{"doi":"10.7554/elife.75600","title":"Rapid, Reference-Free human genotype imputation with denoising autoencoders","abstract":"Genotype imputation is a foundational tool for population genetics. Standard statistical imputation approaches rely on the co-location of large whole-genome sequencing-based reference panels, powerful computing environments, and potentially sensitive genetic study data. This results in computational resource and privacy-risk barriers to access to cutting-edge imputation techniques. Moreover, the accuracy of current statistical approaches is known to degrade in regions of low and complex linkage disequilibrium. Artificial neural network-based imputation approaches may overcome these limitations by encoding complex genotype relationships in easily portable inference models. Here, we demonstrate an autoencoder-based approach for genotype imputation, using a large, commonly used reference panel, and spanning the entirety of human chromosome 22. Our autoencoder-based genotype imputation strategy achieved superior imputation accuracy across the allele-frequency spectrum and across genomes of diverse ancestry, while delivering at least fourfold faster inference run time relative to standard imputation tools.","journal":"eLife","year":2022,"id":262413,"datarank":0.6855674696421066,"base_score":2.70805020110221,"endowment":2.70805020110221,"self_citation_contribution":0.40620753016533157,"citation_network_contribution":0.27935993947677507,"self_endowment_contribution":0.40620753016533157,"citer_contribution":0.27935993947677507,"corpus_percentile":null,"corpus_rank":null,"citation_count":14,"citer_count":12,"citers_with_citation_signal":7,"citers_with_endowment":7,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9492,"is_data_producer":true,"deposit_databanks":{"dbGaP":["phs001416.v2.p1","phs001211.v4.p3"]},"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2022-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":52732,"name":"D. Gareth Evans","orcid":"0000-0002-8482-5784","position":1,"is_corresponding":false},{"id":917808,"name":"Shang‐Fu Chen","orcid":"0000-0001-5467-288X","position":2,"is_corresponding":false},{"id":917809,"name":"Kaiyu Chen","orcid":"0000-0002-4464-0953","position":3,"is_corresponding":false},{"id":913238,"name":"Salvatore Loguercio","orcid":"0000-0002-7544-2992","position":4,"is_corresponding":false},{"id":37994,"name":"Leslie Chan","orcid":"0000-0001-7779-2059","position":5,"is_corresponding":false},{"id":27511,"name":"Ali Torkamani","orcid":"0000-0003-0232-8053","position":6,"is_corresponding":false},{"id":70920,"name":"Raquel Dias","orcid":"0000-0002-8387-1324","position":0,"is_corresponding":true}],"reference_count":39,"raw_metadata":null,"created_at":"2026-07-19T00:26:20.717229Z","pmid":"36148981","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":[]}