{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T19:35:43Z","timestamp":1784748943987,"version":"3.55.0"},"reference-count":43,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T00:00:00Z","timestamp":1735603200000},"content-version":"vor","delay-in-days":5,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,26]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Summary<\/jats:title>\n                  <jats:p>The intrinsic complexity of the microbiota combined with technical variability render shotgun metagenomics challenging to analyze for routine clinical or research applications. In silico data generation offers a controlled environment allowing for example to benchmark bioinformatics tools, to optimize study design, statistical power, or to validate targeted applications. Here, we propose assembly_finder and the Metagenomic Sequence Simulator (MeSS), two easy-to-use Bioconda packages, as part of a benchmarking toolkit to download genomes and simulate shotgun metagenomics samples, respectively. Outperforming existing tools in speed while requiring less memory, MeSS reproducibly generates accurate complex communities based on a list of taxonomic ranks and their abundance.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>All code is released under MIT License and is available on https:\/\/github.com\/metagenlab\/MeSS and https:\/\/github.com\/metagenlab\/assembly_finder.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btae760","type":"journal-article","created":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T16:20:56Z","timestamp":1735662056000},"source":"Crossref","is-referenced-by-count":5,"title":["MeSS and assembly_finder: a toolkit for <i>in silico<\/i> metagenomic sample generation"],"prefix":"10.1093","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-9322-1281","authenticated-orcid":false,"given":"Farid","family":"Chaabane","sequence":"first","affiliation":[{"name":"Institute of Microbiology, Lausanne University Hospital and University of Lausanne , Lausanne, 1011,","place":["Switzerland"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5725-7929","authenticated-orcid":false,"given":"Trestan","family":"Pillonel","sequence":"additional","affiliation":[{"name":"Institute of Microbiology, Lausanne University Hospital and University of Lausanne , Lausanne, 1011,","place":["Switzerland"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0550-8981","authenticated-orcid":false,"given":"Claire","family":"Bertelli","sequence":"additional","affiliation":[{"name":"Institute of Microbiology, Lausanne University Hospital and University of Lausanne , Lausanne, 1011,","place":["Switzerland"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2024,12,31]]},"reference":[{"key":"2025012310372297600_btae760-B1","doi-asserted-by":"crossref","first-page":"40","DOI":"10.7171\/jbt.17-2801-007","article-title":"Precision metagenomics: rapid metagenomic analyses for infectious disease diagnostics and public health surveillance","volume":"28","author":"Afshinnekoo","year":"2017","journal-title":"J Biomol Tech"},{"key":"2025012310372297600_btae760-B2","author":"Baker","year":"2016"},{"key":"2025012310372297600_btae760-B3","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1186\/s12864-022-08365-3","article-title":"Systematic benchmark of state-of-the-art variant calling pipelines identifies major factors affecting accuracy of coding sequence variant discovery","volume":"23","author":"Barbitoff","year":"2022","journal-title":"BMC Genomics"},{"key":"2025012310372297600_btae760-B4","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1186\/s13742-015-0087-0","article-title":"Bioboxes: standardised containers for interchangeable bioinformatics software","volume":"4","author":"Belmann","year":"2015","journal-title":"Gigascience"},{"key":"2025012310372297600_btae760-B5","article-title":"BioConvert: a comprehensive format converter for life sciences","volume":"5","author":"Caro","year":"2023","journal-title":"NAR Genom Bioinform"},{"key":"2025012310372297600_btae760-B6","doi-asserted-by":"crossref","first-page":"10494","DOI":"10.1073\/pnas.142680199","article-title":"Estimating prokaryotic diversity and its limits","volume":"99","author":"Curtis","year":"2002","journal-title":"Proc Natl Acad Sci USA"},{"key":"2025012310372297600_btae760-B7","doi-asserted-by":"crossref","first-page":"316","DOI":"10.1038\/nbt.3820","article-title":"Nextflow enables reproducible computational workflows","volume":"35","author":"Di Tommaso","year":"2017","journal-title":"Nat Biotechnol"},{"key":"2025012310372297600_btae760-B8","doi-asserted-by":"crossref","first-page":"D136","DOI":"10.1093\/nar\/gkr1178","article-title":"The NCBI taxonomy database","volume":"40","author":"Federhen","year":"2012","journal-title":"Nucleic Acids Res"},{"key":"2025012310372297600_btae760-B9","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1186\/s40168-019-0633-6","article-title":"CAMISIM: simulating metagenomes and microbial communities","volume":"7","author":"Fritz","year":"2019","journal-title":"Microbiome"},{"key":"2025012310372297600_btae760-B10","doi-asserted-by":"crossref","first-page":"521","DOI":"10.1093\/bioinformatics\/bty630","article-title":"Simulating