Improving generalizability for MHC-I binding peptide predictions through geometric deep learning

The interaction between peptides and major histocompatibility complex (MHC) molecules is pivotal for tissue transplantation, pathogen recognition and autoimmune disease treatments. Recent advances in cancer immunotherapies demand for more accurate computational prediction of MHC-bound peptides. We a...

Full description

Saved in:
Bibliographic Details
Published inbioRxiv
Main Authors Marzella, Dario F, Crocioni, Giulia, Radusinovic, Tadija, Lepikhov, Daniil, Severin, Heleen, Bodor, Dani L, Rademaker, Daniel T, Lin, Chiayu, Georgievska, Sonja, Renaud, Nicolas, Kessler, Amy Lynn, Lopez-Tarifa, Pablo, Buschow, Sonja, Bekkers, Erik, Xue, Li C
Format Paper
LanguageEnglish
Published Cold Spring Harbor Cold Spring Harbor Laboratory Press 09.02.2024
Subjects
Alleles
Autoimmune diseases
Cancer immunotherapy
Deep learning
Design
Human papillomavirus
Lymphocytes T
Major histocompatibility complex
Peptides
T cell receptors
Online AccessGet full text

Cover

More Information
Summary:The interaction between peptides and major histocompatibility complex (MHC) molecules is pivotal for tissue transplantation, pathogen recognition and autoimmune disease treatments. Recent advances in cancer immunotherapies demand for more accurate computational prediction of MHC-bound peptides. We address the generalizability challenge of MHC-bound peptide predictions, revealing limitations in current sequence-based approaches. Our solution employs structure-based methods leveraging geometric deep learning (GDL), yielding up to 8% improvement in generalizability across unseen MHC alleles. We tackle data efficiency by introducing a self-supervised learning approach surpassing sequence-based methods, even without being trained on binding affinity data. Finally, we demonstrate the resilience of structure-based GDL methods to biases in binding data on an Hepatitis B virus vaccine design case study. This study highlights structure-based methods' potential to enhance generalizability and data efficiency, with implications for data-intensive fields like T-cell receptor specificity predictions, paving the way for enhanced comprehension and manipulation of immune responses.Competing Interest StatementThe authors have declared no competing interest.Footnotes* Updated figures aesthetics. Added panel C in Figure 3. Shortened Introduction and Discussion.
DOI:10.1101/2023.12.04.569776