Skip to main content
. 2013 May 28;14(2):192–200. doi: 10.1038/tpj.2013.18

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.