Illumina metagenomic data with InSilicoSeq","volume":"35","author":"Gourl\u00e9","year":"2019","journal-title":"Bioinformatics"},{"key":"2025012310372297600_btae760-B11","doi-asserted-by":"crossref","first-page":"475","DOI":"10.1038\/s41592-018-0046-7","article-title":"Bioconda: sustainable and comprehensive software distribution for the life sciences","volume":"15","author":"Gr\u00fcning","year":"2018","journal-title":"Nat Methods"},{"key":"2025012310372297600_btae760-B12","author":"Holtgrewe","year":"2010"},{"key":"2025012310372297600_btae760-B13","doi-asserted-by":"crossref","first-page":"593","DOI":"10.1093\/bioinformatics\/btr708","article-title":"ART: a next-generation sequencing read simulator","volume":"28","author":"Huang","year":"2012","journal-title":"Bioinformatics"},{"key":"2025012310372297600_btae760-B14","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1038\/nature11234","article-title":"Structure, function and diversity of the healthy human microbiome","volume":"486","author":"Huttenhower","year":"2012","journal-title":"Nature"},{"key":"2025012310372297600_btae760-B15","doi-asserted-by":"crossref","first-page":"2520","DOI":"10.1093\/bioinformatics\/bts480","article-title":"Snakemake\u2014a scalable bioinformatics workflow engine","volume":"28","author":"K\u00f6ster","year":"2012","journal-title":"Bioinformatics"},{"key":"2025012310372297600_btae760-B16","doi-asserted-by":"crossref","first-page":"2078","DOI":"10.1093\/bioinformatics\/btp352","article-title":"The sequence alignment\/map format and SAMtools","volume":"25","author":"Li","year":"2009","journal-title":"Bioinformatics"},{"key":"2025012310372297600_btae760-B17","doi-asserted-by":"crossref","first-page":"e104","DOI":"10.7717\/peerj-cs.104","article-title":"Bracken: estimating species abundance in metagenomics data","volume":"3","author":"Lu","year":"2017","journal-title":"PeerJ Comput Sci"},{"key":"2025012310372297600_btae760-B18","doi-asserted-by":"crossref","first-page":"e323","DOI":"10.1002\/cpz1.323","article-title":"BUSCO: assessing genomic data quality and Beyond","volume":"1","author":"Manni","year":"2021","journal-title":"Curr Protoc"},{"key":"2025012310372297600_btae760-B19","doi-asserted-by":"crossref","first-page":"4647","DOI":"10.1093\/molbev\/msab199","article-title":"BUSCO update: novel and streamlined workflows along with broader and deeper phylogenetic coverage for scoring of eukaryotic, prokaryotic, and viral genomes","volume":"38","author":"Manni","year":"2021","journal-title":"Mol Biol Evol"},{"key":"2025012310372297600_btae760-B20","doi-asserted-by":"crossref","first-page":"429","DOI":"10.1038\/s41592-022-01431-4","article-title":"Critical assessment of metagenome interpretation: the second round of challenges","volume":"19","author":"Meyer","year":"2022","journal-title":"Nat Methods"},{"key":"2025012310372297600_btae760-B21","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1038\/s41437-022-00577-3","article-title":"Performance evaluation of six popular short-read simulators","volume":"130","author":"Milhaven","year":"2023","journal-title":"Heredity (Edinb)"},{"key":"2025012310372297600_btae760-B22","doi-asserted-by":"crossref","first-page":"1005","DOI":"10.1038\/nmeth.4037","article-title":"Comparison of high-throughput sequencing data compression tools","volume":"13","author":"Numanagi\u0107","year":"2016","journal-title":"Nat Methods"},{"key":"2025012310372297600_btae760-B23","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1038\/nature13786","article-title":"Biogeography and individuality shape function in the human skin metagenome","volume":"514","author":"Oh","year":"2014","journal-title":"Nature"},{"key":"2025012310372297600_btae760-B24","doi-asserted-by":"crossref","first-page":"732","DOI":"10.1038\/s41597-024-03571-y","article-title":"Exploring and retrieving sequence and metadata for species across the tree of life with NCBI datasets","volume":"11","author":"O\u2019Leary","year":"2024","journal-title":"Sci Data"},{"key":"2025012310372297600_btae760-B25","doi-asserted-by":"crossref","first-page":"D733","DOI":"10.1093\/nar\/gkv1189","article-title":"Reference sequence (RefSeq) database at NCBI: current status, taxonomic expansion, and functional annotation","volume":"44","author":"O\u2019Leary","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2025012310372297600_btae760-B26","doi-asserted-by":"crossref","first-page":"lqac092","DOI":"10.1093\/nargab\/lqac092","article-title":"PBSIM3: a simulator for all types of PacBio and ONT long reads","volume":"4","author":"Ono","year":"2022","journal-title":"NAR Genom Bioinform"},{"key":"2025012310372297600_btae760-B27","doi-asserted-by":"crossref","first-page":"1043","DOI":"10.1101\/gr.186072.114","article-title":"CheckM: assessing the quality of microbial genomes recovered from isolates, single cells, and metagenomes","volume":"25","author":"Parks","year":"2015","journal-title":"Genome Res"},{"key":"2025012310372297600_btae760-B28","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1038\/hdy.2016.102","article-title":"From next-generation resequencing reads to a high-quality variant data