OnionMHC: a deep learning model for peptide - HLA-A*02:01 binding predictions

• Main Author: Saxena, Shikhar
• Other Authors: Mu Yuguang
• Format: Thesis-Doctor of Philosophy
• Language: English
• Published: Nanyang Technological University 2022
• Subjects: Science::Biological sciences
• Online Access: https://hdl.handle.net/10356/156853
• Institution: Nanyang Technological University

The peptide binding to Major Histocompatibility Complex (MHC) proteins is an important step in the antigen-presentation pathway. Thus, predicting the binding potential of peptides with MHC is essential for the design of peptide-based therapeutics. Most of the available machine learning-based models predict the peptide-MHC binding based on the sequence of amino acids alone. Given the importance of structural information in determining the stability of the complex, here we have utilized both the complex structure and the peptide sequence features to predict the binding affinity of peptides to human receptor HLA-A*02:01. To our knowledge, no such model has been developed for the human HLA receptor before that incorporates both structure and sequence-based features. We have applied machine learning techniques through the natural language processing (NLP) and convolutional neural network to design a model that performs comparably with the existing state-of-the-art models. Our model shows that the information from both sequence and structure domains results in enhanced performance in the binding prediction compared to the information from one domain alone. The testing results in 18 weekly benchmark datasets provided by the Immune Epitope Database (IEDB) as well as experimentally validated peptides from the whole-exome sequencing analysis of the breast cancer patients indicate that our model has achieved state-of-the-art performance. We have developed a deep-learning model (OnionMHC) that incorporates both structure as well as sequence-based features to predict the binding affinity of peptides with human receptor HLA-A*02:01. The model demonstrates state-of-the-art performance on the IEDB benchmark dataset as well as the experimentally validated peptides. The model can be used in the screening of potential neo-epitopes for the development of cancer vaccines or designing peptides for peptide-based therapeutics.