembly.

RESULTS: In this study, we used long-reads (LR) and bioinformatic tools to construct a comprehensive bovine pangenome, using as a backbone the Hereford ARS-UCD1.2 reference genome assembly, and incorporating genetic diversity of 64 good quality de novo genome assemblies representing 14 French dairy and beef cattle breeds. Using a combination of complementary approaches, we explored the pangenome graph and identified 2.563 Gb of sequences common to all samples, and cumulated 0.295 Gb of variable sequences. Notably, we discovered 0.159 Gb of novel sequences not present in the current reference genome assembly. Our analysis also revealed 109,275 SVs, of which 84,612 were bi-allelic. These included 27,171 insertions and 24,592 deletions, while the remaining 32,849 SVs corresponded to alternate allele sequences defined as sequence substitutions between the reference genome and the sample sequence. Genome-wide association studies using SNPs and a panel of 221 SVs, shared between the pangenome and the EuroGMD chip, revealed well-known QTLs across the genome for the Holstein, Montbéliarde and Normande breeds. Among those, a QTL on chromosome 11 presents an SV with a highly significant effect on stature in the Holstein breed. This SV is a 6.2 kb deletion affecting the 5'UTR, first exon and part of the first intron of the MATN3 gene, suggesting a potential regulatory and coding effect.

CONCLUSIONS: Our study provides new insights into the genetic diversity of 14 French dairy and beef breeds and highlights the utility of pangenome graphs in capturing structural variation. The identified SV associated with stature highlights the importance of integrating SVs into GWAS for a more comprehensive understanding of complex traits.},
}

@article {pmid41126024,
year = {2025},
author = {Man, Q and Li, W and Gao, S and Liu, F and Sun, S and Liu, X and Lin, B and Wang, L and Ding, M and Chen, X and Cui, J},
title = {Pan-genome identification and expression analysis of the ARF gene family in potato.},
journal = {BMC plant biology},
volume = {25},
number = {1},
pages = {1435},
pmid = {41126024},
issn = {1471-2229},
support = {SG2012016//Hebei province detoxigenic potato breeding technology innovation center/ ; SG2012016//Hebei province detoxigenic potato breeding technology innovation center/ ; SG2012016//Hebei province detoxigenic potato breeding technology innovation center/ ; SG2012016//Hebei province detoxigenic potato breeding technology innovation center/ ; SG2012016//Hebei province detoxigenic potato breeding technology innovation center/ ; SG2012016//Hebei province detoxigenic potato breeding technology innovation center/ ; SG2012016//Hebei province detoxigenic potato breeding technology innovation center/ ; SG2012016//Hebei province detoxigenic potato breeding technology innovation center/ ; SG2012016//Hebei province detoxigenic potato breeding technology innovation center/ ; SG2012016//Hebei province detoxigenic potato breeding technology innovation center/ ; SG2012016//Hebei province detoxigenic potato breeding technology innovation center/ ; SC2021028//Hebei Potato Seed Potato Industry Technology Research Institute/ ; SC2021028//Hebei Potato Seed Potato Industry Technology Research Institute/ ; SC2021028//Hebei Potato Seed Potato Industry Technology Research Institute/ ; SC2021028//Hebei Potato Seed Potato Industry Technology Research Institute/ ; SC2021028//Hebei Potato Seed Potato Industry Technology Research Institute/ ; SC2021028//Hebei Potato Seed Potato Industry Technology Research Institute/ ; SC2021028//Hebei Potato Seed Potato Industry Technology Research Institute/ ; SC2021028//Hebei Potato Seed Potato Industry Technology Research Institute/ ; SC2021028//Hebei Potato Seed Potato Industry Technology Research Institute/ ; SC2021028//Hebei Potato Seed Potato Industry Technology Research Institute/ ; SC2021028//Hebei Potato Seed Potato Industry Technology Research Institute/ ; 202206F013//Hebei (Chengde) Potato Seed Potato Industry Technology Research Institute improved innovation ability/ ; 202206F013//Hebei (Chengde) Potato Seed Potato Industry Technology Research Institute improved innovation ability/ ; 202206F013//Hebei (Chengde) Potato Seed Potato Industry Technology Research Institute improved innovation ability/ ; 202206F013//Hebei (Chengde) Potato Seed Potato Industry Technology Research Institute improved innovation ability/ ; 202206F013//Hebei (Chengde) Potato Seed Potato Industry Technology Research Institute improved innovation ability/ ; 202206F013//Hebei (Chengde) Potato Seed Potato Industry Technology Research Institute improved innovation ability/ ; 202206F013//Hebei (Chengde) Potato Seed Potato Industry Technology Research Institute improved innovation ability/ ; 202206F013//Hebei (Chengde) Potato Seed Potato Industry Technology Research Institute improved innovation ability/ ; 202206F013//Hebei (Chengde) Potato Seed Potato Industry Technology Research Institute improved innovation ability/ ; 202206F013//Hebei (Chengde) Potato Seed Potato Industry Technology Research Institute improved innovation ability/ ; 202206F013//Hebei (Chengde) Potato Seed Potato Industry Technology Research Institute improved innovation ability/ ; },
abstract = {BACKGROUND: The auxin response factor (ARF) is a key regulator involved in plant growth, development, and stress response. In this study, we systematically identified the ARF gene family using a pan-genomic approach based on 47 high-quality potato genomes.

RESULTS: Among the 28 members of the potato ARF pan-gene family, no core or private genes were identified. Only one gene was classified as near-core, while the remaining genes were considered non-essential. Ka/Ks analysis indicated that a single gene was under positive selection, whereas the rest of the family members were subject to purifying selection. Structural variations across the 21 potato genomes did not significantly alter the expression of ARF pan-gene family members, and no notable expression differences were detected. However, these structural variations did lead to changes in conserved domains in certain strains. RNA-seq analysis revealed differential expression of ARF family members under drought stress compared to control conditions, with variation in expression levels among different genes. Further investigation suggested that transcription factors are involved in regulating the expression of ARF gene family members.

CONCLUSIONS: Our findings revealed the function of the auxin response-factor family members in biological processes in potato, and provide a new theoretical reference for drought resistance-breeding in this important crop species.},
}

@article {pmid41117958,
year = {2025},
author = {Koech, N and Muoma, J and Banerjee, A and Okoth, P and Wekesa, C},
title = {Modular evolution and regulatory diversification of nodD-like LysR-type transcriptional regulators in α-Proteobacteria.},
journal = {Archives of microbiology},
volume = {207},
number = {12},
pages = {327},
pmid = {41117958},
issn = {1432-072X},
mesh = {*Bacterial Proteins/genetics/metabolism/chemistry ; *Transcription Factors/genetics/metabolism/chemistry ; *Gene Expression Regulation, Bacterial ; *Evolution, Molecular ; *Alphaproteobacteria/genetics/classification/metabolism ; Phylogeny ; Gene Transfer, Horizontal ; Genome, Bacterial ; Operon ; Symbiosis ; },
abstract = {The nodD gene encodes a LysR-type transcriptional regulator critical for nodulation gene expression in rhizobia, yet its evolutionary origin, structural plasticity, and regulatory reach beyond symbiosis remain incompletely resolved. Here we investigate the genomic organization, structural variation, and functional diversification of nodD and its homologs across α-proteobacteria with selected outgroups. Using orthogroup-based pangenome clustering, dated species trees, and gene-tree-species-tree reconciliation, we reconstruct the evolutionary trajectory of nodD, indicating emergence from ancient LTTRs deep in proteobacterial history. Reconciliation reveals widespread duplication and horizontal gene transfer (HGT), with several rhizobia showing notable duplication and exchange, and marine/non-rhizobial taxa contributing to a mosaic of nodD-like genes. Gene-neighborhood and operon analyses show conserved syntenic tendencies in classical rhizobia but extensive architectural divergence in free-living lineages, including frequent monocistronic anchors with extended upstream regions and, when polycistronic, enrichment for transporters and local metabolic enzymes within compact multi-regulator cassettes. Structural comparisons with AlphaFold and PyMOL confirm the canonical LTTR fold while uncovering species-specific deviations concentrated in effector-binding loops and interfaces. Motif discovery and genome-wide scanning identify targets involved in metabolism, stress responses, and transcriptional control, and network analysis reveals modular connectivity spanning core metabolism and accessory processes such as secondary metabolism, transport, and biofilm-associated functions. These findings portray nodD as a structurally conserved yet functionally flexible regulator repeatedly reshaped by duplication, HGT, and local genome context, extending nodD-like systems beyond symbiosis and broadening the regulatory landscape of bacterial LTTRs.},
}

*Bacterial Proteins/genetics/metabolism/chemistry
*Transcription Factors/genetics/metabolism/chemistry
*Gene Expression Regulation, Bacterial
*Evolution, Molecular
*Alphaproteobacteria/genetics/classification/metabolism
Phylogeny
Gene Transfer, Horizontal
Genome, Bacterial
Operon
Symbiosis

