MHCflurry: open-source class I MHC binding affinity prediction

Machine learning prediction of the interaction between major histocompatibility complex I (MHC I) proteins and their small peptide ligands is important for vaccine design and other applications in adaptive immunity. We describe and benchmark a new open-source MHC I binding prediction package, MHCflurry. The software is a collection of allele-specific binding predictors incorporating a novel neural network architecture and adhering to software development best practices. MHCflurry outperformed the standard predictors NetMHC 4.0 and NetMHCpan 3.0 on a benchmark of mass spec-identified MHC ligands and showed competitive accuracy on a benchmark of affinity measurements. The accuracy improvement was due to substantially better prediction of non-9-mer peptide ligands, which offset a narrowly lower accuracy on 9-mers. MHCflurry was on average 8.6X faster than NetMHC and 44X faster than NetMHCpan; performance is further increased when a graphics processing unit (GPU) is available. MHCflurry is freely available to use, retrain, or extend, includes Python library and command line interfaces, and may be installed using standard package managers.

• Publication year

  2017

• Venue

  bioRxiv

• Publication date

  2017-08-09

• Fields of study

  Biology, Medicine, Computer Science

• Identifiers
  DOI 10.1101/174243
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• MHC-I peptides get out of the groove and enable a novel mechanism of HIV-1 escape

  2017cited by this paper
• An immunogenic personal neoantigen vaccine for patients with melanoma

  2017cited by this paper
• Mass Spectrometry Profiling of HLA‐Associated Peptidomes in Mono‐allelic Cells Enables More Accurate Epitope Prediction

  2017cited by this paper
• Toxoplasma gondii peptide ligands open the gate of the HLA class I binding groove

  2016cited by this paper
• Tumor neoantigens: building a framework for personalized cancer immunotherapy.

  2015cited by this paper
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

  2015cited by this paper
• Automated benchmarking of peptide-MHC class I binding predictions

  2015cited by this paper
• Dropout: a simple way to prevent neural networks from overfitting

  2014cited by this paper
• Dataset size and composition impact the reliability of performance benchmarks for peptide-MHC binding predictions

  2014cited by this paper
• The immune epitope database (IEDB) 3.0

  2014influential reference
• T-cell epitope vaccine design by immunoinformatics

  2013cited by this paper
• NetMHCpan, a method for MHC class I binding prediction beyond humans

  2008cited by this paper
• NetMHC-3.0: accurate web accessible predictions of human, mouse and monkey MHC class I affinities for peptides of length 8–11

  2008cited by this paper
• Modeling the adaptive immune system: predictions and simulations

  2007cited by this paper
• High Resolution Structures of Highly Bulged Viral Epitopes Bound to Major Histocompatibility Complex Class I

  2005cited by this paper
• Competition‐Based Cellular Peptide Binding Assay for HLA Class I

  2004cited by this paper
• Competition-based cellular peptide binding assays for 13 prevalent HLA class I alleles using fluorescein-labeled synthetic peptides.

  2003cited by this paper
• Two different, highly exposed, bulged structures for an unusually long peptide bound to rat MHC class I RT1-Aa.

  2001cited by this paper
• Longer peptide can be accommodated in the MHC class I binding site by a protrusion mechanism

  2000cited by this paper
• Crystal structures of two viral peptides in complex with murine MHC class I H-2Kb.

  1994cited by this paper
• Three-dimensional structure of a peptide extending from one end of a class I MHC binding site

  1994cited by this paper

• mRNA vaccines transform personalized lung cancer treatment.

  2026cites this paper
• Toward next-generation therapeutic HPV vaccines: A review on expanding the antigen repertoire and an integrated bioinformatics selection framework

  2026cites this paper
• T cell-based cancer immunotherapy: opportunities and challenges.

  2025cites this paper
• Neoantigen identification and TCR-T therapy development for solid tumors: current advances and future perspectives

  2025cites this paper
• Immunolyser 2.0: An advanced computational pipeline for comprehensive analysis of immunopeptidomic data

  2025cites this paper
• Neoantigen-based immunotherapy: advancing precision medicine in cancer and glioblastoma treatment through discovery and innovation

  2025cites this paper
• High-throughput screening for class I peptide MHC binding via yeast surface display

  2025cites this paper
• Toward equitable major histocompatibility complex binding predictions

  2025cites this paper
• PHLA: A pre-trained model based method incorporating HLA-peptide binding and immunogencity

  2025cites this paper
• PredIG: an interpretable predictor of T-cell epitope immunogenicity

  2025cites this paper
• AttMHCpan: A Cross-Modal Attention-Based MHC - I Peptide Binding Affinity Prediction Method Modulated by Physicochemical Features

  2025cites this paper
• Design of a Multi-Valent SARS-CoV-2 Peptide Vaccine for Broad Immune Protection via Deep Learning

  2025cites this paper
• PHbinder and PSGM: A Cascaded Framework for Epitope Prediction and HLA-I Allele Identification

  2025cites this paper
• Personalized Cancer Vaccines: Current Advances and Emerging Horizons

  2025cites this paper
• TCR-T Cell Recognition of an NY-ESO-1 Epitope Presented by HLA-A2 Supertype: Implications for Cancer Immunotherapy

  2025cites this paper
• PHLA-SiNet: A novel peptide-HLA binding prediction model using heterogeneous Siamese neural networks

  2025cites this paper
• Characterization of Tumor Antigens from Multi-omics Data: Computational Approaches and Resources

  2025influential citation
• Effective design of therapeutic nanovaccines based on tumor neoantigens.

