PT  - JOURNAL ARTICLE
AU  - Dias, Raquel
AU  - Evans, Doug
AU  - Chen, Shang-Fu
AU  - Chen, Kai-Yu
AU  - Chan, Leslie
AU  - Torkamani, Ali
TI  - Rapid, Reference-Free Human Genotype Imputation with Denoising Autoencoders
AID  - 10.1101/2021.12.01.470739
DP  - 2021 Jan 01
TA  - bioRxiv
PG  - 2021.12.01.470739
4099  - http://biorxiv.org/content/early/2021/12/02/2021.12.01.470739.short
4100  - http://biorxiv.org/content/early/2021/12/02/2021.12.01.470739.full
AB  - 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 4-fold faster inference run time relative to standard imputation tools.Competing Interest StatementThe authors have declared no competing interest.