@article {pmid41115209,
year = {2025},
author = {Xue, Z and Wang, Y and Wang, X and Yuan, J and Wang, L and Zeng, J and Jin, X and Zhu, H and Wang, J},
title = {PangenomeX: a graph convolutional network-based pangenome framework for unbiased population-scale genomic variation analysis.},
journal = {Briefings in bioinformatics},
volume = {26},
number = {5},
pages = {},
doi = {10.1093/bib/bbaf550},
pmid = {41115209},
issn = {1477-4054},
support = {72293581//National Natural Science Foundation of China/ ; 72274152//National Natural Science Foundation of China/ ; 62402376//National Natural Science Foundation of China/ ; },
mesh = {Humans ; *DNA Copy Number Variations ; *Genomics/methods ; Polymorphism, Single Nucleotide ; *Genome, Human ; *Software ; Phylogeny ; Genetics, Population ; Whole Genome Sequencing ; },
abstract = {In population-scale genomic variation studies based on shallow whole genome sequencing, pangenomes have become an effective tool for identifying population-specific single-nucleotide polymorphisms and indels. Extending these advantages to copy number variation (CNV), however, remains challenging due to two unresolved issues. First, current pangenome frameworks exhibit pronounced population-representation bias arising from uneven sampling across populations. As the number of samples increases, the pangenome tends to capture variations primarily from majority populations while suppressing signals from minority populations. Second, in population-scale genomic variation analyses, common but benign population-specific copy number polymorphisms (CNPs) frequently obscure pathogenic CNVs. Existing pangenome frameworks lack dedicated mechanisms for representing CNPs and CNVs, limiting their ability to distinguish pathogenic CNVs from benign, population-specific CNPs. In this study, we present PangenomeX, a graph-convolutional pangenome framework tailored for low-coverage, population-scale CNV analysis. To address CNP representation, we embed known CNPs as prior knowledge into the pangenome graph and construct a CNV relationship network guided by a phylogenetic tree. A graph convolutional network (GCN) then learns the interactions between CNV and CNP nodes. To mitigate population-representation bias, the GCN aggregates information from only one- and two-hop neighborhoods, preserving local population context while preventing majority group signals from dominating. Evaluation on simulated cohorts and 561 real samples shows that PangenomeX distinguishes pathogenic CNVs from common population CNPs markedly better than existing methods. Overall, PangenomeX offers a methodological blueprint for large-cohort variant screening and provides a practical path for bringing graph-based genomics into clinical practice.},
}

Humans
*DNA Copy Number Variations
*Genomics/methods
Polymorphism, Single Nucleotide
*Genome, Human
*Software
Phylogeny
Genetics, Population
Whole Genome Sequencing

@article {pmid41114918,
year = {2025},
author = {Wei, ZY and Li, SX and Li, MH and Tang, J and Jiang, YQ and Lu, XY and Zhang, YM and Xue, JY},
title = {Pan-genomic insights into RLK family evolution and adaptation in Dioscorea alata.},
journal = {Plant molecular biology},
volume = {115},
number = {6},
pages = {114},
pmid = {41114918},
issn = {1573-5028},
}

@article {pmid41114504,
year = {2025},
author = {Bahati, SY and Maghembe, RS},
title = {Pangenome analysis of Tanzanian clinical Klebsiella pneumoniae reveals pandemic clones with high genome plasticity and versatile mobilome, virulome, and resistome profiles.},
journal = {Microbiology spectrum},
volume = {},
number = {},
pages = {e0194725},
doi = {10.1128/spectrum.01947-25},
pmid = {41114504},
issn = {2165-0497},
abstract = {Klebsiella pneumoniae is a rapidly evolving pathogen with a diverse pangenome whose mobilome and resistome remain elusive. Here, we aimed to delineate the pangenome of 198 isolates from Tanzanian regions. Raw Illumina reads retrieved from public repositories were assembled and analyzed using multilocus sequence typing, core-genome single nucleotide polymorphism (SNP)-based phylogeny, and capsular polysaccharide (K-locus) and lipopolysaccharide O-antigen (O-locus) typing. A total of 184 isolates were classified as Klebsiella pneumoniae sensu stricto, while 14 belonged to other species within the Klebsiella pneumoniae complex. We identified 90 sequence types (STs), including global high-risk ST45, ST39, ST336, ST14, ST1552, and ST17. KL24 and KL25 were the most common K-loci, while OL2α.1 and OL2α.2 were dominant O-loci. Pangenome analysis revealed 30,992 gene families, distributed as persistent (13.6%), shell (11.2%), and cloud (75.2%) genes, suggesting an open pangenome structure. Core-genome SNP-based phylogeny confirmed clonal expansion and lineage clustering. Virulence profiling showed yersiniabactin in 44% of isolates. Most genomes carried key fimbrial and iron uptake genes. Resistome analysis revealed near-universal presence of bla_CTX-M-15, oqxA/B, fosA6, sul2, and marA. Plasmid typing identified IncF-type (76%) and Col-type (54%) plasmids, while over 120 mobile genetic elements were detected, whose frequencies were on a huge spectrum of insertion sequences (e.g., IS5075 and MITEYpe1) and transposons (e.g., Tn5403 and Tn6082). Conclusively, Tanzanian K. pneumoniae strains exhibit extensive genomic plasticity, high-risk lineages, and a versatile mobilome, calling for national genomic surveillance to inform intervention strategies.IMPORTANCEThe Klebsiella pneumoniae complex comprises a diverse group of bacterial pathogens adapted to thrive over a wide range of environments. Isolates from clinical and environmental samples are implicated in nosocomial infections and multidrug resistance, with similar genome structures and inherent genes. Our study presents the first pangenome report underlying genomic plasticity of K. pneumoniae isolates from Tanzanian clinical specimens, demonstrating versatile clones, mobilome, and resistome profiles. Combining these profiles with the versatility of K and O structures, our study emphasizes the need for comprehensive multidisciplinary surveillance studies to optimize therapeutic and vaccine development.},
}

@article {pmid41110766,
year = {2025},
author = {Saint-Charles, A and Masliah-Planchon, J and Saberi-Ansari, E and Bellini, A and Bernkopf, M and Font de Mora, J and Salvá, RN and Van Roy, N and Goodman, A and Vicha, A and Attignon, V and Combaret, V and Beiske, K and Martinsson, T and Schoumans, J and Rossing, M and Tops, B and Westermann, F and Cotteret, S and Fischer, M and Birger, Y and Mazzocco, K and Chesler, L and Betts, D and Cowley, M and Capasso, M and Bobin, C and Iddir, Y and Zaidi, S and Carcaboso, AM and Vandermeulen, J and Loontiens, S and Gaarder, J and Ibrahim, RR and Rosswog, C and Hameiri-Grossman, M and Shichrur, K and Trahair, T and Barahona, P and Eggert, A and Deubzer, HE and Delattre, O and Pasqualini, C and George, S and Tytgat, G and Tweddle, DA and Taschner-Mandl, S and Schleiermacher, G},
title = {Harmonization of reporting for detection of ALK genetic alterations in neuroblastoma - a SIOPEN Biology study.},
journal = {The Journal of molecular diagnostics : JMD},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.jmoldx.2025.09.007},
pmid = {41110766},
issn = {1943-7811},
abstract = {In high-risk neuroblastoma, identification of ALK activating genetic alterations is considered for clinical decision-making in relapse or more recently frontline treatment. The accurate diagnosis of genetic alterations requires harmonization of molecular techniques and reporting especially when these are considered as inclusion criteria for clinical trials. Analysis and validation was preformed across the 21 SIOPEN (International Society of Paediatric Oncology Europe Neuroblastoma) molecular diagnostic laboratories, with 14 DNA samples harbouring distinct ALK alterations including ALK mutations in or outside hotspots in the tyrosine kinase domain (TKD) with variant allele frequencies (VAF) ranging from 1% to 91%, or ALK genomic amplification shared between the laboratories. Each laboratories employed their own established techniques: ALK amplifications were detected using either pan-genomic copy number techniques or fluorescence in situ hybridization and ALK mutations were characterized by Next Generation Sequencing (NGS) techniques. All laboratories correctly identified high-level ALK amplification and ALK mutations within the TKD hotspots with VAF >5%, with exception of 2 cases. Difference in interpretation and reporting was apparent for samples harbouring mutations with a VAF <5% or outside known hotspots. These results highlight the importance of standard operating procedures, standardized reporting, and the robustness of ALK genetic testing in the SIOPEN laboratories, as well as the need for expert discussions on atypical ALK alterations, to validate eligibility for ALK targeted treatment in clinical trials.},
}

@article {pmid41108646,
year = {2025},
author = {Jeon, JY and Allen, NM and Black, AN and DeWoody, JA},
title = {Short-Read Pangenomes and Their Potential Utility in Population and Conservation Genomics.},
journal = {Molecular ecology resources},
volume = {},
number = {},
pages = {e70060},
doi = {10.1111/1755-0998.70060},
pmid = {41108646},
issn = {1755-0998},
abstract = {As a collection of all the genetic variants in the gene pool, the pangenome is a concept that will become fundamental to conservation genomic studies. Unfortunately, most pangenomic approaches developed for humans and model organisms are financially impractical for conservation genomic studies of threatened or endangered species due to the high costs associated with deep sequencing multiple individuals using long-read platforms. Here, by integrating metagenomic and iterative map-then-assemble approaches, we (1) propose novel workflows to construct graph pangenomes from multiple low-coverage short-read datasets; (2) benchmark these short-read pangenomes (both linear and graph) against a previously published long-read graph pangenome of the barn swallow; and (3) evaluate the utility of our workflows in population and conservation genomics. Our results indicate that economical short-read graph pangenomes can recover the vast majority of the variants identified through expensive long-read graph approaches, and that these variants accurately detect important biological signals (e.g., spatial structure and independent taxonomic delineations). These results mean that researchers can utilize their limited, conservation-oriented funding to more fully characterize all the variants in a particular gene pool for population-level analyses.},
}

