vaccines and immunoinformatics approaches

The paper integrates MHC Class I visibility targets into the ProteinMPNN protein design process to reduce immune visibility while preserving structure.

TransHLA predicts epitopes across all HLA alleles with high accuracy, outperforming existing models in specificity and sensitivity for immunogenic and neoepitope identification.

NERVE 2.0 improves vaccine candidate identification through AI models and a user-friendly web interface, outperforming previous versions and other RV tools.

VaxOptiML predicts MHC-I and MHC-II epitopes using machine learning, offering higher accuracy and usability for cancer immunotherapy.

This study quantifies conformational changes in the TCR:pMHC-I binding interface using a dataset of 358 structures, showing that CDR3 and CDR3β loops modify their shape upon binding and peptides undergo conformational changes dependent on their anchoring in the MHC groove.

The paper introduces metrics to quantify CD8+ T cell responses to vaccine antigens, considering HLA genetic variation and viral evolution, using Ebola, SARS-CoV-2, and Burkholderia pseudomallei as examples.

The paper develops a hybrid method to predict IFN-gamma inducing peptides in human and mouse, achieving higher AUROC scores than existing methods.

This study identifies widespread linear molecular mimicry across the human virome, linking it to autoimmunity, particularly in multiple sclerosis, and suggests therapeutic strategies targeting viral infections.

This study enhances Vaxign-DL by integrating ESM-generated features, showing improved performance in predicting bacterial vaccine antigens.

This paper introduces EPACT, a deep-learning framework for predicting TCR-antigen binding pairs, showing high accuracy in epitope recognition and TCR repertoire analysis.

The paper predicts the immunogenicity and safety of two vaccine candidates against onchocerciasis using immunoinformatics, identifying their potential to induce protective immune responses.

This paper introduces HLA-DR4Pred2, an improved method for predicting HLA-DRB1*04:01 binders using a larger dataset and hybrid approaches, achieving higher AUC scores than existing methods.

This paper develops a machine learning model that integrates TCRβ and pHLA binding data to improve neoantigen prioritization in colorectal cancer, showing better performance than existing tools.

The paper develops a phylogeny-aware model to predict linear B-cell epitopes for Monkeypox virus, identifying nine specific peptides as potential diagnostic targets.

The paper introduces RobustpMHC, a self-supervised learning method for peptide-MHC class I binding prediction, showing improvements over existing approaches across multiple datasets.

The paper introduces ISPIPab, a program that predicts multiple antigen epitopes by combining feature-based and docking-based methods, outperforming existing approaches and revealing novel targets.

This paper analyzes the sequence-dependent energy landscapes of MHC-peptide binding, showing class-specific nonlinearities and their implications for immune recognition and escape.

This paper develops a deep learning model to analyze antibody-antigen interactions, achieving high accuracy in distinguishing antibody-antigen complexes from other protein complexes and identifying antigens from epitope information.

This study evaluates computational epitope prediction tools on Fel d 1 allergen and other allergens, finding limited effectiveness and highlighting the need for improved methods.

This study presents a computational method to identify antigen-specific BCRs from immune repertoires using sequence similarity and validates it with human data post-vaccination and infection.

TCRpcDist clusters TCR repertoires based on physico-chemical properties to predict antigen specificity and identify TCR groups likely to bind similar epitopes.

TCR-H is a SVM model trained on experimentally validated non-binders to predict TCR epitope binding, achieving high AUC on unseen test sets.

P-TEAM predicts the effect of epitope mutations on T cell functionality using a Random Forest model trained on murine and human TCR-epitope interactions.

The paper identifies post-translationally modified self-peptides linked to hypertension using a combined computational and experimental approach.

This study designs a recombinant fusion protein vaccine targeting epitopes of two toxins from Clostridium perfringens and Clostridium novyi to enhance immunogenicity against livestock infections.

The paper identifies conserved T cell epitopes in Bluetongue Virus non-structural proteins and evaluates their potential as a broad-spectrum vaccine using computational methods.

The paper analyzes virus-specific B cell epitopes to show most are hidden within viral particles and host cells, requiring degradation for antibody recognition.

The paper predicts MHC-I restriction of T cell receptors for public antigens using structural analysis of TCR:pHLA complexes.

TULIP is an unsupervised transformer model for predicting TCR epitope binding, outperforming existing methods on unseen epitopes by addressing data limitations and bias.

The paper evaluates gene and protein sequence features as predictors of HLA class I ligand presentation, showing they improve predictions comparable to experimental gene expression data.