{"doi":"10.1371/journal.pone.0250092","title":"Supervised extraction of near-complete genomes from metagenomic samples: A new service in PATRIC","abstract":"Large amounts of metagenomically-derived data are submitted to PATRIC for analysis. In the future, we expect even more jobs submitted to PATRIC will use metagenomic data. One in-demand use case is the extraction of near-complete draft genomes from assembled contigs of metagenomic origin. The PATRIC metagenome binning service utilizes the PATRIC database to furnish a large, diverse set of reference genomes. We provide a new service for supervised extraction and annotation of high-quality, near-complete genomes from metagenomically-derived contigs. Reference genomes are assigned to putative draft genome bins based on the presence of single-copy universal marker roles in the sample, and contigs are sorted into these bins by their similarity to reference genomes in PATRIC. Each set of binned contigs represents a draft genome that will be annotated by RASTtk in PATRIC. A structured-language binning report is provided containing quality measurements and taxonomic information about the contig bins. The PATRIC metagenome binning service emphasizes extraction of high-quality genomes for downstream analysis using other PATRIC tools and services. Due to its supervised nature, the binning service is not appropriate for mining novel or extremely low-coverage genomes from metagenomic samples.","journal":"PLoS ONE","year":2021,"id":177258,"datarank":0.8473054458817166,"base_score":3.044522437723423,"endowment":3.044522437723423,"self_citation_contribution":0.4566783656585135,"citation_network_contribution":0.3906270802232031,"self_endowment_contribution":0.4566783656585135,"citer_contribution":0.3906270802232031,"corpus_percentile":76.24352131198268,"corpus_rank":3072,"citation_count":20,"citer_count":18,"citers_with_citation_signal":13,"citers_with_endowment":13,"datacite_reuse_total":0,"is_dataset":true,"is_dataset_confidence":0.7182,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2021-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":720914,"name":"Rory Butler","orcid":"0000-0003-1667-1709","position":1,"is_corresponding":false},{"id":720915,"name":"Philippe Chlenski","orcid":"0000-0002-2951-4385","position":2,"is_corresponding":false},{"id":42093,"name":"Gordon D. Pusch","orcid":"0000-0003-1471-0401","position":3,"is_corresponding":false},{"id":42100,"name":"Ross Overbeek","orcid":null,"position":4,"is_corresponding":false},{"id":42092,"name":"Bruce Parrello","orcid":null,"position":0,"is_corresponding":true}],"reference_count":11,"raw_metadata":null,"created_at":"2026-07-18T23:47:28.018172Z","pmid":"33857229","pmcid":"PMC8049274","fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}