@article {pmid41107551,
year = {2025},
author = {Prodanov, T and Plender, EG and Seebohm, G and Meuth, SG and Eichler, EE and Marschall, T},
title = {Locityper enables targeted genotyping of complex polymorphic genes.},
journal = {Nature genetics},
volume = {},
number = {},
pages = {},
pmid = {41107551},
issn = {1546-1718},
support = {R01 HG002385/HG/NHGRI NIH HHS/United States ; R01 HG002385/HG/NHGRI NIH HHS/United States ; },
abstract = {The human genome contains many structurally variable polymorphic loci, including several hundred disease-associated genes, almost inaccessible for accurate variant calling. Here we present Locityper, a tool capable of genotyping such challenging genes using short-read and long-read whole-genome sequencing. For each target, Locityper recruits and aligns reads to locus haplotypes, for instance, extracted from a pangenome, and finds the likeliest haplotype pair by optimizing read alignment, insert size and read depth profiles. Across 256 challenging medically relevant loci, Locityper achieves a median quality value (QV) above 35 from both long-read and short-read data, outperforming state-of-the-art Illumina and PacBio HiFi variant calling pipelines by 10.9 and 1.7 points, respectively. Furthermore, Locityper provides access to hyperpolymorphic HLA genes and other gene families, including KIR, MUC and FCGR. With its low running time of 1 h 35 m per sample at eight threads, Locityper is scalable to biobank-sized cohorts, enabling association studies for previously intractable disease-relevant genes.},
}

@article {pmid41107550,
year = {2025},
author = {Ma, W and Chaisson, MJP},
title = {Genotyping sequence-resolved copy number variation using pangenomes reveals paralog-specific global diversity and expression divergence of duplicated genes.},
journal = {Nature genetics},
volume = {},
number = {},
pages = {},
pmid = {41107550},
issn = {1546-1718},
support = {U01HG010973//U.S. Department of Health & Human Services | NIH | National Human Genome Research Institute (NHGRI)/ ; },
abstract = {Copy number variable (CNV) genes are important in evolution and disease, yet their sequence variation remains a blind spot in large-scale studies. We present ctyper, a method that leverages pangenomes to produce allele-specific copy numbers with locally phased variants from next-generation sequencing samples. Benchmarking on 3,351 CNV genes and 212 challenging medically relevant (CMR) genes, ctyper captures 96.5% of phased variants with ≥99.1% correctness of copy number in CNV genes and 94.8% of phased variants in CMR genes. Ctyper takes 1.5 h to genotype a genome on one CPU. The ctyper genotypes give a 4.81-fold improvement in predictions of gene expression compared to known expression quantitative trait locus (eQTL) variants. Allele-specific expression quantified divergent expression in 7.94% of paralogs and tissue-specific biases in 4.68%. We found reduced expression of SMN2 due to SMN1 conversion, potentially affecting spinal muscular atrophy, and increased expression of translocated duplications of AMY2B. Overall, ctyper enables biobank-scale genotyping of CNV and CMR genes.},
}

@article {pmid41106384,
year = {2025},
author = {Liu, HS and Wang, WH and Song, YF and Yang, Y and Zhang, DY and Bai, WN and Zhang, BW},
title = {A pan-genome framework reveals structural variation and small RNA regulation underlying heterodichogamy in Pterocarya.},
journal = {Current biology : CB},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.cub.2025.09.017},
pmid = {41106384},
issn = {1879-0445},
abstract = {Heterodichogamy, characterized by reciprocal timing of male and female flowering, promotes disassortative mating yet remains poorly understood at the genomic level. Here, we investigated this mating system in Pterocarya, a genus within Juglandaceae, using a low-input pan-genome framework that integrates phased assemblies with population resequencing. We identified a deeply divergent 78-kb locus associated with mating morphs in P. stenoptera, marked by repeat-rich structural variants and containing a FAF-like gene linked to floral development. This region also produces small RNAs that potentially regulate key floral and hormonal pathways, suggesting pleiotropic trans-regulatory effects. Comparative analyses reveal that although the loci controlling heterodichogamy in Juglans, Carya, and Pterocarya are non-homologous, they appear to share convergent evolutionary solutions involving tandem repeats or transposable element (TE) insertions. Our study uncovers the genomic basis of heterodichogamy in Pterocarya and underscores the utility of pan-genome approaches for dissecting structural variation-associated traits.},
}

@article {pmid41101942,
year = {2025},
author = {Lim, SL and Chin, CH and Chiou, YJ and Hsu, MT and Chiang, PW and Chen, HJ and Tu, YC and Tzou, WS and Tang, SL},
title = {Unveiling Unusual Ecofunctional Traits of Endozoicomonas Species Through Comprehensive Comparative Genomics.},
journal = {Environmental microbiology},
volume = {27},
number = {10},
pages = {e70191},
doi = {10.1111/1462-2920.70191},
pmid = {41101942},
issn = {1462-2920},
support = {AS-IA-109-L05//Academia Sinica/ ; },
mesh = {*Genome, Bacterial ; Genomics ; Phylogeny ; Prophages/genetics ; Bacterial Proteins/genetics ; *Gammaproteobacteria/genetics ; Quorum Sensing ; },
abstract = {Endozoicomonas is an omnipresent marine bacterial genus, associated with various marine organisms, that contributes to host health, nutrient cycling and disease resistance. Nonetheless, its genomic features remain poorly characterised due to a paucity of high-quality genomes. In this study, we sequenced 5 novel Endozoicomonas strains and re-sequenced 1 known strain to improve genomic resolution. By integrating these 6 high-quality genomes with 31 qualified published genomes, our pan-genomic analysis revealed variation in genetic traits among clades. Notably, Endozoicomonas lacks quorum-sensing capabilities, suggesting resistance to quorum quenching mechanisms. It also lacks the capacity to synthesise and transport vitamin B12, indicating that it does not supply this nutrient to holobionts. Remarkably, Endozoicomonas genomes encode 92 identified giant proteins (15-65 kbp). These proteins cluster into three major groups associated with antimicrobial peptide synthesis, exotoxin production and cell adhesion. Additionally, we found that Endozoicomonas has acquired prophages from diverse sources via infection or other types of gene transfer. Notably, CRISPR-Cas sequences suggest evolutionary trajectories independent of both prophage acquisition and phylogenetic lineage, implying potential geographic influences or environmental pressures. This study provides new insights into the genomic diversity of Endozoicomonas and its genetic adaptations to diverse hosts.},
}

*Genome, Bacterial
Genomics
Phylogeny
Prophages/genetics
Bacterial Proteins/genetics
*Gammaproteobacteria/genetics
Quorum Sensing

@article {pmid41100528,
year = {2025},
author = {Deschner, D and Hill, JE},
title = {Identification of genes that differentiate Mannheimia haemolytica genotypes 1 and 2 using a pangenome approach.},
journal = {PloS one},
volume = {20},
number = {10},
pages = {e0325338},
doi = {10.1371/journal.pone.0325338},
pmid = {41100528},
issn = {1932-6203},
mesh = {*Mannheimia haemolytica/genetics/pathogenicity/classification ; Genotype ; *Genome, Bacterial ; Animals ; Cattle ; *Genes, Bacterial ; Bacterial Proteins/genetics ; },
abstract = {Mannheimia haemolytica is an opportunistic bacterial pathogen associated with the economically costly bovine respiratory disease. Two genotypes have been described, of which genotype 2 is more strongly associated with disease. Several previous studies have investigated the genomic differences between the genotypes and/or the major serotypes (1, 2 and 6) of M. haemolytica, however we still lack a clear basis for the greater disease association of genotype 2 (serotypes 1 and 6) and demonstrations of phenotypic differences are scarce. This work builds upon previous investigations to identify genes that differentiate the two genotypes with a particular focus on genes that may play a role in virulence and fitness in the respiratory tract microbiome. We identified 422 genotype differentiating genes in a collection of 206 unique M. haemolytica genomes (61 genotype 1, 145 genotype 2). Genotype differentiating genes included genotype-associated variants of a TonB-dependent siderophore receptor homolog, transferrin binding protein B, leukotoxin A, and IgA1 proteases. We also identified a genotype 1 associated lytic transglycosylase, and a genotype 2 specific highly immunogenic outer membrane lipoprotein. Genotype 2 genomes were significantly larger in size and contained more predicted protein coding genes than genotype 1 genomes. These results expand our knowledge of what differentiates the genotypes 1 and 2 of M. haemolytica and provides information that can be used as the basis for laboratory investigations of corresponding phenotypic differences.},
}

*Mannheimia haemolytica/genetics/pathogenicity/classification
Genotype
*Genome, Bacterial
Animals
Cattle
*Genes, Bacterial
Bacterial Proteins/genetics

@article {pmid41097617,
year = {2025},
author = {Abitayeva, G and Kurmangali, D and Baikonys, T and Bekshin, Z},
title = {Lacticaseibacillus paracasei subsp. paracasei 2LB: Identification of Genes to Assess the Safety and Probiotic Potential of the Strain.},
journal = {Foods (Basel, Switzerland)},
volume = {14},
number = {19},
pages = {},
doi = {10.3390/foods14193449},
pmid = {41097617},
issn = {2304-8158},
support = {АР19679863//This research has been funded by the Science Committee of the Ministry of Science and Higher Education of the Republic of Kazakhstan/ ; },
abstract = {In this study, we conducted a whole-genome analysis of the Lacticaseibacillus paracasei subsp. paracasei 2LB isolated from Kazakh traditional fermented milk (koumiss) to identify genes associated with the safety and probiotic potential of the strain. A comparative genomic analysis of the core and pan-genome of L. paracasei 2LB was performed. Functional annotation revealed the presence of genes putatively involved in metabolism, genetic information processing, and cellular processes. In terms of safety parameters, the stability of its genetic material, the absence of the ability to synthesize virulence factors, and genes responsible for antibiotic resistance were characterized. Also, in vitro studies of the L. paracasei 2LB strain showed resistance to stress factors and antimicrobial activity, and the presence of coding sequences encoding adhesion factors, bacteriocins, bile salts, pH, cold and heat shock, and osmotic stress was observed through genomic analysis. These results indicate that the L. paracasei 2LB strain is a potential probiotic candidate and demonstrate that whole-genome analysis is a useful method for assessing the quality and safety of probiotics.},
}