set","volume":"118","author":"Pfeifer","year":"2017","journal-title":"Heredity"},{"key":"2025012310372297600_btae760-B29","doi-asserted-by":"crossref","first-page":"833","DOI":"10.1038\/nbt.3935","article-title":"Shotgun metagenomics, from sampling to analysis","volume":"35","author":"Quince","year":"2017","journal-title":"Nat Biotechnol"},{"key":"2025012310372297600_btae760-B30","doi-asserted-by":"crossref","first-page":"e1010705","DOI":"10.1371\/journal.pcbi.1010705","article-title":"Ten simple rules and a template for creating workflows-as-applications","volume":"18","author":"Roach","year":"2022","journal-title":"PLoS Comput Biol"},{"key":"2025012310372297600_btae760-B31","doi-asserted-by":"crossref","first-page":"giab005","DOI":"10.1093\/gigascience\/giab005","article-title":"MB-GAN: microbiome simulation via generative adversarial network","volume":"10","author":"Rong","year":"2021","journal-title":"Gigascience"},{"key":"2025012310372297600_btae760-B32","doi-asserted-by":"crossref","first-page":"356","DOI":"10.1080\/1040841X.2021.1975642","article-title":"Building up a clinical microbiota profiling: a quality framework proposal","volume":"48","author":"Scherz","year":"2022","journal-title":"Crit Rev Microbiol"},{"key":"2025012310372297600_btae760-B33","doi-asserted-by":"crossref","first-page":"e0163962","DOI":"10.1371\/journal.pone.0163962","article-title":"SeqKit: a cross-platform and ultrafast toolkit for FASTA\/Q file manipulation","volume":"11","author":"Shen","year":"2016","journal-title":"PLoS One"},{"key":"2025012310372297600_btae760-B34","doi-asserted-by":"crossref","first-page":"844","DOI":"10.1016\/j.jgg.2021.03.006","article-title":"TaxonKit: a practical and efficient NCBI taxonomy toolkit","volume":"48","author":"Shen","year":"2021","journal-title":"J Genet Genomics"},{"key":"2025012310372297600_btae760-B35","doi-asserted-by":"crossref","first-page":"e0167047","DOI":"10.1371\/journal.pone.0167047","article-title":"Simulating next-generation sequencing datasets from empirical mutation and sequencing models","volume":"11","author":"Stephens","year":"2016","journal-title":"PLoS One"},{"key":"2025012310372297600_btae760-B36","doi-asserted-by":"crossref","first-page":"618","DOI":"10.1038\/s41592-021-01141-3","article-title":"Challenges in benchmarking metagenomic profilers","volume":"18","author":"Sun","year":"2021","journal-title":"Nat Methods"},{"key":"2025012310372297600_btae760-B37","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1007\/s10295-016-1809-8","article-title":"Metagenomic applications in environmental monitoring and bioremediation","volume":"43","author":"Techtmann","year":"2016","journal-title":"J Ind Microbiol Biotechnol"},{"key":"2025012310372297600_btae760-B38","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1111\/j.1365-294X.2010.04948.x","article-title":"Species abundance distributions and richness estimations in fungal metagenomics\u2014lessons learned from community ecology","volume":"20","author":"Unterseher","year":"2011","journal-title":"Mol Ecol"},{"key":"2025012310372297600_btae760-B39","doi-asserted-by":"crossref","first-page":"lqac050","DOI":"10.1093\/nargab\/lqac050","article-title":"SEQ2MGS: an effective tool for generating realistic artificial metagenomes from the existing sequencing data","volume":"4","author":"Van Camp","year":"2022","journal-title":"NAR Genom Bioinform"},{"key":"2025012310372297600_btae760-B40","doi-asserted-by":"crossref","first-page":"1316","DOI":"10.21105\/joss.01316","article-title":"Badread: simulation of error-prone long reads","volume":"4","author":"Wick","year":"2019","journal-title":"J Open Source Softw"},{"key":"2025012310372297600_btae760-B41","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1186\/s13059-019-1891-0","article-title":"Improved metagenomic analysis with Kraken 2","volume":"20","author":"Wood","year":"2019","journal-title":"Genome Biol"},{"key":"2025012310372297600_btae760-B42","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1007\/10968987_3","volume-title":"Job Scheduling Strategies for Parallel Processing","author":"Yoo","year":"2003"},{"key":"2025012310372297600_btae760-B43","doi-asserted-by":"crossref","first-page":"565","DOI":"10.1126\/science.aad3369","article-title":"Population-based metagenomics analysis reveals markers for gut microbiome composition and diversity","volume":"352","author":"Zhernakova","year":"2016","journal-title":"Science"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btae760\/61301524\/btae760.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/1\/btae760\/61301524\/btae760.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/1\/btae760\/61301524\/btae760.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,23]],"date-time":"2025-01-23T10:37:47Z","timestamp":1737628667000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btae760\/7935384"}},"subtitle":[],"editor":[{"given":"Can","family":"Alkan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,12,26]]},"references-count":43,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,12,26]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btae760","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,1]]},"published":{"date-parts":[[2024,12,26]]},"article-number":"btae760"}}