TripHLApan: predicting HLA molecules binding peptides based on triple coding matrix and transfer learning

  title={TripHLApan: predicting HLA molecules binding peptides based on triple coding matrix and transfer learning},
  author={M. Wang and Chuqi Lei and Jianxin Wang and Yaohang Li and Min Li},
Human leukocyte antigen (HLA) is an important molecule family in the field of human immunity, which recognizes foreign threats and triggers immune responses by presenting peptides to T cells. In recent years, the synthesis of tumor vaccines to induce specific immune responses has become the forefront of cancer treatment. Computationally modeling the binding patterns between peptide and HLA can greatly accelerate the development of tumor vaccines. However, most of the prediction methods… 

Figures and Tables from this paper



MATHLA: a robust framework for HLA-peptide binding prediction integrating bidirectional LSTM and multiple head attention mechanism

A pan-allele HLA-peptide binding prediction framework—MATHLA which integrates bi-directional long short-term memory network and multiple head attention mechanism is presented which achieves better prediction accuracy in both fivefold cross-validation test and independent test dataset.

DeepSeqPan, a novel deep convolutional neural network model for pan-specific class I HLA-peptide binding affinity prediction

Evaluation on public benchmark datasets shows that the proposed DeepSeqPan model without HLA structural information in training achieves state-of-the-art performance on a large number of HLA alleles with good generalization capability.

Predicting HLA class II antigen presentation through integrated deep learning

A neural network trained on diverse datasets improves prediction of HLA class II epitope presentation, and across independent cancer neoantigen studies, peptides with high MARIA scores are more likely to elicit strong CD4+ T cell responses.

HLA class I binding prediction via convolutional neural networks

A new distributed representation of amino acids, named HLA-Vec, is introduced that can be used for a variety of downstream proteomic machine learning tasks and a deep convolutional neural network architecture is proposed for the task of HLA class I-peptide binding prediction.

ACME: Pan-specific peptide-MHC class I binding prediction through attention-based deep neural networks

ACME (Attention-based Convolutional neural networks for MHC Epitope binding prediction), a new pan-specific algorithm to accurately predict the binding affinities between peptides and MHC class I molecules, even for those new alleles that are not seen in the training data.

DeepHLApan: A Deep Learning Approach for Neoantigen Prediction Considering Both HLA-Peptide Binding and Immunogenicity

The binding model achieves comparable performance with other well-acknowledged tools on the latest Immune Epitope Database (IEDB) benchmark datasets and an independent mass spectrometry (MS) dataset, and the immunogenicity model could significantly improve the prediction precision of neoantigens.

MHCAttnNet: predicting MHC-peptide bindings for MHC alleles classes I and II using an attention-based deep neural model

A deep neural model that uses an attention mechanism to capture the relevant subsequences of the amino acid sequences of peptides and MHC alleles and accurately predict the MHC-peptide binding, which outperforms the state-of-the-art models for this task.

Peptide binding predictions for HLA DR, DP and DQ molecules

This study aimed to narrow the gap in knowledge by providing a large scale dataset of over 17,000 HLA-peptide binding affinities for a set of 11 HLA DP and DQ alleles and found that prediction methodologies developed for HLA DR molecules perform equally well for DP or DQ molecules.

A large peptidome dataset improves HLA class I epitope prediction across most of the human population

HLAthena is developed, providing allele-and-length-specific and pan-allele-pan-length prediction models for endogenous peptide presentation that correctly identified >75% of HLA-bound peptides that were observed experimentally in 11 patient-derived tumor cell lines.

A comprehensive review and performance evaluation of bioinformatics tools for HLA class I peptide-binding prediction

A comprehensive review of currently available tools for predicting the binding of peptides to a selection of HLA-I allomorphs and a benchmarking survey will assist researchers in selecting appropriate prediction tools that best suit their purposes and provide useful guidelines for the development of improved antigen predictors in the future.