@article {pmid41097310,
year = {2025},
author = {Zhou, B and Nie, X and Mao, X and Chen, J and Chen, J and Ma, B and Wu, X},
title = {Novel ST-Specific Molecular Target-Based Method for Simultaneous and Quantitative Detection of Staphylococcus aureus ST7, ST188 and ST398.},
journal = {Molecules (Basel, Switzerland)},
volume = {30},
number = {19},
pages = {},
doi = {10.3390/molecules30193889},
pmid = {41097310},
issn = {1420-3049},
support = {20242BAB20333//Jiangxi Provincial Natural Science Foundation/ ; GSJK202401//Science and Technology Project of Jiangxi Provincial Administration for Market Regulation/ ; ZYK202403//Research Project of Jiangxi General Institute of Testing and Certification/ ; },
mesh = {*Staphylococcus aureus/genetics/isolation & purification/classification ; Food Microbiology ; Humans ; Staphylococcal Infections/microbiology/diagnosis ; Genome, Bacterial ; Limit of Detection ; Real-Time Polymerase Chain Reaction ; },
abstract = {Staphylococcus aureus is a globally crucial foodborne pathogen that can cause diarrhea, vomiting, and bloodstream infection in immunocompromised individuals. S. aureus has three predominant sequence types (STs) (ST7, ST188 and ST398) that are prevalent clones in both food and clinical cases. This study aimed to screen ST-specific targets for S. aureus ST7, ST188 and ST398, and then developed a novel rapid and accurate assay for the detection of these three predominant S. aureus STs in food. A total of 505 Staphylococcus strain genome sequences including 371 sequences of 58 different STs and 134 other non-target S. aureus ST genome sequences were subjected to pan-genome analysis; we successfully screened five novel ST-specific targets (group_10498 and group_10499 target for S. aureus ST7, group_9415 and group_9419 target for S. aureus ST188, group_9911 target for S. aureus ST398). The excellent specificity and sensitivity of all the targets were confirmed by PCR assays. Based on these molecular targets, mPCR and qPCR methods were developed for specifically identifying S. aureus' three predominant STs without non-target bacterial interference. The limits of detection (LODs) for the mPCR assay in artificially contaminated milk were determined to be 10[4] CFU/mL for ST7, 10[5] CFU/mL for ST188, and 10[4] CFU/mL for ST398, while the LODs achieved by the qPCR method were 8.6 × 10[2] CFU/mL, 1.2 × 10[2] CFU/mL, and 6.4 × 10[3] CFU/mL, respectively. The testing results for actual food samples suggested that the developed mPCR or qPCR assays could be used as an alternative to standard MLST analysis, for the rapid and reliable identification of S. aureus STs. The novel molecular detection technology established in this study provides an efficient and reliable detection method for the prevention and control of predominant S. aureus ST contamination in food and has important application potential and promotion prospects.},
}

*Staphylococcus aureus/genetics/isolation & purification/classification
Food Microbiology
Humans
Staphylococcal Infections/microbiology/diagnosis
Genome, Bacterial
Limit of Detection
Real-Time Polymerase Chain Reaction

@article {pmid41097292,
year = {2025},
author = {Buyuklyan, JA and Biryukov, MV and Zakalyukina, YV and Sacharov, AA},
title = {The Regulation of the Albomycin and Desferrioxamine E Biosynthesis in Streptomyces globisporus bja209.},
journal = {Molecules (Basel, Switzerland)},
volume = {30},
number = {19},
pages = {},
doi = {10.3390/molecules30193871},
pmid = {41097292},
issn = {1420-3049},
mesh = {*Streptomyces/metabolism/genetics ; *Anti-Bacterial Agents/biosynthesis/pharmacology ; *Deferoxamine/pharmacology ; Phylogeny ; Biosynthetic Pathways ; },
abstract = {We identified Streptomyces globisporus bja209 through a targeted screen of actinomycetes from natural habitats using an E. coli JW5503 ΔtolC DualRep2(c) reporter strain. This strain produced antibacterial compounds whose action depended on the growth medium. HPLC-MS and genomic analysis revealed two metabolites: albomycin δ2 (a translation inhibitor) and desferrioxamine E. The latter induced the SOS response. Desferrioxamine E exhibited a narrow spectrum of antagonistic activity against carbapenem-resistant A. baumannii and C. michiganensis, and its production was critically regulated by iron concentration. Notably, the structurally similar desferrioxamine B was inactive. Contrary to previous reports, pangenome analysis of published GenBank genomes revealed that albomycin BGC is restricted to specific S. globisporus strains and not present in other Streptomycetes phylogenetic clades. The C-1027 BGC was found in a large linear plasmid (165.5 kb) of the S. globisporus bja209 strain and also found exclusively on linear plasmids in some of the published S. globisporus genomes.},
}

*Streptomyces/metabolism/genetics
*Anti-Bacterial Agents/biosynthesis/pharmacology
*Deferoxamine/pharmacology
Phylogeny
Biosynthetic Pathways

@article {pmid41094142,
year = {2025},
author = {Loegler, V and Thiele, P and Teyssonnière, E and Tsouris, A and Brach, G and Cruaud, C and Payen, E and Engelen, S and Dunham, MJ and Hou, J and Friedrich, A and Schacherer, J},
title = {From genotype to phenotype with 1,086 near telomere-to-telomere yeast genomes.},
journal = {Nature},
volume = {},
number = {},
pages = {},
pmid = {41094142},
issn = {1476-4687},
abstract = {Unravelling the genetic basis of the remarkable phenotypic diversity observed in natural populations remains a central challenge in biology[1-4]. Despite major advances[5-19], no species has yet been characterized with a truly comprehensive atlas of genetic variation. Here we present an extensive genomic and phenotypic resource for the yeast Saccharomyces cerevisiae based on near telomere-to-telomere assemblies of 1,086 natural isolates. Leveraging these high-contiguity assemblies, we generated a highly complete species-wide structural variant atlas, gene-based pangenome and graph pangenome. By incorporating the full spectrum of genetic variation captured across the species, we conducted genome-wide association studies across 8,391 molecular and organismal traits[19-22]. The inclusion of structural variants and small insertion-deletion mutations improved heritability estimates by an average of 14.3% compared with analyses based only on single-nucleotide polymorphisms. Structural variants were more frequently associated with traits and exhibited greater pleiotropy than other variant types. Notably, the genetic architecture of molecular and organismal traits differed markedly. Together, this work provides a unique dataset that illuminates how diverse forms of genetic variation shape phenotypic diversity and lays the groundwork for integrative, genome-scale studies in other eukaryotic systems.},
}

@article {pmid41092514,
year = {2025},
author = {Goddard, M and Martín, JS and Molina-Mora, JA and Collado, L and Rodriguez, J and Galarce, N and Mella, A},
title = {Genetic diversity of Mycoplasma bovis isolated from bovine respiratory disease and bovine mastitis in Chile.},
journal = {Veterinary microbiology},
volume = {311},
number = {},
pages = {110752},
doi = {10.1016/j.vetmic.2025.110752},
pmid = {41092514},
issn = {1873-2542},
abstract = {Mycoplasma bovis, a major bacterial pathogen for cattle, is responsible for diseases such as pneumonia, mastitis, otitis, and arthritis, leading to substantial economic losses and animal welfare concerns. Despite its wide global distribution, there is limited information in South America. M. bovis has been reported as a mastitis agent in Chile, but its genetic diversity is poorly understood. Therefore, this study aimed to determine the genetic diversity of M. bovis isolates from Chilean dairy cattle (from bovine respiratory disease and mastitis cases) in the last two decades and evaluate their genetic relatedness with strains isolated in different countries using a whole genome sequencing approach. The M. bovis population in Chile was found to be highly homogeneous, with MLST and phylogenomic analysis identifying ST60 as the dominant clone, representing most of the isolates (97.8 %), while just one isolate was typed as ST12 (2.2 %). Phylogenomic analysis revealed close genetic relatedness among most Chilean isolates, showing a close genetic relationship with North American strains, forming a tight clade with Canadian ST60 strains, while the single Chilean ST12 isolate clustered with North American, Israeli, and European strains and clustered with the type strain (PG45) of this species. Moreover, the pangenome analysis confirms that M. bovis has an open pangenome, with a large range of accessory genes that remain largely unexplored and may hold key insights into its genome plasticity, thereby opening future research. The findings of this study provide the first insights into the Chilean population structure of M. bovis, contributing to the global epidemiology of this pathogen with a focus on South America. These results also open future research focused on the comprehensive characterization of this dominant clone, inspiring the scientific community to further exploration into the genetic diversity of M. bovis in Chile.},
}

