vaccines and immunoinformatics approaches

AGZArank: Investigating epitope-conditioned antibody binder ranking with structure-derived synthetic supervision

AGZArank improves antibody binder ranking by using geometric deep learning with structure-derived synthetic supervision, achieving top-10 recovery in 44.4% of cases on validated antibody-antigen interfaces.

MHC Attention: Identifying HLA-E presented cancer antigens through deep learning and high-throughput screening

The paper develops MHC Attention, a deep learning model, and combines it with high-throughput screening to identify novel HLA-E presented cancer peptides.

Revised Adaptive Immune Receptor Data in the Immune Epitope Database

The paper revises the standardization and validation pipeline for immune receptor data in the IEDB to improve data consistency and usability.

HLA micropolymorphisms confine neoantigen conformational adaptability and guide T cell receptor selectivity

This study shows that micropolymorphisms in HLA-A3 superfamily members affect neoantigen conformational adaptability, influencing TCR recognition.

PMGen: From Peptide-MHC Structure Prediction to Peptide Generation

PMGen improves peptide-MHC structure prediction and enables structure-guided peptide design, achieving high accuracy and enhancing ML model performance.

Epistatic evolution drives HLA-dependent CD8+ T Cell escape risk in diverse populations

The paper models HLA diversity and viral evolution to assess T cell escape risk across populations, finding that escape mutations gain fitness with additional mutations.

Human neurons stimulated with IFNγ present HLA class I-restricted autoantigens to cytotoxic CD8+ T cells

This study identifies IFNγ-induced HLA class I-restricted neuronal autoantigens and their recognition by CD8+ T cells using human iPSC-derived neurons and immunopeptidomics.

A funnel approach to enable analyses of epitope-specific human CD4 T cells specific for influenza and SARS-CoV-2.

The paper introduces a funnel approach to identify epitope-specific CD4 T cells for influenza and SARS-CoV-2 by narrowing down potential epitopes using HLA-DR transgenic mice and ELISpot assays.

Large-Scale Assessment of NF1 Single Amino Acid Variants as HLA Class I Neoantigens

The paper evaluates NF1-derived single amino acid variants as HLA class I neoantigens using computational prediction and experimental validation, finding discrepancies between predictions and observed sequences.

HAIRpred2: Human Host-Specific Prediction of Antibody-Interacting Residues Using Hybrid Physicochemical and Structural Features

HAIRpred2 predicts antibody-interacting residues in human antigens using structural features, achieving an AUC of 0.78 on an independent test set.

A novel vaccine and drug targets for global eradication of bovine tuberculosis: Holistic frameworks for construction of a potent vaccine and identification of drug targets

This paper identifies potential vaccine candidates and drug targets for bovine tuberculosis using bioinformatics approaches and proteomic analysis of Mycobacterium bovis strains.

AI-enabled virtual immunopeptidomics links quantitative neoantigen presentation to immunogenicity

The paper develops epiVIP, a deep learning framework to predict HLA-I peptide abundance from (sc)RNA-seq data, showing that peptide abundance and non-selfness jointly determine antigenicity and predict tumor reactivity and survival.

Deep Learning-Based Structure Modeling of the Treponema pallidum Proteome: Insights into Pathogenesis and Syphilis Vaccine Development

This paper uses AI to model the structure of T. pallidum proteins, annotates their functions, identifies potential pathogenesis-related proteins, and highlights vaccine targets.

A vaccine for global eradication of TB - A novel conceptual framework and design of a potent peptide-based vaccine with universal coverage through advanced computational vaccinology

This paper proposes a peptide-based TB vaccine using computational vaccinology to identify conserved epitopes across TB strains, aiming for broad-spectrum protection and universal coverage.

SwiftTCR: Efficient Computational Docking protocol of TCRpMHC-I Complexes Using Restricted Rotation Matrices

The paper introduces a fast computational docking protocol for TCRpMHC-I complexes, achieving faster modeling and better model quality than existing tools.

Molecular Mimicry Between Epstein-Barr Virus and Human Herpesvirus-6 Proteins and Central Nervous System Proteins: Implications for T and B Cell Immunogenicity in an In Silico Study.

This study identifies shared pentapeptides between EBV and HHV-6 antigens and CNS proteins, suggesting molecular mimicry may trigger autoimmune responses via T and B cell activation.

Benchmarking TCR-pMHC structure prediction: a unified evaluation and CDR3-based functional insights

This paper benchmarks TCR-pMHC structure prediction tools using 70 unseen complexes and identifies the pLDDT score of the TCR CDR3 region as a key indicator of structural and functional accuracy.

TcrDesign: De novo design of epitope specific full-length T cell receptors

TcrDesign generates experimentally validated, functional, full-length TCRs using deep learning, achieving state-of-the-art performance in binding prediction and sequence generation.

Computational design of HLA class I superbinders for broad T cell immunogenicity

The paper designs HLA class I superbinders using a computational framework, identifying peptides that bind multiple HLA alleles and showing broad immunogenic potential.

Mapping the Peptide Interaction Fingerprint of the Behcet's disease associated HLA-B*51

This study maps the peptide interaction fingerprint of HLA-B*51:01 using MD simulations to understand its role in Behcet's disease and guide therapeutic peptide design.

EpiRanha: Hunting for Epitope Similarity with a Structure- and Residue-Aware Graph Neural Network

EpiRanha identifies epitope similarities using a structure- and residue-aware graph neural network, improving detection of cross-reactive epitopes and off-target interactions.

An autonomous LLM agent platform for computational binder design and conjugation-aware prioritization of antibody drug conjugates

This paper introduces an autonomous LLM agent platform for computational binder design and ADC prioritization, achieving accurate classification across oncology targets with minimal human intervention.

Continual Learning for Emerging Epitope Landscapes in TCR peptide Binding Prediction

This paper introduces ContinualTCR, a continual learning framework for TCR peptide binding prediction that reduces catastrophic forgetting when adapting to new epitopes.

CD8scape: an accessible, command-line tool for predicting viral escape from the CD8+ T cell response

CD8scape predicts viral escape from CD8+ T cell response using HLA genotype and within-host sequence variation to identify immune escape potential.

Unsupervised Machine Learning for Adaptive Immune Receptors with immuneML

This paper introduces immuneML, a framework for unsupervised machine learning in adaptive immune receptor repertoires, demonstrating its use in generative modeling, clustering, and dataset analysis.

Active Learning for Budget-Constrained TCR--pMHC Wet-Lab Validation

This paper introduces UDAL, an active learning strategy to reduce wet-lab costs for TCR-pMHC binding validation by efficiently selecting candidate pairs for experimental testing.

NetMHCIIphosPan: a machine learning tool for predictingHLA class II antigen presentation of phosphorylated peptides.

NetMHCIIphosPan predicts HLA class II antigen presentation of phosphorylated peptides using immunopeptidomics data, outperforming existing tools.

FairTCR: Equity-Aware TCR--pMHC Binding Prediction\\Across HLA Alleles and Cohort Strata

FairTCR improves TCR-pMHC binding prediction equity across HLA alleles and cohort strata by reducing disparity in average-worst-group AUPRC.

ORION: An agentic reasoning construct for the analysis of complex human immune profiling

ORION uses AI to analyze immune profiling data, reducing analysis time from months to hours and generating testable hypotheses.

A major histocompatibility complex (MHC) class II molecule that binds the same viral pathogen peptide with both nonamer and decamer core sequences for presentation to T cells

The paper identifies a chicken MHC class II molecule that binds the same viral peptide with both nonamer and decamer core sequences, revealing binding plasticity in immune response to MDV.