MHC*IMP - Imputation of Alleles for Genes in the Major Histocompatibility Complex
Squire, D. M.; Motyer, A.; Ahn, R. S.; Nitiham, J.; Huang, Z.-M.; Oksenberg, J. R.; Liao, W.; Leslie, S.
Show abstract
We report the development of MHC*IMP, a method for imputing non-classical HLA and other genes in the human Major Histocompatibility Complex (MHC). We created a reference panel for 25 genes in the MHC using allele calls from Whole Genome Sequencing data, combined with SNP data for the same individuals. We used this to construct an allele imputation model, MHC*IMP, for each gene. Cross-validation showed that MHC*IMP performs very well, with allele prediction accuracy 93% or greater for all but two of the genes, and greater than 95% for all but four.
Matching journals
The top 9 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Boosting polygenic risk scores 92%
- Accelerated matrix-vector multiplications for matrices involving genotype covariates with applications in genomic prediction 91%
- Genetic landscape of rare autoinflammatory disease variants in Qatar and Middle Eastern populations through the integration of whole-genome and exome datasets 90%
Similar papers in this journal
- Accurate multi-population imputation of MICA, MICB, HLA-E, HLA-F and HLA-G alleles from genome SNP data 93%
- Enabling interpretable machine learning for biological data with reliability scores 92%
- Evaluating the utility of amino acid similarity-aware kmers to represent TCR repertoires for classification 91%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.