@article {pmid41090561,
year = {2025},
author = {Zhang, T and Luo, D and Li, G and Wang, H and Cao, Q and Zhang, R and Li, Y and Zhu, Y and Ma, C and Liston, A and Sun, H and Qiao, Q},
title = {Multi-omics analyses shed lights on the evolution and fruit development of Chinese raspberries (Rubus spp.).},
journal = {Journal of integrative plant biology},
volume = {},
number = {},
pages = {},
doi = {10.1111/jipb.70052},
pmid = {41090561},
issn = {1744-7909},
support = {202301AS070071//Yunnan Fundamental Research Projects/ ; 202505AS350015//Yunnan Fundamental Research Projects/ ; 202501AS070177//Yunnan Fundamental Research Projects/ ; 32260094//National Natural Science Foundation of China/ ; 32372655//National Natural Science Foundation of China/ ; 82260739//National Natural Science Foundation of China/ ; 2024YFF1306702//National Key Research and Development Program of China/ ; },
abstract = {Rubus (raspberries and blackberries) is a large genus of over 700 species well known for its taxonomic challenges. Many of its species hold significant economic value as important edible and medicinal plants. Here, near-complete genomes for four wild diploid raspberry species were assembled, including R. ellipticus, R. niveus, as well as the highly heterozygous diploid red raspberry (R. idaeus), and its closely related species R. sachalinensis. Pan-genome analysis of Rubus identified 10,243 core gene families (64% of total), and highlights expansions of flavonoid/terpenoid pathways in Rubus, correlating with fruit bioactive compound diversity. Our discovery of shared ancestral components between R. idaeus and R. sachalinensis subgenomes provides evidence for their homoploid hybrid origin. The centromere sequence characteristics could serve as markers for subgenome assignment in R. idaeus and R. sachalinensis. Moreover, population genomic studies of 125 accessions from ca. 80 species uncovered widespread genetic introgression, particularly in red raspberries, with centromeric haplotype signatures tracing ancestral contributions to cultivated varieties. By integrating metabolome and transcriptome data, we explore the fruit quality regulatory network of Chinese raspberries. We identified a glutathione S-transferase gene that may inhibit the successful transport of anthocyanins into the vacuole and appears to be a limiting factor for the anthocyanin pigmentation in R. ellipticus fruits. In summary, this research sheds new light on the genetic intricacies of raspberry species and their cultivars, and provides a robust foundation for horticultural improvement and genomic selection in raspberry breeding.},
}

@article {pmid41087872,
year = {2025},
author = {Wang, Y and Meng, S and Bahetijiang, H and Li, H and Wang, T and Assabayev, T and Barkema, HW and Kastelic, JP and Han, B and Deng, Z},
title = {Phenotypic and genotypic characterization of ST103 serotype Ia Streptococcus agalactiae isolated from bovine mastitis in China.},
journal = {BMC microbiology},
volume = {25},
number = {1},
pages = {662},
pmid = {41087872},
issn = {1471-2180},
support = {31772813//National Natural Science Foundation of China/ ; G2022108009L//High-end Foreign Experts Recruitment Plan of China/ ; 6244052//Natural Science Foundation of Beijing, China/ ; },
abstract = {Streptococcus agalactiae is a contagious pathogen responsible for bovine mastitis, leading to significant economic losses in the global dairy industry. Our objectives were to determine the population structure, to profile the antimicrobial resistance and to investigate the pathogenicity and genes associated with pathogenicity in S. agalactiae isolated from Chinese dairy herds. A total of 266 milk samples were collected on three dairy farms in Ningxia (herd A) and Hebei provinces (herds B & C) with outbreaks of bovine mastitis from September 2020 to April 2021. There were 116 isolates identified as Streptococcus agalactiae by 16S rRNA sequencing. Twenty-seven S. agalactiae isolates were randomly selected using a stratified approach from the three farms for whole genome sequencing analysis and phenotypic analyses, including antimicrobial resistance profiling, identification of adhesion, invasion and virulence genes using in vitro bovine mammary epithelial cell models and in vivo Galleria mellonella models. Multilocus sequence typing and serotyping showed that all isolates belonged to sequence type ST103 and serotype Ia. In total, 34 genes were identified as virulence genes in Streptococcus species. Isolates from herd C had significantly higher virulence than those from herd B. Genome-wide association analysis revealed 166 virulence-related genes, 221 adhesion-related genes and 218 invasion-related genes. Furthermore, 47 genes were associated with pathogenicity in infecting G. mellonella. Resistance to tetracycline and macrolides was related to the presence of antimicrobial resistance genes tetO, tetM, and ermB. Pan-genome analyses revealed that 1,421 S. agalactiae isolates (27 from our study and 1,394 from the NCBI genome database) had 20,955 genes, including 666 and 20,289 genes in the core and accessory genomes, respectively. This study characterized the phenotypic and genotypic profiles for S. agalactiae, and identified associations between phenotypic traits and genetic determinants of virulence and antimicrobial resistance, providing new insights into controlling S. agalactiae mastitis in Chinese dairy herds.},
}

@article {pmid41087377,
year = {2025},
author = {Karouia, F and de Oliveira, LC and Hameed, A and Simpson, A and Singh, N and Rekha, PD and Mason, CE and Venkateswaran, K},
title = {Genomic characterization of Microbacterium meiriae sp. nov., a novel bacterium isolated from the International Space Station.},
journal = {Scientific reports},
volume = {15},
number = {1},
pages = {35770},
pmid = {41087377},
issn = {2045-2322},
support = {19-12829-26//National Aeronautics and Space Adminstration/ ; },
mesh = {Phylogeny ; RNA, Ribosomal, 16S/genetics ; *Genome, Bacterial ; *Microbacterium/genetics/isolation & purification/classification ; *Spacecraft ; Whole Genome Sequencing ; DNA, Bacterial/genetics ; Genomics/methods ; Russia ; },
abstract = {During the microbial surveillance of the International Space Station (ISS) in April 2018, four Gram-stain positive bacterial strains, designated as F6_8S_P_2B[T], F6_8S_P_3A, F6_8S_P_3B and F6_8S_P_3C, belonging to the genus Microbacterium were isolated from the walls of crew quarters. All four strains exhibited high 16S rRNA gene sequence similarity (> 99%), low average nucleotide identity (93%), and < 49.7% digital DNA: DNA hybridization values with the closest recognized Microbacterium paraoxydans DSM 15019[T], delineating new phylogenetic branches within the genus. Further whole-genome sequencing (WGS) and phylogenomic analysis revealed a close genetic relationship (> 98% ANI; > 83% dDDH) between the ISS strains and Microbacterium sp. LTR1 strain isolated from the larva skin of Lissotriton vulgaris from Tula region, Russia, which was misidentified as M. paraoxydans. The pangenomic analysis also shows high correlation between the ISS strains and their proximity to the type strain M. paraoxydans DSM 15019[T]. These analyses suggest that strain LTR1, previously characterized as M. paraoxydans, should be included in this new Microbacterium clade alongside the four novel ISS strains. Functional genome analysis revealed unique proteins associated with transcription, defense, and metabolism. The genome harbored toxin-antitoxin modules (e.g., VapBC, Phd/YuzE), stress response regulators (FrmR, YhcF), and genes involved in formaldehyde resistance and glycoside hydrolase activity. Secondary metabolite gene clusters included beta-lactone, terpene, and T3PKS. Notably, tetracycline resistance gene tet(42) was present, indicating potential clinical relevance. The ISS strains grew at 4-40 °C, 0.5-8% NaCl, and pH 6.0-9.0. Chemotaxonomic features included anteiso-C15:0 and anteiso-C17:0 as major fatty acids, MK-12 as the predominant menaquinone, and ornithine as the diagnostic diamino acid in B2β-type peptidoglycan. The genomic DNA G+C content was 70.03 mol%. The polyphasic taxonomy showed that the ISS isolates along with LTR1 represent distinct strains of a new Microbacterium species, herein named Microbacterium meiriae. The type strain is F6_8S_P_2B[T] (DSM 115935[T] = NRRL B-65668[T]).},
}

Phylogeny
RNA, Ribosomal, 16S/genetics
*Genome, Bacterial
*Microbacterium/genetics/isolation & purification/classification
*Spacecraft
Whole Genome Sequencing
DNA, Bacterial/genetics
Genomics/methods
Russia

@article {pmid41081913,
year = {2025},
author = {Amaresh, and Aswini, N and Krishnappa, G and Durai, AA and Manimekalai, R and Swamy, HKM and Pathy, TL and Vinayaka, and Dhanya, VG and Rathan, ND and Nandakumar, S and Shwetha, K and Sreenivasa, V and Maruthi, RT and Suresha, GS and Hemaprabha, G and Govindaraj, P},
title = {Next-generation molecular breeding tools to harness higher genetic gains in sugarcane.},
journal = {Planta},
volume = {262},
number = {5},
pages = {122},
pmid = {41081913},
issn = {1432-2048},
mesh = {*Saccharum/genetics ; *Plant Breeding/methods ; Genetic Variation ; Genome, Plant/genetics ; Genotype ; },
abstract = {Next-generation molecular tools with AI integration can accelerate genetic gain in sugarcane by enhancing variation, accuracy, and efficiency, enabling rapid development of high-yielding, high-quality, and climate-resilient varieties. Enhancing genetic gain is essential for sustainable sugar and bioenergy production, especially amid growing global reliance on renewable energy sources. Sugarcane and its byproducts serve as important feedstocks for both first and second-generation biofuels, and face several breeding challenges due to its genetic complexity, extended breeding cycles, and strong environmental interactions. The breeder's equation offers a quantitative framework to accelerate genetic improvement by optimizing four key components: additive genetic variation (σa), heritability (h[2]), selection intensity (i), and breeding cycle length (L). Additive genetic variation can be enhanced through genome-wide exploration, including genome, pan-genome, and super pangenome analyses, gene discovery, characterization, and the induction of novel variations. Precise estimation of heritability in sugarcane can be achieved through the large-scale characterization of germplasm, high-throughput phenotyping, and detailed genotype × environment interaction (G × E) studies. Selection intensity can be increased by expanding population sizes via genotypic, genomic, and in vitro selection, leveraging the law of large numbers, and adopting technologies that provide greater throughput, precision, and cost efficiency. Breeding cycle time can be significantly reduced using tools, such as marker-assisted selection, genomic selection, emerging doubled haploid strategies (though still challenging in polyploid crops like sugarcane), speed breeding, transgenic approaches, and genome editing technologies like CRISPR/Cas9 (including base and prime editing), TALENs. This review provides a comprehensive overview of each component of the breeder's equation in sugarcane breeding and highlights next-generation molecular strategies and tools aligned to these components. The integration of these advanced tools with artificial intelligence holds immense potential to enhance genetic gain and accelerate the development of high-yielding, high-quality, and climate-resilient sugarcane varieties.},
}

