vaccines and immunoinformatics approaches

This paper develops a cytotoxic T-cell-based vaccine using synthetic long peptides to induce robust immune responses against SARS-CoV-2.

immuneML provides an open-source ecosystem for reproducible and interoperable machine learning analysis of adaptive immune receptor repertoires, demonstrating its utility through benchmarking and novel methods.

This paper introduces MHCfovea, a deep learning framework that connects HLA alleles with binding motifs, revealing critical polymorphic residues for antigen discovery and vaccine design.

ISOTOPE identifies tumor-specific splicing-derived epitopes using RNA sequencing and mass spectrometry, showing splicing neoepitopes have higher MHC-I binding affinity in immune responders.

SwarmTCR predicts T cell receptor specificity using a nearest-neighbor approach, outperforming TCRdist on specific epitopes with single-cell and bulk data.

Pepsickle predicts proteasomal cleavage sites more accurately and quickly than existing tools, improving neoantigen identification for vaccine development.

This paper develops a probabilistic machine learning model to identify antigen-specific TCRs using sequence data and clone abundance, enabling personalized discrimination of specific versus non-specific T-cell responses.

T-CoV analyzes how SARS-CoV-2 mutations affect HLA-peptide interactions to predict variant-specific immune evasion.

EpitopeVec improves linear epitope prediction using deep protein sequence embeddings, achieving better accuracy and AUC than existing methods.

clusTCR is a Python tool for fast clustering of large CDR3 sequences, offering improved speed over existing methods while maintaining comparable accuracy.

BERTMHC improves MHC class II peptide binding prediction using a transformer model and multiple instance learning, outperforming existing methods.

NAP-CNB is a web server tool that predicts MHC-I-restricted T cell epitopes in mice using recurrent neural networks, achieving an AUC of 0.95 for H-2 peptide ligands.

The paper predicts B- and T-cell epitopes from the Fba1 protein of Candida glabrata using in silico tools to design an epitope-based vaccine.

The paper introduces SeRenDIP-CE, a sequence-based method for predicting conformational epitopes, achieving better performance than existing predictors on an antibody-antigen structure.

DeepSeqPanII predicts peptide-HLA class II binding using an interpretable recurrent neural network with attention mechanisms, achieving state-of-the-art performance.

This paper predicts TCR-epitope binding specificity using deep metric learning and multimodal learning, revealing key amino acid patterns and challenging assumptions about physical proximity.

The paper identifies SARS-CoV-2 low complexity regions (LCRs) that are similar to human proteins, suggesting potential risks in vaccine design targeting these regions.

DeepImmuno predicts and generates immunogenic peptides using deep learning models, outperforming existing methods and providing insights into T cell antigen recognition.

The paper integrates immunopeptidomics and immunoinformatics to characterize BoLA-DR antigen presentation and identify CD4 T cell epitopes with high predictive accuracy.

This paper uses AI and bioinformatics to design epitope-based vaccines for cellular immunity against SARS-CoV-2, evaluating immunogenicity and safety risks.

This paper designs a peptide vaccine targeting the L-protein of Marburg virus using vaccinomics, identifying four epitopes with high conservancy and immunogenic potential.

epitopepredict is a tool that integrates multiple MHC binding prediction algorithms to identify potential T cell epitopes from whole genomes.

The paper predicts SARS-CoV-2 B-cell epitopes using computational methods and validates them with ELISA, finding two antigens with high sensitivity and specificity for serological diagnosis of COVID-19.

The paper uses neural language models to predict viral escape mutations by modeling semantic change and grammaticality in viral sequences.

The paper designs a multi-epitope peptide vaccine against SARS-CoV-2 using spike protein epitopes and MD simulations, showing potential for TLR4 docking.

The paper designs a multi-epitope peptide vaccine targeting Bombali Ebolavirus VP40 using immunoinformatics and molecular docking, identifying epitopes with high MHC affinity and population coverage.

This paper introduces SHERPA, a pan-allelic MHC-peptide prediction algorithm, which improves neoantigen discovery by integrating immunopeptidomics data and composite modeling.

Ab-Ligity identifies sequence-dissimilar antibodies that bind to the same epitope by analyzing antibody-antigen interfaces, outperforming existing tools in precision and speed.

The paper proposes an attention-based LSTM network to improve epitope prediction accuracy by considering the whole antigen protein sequence and features.

This study designs SARS-CoV-2 spike protein variants with enhanced immunogenicity by engineering T cell epitopes while preserving structure and function.