3pHLA-score improves structure-based peptide-HLA binding affinity prediction
Abstract Binding of peptides to Human Leukocyte Antigen (HLA) receptors is a prerequisite for triggering immune response. Estimating peptide-HLA (pHLA) binding is crucial for peptide vaccine target identification and epitope discovery pipelines. Computational methods for binding affinity prediction...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2022-06-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-022-14526-x |
_version_ | 1811334580476575744 |
---|---|
author | Anja Conev Didier Devaurs Mauricio Menegatti Rigo Dinler Amaral Antunes Lydia E. Kavraki |
author_facet | Anja Conev Didier Devaurs Mauricio Menegatti Rigo Dinler Amaral Antunes Lydia E. Kavraki |
author_sort | Anja Conev |
collection | DOAJ |
description | Abstract Binding of peptides to Human Leukocyte Antigen (HLA) receptors is a prerequisite for triggering immune response. Estimating peptide-HLA (pHLA) binding is crucial for peptide vaccine target identification and epitope discovery pipelines. Computational methods for binding affinity prediction can accelerate these pipelines. Currently, most of those computational methods rely exclusively on sequence-based data, which leads to inherent limitations. Recent studies have shown that structure-based data can address some of these limitations. In this work we propose a novel machine learning (ML) structure-based protocol to predict binding affinity of peptides to HLA receptors. For that, we engineer the input features for ML models by decoupling energy contributions at different residue positions in peptides, which leads to our novel per-peptide-position protocol. Using Rosetta’s ref2015 scoring function as a baseline we use this protocol to develop 3pHLA-score. Our per-peptide-position protocol outperforms the standard training protocol and leads to an increase from 0.82 to 0.99 of the area under the precision-recall curve. 3pHLA-score outperforms widely used scoring functions (AutoDock4, Vina, Dope, Vinardo, FoldX, GradDock) in a structural virtual screening task. Overall, this work brings structure-based methods one step closer to epitope discovery pipelines and could help advance the development of cancer and viral vaccines. |
first_indexed | 2024-04-13T17:11:01Z |
format | Article |
id | doaj.art-b3bf14ad1c474631b3a0c2f7aeab1c87 |
institution | Directory Open Access Journal |
issn | 2045-2322 |
language | English |
last_indexed | 2024-04-13T17:11:01Z |
publishDate | 2022-06-01 |
publisher | Nature Portfolio |
record_format | Article |
series | Scientific Reports |
spelling | doaj.art-b3bf14ad1c474631b3a0c2f7aeab1c872022-12-22T02:38:17ZengNature PortfolioScientific Reports2045-23222022-06-0112111110.1038/s41598-022-14526-x3pHLA-score improves structure-based peptide-HLA binding affinity predictionAnja Conev0Didier Devaurs1Mauricio Menegatti Rigo2Dinler Amaral Antunes3Lydia E. Kavraki4Department of Computer Science, Rice UniversityMRC Institute of Genetics and Cancer, University of EdinburghDepartment of Computer Science, Rice UniversityDepartment of Biology and Biochemistry, University of HoustonDepartment of Computer Science, Rice UniversityAbstract Binding of peptides to Human Leukocyte Antigen (HLA) receptors is a prerequisite for triggering immune response. Estimating peptide-HLA (pHLA) binding is crucial for peptide vaccine target identification and epitope discovery pipelines. Computational methods for binding affinity prediction can accelerate these pipelines. Currently, most of those computational methods rely exclusively on sequence-based data, which leads to inherent limitations. Recent studies have shown that structure-based data can address some of these limitations. In this work we propose a novel machine learning (ML) structure-based protocol to predict binding affinity of peptides to HLA receptors. For that, we engineer the input features for ML models by decoupling energy contributions at different residue positions in peptides, which leads to our novel per-peptide-position protocol. Using Rosetta’s ref2015 scoring function as a baseline we use this protocol to develop 3pHLA-score. Our per-peptide-position protocol outperforms the standard training protocol and leads to an increase from 0.82 to 0.99 of the area under the precision-recall curve. 3pHLA-score outperforms widely used scoring functions (AutoDock4, Vina, Dope, Vinardo, FoldX, GradDock) in a structural virtual screening task. Overall, this work brings structure-based methods one step closer to epitope discovery pipelines and could help advance the development of cancer and viral vaccines.https://doi.org/10.1038/s41598-022-14526-x |
spellingShingle | Anja Conev Didier Devaurs Mauricio Menegatti Rigo Dinler Amaral Antunes Lydia E. Kavraki 3pHLA-score improves structure-based peptide-HLA binding affinity prediction Scientific Reports |
title | 3pHLA-score improves structure-based peptide-HLA binding affinity prediction |
title_full | 3pHLA-score improves structure-based peptide-HLA binding affinity prediction |
title_fullStr | 3pHLA-score improves structure-based peptide-HLA binding affinity prediction |
title_full_unstemmed | 3pHLA-score improves structure-based peptide-HLA binding affinity prediction |
title_short | 3pHLA-score improves structure-based peptide-HLA binding affinity prediction |
title_sort | 3phla score improves structure based peptide hla binding affinity prediction |
url | https://doi.org/10.1038/s41598-022-14526-x |
work_keys_str_mv | AT anjaconev 3phlascoreimprovesstructurebasedpeptidehlabindingaffinityprediction AT didierdevaurs 3phlascoreimprovesstructurebasedpeptidehlabindingaffinityprediction AT mauriciomenegattirigo 3phlascoreimprovesstructurebasedpeptidehlabindingaffinityprediction AT dinleramaralantunes 3phlascoreimprovesstructurebasedpeptidehlabindingaffinityprediction AT lydiaekavraki 3phlascoreimprovesstructurebasedpeptidehlabindingaffinityprediction |