*Saccharum/genetics
*Plant Breeding/methods
Genetic Variation
Genome, Plant/genetics
Genotype

@article {pmid41079324,
year = {2025},
author = {Fontanet-Manzaneque, JB and Hernández, DM and Giordano, A and Caño-Delgado, AI},
title = {Sorghum as a monocot model for drought research.},
journal = {Frontiers in plant science},
volume = {16},
number = {},
pages = {1665967},
pmid = {41079324},
issn = {1664-462X},
abstract = {Climate change is intensifying drought events, posing a major threat to global food security. Sorghum bicolor (L.) Moench (Sorghum), a C4 monocot grass, is emerging as a valuable model for drought research due to its natural tolerance to water limitation and adaptability to semi-arid and arid environments. Sorghum cultivation requires significantly less water than major cereals such as rice, maize, and wheat, making it an attractive crop for sustaining agricultural productivity under water-limiting conditions. In fact, Sorghum uses up to 34% less water than rice in rainfed systems and up to 50% less under irrigation, with rice-to-Sorghum substitution potentially reducing water demand by 33%. Its lower water requirements, along with the compact growth of commonly used accessions such as TX430 and BTx623, make Sorghum a practical system for experimentation, particularly in genome editing studies. Maize, which shares close genetic similarity and also belongs to the Panicoideae subfamily, could particularly benefit from Sorghum-based insights. Sorghum also overcomes key limitations of model species such as Arabidopsis thaliana, offering greater relevance to monocot crops. Additionally, advances in metabolomics, transcriptomics, proteomics, phenomics, population genomics and pangenomics are expanding our understanding of the molecular and physiological mechanisms underlying Sorghum's drought resilience. Despite these advantages, challenges remain in transformation efficiency and the availability of genomic tools. This review highlights Sorghum's drought tolerance mechanisms, available omics and genetic tools, described drought-related genes and regulatory networks, and the limitations and progress in gene manipulation for climate-resilient crop development. Sorghum uniquely combines the advantages of a staple crop and a model organism, making it a powerful next-generation system for climate-resilient agriculture.},
}

@article {pmid41077207,
year = {2025},
author = {Qiao, P and Saleem, N and Zhao, J and Zhao, C and Zhang, M},
title = {Pan-genome analysis of the LATERAL ORGAN BOUNDARIES domain family in camelina and function investigation of LATERAL ORGAN BOUNDARIES domain 40 in fatty acid synthesis.},
journal = {International journal of biological macromolecules},
volume = {},
number = {},
pages = {148232},
doi = {10.1016/j.ijbiomac.2025.148232},
pmid = {41077207},
issn = {1879-0003},
abstract = {Camelina (Camelina sativa (L.) Crantz) is an allohexaploid oilseed crop with a cultivation history of about six thousand years, yet its pan-genome was poorly studied. Moreover, Lateral Organ Boundary Domain (LBD) transcription factor family remains uninvestigated. Here, we performed a pan-genome analysis of LBD genes across 13 camelina accessions, identifying 1487 members classified into 44 Core, 2 SoftCore, 15 Dispensable, and 21 Private orthologous groups. Camelina LBDs were classified into Class I (six subclasses) and Class II (two subclasses). Selection pressure analysis showed that compared with Core LBD genes and SoftCore genes, Dispensable genes have undergone obvious relaxed selection. Promoter analysis identified subclass-specific regulatory elements, with Class IIB significantly enriched in endosperm-specific expression motifs and Class IA1 associated with stress responses. Transcriptome profiling revealed some tissue-specific expression patterns, including potential roles of LBD40/41 in seed development. Functional validation demonstrated that AtLBD40 overexpression in Arabidopsis and camelina remodeled fatty acid composition by suppressing FAD3 and KCS18, thereby reducing the relative contents of 18:3 and 22:1. Arabidopsis lbd40-1 and lbd40-2 mutant analyses suggested a possible functional redundancy between LBD40 and LBD41. This study elucidates the dynamic evolution of the camelina LBD family and its pivotal role in regulating the fatty acid profile in seeds, establishing a foundation for targeted oil quality improvement in this versatile crop.},
}

@article {pmid41074924,
year = {2025},
author = {Zhou, Z and Xiang, W and Fang, C and Shen, H},
title = {Genomic and Pan-Genomic Characterization of Elizabethkingia meningoseptica Reveals Resistance Gene Profiles, Phylogenetic Clusters, and Functional Landscape.},
journal = {Current microbiology},
volume = {82},
number = {12},
pages = {546},
pmid = {41074924},
issn = {1432-0991},
mesh = {*Phylogeny ; *Genome, Bacterial ; Humans ; Flavobacteriaceae Infections/microbiology ; Anti-Bacterial Agents/pharmacology ; Genomics ; *Drug Resistance, Bacterial/genetics ; Polymorphism, Single Nucleotide ; Multigene Family ; *Chryseobacterium/genetics/drug effects/classification ; Bacterial Proteins/genetics ; Drug Resistance, Multiple, Bacterial/genetics ; },
abstract = {Elizabethkingia meningoseptica (E. meningoseptica) is a significant pathogen associated with various infections. This study aimed to analyze the general molecular and pan-genomic characteristics of E. meningoseptica. The 104 E. meningoseptica genomes were retrieved from NCBI, annotated using Prokka, and screened for antibiotic resistance genes via ABRicate. Core-genome single-nucleotide polymorphisms (SNPs) were identified using Parsnp, with phylogenetic trees constructed. Pan-genomic analysis employed BPGA for gene clustering at 80% identity, supplemented by COG and KEGG functional annotations. Among the 104 sequences, 86 were from human sources, 12 from nonhuman sources, and 6 had unknown origins. Phylogenetic analysis classified the strains into three clades (A, B, and C), with 95 strains (91.3%) in clade C. Nineteen resistance genes were identified, with 11 being carbapenem-resistance genes. Significant differences in the distribution of resistance genes were observed between human and non-human sources. Pan-genomic analysis revealed 8856 genes in total, including 2267 core genes, 4052 accessory genes, and 2537 unique genes. The median genomic G + C content was 36.9% (36.8%-37.0%). The pan-genome was still open but approaching closure. In COG functional classification, significant differences were found in "Information storage and processing", "cellular processes and signaling" and "Metabolism" between core genes and accessory/unique genes. Similar significant differences were also observed in KEGG functional classification, especially in Cellular Processes, Human Diseases, and Metabolism. This study provides valuable insights into the genomic characteristics of E. meningoseptica, which can contribute to understanding its evolution, pathogenicity, and drug resistance mechanisms.},
}

*Phylogeny
*Genome, Bacterial
Humans
Flavobacteriaceae Infections/microbiology
Anti-Bacterial Agents/pharmacology
Genomics
*Drug Resistance, Bacterial/genetics
Polymorphism, Single Nucleotide
Multigene Family
*Chryseobacterium/genetics/drug effects/classification
Bacterial Proteins/genetics
Drug Resistance, Multiple, Bacterial/genetics

@article {pmid41074769,
year = {2025},
author = {Tucker, SJ and Freel, KC and Eren, AM and Rappé, MS},
title = {Habitat-specificity in SAR11 is associated with a few genes under high selection.},
journal = {The ISME journal},
volume = {},
number = {},
pages = {},
doi = {10.1093/ismejo/wraf216},
pmid = {41074769},
issn = {1751-7370},
abstract = {The order Pelagibacterales (SAR11) is the most abundant group of heterotrophic bacteria in the global surface ocean, where individual sublineages likely play distinct roles in oceanic biogeochemical cycles. Yet, understanding the determinants of niche partitioning within SAR11 has been a formidable challenge due to the high genetic diversity within individual SAR11 sublineages and the limited availability of high-quality genomes from both cultivation and metagenomic reconstruction. Through an integrated metapangenomic analysis of 71 new SAR11 isolate genomes and a time-series of metagenomes from the prominent source of isolation, we reveal an ecological and phylogenetic partitioning of metabolic traits across SAR11 genera. We resolve distinct habitat preferences among genera for coastal or offshore environments of the tropical Pacific and identify a handful of genes involved in carbon and nitrogen metabolisms that appear to contribute to these contrasting lifestyles. Furthermore, we find that some habitat-specific genes experience high selective pressures, indicating that they are critical determinants of SAR11 fitness and niche differentiation. Together, these insights reveal the underlying evolutionary processes shaping niche-partitioning within sympatric and parapatric populations of SAR11 and demonstrate that the immense genomic diversity of SAR11 bacteria naturally segregates into ecologically and genetically cohesive units, or ecotypes, that vary in spatial distributions in the tropical Pacific.},
}