  2025cites this paper
• AI/ML-empowered approaches for predicting T Cell-mediated immunity and beyond

  2025cites this paper
• AI-driven epitope prediction: a systematic review, comparative analysis, and practical guide for vaccine development

  2025cites this paper
• Leveraging attention-based deep multiple instance and multiple task learning for improved neoepitope identification.

  2025cites this paper
• Computational identification of cross-reactive TCR epitopes with ARDitox

  2025cites this paper
• Progress of Deep Learning Prediction of CD8+ T‐Cell Epitopes

  2025cites this paper
• A Computational Pipeline for Glioblastoma Vaccine Development: Integrating Novel Omics-Driven OIP5 Target Discovery to Create a Deep Learning-Based Immunogenicity Framework for Personalized Immunotherapy

  2025cites this paper
• In-silico epitope-based vaccines design: progress, challenges and the road ahead

  2025cites this paper
• Targeting neoantigens conserved across organs and species overcomes tumor immune escape

  2025cites this paper
• OnmiMHC: a machine learning solution for UCEC tumor vaccine development through enhanced peptide-MHC binding prediction

  2025cites this paper
• Development of therapeutic cancer vaccines based on cancer immunity cycle

  2025cites this paper
• DPCMHC: efficient prediction of MHC-peptide binding affinity by deep learning based on dual-padding convolution

  2025cites this paper
• Multi-epitope vaccines: charting a new frontier in monkeypox prevention and control

  2025cites this paper
• Alternative splicing: from tumorigenesis to neoantigen-mediated cancer immunotherapy

  2025cites this paper
• Leveraging artificial intelligence and machine learning for unraveling pathogenesis and advancing precision medicine in autoimmune diseases

  2025cites this paper
• Neoantigen-Driven Immunotherapy in Triple-Negative Breast Cancer: Emerging Strategies and Clinical Potential

  2025cites this paper
• Neoantigen Vaccines in Cancer Prevention

  2025cites this paper
• TinyHLAnet: A Light‐Weight 3D Structure‐Aware Architecture for Rapid and Explainable Identification of CD8+ T‐Cell Antigens

  2025cites this paper
• Deciphering the tumor immune microenvironment: Microscale measurements for precision detection and multidimensional analysis

  2025cites this paper
• DeepPROTECTNeo: A Deep learning-based Personalized and RV-guided Optimization tool leveraging TCR Epitope interaction using Context-aware Transformers

  2025cites this paper
• Leveraging mRNA technology for antigen based immuno-oncology therapies

  2025cites this paper
• pMHChat, characterizing the interactions between major histocompatibility complex class II molecules and peptides with large language models and deep hypergraph learning

  2025cites this paper
• High-throughput screening for class I peptide MHC binding via yeast surface display.

  2025cites this paper
• Dendritic Cell Immunotherapy for Solid Tumors: Advances in Translational Research and Clinical Application

  2025cites this paper
• Neoantigens: new hope for cancer therapy

  2025cites this paper
• Vaccine therapies for glioma: clinical frontiers and potential breakthrough

  2025cites this paper
• Strategies for neoantigen screening and immunogenicity validation in cancer immunotherapy (Review)

  2025cites this paper
• Computational design of HLA class I superbinders for broad T cell immunogenicity

  2025influential citation
• Autoimmunity, epitope analysis, and molecular mimicry.

  2025cites this paper
• Computation strategies and clinical applications in neoantigen discovery towards precision cancer immunotherapy

  2025cites this paper
• Technical review of artificial intelligence in TCR-T therapy

  2025cites this paper
• mRNA-Based Personalized Cancer Vaccines: Opportunities, Challenges and Outcomes

  2025cites this paper
• Energy landscapes of peptide-MHC binding

  2024cites this paper
• ConvNeXt-MHC: improving MHC–peptide affinity prediction by structure-derived degenerate coding and the ConvNeXt model

  2024influential citation
• NeoAgDT: optimization of personal neoantigen vaccine composition by digital twin simulation of a cancer cell population

  2024cites this paper
• Towards Equitable MHC Binding Predictions: Computational Strategies to Assess and Reduce Data Bias

  2024cites this paper
• Glioblastoma evolution and heterogeneity from a 3D whole-tumor perspective.

  2024cites this paper
• A computational exploration of global and temporal dynamics of selection pressure on HIV-1 Vif polymorphism

  2024cites this paper
• Stimulating T cell responses against patient-derived breast cancer cells with neoantigen peptide-loaded peripheral blood mononuclear cells

  2024cites this paper
• The journey towards complete and accurate prediction of HLA antigen presentation

  2024cites this paper
• Enhancing antigenic peptide discovery: Improved MHC-I binding prediction and methodology.

