RefRGim: an intelligent reference panel reconstruction method for genotype imputation with convolutional neural networks. Issue 6 (17th August 2021)

• Record Type: Journal Article
• Authors: Shi, Shuo; Qian, Qiheng; Yu, Shuhuan; Wang, Qi; Wang, Jinyue; Zeng, Jingyao; Du, Zhenglin; Xiao, Jingfa
• Is Part Of: Briefings in bioinformatics. Volume 22:Issue 6(2021)
• Publication Date: 2021-08-17
• Subjects: genotype imputation -- reference reconstruction -- deep learning -- genome-wide association study; Genetics -- Data processing -- Periodicals; Molecular biology -- Data processing -- Periodicals; Genomes -- Data processing -- Periodicals; 572.80285
• DOI: 10.1093/bib/bbab326
• Languages: English
• ISSNs: 1467-5463

Abstract

Abstract: Genotype imputation is a statistical method for estimating missing genotypes from a denser haplotype reference panel. Existing methods usually performed well on common variants, but they may not be ideal for low-frequency and rare variants. Previous studies showed that the population similarity between study and reference panels is one of the key factors influencing the imputation accuracy. Here, we developed an imputation reference panel reconstruction method (RefRGim) using convolutional neural networks (CNNs), which can generate a study-specified reference panel for each input data based on the genetic similarity of individuals from current study and references. The CNNs were pretrained with single nucleotide polymorphism data from the 1000 Genomes Project. Our evaluations showed that genotype imputation with RefRGim can achieve higher accuracies than original reference panel, especially for low-frequency and rare variants. RefRGim will serve as an efficient reference panel reconstruction method for genotype imputation. RefRGim is freely available via GitHub: https://github.com/shishuo16/RefRGim