@article {pmid41074339,
year = {2025},
author = {Xu, Y and Sun, R and Zheng, Z and Ye, L and Peng, M and Chen, S},
title = {Genomic and phenotypic analysis of virulence, antimicrobial resistance, and transmission routes of Vibrio vulnificus from food and clinical sources in China.},
journal = {Food research international (Ottawa, Ont.)},
volume = {220},
number = {},
pages = {117148},
doi = {10.1016/j.foodres.2025.117148},
pmid = {41074339},
issn = {1873-7145},
mesh = {*Vibrio vulnificus/genetics/pathogenicity/drug effects/isolation & purification ; Animals ; China ; Humans ; Virulence/genetics ; *Food Microbiology ; Mice ; Seafood/microbiology ; *Vibrio Infections/transmission/microbiology ; Anti-Bacterial Agents/pharmacology ; Phenotype ; *Drug Resistance, Bacterial/genetics ; Virulence Factors/genetics ; Whole Genome Sequencing ; Microbial Sensitivity Tests ; Foodborne Diseases/microbiology ; Genome, Bacterial ; Genomics ; },
abstract = {Vibrio vulnificus is a zoonotic pathogen that imposes significant economic burdens on healthcare and aquaculture. It represents a serious public health threat by causing primary septicemia through the consumption of raw shellfish and secondary septicemia via wound exposure to contaminated seawater. In this study, we aimed to compare the genomic features and virulence of foodborne V. vulnificus isolates with clinical strains to assess their public health threat. V. vulnificus isolates from Shenzhen (24 from seafood and meat, 4 clinical) were subjected to Whole-genome sequencing (WGS) and phenotypic assays including antibiotic susceptibility testing, human serum resistance, and a mouse infection model to evaluate virulence. Our results show that only a few food-derived isolates harbored antibiotic resistance genes (ARGs) encoding resistance towards rifamycin, aminoglycoside, trimethoprim, phenicol, quinolone, sulfonamide, and tetracycline; whereas all isolates possessed an extensive array of virulence factors (VFs) related to motility, adherence, and exotoxins. Two-thirds of food isolates were serum resistant and were able to survive in human serum like clinical isolates. In vivo experiments further confirmed that food-derived isolates can cause mouse mortality comparable to a clinical isolate. Genomic analysis of 685 V. vulnificus genomes from different provinces of China (including 28 genomes sequenced in this study and 657 publicly available genomes in China) revealed that V. vulnificus has an open pan-genome and there is no clear separation between clinical isolates and food isolates, either in phylogeny or VF profiles. Phylogeographic analysis indicated that Guangdong and Zhejiang provinces might play a key role in spreading V. vulnificus nationally. Collectively, this study highlights foodborne V. vulnificus isolates exhibit virulence potential equivalent to clinical strains and underscores the need for strict food safety monitoring and interventions to prevent severe infections.},
}

*Vibrio vulnificus/genetics/pathogenicity/drug effects/isolation & purification
Animals
China
Humans
Virulence/genetics
*Food Microbiology
Mice
Seafood/microbiology
*Vibrio Infections/transmission/microbiology
Anti-Bacterial Agents/pharmacology
Phenotype
*Drug Resistance, Bacterial/genetics
Virulence Factors/genetics
Whole Genome Sequencing
Microbial Sensitivity Tests
Foodborne Diseases/microbiology
Genome, Bacterial
Genomics

@article {pmid41074336,
year = {2025},
author = {Huang, J and Zhang, Z and Li, Q and Chen, J and Mei, L and Qi, X and Chen, L and Zhang, J and Lv, C and Li, M and Chen, H and Zhang, Y and Wu, B and Yu, K and Zhang, Y and Zhan, L and Zhu, Y},
title = {Emergence and genomic characterization of Vibrio parahaemolyticus serotype O10:K4 from seafood-linked diarrheal cases in Zhejiang, China (2016-2023).},
journal = {Food research international (Ottawa, Ont.)},
volume = {220},
number = {},
pages = {117144},
doi = {10.1016/j.foodres.2025.117144},
pmid = {41074336},
issn = {1873-7145},
mesh = {*Vibrio parahaemolyticus/genetics/isolation & purification/classification/pathogenicity ; Humans ; *Seafood/microbiology ; China/epidemiology ; *Vibrio Infections/epidemiology/microbiology ; Whole Genome Sequencing ; Serogroup ; *Diarrhea/microbiology/epidemiology ; Genome, Bacterial ; Virulence Factors/genetics ; },
abstract = {Vibrio parahaemolyticus is a leading cause of seafood-associated gastroenteritis, posing increasing public health challenges globally. We conducted a large-scale molecular epidemiological analysis of 7932 clinical isolates collected from seafood-associated diarrheal patients in 69 sentinel hospitals across 11 prefecture-level cities in Zhejiang Province between 2016 and 2023. Whole-genome sequencing (WGS) was performed on 1261 representative isolates, supplemented by 11,555 publicly available genomes. We analyzed temporal serotype dynamics, antimicrobial resistance genes (ARGs), virulence factors, and pangenomic diversity, with an emphasis on the globally prevalent ST3 lineage. Notably, the O10:K4 serotype emerged as the second most common within ST3, increasing in prevalence from 40.0 % to 65.6 % over the study period. O10:K4 isolates exhibited a significantly higher frequency of tdh (96.3 % vs. 78.2 %) and complete T3SS2 effector gene clusters. Nearly all isolates harbored tet(35) and blaCARB-22, indicating widespread resistance. Comparative pangenome analysis revealed O10:K4-specific acquisitions in chemotaxis and LPS synthesis (e.g., per, mcpQ, fcl) and loss of key polyamine metabolism genes (aguA, puu operon). These findings suggest that the emergence and clonal expansion of the O10:K4 serotype represent a significant epidemiological shift characterized by enhanced virulence and multidrug resistance. Sustained genomic surveillance is imperative to guide seafood safety management and clinical interventions.},
}

*Vibrio parahaemolyticus/genetics/isolation & purification/classification/pathogenicity
Humans
*Seafood/microbiology
China/epidemiology
*Vibrio Infections/epidemiology/microbiology
Whole Genome Sequencing
Serogroup
*Diarrhea/microbiology/epidemiology
Genome, Bacterial
Virulence Factors/genetics

@article {pmid41071885,
year = {2025},
author = {VanGessel, CJ and Felderhoff, TJ and Prigozhin, DM and Cui, M and Pressoir, G and Healey, AL and Lovell, JT and Nalam, VJ and Nishimura, MT and Morris, GP},
title = {Ancient pangenomic origins of noncanonical NLR genes underlying the recent evolutionary rescue of a staple crop.},
journal = {Science advances},
volume = {11},
number = {41},
pages = {eady1667},
doi = {10.1126/sciadv.ady1667},
pmid = {41071885},
issn = {2375-2548},
mesh = {*NLR Proteins/genetics ; *Evolution, Molecular ; *Sorghum/genetics/parasitology ; Disease Resistance/genetics ; *Plant Proteins/genetics ; Animals ; Plant Diseases/genetics/parasitology ; *Crops, Agricultural/genetics ; Aphids ; Phylogeny ; },
abstract = {The recent adaptation of the cereal crop sorghum to a global aphid outbreak was a fortuitous case of evolutionary rescue, but the pangenomic and molecular basis is not known. We show that RMES1 disrupts phloem feeding via activation of conserved immunity networks, with a growth-to-defense transition mediated by phytohormone signaling and activated by nucleotide-binding site-leucine-rich repeat receptor (NLR) resistance genes on a structural variant. The causative NLRs [resistance to Melanaphis sorghi 1A (RMES1A) and RMES1B] lack signaling domains and have adenosine triphosphatase mutations expected to abrogate function, suggesting that RMES1 NLRs regulate immunity via a noncanonical mechanism. The RMES1 NLR family is ancient, orthologous to phloem-feeding resistance genes in rice and syntenic across the grass superpangenome. Thus, gene birth-and-death processes at an ancient gene cluster created rare standing variation and provided the adaptive allele for evolutionary rescue.},
}

*NLR Proteins/genetics
*Evolution, Molecular
*Sorghum/genetics/parasitology
Disease Resistance/genetics
*Plant Proteins/genetics
Animals
Plant Diseases/genetics/parasitology
*Crops, Agricultural/genetics
Aphids
Phylogeny

