AUTHOR=Su Lingtao , Yan Yan , Ma Bo , Zhao Shiwei , Cui Zhenyu 

TITLE=GIHP: Graph convolutional neural network based interpretable pan-specific HLA-peptide binding affinity prediction

JOURNAL=Frontiers in Genetics

VOLUME=Volume 15 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/genetics/articles/10.3389/fgene.2024.1405032

DOI=10.3389/fgene.2024.1405032

ISSN=1664-8021

ABSTRACT=Predicting the binding affinity between Human Leukocyte Antigen (HLA) molecules and peptides is crucial for understanding the immune response and can have implications in vaccine design and immunotherapy. Existing sequence-based methods are insufficient to capture the structure information. Besides, the current methods lack model interpretability, which hinder revealing the key binding amino acids between the two molecules. To address these limitations, we proposed an interpretable graph convolutional neural network (GCNN) based prediction method named GIHP. Considering the size differences between HLA and short peptides, GIHP represent HLA structure as amino acid-level graph while represent peptide SMILE string as atom-level graph. For interpretation, GIHP includes a novel visual explanation method, gradient weighted activation mapping (Grad-WAM), for identifying key binding residues. GIHP achieved better prediction accuracy than stateof-the-art methods across various datasets. According to current research findings, key HLA-peptide binding residues mutations directly impact immunotherapy efficacy. Therefore, we verified our highlighted key residues to see whether they can significantly distinguish immunotherapy patient groups. We verified these functional residues on breast, bladder, and pan-cancer datasets all can successfully separate patient survival groups. Results demonstrate that GIHP improves the accuracy and interpretation capabilities of HLA-peptide prediction, and the findings of this study can be used to guide personalized cancer immunotherapy treatment. Codes and datasets are publicly accessible at: https://github.com/sdustSu/GIHP.