vaccines and immunoinformatics approaches

The paper develops PEPPRMINT, a statistical model to predict HLA-I peptide presentation, and applies it to identify immunogenic neoantigens in melanoma patients.

This paper presents a multi-objective approach to prioritize epitopes for diagnostic tests, balancing immunogenicity and cross-reactivity, and identifies 20 new potential epitopes across three pathogens.

The paper develops a deep neural network to predict epitopes from TCR beta-chain CDR3 sequences, achieving 98% accuracy using VDJdb and McPAS-TCR datasets.

IntroSpect improves HLA binding peptide identification sensitivity by 80% using motif-guided database building, while maintaining high accuracy and FDR control.

This paper introduces a deep learning-based method to analyze B cell receptor repertoires in COVID-19 patients and healthy subjects, enabling accurate clustering and classification of immune status changes.

The paper designs a multi-epitope vaccine candidate against SARS-CoV-2 by analyzing the spike glycoprotein's immunogenic properties and predicting B-cell epitopes.

The paper predicts epitope-based peptides for a vaccine against European bat lyssavirus type 2 using immunoinformatic methods and identifies a highly conserved epitope with broad population coverage.

This paper introduces an immunopeptidomics workflow using PEAKS XPro to identify HLA-I ligands and neoantigens without relying on standard databases, revealing diverse peptides and mutations in colorectal cancer.

This paper introduces a flexibility-aware graph-based model to identify antigen epitopes, achieving an F1-score of 0.656 and improving upon existing methods by 16.3%.

This study identifies and characterizes B cell and T cell epitopes in SARS-CoV-2 Nsp13, revealing mutations that may impact antigenicity and immune recognition.

The paper designs a multiepitope vaccine against SARS-CoV-2 membrane protein using immunoinformatic methods and identifies an epitope with strong binding to HLA-A and HLA-B alleles.

The paper develops a machine learning method to predict antibody-antigen binding using sequence data and evaluates it on a dataset of 600 antibodies and 50 antigens, achieving 76% classification accuracy.

This study identifies T and B cell epitopes in SARS-CoV-2 Spike protein and designs a multiepitope vaccine construct targeting the UK variant, showing its potential to elicit immune responses.

This paper reviews linear B-cell epitope prediction methods available via command-line interface and introduces a consensus classifier to improve performance for vaccine design.

This paper designs a multiepitope vaccine against Leptospirosis using immunoinformatics, identifying 6 vaccine candidates and constructing a stable vaccine with strong immune simulation results.

The paper shows HLA alleles preferentially present peptides from proteins with specific molecular functions, linking these preferences to HLA allele differences and disease susceptibility.

The paper uses CAMAP to predict SARS-CoV-2 MHC-I peptides, identifies 48 vaccine candidates covering most HLA haplotypes and strains, and provides an interactive portal for exploration.

The paper uses reverse vaccinology to identify epitope-based vaccine candidates against SARS-CoV-2 by analyzing antigenic elements from viral proteins and their interactions with Toll-Like Receptors.

This work uses AI methods to analyze anti-SARS-CoV2 antibodies, group them by epitope, predict epitopes, and assess their response to viral mutations.

The paper designs a SARS-CoV-2 vaccine candidate using lambda superstrings and validates its immunogenicity through assays.

The paper identifies potentially immunopathogenic SARS-CoV-2 epitopes using immunoinformatic methods and develops a web tool to visualize cross-reactive epitopes for vaccine design.

This paper improves T cell epitope predictions by combining MHC binding affinities with antigen expression levels, showing better performance than methods using only binding or expression data.

The paper provides detailed experimental protocols and an open-source tool, MhcVizPipe, for analyzing MHC I and II ligand datasets in immunopeptidomics.

This study identifies four SARS-CoV-2 proteins with strong HLA-1 binding and low energy that could serve as subunit vaccine candidates through immuno-informatics analysis.

This study identifies LptD and LptE as potential vaccine targets against Salmonella typhi using reverse vaccinology and subtractive genomics.

This paper designs a multi-epitope vaccine against SARS-CoV-2 by identifying immunogenic regions in the spike glycoprotein using immunoinformatics methods.

This study predicts epitope-based peptides for a Lujo virus vaccine using immunoinformatics, identifying two peptides with strong MHC binding affinity and global population coverage.

This study predicts a novel T cell epitope from the conserved spike glycoprotein of SARS-CoV-2 for an epitope-based vaccine using in-silico methods.