Snowflake: A deep learning-based human leukocyte antigen matching algorithm considering allele-specific surface accessibility

Abstract

Histocompatibility in solid-organ transplantation has a strong impact on long-term graft survival. Although recent advances in matching of both B-cell epitopes and T-cell epitopes have improved understanding of allorecognition, the immunogenic determinants are still not fully understood. We hypothesized that HLA solvent accessibility is allele-specific, thus supporting refinement of HLA B-cell epitope prediction. We developed a computational pipeline named Snowflake to calculate solvent accessibility of HLA Class I proteins for deposited HLA crystal structures, supplemented by constructed HLA structures through the AlphaFold protein folding predictor and peptide binding predictions of the APE-Gen docking framework. This dataset trained a four-layer long short-term memory bidirectional recurrent neural network, which in turn inferred solvent accessibility of all known HLA Class I proteins. We extracted 676 HLA Class-I experimental structures from the Protein Data Bank and supplemented it by 37 Class-I alleles for which structures were predicted. For each of the predicted structures, 10 known binding peptides as reported by the Immune Epitope DataBase were rendered into the binding groove. Although HLA Class I proteins predominantly are folded similarly, we found higher variation in root mean square difference of solvent accessibility between experimental structures of different HLAs compared to structures with identical amino acid sequence, suggesting HLA’s solvent accessible surface is protein specific. Hence, residues may be surface-accessible on e.g. HLA-A*02:01, but not on HLA-A*01:01. Mapping these data to antibody-verified epitopes as defined by the HLA Epitope Registry reveals patterns of (1) consistently accessible residues, (2) only subsets of an epitope’s residues being consistently accessible and (3) varying surface accessibility of residues of epitopes. Our data suggest B-cell epitope definitions can be refined by considering allele-specific solvent-accessibility, rather than aggregating HLA protein surface maps by HLA class or locus. To support studies on epitope analyses in organ transplantation, the calculation of donor-allele-specific solvent-accessible amino acid mismatches was implemented as a cloud-based web service.

Snowflake epitope matching correlates with child-specific antibodies during pregnancy and donor-specific antibodies after kidney transplantation

“…The Snowflake algorithm is an integrated computational pipeline counting the number of HLA protein-specific solvent accessible amino acid mismatches between donor and recipient. It has been shown, solvent-accessibility is protein-specific, and thus proposed to be considered individually ( 16 ). For that purpose, Niemann et al.…”

“…interlocus). The full matching pipeline was implemented as a web service, featuring CSV input and output formats for batch processing ( , version 3.47) ( 16 ).…”

“…The Snowflake algorithm is an integrated computational pipeline counting the number of HLA protein-specific solvent accessible amino acid mismatches between donor and recipient. It has been shown, solvent-accessibility is protein-specific, and thus proposed to be considered individually (16). For that purpose, Niemann et al extracted 676 experimental HLA Class I structures of the Protein Data Bank (www.rcsb.org) and supplemented these by 37 predicted structures using the AlphaFold predictor (DeepMind Technologies Limited, London, UK) (22)(23)(24).…”

“…HLAMatchmaker assumes two proteins with the same amino acid configuration as both carrying the same eplet, assuming identical folding or alleles within the same locus ( 15 ). Likewise, HLA-EMMA considers surface-accessible amino acid positions per HLA locus, which however may be not identical across different HLA proteins given slight variations in protein folding ( 16 ). Refining that concept, the proposed Snowflake algorithm defines the HLA protein-specific surface accessibility, taking into account structural deviations between HLA proteins.…”

“…Refining that concept, the proposed Snowflake algorithm defines the HLA protein-specific surface accessibility, taking into account structural deviations between HLA proteins. Amino acid mismatches at solvent accessible positions of the respective donor HLA are hypothesized to increase risk of B cell allorecognition ( 16 ). Within this work, we evaluated the correlation between the number of such HLA Class I-specific solvent-accessible amino acid mismatches (Snowflake score) and the incidence of donor-specific HLA antibodies (DSA) after kidney transplantation and child-specific HLA antibodies (CSA) during pregnancy, respectively (collectively immunizer-specific antibodies, ISA).…”