Rapid and accurate multi-phenotype imputation for millions of individuals

Deep phenotyping can enhance the power of genetic analysis, including genome-wide association studies (GWAS), but the occurrence of missing phenotypes compromises the potential of such resources. Although many phenotypic imputation methods have been developed, the accurate imputation of millions of individuals remains extremely challenging. In the present study, we developed a novel multi-phenotype imputation method based on mixed fast random forest (PIXANT) by leveraging efficient machine learning (ML)-based algorithms. We demonstrate that PIXANT runtime is faster and computer memory usage is less than that of other state-of-the-art methods when applied to the UK Biobank (UKB) data, suggesting that PIXANT is scalable to cohorts with millions of individuals. Our simulations with hundreds of individuals showed that PIXANT accuracy was superior to or comparable to the accuracy of the most advanced methods available. PIXANT was used to impute 425 phenotypes for the UKB data of 277,301 unrelated White British citizens. When GWAS was subsequently performed on the imputed phenotypes, 18.4% more GWAS loci were identified than before imputation (8,710 vs 7,355). The increased statistical power of GWAS identified novel positional candidate genes affecting heart rate, such as RNF220, SCN10A, and RGS6, suggesting that the use of imputed phenotype data from a large cohort may lead to the discovery of novel genes for complex traits.