vaccines and immunoinformatics approaches

The paper introduces meTCRs, a deep-learning method to embed TCR sequences for clustering and querying TCR-epitope databases.

The paper develops PIA-M, a multimodal transformer-based tool for predicting HLA-II peptide presentation, achieving higher accuracy and faster runtime than existing methods.

This paper develops models to predict, scan, and design TNF-α inducing epitopes for human and mouse, achieving AUROC values up to 0.83 for human and 0.77 for mouse.

This paper develops methods to predict and design T1DM-associated peptides, achieving high accuracy with a hybrid approach and a webserver for peptide prediction.

This paper uses in silico reverse vaccinology to identify a multi-epitope subunit vaccine candidate against SARS-CoV2 with high antigenicity and population coverage.

This study introduces DeepNovo Peptidome and DeepSelf for neoantigen discovery and validation using immunopeptidomics and deep learning, demonstrating their application in cervical cancer tissues.

This study uses bioinformatics and structural vaccinology to identify three epitopes from the EsxG·EsxH complex for potential use in tuberculosis vaccines.

The paper identifies secretion type-associated motifs from pathogenic bacterial sequences to improve vaccine candidate identification.

The paper introduces neoIM, a machine learning model that improves the prediction of immunogenic peptides by classifying them as immunogenic or non-immunogenic with high accuracy.

This study designs a multi-epitope vaccine against Acinetobacter baumannii using immunoinformatic approaches and in silico simulations, showing high immunogenic potential and stability.

TCRconv predicts T-cell receptor-epitope recognition using a deep learning model and provides insights into T-cell dynamics in COVID-19 patients.

The paper improves epitope prediction by integrating HLA-I ligand data and TCR recognition models, identifying potent SARS-CoV-2 CD8+ T-cell epitopes with experimental validation.

neoMS predicts MHC-I epitope presentation using mass spectrometry data, achieving higher accuracy than existing methods and improving immunotherapy response prediction.

The paper benchmarks neoantigen immunogenicity predictors and finds that MHC-I binding affinity and its derived metrics are insufficient to predict immunogenicity or tumor neoantigen burden as biomarkers.

PANDORA is a fast pMHC structure modelling pipeline that uses anchor restraints to generate accurate models with high success rate and speed.

EpiBERTope is a BERT-based model that predicts linear and structural epitopes from protein sequences, achieving high AUC scores and outperforming traditional models.

The paper predicts B and T cell epitopes in SARS-CoV-2 proteins and analyzes their conservation across coronaviruses to assess cross-reactivity potential between variants and other coronaviruses.

This paper designs a multi-epitope vaccine candidate against Salmonella Typhi using immunoinformatics, showing cross-protection against related serovars.

The paper analyzes MHC binding and CD8+ T-cell immune escape of SARS-CoV-2 Omicron and Delta variants by comparing epitope binding affinities and identifying mutations affecting immune recognition.

The paper develops COD-dipp to map MHC Class I antigens from cancer studies and identifies immune-relevant genomic regions for vaccine design.

The paper identifies four epitopes on SARS-CoV-2 proteins with potential for vaccine development through computational analysis of antigenicity, epitope prediction, and structural modeling.

This study identifies potential epitopes for a peptide vaccine against Brucella abortus OmpW protein using immunoinformatics tools.

This paper introduces a deep learning model to predict neoantigens by integrating HLA-peptide binding and immunogenicity, achieving better performance than existing methods.

The paper develops a web application to compare segment variability, sequence evolution, and immunogenic properties of viral proteins, using SARS-CoV-2 proteins as an example.

TCR-BERT uses self-supervised transfer learning on unlabeled T-cell receptor sequences to learn representations that improve antigen-binding prediction, specificity clustering, and computational TCR sequence design.

The paper presents a BERT-based model using self-supervised transfer learning to predict SARS-CoV-2 epitope-specific TCR recognition, showing high performance on independent datasets.

This paper uses XGBoost with tri-peptide similarity to predict MHC epitopes for cancer neoantigen discovery, tested on experimentally validated peptides.

This paper investigates how organism-specific training improves epitope prediction performance, even with small datasets, and shows it can outperform generalist models.

The paper shows that neopeptide immunogenicity is influenced by the subcellular location of their parent proteins, improving predictions of vaccine and immunotherapy responses.

The paper quantifies MHC Class I peptide origins under UPS perturbation, revealing 30% of peptides are UPS-independent and 10% proteasome-independent, with implications for immune activation.