DeepLigand: accurate prediction of MHC class I ligands using peptide embedding
Authors:
Open Access
- 5 July 2019
- journal article
- conference paper
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 35 (14) , i278-i283
Abstract
The computational modeling of peptide display by class I major histocompatibility complexes (MHCs) is essential for peptide-based therapeutics design. Existing computational methods for peptide-display focus on modeling the peptide-MHC-binding affinity. However, such models are not able to characterize the sequence features for the other cellular processes in the peptide display pathway that determines MHC ligand selection. We introduce a semi-supervised model, DeepLigand that outperforms the state-of-the-art models in MHC Class I ligand prediction. DeepLigand combines a peptide language model and peptide binding affinity prediction to score MHC class I peptide presentation. The peptide language model characterizes sequence features that correspond to secondary factors in MHC ligand selection other than binding affinity. The peptide embedding is learned by pre-training on natural ligands, and can discriminate between ligands and non-ligands in the absence of binding affinity prediction. Although conventional affinity-based models fail to classify peptides with moderate affinities, DeepLigand discriminates ligands from non-ligands with consistently high accuracy. We make DeepLigand available at https://github.com/gifford-lab/DeepLigand. Supplementary data are available at Bioinformatics online.Keywords
Funding Information
- National Institute of Health (R01CA218094)
This publication has 22 references indexed in Scilit:
- Mutant MHC class II epitopes drive therapeutic immune responses to cancerNature, 2015
- Dataset size and composition impact the reliability of performance benchmarks for peptide-MHC binding predictionsBMC Bioinformatics, 2014
- Relative Quantification: Characterization of Bias, Variability and Fold Changes in Mass Spectrometry Data from iTRAQ-Labeled PeptidesJournal of Proteome Research, 2011
- NetMHC-3.0: accurate web accessible predictions of human, mouse and monkey MHC class I affinities for peptides of length 8–11Nucleic Acids Research, 2008
- NetMHCpan, a Method for Quantitative Predictions of Peptide Binding to Any HLA-A and -B Locus Protein of Known SequencePLOS ONE, 2007
- The role of the proteasome in generating cytotoxic T-cell epitopes: insights obtained from improved predictions of proteasomal cleavageImmunogenetics, 2005
- WebLogo: A Sequence Logo Generator: Figure 1Genome Research, 2004
- Reliable prediction of T‐cell epitopes using neural networks with novel sequence representationsProtein Science, 2003
- Human Leukocyte Antigen Gene Polymorphism and the Histocompatibility LaboratoryThe Journal of Molecular Diagnostics, 2001
- Selection of representative protein data setsProtein Science, 1992