neoag
Neoantigen × AI
Daily research signal
TOPICS / MODALITY

Peptide vaccines

Synthetic long-peptide vaccines that present chosen neoepitopes directly, often with an adjuvant — the most clinically mature personalized-vaccine approach.

Topic21 items2026-06-21 – 2026-09-05
Modalities
mRNA vaccines60Peptide vaccines21TCR & T-cell receptor14Dendritic-cell vaccines12Shared & off-the-shelf8Lipid nanoparticles7DNA vaccines4Viral-vector vaccines1
01
AI / Methods

Multifunctional nano-vaccines integrating lipid-conjugated tumor antigens with TLR/STING agonists enhance cancer immunotherapy.

The paper describes a polymer-based polyvalent peptide and adjuvant platform, SPPA, designed to address limitations of neoantigen peptide vaccines such as poor antigen stability, inefficient delivery, and inadequate immune activation. SPPA co-delivers lipid-conjugated tumor-specific peptides with a TLR7/8 agonist, 3M-052, and a STING agonist, 2'3'-cGAMP, to improve peptide encapsulation, sustained release, and targeted delivery to antigen-presenting cells. In vitro, SPPA upregulated pro-inflammatory genes and cytokine secretion and showed effective cellular uptake and lymphatic trafficking. In vivo, SPPA alone or with anti-PD-1 antibody elicited cytotoxic T lymphocyte responses and inhibited tumor growth in four aggressive syngeneic mouse models, including triple-negative breast cancer.

Breast cancer
europepmc · brief 2026-09-05 · published 2026-07-20
02
AI / Methods

Label Noise Limits TCR-pMHC Specificity Prediction: Improved Performance Through AlphaFold3-Based Structural Modeling and Data Denoising

The study argues that label noise in TCR-pMHC specificity datasets is a major driver of weak performance for unseen peptide prediction, where structural modeling has so far shown the most predictive power. Using an AlphaFold3-based pipeline adapted for TCR-pMHC structural modeling, the authors report state-of-the-art specificity prediction that outperforms AlphaFold2.3-based and sequence-based methods and performs at par with the leading Immrep2025 competition submission. A cluster-based denoising step that removes mislabeled points from a large specificity dataset increased binder ranking accuracy by more than 70% relative to the full dataset, implying that data quality improvements could materially affect TCR-based immunotherapy and vaccine design.

TCR & T-cell receptor
biorxiv · brief 2026-08-30 · published 2026-08-28
04
AI / Methods

Discovery and Targeting of a Cryptic Human Proteome

Researchers present RyboCypher, an AI-assisted proteogenomics platform that identified ~80,000 cryptic peptides (including ~10,000 cancer-associated) from 2,229 patient samples. By mapping the 'dark transcriptome' to unannotated proteins, the study establishes the CypherAtlas, offering a vast new reservoir of potential neoantigen targets for first-in-class therapeutic discovery.

biorxiv · brief 2026-08-12 · published 2026-08-11
05
AI / Methods

MHChron: diversity-balanced dataset design for robust peptide-MHC binding prediction across MHC class I and II

MHChron introduces a unified peptide-MHC binding prediction framework built on a diverse dataset covering 214 class I and 98 class II alleles, with peptides ranging from 8 to 36 residues. The study emphasizes rigorous data curation and leakage-controlled splits to ensure robust generalization. Both sequence-based and structure-aware models trained on this balanced dataset outperformed state-of-the-art predictors, particularly in extrapolating to unseen alleles.

biorxiv · brief 2026-08-07 · published 2026-08-04
07
AI / Methods

Quantum convolutional HLA immunogenic peptide prediction (Q-CHIPP): Next-generation neoantigen prediction with quantum neural network.

