vaccines and immunoinformatics approaches

The paper introduces TCRGP, a Gaussian process method for predicting TCR epitope specificity, and applies it to scRNA+TCRβ data to identify HBV-epitope specific T cells in hepatocellular carcinoma patients.

This paper introduces a generalized similarity metric, the Total Similarity Score, to predict peptide binding affinity by benchmarking it on peptide-protein datasets.

neoepiscope improves neoepitope prediction by incorporating germline context and somatic variant phasing, addressing limitations in existing tools.

DeepBCR predicts cancer type and binding affinity of BCRs using deep learning, validated with anti-PD1 drug affinities.

The paper designs a chimeric polyvalent vaccine against HSV-1 and HSV-2 using immunoinformatic methods to identify and combine epitopes from six viral proteins.

PEPOP provides 35 peptide design methods to generate sequences mimicking discontinuous epitopes for antibody interactions, improving experimental applications.

MHCSeqNet is a deep learning model for predicting MHC binding affinity, outperforming existing methods and generalizing to new MHC alleles.

ACME improves peptide-MHC class I binding prediction using attention-based deep learning, outperforming existing methods and providing interpretable insights.

The paper identifies two unique tick AQP1 peptide motifs with high immunogenic potential for peptide-based anti-tick vaccine development using in silico analysis.

The paper proposes computational methods to identify low variability pathogen targets for medical countermeasure development using variation analysis.

HABIT is a webserver that uses machine learning to predict and analyze T cell epitopes for neoepitope discovery in immunotherapy.

This paper designs a chimeric vaccine against Marburg virus using reverse vaccinology, identifying antigenic epitopes from envelope glycoprotein and VP40, and evaluates its physicochemical properties and immune receptor interactions.

This paper designs a novel multi-epitope subunit vaccine against H7N9 avian influenza using in silico reverse vaccinology and experimental validation.

This paper designs a multi-epitope peptide vaccine against Cryptococcus neoformans var. grubii heat shock 70KDa protein using computational vaccinology methods, identifying ten epitopes with high population coverage and immunogenic potential.

DeepSeqPan is a deep convolutional neural network for predicting HLA-peptide binding affinity without requiring structural information, achieving state-of-the-art performance on multiple HLA alleles.

OLGA calculates amino acid sequence generation probabilities for B- and T-cell receptors using dynamic programming, showing agreement with published data and potential for vaccine design.

The paper trains a random forest classifier, ForestMHC, to predict MHC-I peptide presentation using a million human peptides, outperforming existing tools on test sets and mass spectrometry data.

This paper introduces ITCell, a method that predicts CD4 T-cell epitopes by integrating antigen cleavage, MHCII presentation, and TCR recognition, achieving higher accuracy than single-stage methods.

Vaxrank selects neoantigen vaccine peptides from tumor mutations, RNA data, and HLA type to design personalized cancer vaccines.

The paper designs a peptide vaccine against Madurella mycetomatis TCTP using immunoinformatics tools, identifying epitopes that bind to MHC I and II alleles with high population coverage.

The paper designs an epitope-based peptide vaccine against Cryptococcus neoformans using in silico simulations and identifies conserved B- and T-cell epitopes with high population coverage.

A sequence-only convolutional network trained on T cell receptor (TCR)-peptide pairs for HLA-A*02:01 can single out TCRs that bind a target peptide among many non-binding ones.

The paper proposes a protocol for designing country-specific peptide vaccines against Nipah and Hendra viruses by analyzing epitope differences in surface proteins across affected regions.

The paper evaluates unsupervised clustering methods for T-cell receptor sequences and finds distinct clusters that target the same epitopes.

The paper presents a TensorFlow-based deep learning model for MHC class I peptide binding prediction, along with code, benchmark datasets, and a Snakemake workflow for parallel analysis.

The paper reanalyzes the contribution of proteasomal spliced peptides to the HLA-I ligandome and finds that only 2-4% of the ligandome may be explained by such peptides.

The paper develops machine learning models to predict antigen presenting cell modulators (A-cell epitopes) and implements them in a web server for vaccine adjuvant design.

AI-MHC improves Class I and Class II HLA-binding predictions using a deep learning framework that integrates allele information and achieves state-of-the-art performance.

The paper describes a computational pipeline for a personalized neoantigen vaccine trial, including tools for variant calling, peptide selection, and sequence reconstruction.

The paper describes computational approaches for analyzing immunopeptidomics data, focusing on motif identification, false hit filtering, and machine learning applications for predicting MHC ligands.