Accurate multi-population imputation of MICA, MICB, HLA-E, HLA-F and HLA-G alleles from genome SNP data.

In addition to the classical HLA genes, the major histocompatibility complex (MHC) harbors a high number of other polymorphic genes with less established roles in disease associations and transplantation matching. To facilitate studies of the non-classical and non-HLA genes in large patient and biobank cohorts, we trained imputation models for MICA, MICB, HLA-E, HLA-F and HLA-G alleles on genome SNP array data. We show, using both population-specific and multi-population 1000 Genomes references, that the alleles of these genes can be accurately imputed for screening and research purposes. The best imputation model for MICA, MICB, HLA-E, -F and -G achieved a mean accuracy of 99.3% (min, max: 98.6, 99.9). Furthermore, validation of the 1000 Genomes exome short-read sequencing-based allele calling against a clinical-grade reference data showed an average accuracy of 99.8%, testifying for the quality of the 1000 Genomes data as an imputation reference. We also fitted the models for Infinium Global Screening Array (GSA, Illumina, Inc.) and Axiom Precision Medicine Research Array (PMRA, Thermo Fisher Scientific Inc.) SNP content, with mean accuracies of 99.1% (97.2, 100) and 98.9% (97.4, 100), respectively.

A machine-learning method for biobank-scale genetic prediction of blood group antigens.

A key element for successful blood transfusion is compatibility of the patient and donor red blood cell (RBC) antigens. Precise antigen matching reduces the risk for immunization and other adverse transfusion outcomes. RBC antigens are encoded by specific genes, which allows developing computational methods for determining antigens from genomic data. We describe here a classification method for determining RBC antigens from genotyping array data. Random forest models for 39 RBC antigens in 14 blood group systems and for human platelet antigen (HPA)-1 were trained and tested using genotype and RBC antigen and HPA-1 typing data available for 1,192 blood donors in the Finnish Blood Service Biobank. The algorithm and models were further evaluated using a validation cohort of 111,667 Danish blood donors. In the Finnish test data set, the median (interquartile range [IQR]) balanced accuracy for 39 models was 99.9 (98.9-100)%. We were able to replicate 34 out of 39 Finnish models in the Danish cohort and the median (IQR) balanced accuracy for classifications was 97.1 (90.1-99.4)%. When applying models trained with the Danish cohort, the median (IQR) balanced accuracy for the 40 Danish models in the Danish test data set was 99.3 (95.1-99.8)%. The RBC antigen and HPA-1 prediction models demonstrated high overall accuracies suitable for probabilistic determination of blood groups and HPA-1 at biobank-scale. Furthermore, population-specific training cohort increased the accuracies of the models. This stand-alone and freely available method is applicable for research and screening for antigen-negative blood donors.