Skip to main page content
Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
, 14 (2), 192-200

HIBAG--HLA Genotype Imputation With Attribute Bagging

Affiliations

HIBAG--HLA Genotype Imputation With Attribute Bagging

X Zheng et al. Pharmacogenomics J.

Abstract

Genotyping of classical human leukocyte antigen (HLA) alleles is an essential tool in the analysis of diseases and adverse drug reactions with associations mapping to the major histocompatibility complex (MHC). However, deriving high-resolution HLA types subsequent to whole-genome single-nucleotide polymorphism (SNP) typing or sequencing is often cost prohibitive for large samples. An alternative approach takes advantage of the extended haplotype structure within the MHC to predict HLA alleles using dense SNP genotypes, such as those available from genome-wide SNP panels. Current methods for HLA imputation are difficult to apply or may require the user to have access to large training data sets with SNP and HLA types. We propose HIBAG, HLA Imputation using attribute BAGging, that makes predictions by averaging HLA-type posterior probabilities over an ensemble of classifiers built on bootstrap samples. We assess the performance of HIBAG using our study data (n=2668 subjects of European ancestry) as a training set and HLA data from the British 1958 birth cohort study (n≈1000 subjects) as independent validation samples. Prediction accuracies for HLA-A, B, C, DRB1 and DQB1 range from 92.2% to 98.1% using a set of SNP markers common to the Illumina 1M Duo, OmniQuad, OmniExpress, 660K and 550K platforms. HIBAG performed well compared with the other two leading methods, HLA*IMP and BEAGLE. This method is implemented in a freely available HIBAG R package that includes pre-fit classifiers for European, Asian, Hispanic and African ancestries, providing a readily available imputation approach without the need to have access to large training data sets.

Figures

Figure 1
Figure 1
Overview of the HIBAG prediction algorithm. HIBAG is an ensemble classifier consisting of individual classifiers (Ck) with human leukocyte antigen (HLA) and single-nucleotide polymorphism (SNP) haplotype probabilities estimated from bootstrapped samples (Bk) and SNP subsets (Sk). The SNP subsets are determined by a variable selection algorithm with a random component. HLA-type predictions are averaged over the posterior probabilities from all classifiers.
Figure 2
Figure 2
The relationship between accuracy and call rate when HLARES data for individuals of European ancestry are divided into training and validation sets with equal sizes. On the curve for each HLA (human leukocyte antigen) locus, the 0.5 call threshold is indicated by •.
Figure 3
Figure 3
The relationship between training sample size and accuracy. HLARES data of European ancestry were divided into training and validation sets with equal sizes, and random subsets of training samples (n=100, 250, 500, 750, 1000 and max) were used to build a HIBAG model, which was applied to the same validation samples. No call threshold was applied.

Similar articles

See all similar articles

Cited by 88 articles

See all "Cited by" articles

References

    1. Shiina T, Hosomichi K, Inoko H, Kulski J. The HLA genomic loci map: expression, interaction, diversity and disease. J Human Genet. 2009;54:15–39. - PubMed
    1. Robinson J, Halliwell J, McWilliam H, Lopez R, Parham P, Marsh S. The IMGT/HLA database. Nucleic Acids Res. 2013;41:1222–1227. - PMC - PubMed
    1. de Bakker P, McVean G, Sabeti P, Miretti M, Green T, Marchini J, et al. A high-resolution HLA and SNP haplotype map for disease association studies in the extended human MHC. Nat Genet. 2006;38:1166–1172. - PMC - PubMed
    1. Evseeva I, Nicodemus K, Bonilla C, Tonks S, Bodmer W. Linkage disequilibrium and age of HLA region SNPs in relation to classic HLA gene alleles within Europe. Eur J Hum Genet. 2010;18:924–932. - PMC - PubMed
    1. Leslie S, Donnelly P, McVean G. A statistical method for predicting classical HLA alleles from SNP data. Am J Hum Genet. 2008;82:48–56. - PMC - PubMed

Publication types

MeSH terms

Feedback