@article {pmid41068364,
year = {2025},
author = {Umer, MJ and Huang, L and Liu, H and Batool, R and Li, H and Li, S and Hong, Y and Wang, R and Yu, Q and Lu, Q and Varshney, RK and Chen, X},
title = {Integrative genomics and genetics from evolutionary insights to precision breeding in peanuts (Arachis Hypogaea L.).},
journal = {Functional & integrative genomics},
volume = {25},
number = {1},
pages = {206},
pmid = {41068364},
issn = {1438-7948},
support = {32172051, 32301869 and 32401893//The National Natural Science Foundation of China/ ; 32172051, 32301869 and 32401893//The National Natural Science Foundation of China/ ; 32172051, 32301869 and 32401893//The National Natural Science Foundation of China/ ; 2023A04J0776 and 2024A04J3870//Guangzhou Basic and Applied Basic Research Foundation/ ; 2023A04J0776 and 2024A04J3870//Guangzhou Basic and Applied Basic Research Foundation/ ; 2023B1212060038//Science and Technology Planning Project of Guangdong Province/ ; 2024B1212060003//Science and Technology Planning Project of Guangdong Province/ ; CARS-13//China Agriculture Research System of MOF and MARA/ ; 2019KJ136-02//Technology Special Fund of Guangdong Province Agriculture and Rural Affairs Department/ ; 2024-NPY-00-018//Special Funds for the Revitalization of Agriculture through Seed Industry under the Provincial Rural Revitalization Strategy/ ; R2020PY-JX004, R2020PY-JG005, R2021PY-QY003, R2022YJ-YB3025 and R2023PY-JG007//Special Fund for Scientific Innovation Strategy-Construction of High-level Academy of Agriculture Science/ ; XTXM202203//The Project of Collaborative Innovation Center of GDAAS/ ; 2023YFD1202800//National Key Research and Development Program of China/ ; 2021TX06N789//The Special Support Program of Guangdong Province/ ; 2022SDZG05//The Open Competition Program of Top Ten Critical Priorities of Agricultural Science and Technology Innovation for the 14th Five-Year Plan in Guangdong Province/ ; 2022B0202060004//Guangdong Provincial Key Research and Development Program-Modern Seed Industry/ ; 2023A1515010098 and 2024A1515010511//Basic and Applied Basic Research Foundation of Guangdong Province/ ; 202101, 202201 and 202306//The Foundation of Director of Crop Research Institute of Guangdong Academy of Agriculture Sciences/Open Fund of Guangdong Provincial Key Laboratory of Crop Genetic Improvement/ ; },
mesh = {*Arachis/genetics/metabolism/growth & development ; *Plant Breeding/methods ; *Genome, Plant ; *Genomics ; *Evolution, Molecular ; },
abstract = {Peanut (Arachis hypogaea L.), a globally important oilseed crop, increasingly challenged by rising edible oil demands as well as biotic and abiotic stresses. This review synthesizes recent advances in peanut genomics, evolutionary biology, and breeding technologies to address these challenges aimed at improving yield, oil quality, and resilience. Cultivated peanut is an allotetraploid (AABB), derived from hybridization of the diploid ancestors, A. duranensis and A. ipaensis followed by polyploidization. However, competing evolutionary models highlight unresolved aspects of its domestication history. Advances in sequencing have enabled the high-quality genome assembly of cultivated peanuts, facilitating the development of markers (SSRs, SNPs), trait dissection, and cross omics integration. Genomic studies reveal asymmetric subgenome evolution, chromosomal rearrangements, and structural variations associated with key traits like oil biosynthesis and stress adaptation. Markers assisted selection (MAS) and genomic selection (GS) now accelerate breeding by enabling accurate prediction of complex traits, including yield, disease resistance, and oil quality. Genome editing via CRISPR-Cas9 has transformed trait improvement by enabling accurate modifications in fatty acid desaturases (FAD2), allergen genes, and stress regulators. Multi-omics strategies like transcriptomics, proteomics, metabolomics, lipidomics, and single-cell atlases uncover cell-type specific networks governing pod development and drought responses. Despite progress, polyploid complexity, low transformation efficiency, and genotype-environment interactions remain bottlenecks. Future efforts must leverage pangenomes, machine learning, and high throughput phenotyping to bridge these gaps. This review highlights the potential of integrated genomics and precision breeding to develop high oleic, climate resilient peanut varieties, critical for global food and nutritional security.},
}

*Arachis/genetics/metabolism/growth & development
*Plant Breeding/methods
*Genome, Plant
*Genomics
*Evolution, Molecular

@article {pmid41068119,
year = {2025},
author = {Liu, S and Feng, B and Zhang, Z and Miao, J and Lai, X and Zhao, W and Xie, Q and Ye, X and Cao, C and Yu, P and Sun, J and Guo, J and Wang, Z and Wang, Q and Zhang, Z and Pan, Y},
title = {UPGG: expanding the taxonomic and functional diversity of the pig gut microbiome with an enhanced genome catalog.},
journal = {NPJ biofilms and microbiomes},
volume = {11},
number = {1},
pages = {196},
pmid = {41068119},
issn = {2055-5008},
support = {LZ23C170003//Zhejiang Provincial Natural Science Foundation of China/ ; LZ23C170003//Zhejiang Provincial Natural Science Foundation of China/ ; 2021YFD1200802,2023YFF1001100//National Key Research and Development Program of China/ ; 2021YFD1200802,2023YFF1001100//National Key Research and Development Program of China/ ; 32272832//National Natural Science Foundation of China/ ; 32272832//National Natural Science Foundation of China/ ; },
mesh = {Animals ; *Gastrointestinal Microbiome/genetics ; Swine/microbiology ; *Bacteria/genetics/classification/isolation & purification ; *Archaea/genetics/classification/isolation & purification ; Metagenome ; *Genome, Bacterial ; Interspersed Repetitive Sequences ; Phylogeny ; Metagenomics ; },
abstract = {The porcine gut microbiome is crucial for pig health and key to its production performance. However, genome-level analysis across multiple kingdoms remains limited. Here, we reconstructed the unified pig gastrointestinal genome (UPGG), including bacterial, archaeal, and annotated over 78 million non-redundant protein-coding genes using 5784 metagenome samples. We identified antibiotic resistance genes (ARGs) and mobile genetic elements (MGEs), and the distribution of 72,056 metabolic gene clusters within existing populations. We have constructed pan-genomes of 436 high-quality microbial species and, using these as references, discovered intraspecies genomic variations that revealed 23,350,975 single-nucleotide variants (SNVs). Finally, through comparative analysis of gut microbiome genomes conducted in this study, we observed that pigs may serve as a more suitable model than other animals for investigating human gut microbiota composition and functional patterns. In summary, we constructed a comprehensive reference catalog of the porcine gut microbiome and enhanced the understanding of the host-microbe coevolution.},
}

Animals
*Gastrointestinal Microbiome/genetics
Swine/microbiology
*Bacteria/genetics/classification/isolation & purification
*Archaea/genetics/classification/isolation & purification
Metagenome
*Genome, Bacterial
Interspersed Repetitive Sequences
Phylogeny
Metagenomics

@article {pmid41067298,
year = {2025},
author = {Trisakul, K and Sirichoat, A and Nithichanon, A and Rotcheewaphan, S and Phelan, J and Clark, TG and Faksri, K},
title = {Genomic insights into persistent infections, reinfections, and subspecies diversity of Mycobacteroides abscessus: A whole-genome sequencing study of Thai and global isolates.},
journal = {Infection, genetics and evolution : journal of molecular epidemiology and evolutionary genetics in infectious diseases},
volume = {},
number = {},
pages = {105838},
doi = {10.1016/j.meegid.2025.105838},
pmid = {41067298},
issn = {1567-7257},
abstract = {Mycobacteroides abscessus is a highly resistant pathogen with significant genetic diversity and complicating clinical management. This study used whole-genome sequencing to analyze genomic variations in seven serially collected isolates from three Thai patients, distinguishing between persistent infections and reinfections. Comparative analysis with 43 global isolates revealed subspecies-specific genetic diversity and distribution patterns. Among Thai isolates, two paired samples (P7.1-P7.2 and P15.1-P15.2) were persistent infections (same clone), while two (P8.1-P8.2 and P15.2-P15.3) were reinfections (different clones). Genome-wide comparisons revealed depth distribution patterns and gene cluster variations among different clones, whereas minimal divergence was observed within persistent infections. Although initial pan-genome analysis identified unique genes in same-clone pairs (P7.1 vs. P7.2 and P15.1 vs. P15.2), further validation using raw read mapping confirmed these genes were not truly unique. Analysis of global isolates showed subspecies-specific genetic variations. M. abscessus subsp. abscessus (MAB) and M. abscessus subsp. massiliense (MMAS) exhibited distinct genotypically drug resistance profiles, with unique core genes linked to adaptation and resistance mechanisms. STRING analysis identified 42 unique core genes in MAB, with 11 gene interactions-truB, prmC_2, and aguA_2 showing the highest interaction scores. In contrast, MMAS had 11 unique core genes with a single interaction between lgrD_4 and rnc. Subsequent validation using NCBI BLAST showed only fmt_2 and aguA_2 were truly unique to MAB. This study provides new insights into the genomic evolution of M. abscessus during persistent and reinfections and genetic variation among subspecies. The findings enhance understanding of M. abscessus epidemiology and may inform therapeutic and infection control.},
}

@article {pmid41064766,
year = {2025},
author = {Liu, C and Xu, H and Li, Z and Wang, Y and Zhang, J and Qiao, S and Zhang, H},
title = {From map to blueprint: the plant pan-genome unraveling genetic mysteries and powering precision breeding.},
journal = {Frontiers in plant science},
volume = {16},
number = {},
pages = {1673637},
pmid = {41064766},
issn = {1664-462X},
abstract = {With the rapid advancement of sequencing technologies and bioinformatics, coupled with significant progress in sequencing efficiency and reduced costs, substantial breakthroughs have been achieved in plant functional genomics, evolutionary genetics, and molecular breeding. However, as research deepens, accumulating evidence demonstrates that reference genomes derived from a single individual fail to adequately represent the genetic diversity of entire species. This limitation has catalyzed the emergence of the pan-genome concept. Pan-genome research now stands at the forefront of plant genomics, serving as a pivotal area of focus. Its application in plant studies has unveiled extensive genetic variations, identified numerous novel genes, and significantly enhanced our understanding of genetic diversity within relevant species. This review comprehensively summarizes recent progress in plant pan-genome research, construction methodologies, current applications in plant science, and key achievements. Finally, we outline future research directions, aiming to provide a reference for theoretical and applied pan-genome studies while offering novel perspectives for deciphering the genetic basis of plant breeding, evolutionary domestication, and phenotypic diversity.},
}