Efficient HLA imputation from sequential SNPs data by Transformer
This work addresses the need for more efficient HLA imputation in genetics research, particularly for disease association studies, but it is incremental as it builds on existing deep learning approaches.
The researchers tackled the problem of imputing HLA alleles from sequential SNPs data, which is costly to type directly, by developing a Transformer-based model called HLARIMNT. They achieved higher accuracy than a previous CNN-based method, especially for infrequent alleles, using reference panels of up to 5,225 samples.
Human leukocyte antigen (HLA) genes are associated with a variety of diseases, however direct typing of HLA is time and cost consuming. Thus various imputation methods using sequential SNPs data have been proposed based on statistical or deep learning models, e.g. CNN-based model, named DEEP*HLA. However, imputation efficiency is not sufficient for in frequent alleles and a large size of reference panel is required. Here, we developed a Transformer-based model to impute HLA alleles, named "HLA Reliable IMputatioN by Transformer (HLARIMNT)" to take advantage of sequential nature of SNPs data. We validated the performance of HLARIMNT using two different reference panels; Pan-Asian reference panel (n = 530) and Type 1 Diabetes Genetics Consortium (T1DGC) reference panel (n = 5,225), as well as the mixture of those two panels (n = 1,060). HLARIMNT achieved higher accuracy than DEEP*HLA by several indices, especially for infrequent alleles. We also varied the size of data used for training, and HLARIMNT imputed more accurately among any size of training data. These results suggest that Transformer-based model may impute efficiently not only HLA types but also any other gene types from sequential SNPs data.