{"doi":"10.1101/2023.06.02.543519","title":"Rapid and sensitive detection of genome contamination at scale with FCS-GX","abstract":"Assembled genome sequences are being generated at an exponential rate. Here we present FCS-GX, part of NCBI's Foreign Contamination Screen (FCS) tool suite, optimized to identify and remove contaminant sequences in new genomes. FCS-GX screens most genomes in 0.1-10 minutes. Testing FCS-GX on artificially fragmented genomes demonstrates sensitivity >95% for diverse contaminant species and specificity >99.93%. We used FCS-GX to screen 1.6 million GenBank assemblies and identified 36.8 Gbp of contamination (0.16% of total bases), with half from 161 assemblies. We updated assemblies in NCBI RefSeq to reduce detected contamination to 0.01% of bases. FCS-GX is available at https://github.com/ncbi/fcs/.","journal":"bioRxiv (Cold Spring Harbor Laboratory)","year":2023,"id":389386,"datarank":0.611630616585858,"base_score":4.07753744390572,"endowment":4.07753744390572,"self_citation_contribution":0.611630616585858,"citation_network_contribution":0.0,"self_endowment_contribution":0.611630616585858,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":58,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9575,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2023-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":575580,"name":"Eric S. Tvedte","orcid":"0000-0003-1169-3079","position":1,"is_corresponding":false},{"id":1160512,"name":"Deacon Sweeney","orcid":null,"position":2,"is_corresponding":false},{"id":96589,"name":"Victor Sapojnikov","orcid":null,"position":3,"is_corresponding":false},{"id":1160513,"name":"Nathan Bouk","orcid":null,"position":4,"is_corresponding":false},{"id":551093,"name":"Victor Joukov","orcid":null,"position":5,"is_corresponding":false},{"id":1160514,"name":"Eyal Mozes","orcid":null,"position":6,"is_corresponding":false},{"id":1087283,"name":"Pooja K Strope","orcid":null,"position":7,"is_corresponding":false},{"id":1160515,"name":"Pape M. Sylla","orcid":null,"position":8,"is_corresponding":false},{"id":1015282,"name":"Lukas Wagner","orcid":null,"position":9,"is_corresponding":false},{"id":1160516,"name":"Shelby Bidwell","orcid":null,"position":10,"is_corresponding":false},{"id":89204,"name":"Karen Clark","orcid":"0000-0003-4403-1477","position":11,"is_corresponding":false},{"id":1159683,"name":"Emily W. Davis","orcid":"0009-0002-0120-2299","position":12,"is_corresponding":false},{"id":1160517,"name":"Brian Smith-White","orcid":null,"position":13,"is_corresponding":false},{"id":96543,"name":"Wratko Hlavina","orcid":"0000-0001-8250-5675","position":14,"is_corresponding":false},{"id":2100,"name":"Kim D. Pruitt","orcid":"0000-0001-7950-1374","position":15,"is_corresponding":false},{"id":2127,"name":"Valérie Schneider","orcid":"0000-0002-3442-1888","position":16,"is_corresponding":false},{"id":2099,"name":"Terence D. Murphy","orcid":"0000-0001-9311-9745","position":17,"is_corresponding":false},{"id":196134,"name":"Alexander Astashyn","orcid":null,"position":0,"is_corresponding":true}],"reference_count":38,"raw_metadata":{"citation_network_status":"fetched"},"created_at":"2026-07-19T01:18:27.054415Z","pmid":"37292984","pmcid":null,"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":[]}