  2024cites this paper
• Advances in Therapeutic Cancer Vaccines, Their Obstacles, and Prospects Toward Tumor Immunotherapy

  2024cites this paper
• An Efficient Approach to the Accurate Prediction of Mutational Effects in Antigen Binding to the MHC1

  2024cites this paper
• Informing immunotherapy with multi-omics driven machine learning

  2024cites this paper
• Circular RNA as a source of neoantigens for cancer vaccines

  2024cites this paper
• Virus-like particle-mediated delivery of structure-selected neoantigens demonstrates immunogenicity and antitumoral activity in mice

  2024cites this paper
• A unified cross-attention model for predicting antigen binding specificity to both HLA and TCR molecules

  2024cites this paper
• Meta learning for mutant HLA class I epitope immunogenicity prediction to accelerate cancer clinical immunotherapy

  2024cites this paper
• TlcMHCpan: A Novel Deep Learning Model for Enhanced Pan-Specific Prediction of Peptide-HLA Binding

  2024cites this paper
• Machine learning-enhanced immunopeptidomics applied to T-cell epitope discovery for COVID-19 vaccines

  2024cites this paper
• ImmuneApp for HLA-I epitope prediction and immunopeptidome analysis

  2024cites this paper
• Tumour mutational burden: clinical utility, challenges and emerging improvements

  2024influential citation
• Tailoring potential antigenic regions on pandemic SARS spike protein

  2024cites this paper
• Exploring treatment options in cancer: tumor treatment strategies

  2024cites this paper
• GIHP: Graph convolutional neural network based interpretable pan-specific HLA-peptide binding affinity prediction

  2024cites this paper
• Mutations in glioblastoma proteins do not disrupt epitope presentation and recognition, maintaining a specific CD8 T cell immune response potential

  2024cites this paper
• Transformers meets neoantigen detection: a systematic literature review

  2024cites this paper
• Advances in Vaccines for Melanoma.

  2024cites this paper
• RLpMIEC: High-Affinity Peptide Generation Targeting Major Histocompatibility Complex-I Guided and Interpreted by Interaction Spectrum-Navigated Reinforcement Learning

  2024cites this paper
• Crucial Parameters for Immunopeptidome Characterization: A Systematic Evaluation

  2024cites this paper
• DiscovEpi: automated whole proteome MHC-I-epitope prediction and visualization

  2024cites this paper
• TransfIGN: A Structure-Based Deep Learning Method for Modeling the Interaction between HLA-A*02:01 and Antigen Peptides

  2024cites this paper
• Cancer Immunotherapies Ignited by a Thorough Machine Learning‐Based Selection of Neoantigens

  2024cites this paper
• Tumor Neoepitope-Based Vaccines: A Scoping Review on Current Predictive Computational Strategies

  2024cites this paper
• Design, Development and Immunogenicity Study of a Multi-Epitope Vaccine Prototype Against SARS-CoV-2

  2024cites this paper
• Artificial intelligence and neoantigens: paving the path for precision cancer immunotherapy

  2024cites this paper
• Genetic landscape of interval and screen detected breast cancer

  2024cites this paper
• Neoantigen-specific stimulation of tumor-infiltrating lymphocytes enables effective TCR isolation and expansion while preserving stem-like memory phenotypes

  2024cites this paper
• Rescoring Peptide Spectrum Matches: Boosting Proteomics Performance by Integrating Peptide Property Predictors Into Peptide Identification

  2024cites this paper
• A modular protein language modelling approach to immunogenicity prediction

  2024influential citation
• RankMHC: Learning to Rank Class-I Peptide-MHC Structural Models

  2024cites this paper
• Allopurinol non-covalently facilitates binding of unconventional peptides to HLA-B*58:01

  2023cites this paper
• T OWARDS ANTIGENIC PEPTIDE DISCOVERY WITH BETTER MHC - I BINDING PREDICTION AND IMPROVED BENCHMARK METHODOLOGY

  2023cites this paper
• Advancements and hurdles in the development of a vaccine for triple-negative breast cancer: A comprehensive review of multi-omics and immunomics strategies.

  2023cites this paper
• Targeted delivery of tumor necrosis factor in combination with CCNU induces a T cell–dependent regression of glioblastoma

  2023cites this paper
• Transfer learning improves pMHC kinetic stability and immunogenicity predictions

  2023cites this paper
• IEPAPI: a method for immune epitope prediction by incorporating antigen presentation and immunogenicity

  2023cites this paper
• A comprehensive assessment and comparison of tools for HLA class I peptide-binding prediction

  2023cites this paper
• Comparison of the somatic genomic landscape between central- and peripheral-type non-small cell lung cancer.

  2023cites this paper
• Neoantigen cancer vaccines: a new star on the horizon

  2023cites this paper
• Tutorial: integrative computational analysis of bulk RNA-sequencing data to characterize tumor immunity using RIMA

  2023cites this paper
• ARDitox: platform for the prediction of TCRs potential off-target binding

  2023cites this paper
• VitTCR: A deep learning method for peptide recognition prediction

  2023cites this paper