Cargando…

Rapid, Reference-Free human genotype imputation with denoising autoencoders

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...

Descripción completa

Detalles Bibliográficos
Autores principales: Dias, Raquel, Evans, Doug, Chen, Shang-Fu, Chen, Kai-Yu, Loguercio, Salvatore, Chan, Leslie, Torkamani, Ali
Formato: Online Artículo Texto
Lenguaje:English
Publicado: eLife Sciences Publications, Ltd 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9555874/
https://www.ncbi.nlm.nih.gov/pubmed/36148981
http://dx.doi.org/10.7554/eLife.75600
_version_ 1784806947859464192
author Dias, Raquel
Evans, Doug
Chen, Shang-Fu
Chen, Kai-Yu
Loguercio, Salvatore
Chan, Leslie
Torkamani, Ali
author_facet Dias, Raquel
Evans, Doug
Chen, Shang-Fu
Chen, Kai-Yu
Loguercio, Salvatore
Chan, Leslie
Torkamani, Ali
author_sort Dias, Raquel
collection PubMed
description 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.
format Online
Article
Text
id pubmed-9555874
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher eLife Sciences Publications, Ltd
record_format MEDLINE/PubMed
spelling pubmed-95558742022-10-13 Rapid, Reference-Free human genotype imputation with denoising autoencoders Dias, Raquel Evans, Doug Chen, Shang-Fu Chen, Kai-Yu Loguercio, Salvatore Chan, Leslie Torkamani, Ali eLife Computational and Systems Biology 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. eLife Sciences Publications, Ltd 2022-09-23 /pmc/articles/PMC9555874/ /pubmed/36148981 http://dx.doi.org/10.7554/eLife.75600 Text en © 2022, Dias et al https://creativecommons.org/licenses/by/4.0/This article is distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use and redistribution provided that the original author and source are credited.
spellingShingle Computational and Systems Biology
Dias, Raquel
Evans, Doug
Chen, Shang-Fu
Chen, Kai-Yu
Loguercio, Salvatore
Chan, Leslie
Torkamani, Ali
Rapid, Reference-Free human genotype imputation with denoising autoencoders
title Rapid, Reference-Free human genotype imputation with denoising autoencoders
title_full Rapid, Reference-Free human genotype imputation with denoising autoencoders
title_fullStr Rapid, Reference-Free human genotype imputation with denoising autoencoders
title_full_unstemmed Rapid, Reference-Free human genotype imputation with denoising autoencoders
title_short Rapid, Reference-Free human genotype imputation with denoising autoencoders
title_sort rapid, reference-free human genotype imputation with denoising autoencoders
topic Computational and Systems Biology
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9555874/
https://www.ncbi.nlm.nih.gov/pubmed/36148981
http://dx.doi.org/10.7554/eLife.75600
work_keys_str_mv AT diasraquel rapidreferencefreehumangenotypeimputationwithdenoisingautoencoders
AT evansdoug rapidreferencefreehumangenotypeimputationwithdenoisingautoencoders
AT chenshangfu rapidreferencefreehumangenotypeimputationwithdenoisingautoencoders
AT chenkaiyu rapidreferencefreehumangenotypeimputationwithdenoisingautoencoders
AT loguerciosalvatore rapidreferencefreehumangenotypeimputationwithdenoisingautoencoders
AT chanleslie rapidreferencefreehumangenotypeimputationwithdenoisingautoencoders
AT torkamaniali rapidreferencefreehumangenotypeimputationwithdenoisingautoencoders