{"doi":"10.1093/bioinformatics/btae698","title":"Polyphonia: detecting inter-sample contamination in viral genomic sequencing data","abstract":"SUMMARY: In viral genomic research and surveillance, inter-sample contamination can affect variant detection, analysis of within-host evolution, outbreak reconstruction, and detection of superinfections and recombination events. While sample barcoding methods exist to track inter-sample contamination, they are not always used and can only detect contamination in the experimental pipeline from the point they are added. The underlying genomic information in a sample, however, carries information about inter-sample contamination occurring at any stage. Here, we present Polyphonia, a tool for detecting inter-sample contamination directly from deep sequencing data without the need for additional controls, using intrahost variant frequencies. We apply Polyphonia to 1102 SARS-CoV-2 samples sequenced at the Broad Institute and already tracked using molecular barcoding for comparison. AVAILABILITY AND IMPLEMENTATION: Polyphonia is available as a standalone Docker image and is also included as part of viral-ngs, available in Dockstore. Full documentation, source code, and instructions for use are available at https://github.com/broadinstitute/polyphonia.","journal":"Bioinformatics","year":2024,"id":482651,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":1,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9548,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2024-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":472081,"name":"Christopher H. Tomkins-Tinch","orcid":"0000-0002-9114-6421","position":1,"is_corresponding":false},{"id":841633,"name":"Alton C. Gayton","orcid":"0000-0002-2411-0621","position":2,"is_corresponding":false},{"id":62163,"name":"S. F. Schaffner","orcid":"0000-0001-6699-3568","position":3,"is_corresponding":false},{"id":731770,"name":"Sabrina T. Dobbins","orcid":null,"position":4,"is_corresponding":false},{"id":730976,"name":"Adrianne Gladden-Young","orcid":"0000-0001-6307-0012","position":5,"is_corresponding":false},{"id":251084,"name":"Katherine J. Siddle","orcid":"0000-0002-1799-7295","position":6,"is_corresponding":false},{"id":251090,"name":"Daniel J. Park","orcid":"0000-0001-7226-7781","position":7,"is_corresponding":false},{"id":7155,"name":"Pardis C. Sabeti","orcid":"0000-0002-9843-1890","position":8,"is_corresponding":false},{"id":317229,"name":"Lydia A. Krasilnikova","orcid":"0000-0003-4163-706X","position":0,"is_corresponding":true}],"reference_count":17,"raw_metadata":null,"created_at":"2026-07-19T02:07:18.280369Z","pmid":"39673434","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":[]}