{"doi":"10.1101/2025.11.06.686913","title":"Genotype-level quality control substantially reduces error rates in population-scale whole-genome sequencing","abstract":"Abstract Population-scale whole-genome sequencing data will contain many individual-level genotype errors, even after allele-level quality control (QC). We establish the need for genotype-level QC using UK Biobank (N=490,726) and All of Us v8 (N=414,830), where we remove up to 100 million (∼9%) additional low-quality variants. We demonstrate reduced false positive rate in downstream genetic association studies, highlight the power of parent-offspring trios for QC, and illustrate the need for sex-specific X-chromosome filtering. We provide a QCed All of Us v8 dataset in plink -pgen format, and an efficient pipeline for QC and conversion from VCF to plink- pgen for UK Biobank.","journal":"bioRxiv (Cold Spring Harbor Laboratory)","year":2025,"id":580410,"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":0,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9419,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2025-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":25373,"name":"Harrison I.W. Wright","orcid":"0009-0009-1900-163X","position":1,"is_corresponding":false},{"id":16114,"name":"Timothy M. Frayling","orcid":"0000-0001-8362-2603","position":2,"is_corresponding":false},{"id":345045,"name":"Andrew R. Wood","orcid":"0000-0003-1726-948X","position":3,"is_corresponding":false},{"id":22004,"name":"Michael N. Weedon","orcid":"0000-0002-6174-6135","position":4,"is_corresponding":false},{"id":25378,"name":"Caroline F. Wright","orcid":"0000-0003-2958-5076","position":5,"is_corresponding":false},{"id":241472,"name":"Robin N. Beaumont","orcid":"0000-0003-0750-8248","position":6,"is_corresponding":false},{"id":25381,"name":"Gareth Hawkes","orcid":"0000-0002-3367-789X","position":7,"is_corresponding":false},{"id":25376,"name":"V. Kartik Chundru","orcid":"0000-0002-6348-5565","position":0,"is_corresponding":true}],"reference_count":22,"raw_metadata":null,"created_at":"2026-07-19T02:58:38.868285Z","pmid":null,"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":[]}