Researchers have applied Quantum Convolutional Neural Networks (QCNNs) to neoantigen prediction, addressing limitations of classical models in handling noisy, small datasets. Using a 46-qubit hardware experiment with noise mitigation techniques, the study achieved a 6% increase in classification accuracy for MHC binding and immunogenicity prediction compared to classical baselines. This work demonstrates the potential of quantum computing to enhance precision in neoantigen identification.

europepmc · brief 2026-07-25 · published 2026-07-24
08
AI / Methods

Profiling immunogenic neoantigen peptides elicited by personalized neoantigen vaccine in cancer patients - Frontiers

An analysis of 352 patients receiving personalized peptide-pulsed dendritic cell vaccines reveals that only 10-20% of selected peptides induce detectable T-cell responses. The study evaluated 2,317 short peptides from single nucleotide variants using IFN-γ ELISPOT assays to define immunogenicity thresholds. These findings underscore the current limitations of prediction algorithms and the need for improved biomarkers to select clinically relevant neoantigens.

Dendritic-cell vaccines
news · brief 2026-07-25 · published 2026-05-08
09
AI / Methods

A Self-assembly Carrier-Free Nanovaccine based on Fluorinated CpG and Neoantigen Peptides for Hepatocellular Carcinoma Immunotherapy.

Scientists developed a carrier-free nanovaccine for hepatocellular carcinoma by self-assembling fluorinated CpG with HCC neoantigen peptides. The resulting 69 nm nanoparticles demonstrated high loading efficiency and enhanced dendritic cell uptake, improving antigen cross-presentation by 2.05-fold in vitro. In vivo, the formulation targeted lymph nodes to orchestrate both innate and adaptive immune responses, offering a biosafe alternative to traditional adjuvant-loaded nanovaccines.

Dendritic-cell vaccinesLipid nanoparticlesLiver cancer (HCC)
europepmc · brief 2026-07-25 · published 2026-07-09
10
AI / Methods

DRIVE: a comprehensive resource deciphering drug-induced transcriptomic and splicing response in cancer cell.

The DRIVE database addresses the lack of resources linking drug-induced transcriptomic changes to neoantigen potential by integrating 3,911 samples across 278 drugs and 272 cell lines. Using LLMs for metadata curation, it quantifies differential splicing events and predicts resulting HLA-binding peptides. This resource enables the systematic identification of immunogenic neoantigens derived from drug-induced aberrant splicing, offering a new avenue for vaccine target discovery in pharmacotherapy contexts.

europepmc · brief 2026-07-13 · published 2026-07-10
11
AI / Methods

Geometric deep learning improves generalizability of MHC-bound peptide predictions - Nature

Researchers have identified limitations in current sequence-based approaches for predicting MHC-peptide interactions and introduced a structure-based method using geometric deep learning (GDL). By employing self-supervised learning on 3D structures without exposure to binding affinity data, the model shows improved generalizability across unseen MHC alleles. This suggests a viable path toward more robust computational tools for neoantigen identification in cancer immunotherapy.

news · brief 2026-07-12 · published 2024-12-19
13
AI / Methods

Benchmarking AlphaFold and related deep learning approaches for modeling antibody and TCR antigen recognition

Researchers benchmarked AlphaFold2, AlphaFold3, and related deep learning methods for modeling antibody-protein, antibody-peptide, and TCR-pMHC recognition. Results indicate that increased sampling and AlphaFold3 generally outperform default AlphaFold2 settings, though predictive accuracy varies significantly by interface class. The authors note that antibody-peptide complexes remain particularly difficult to model accurately and propose model pooling as a potential solution to leverage method complementarity.

TCR & T-cell receptor
biorxiv · brief 2026-07-09 · published 2026-07-06
14
AI / Methods

AI-driven neoantigen identification: a comprehensive review from somatic variant calling to T cell recognition.

This review details AI workflows that combine transcriptomics and immunopeptidomics to nominate candidate neoepitopes, moving beyond tailored experimental methods. It emphasizes the critical challenge of predicting which tumor mutations result in T cell recognition via class I and II peptide-binding grooves. The piece serves as a technical baseline for understanding the computational layers required to reduce false positives in personalized vaccine design.

europepmc · brief 2026-07-08 · published 2026-07-06
15
Clinical

Neoantigen Peptide Vaccine Plus Pembrolizumab in Renal Cell Carcinoma

Peking University First Hospital is launching a Phase I investigator-initiated trial to evaluate a personalized neoantigen polyepitope peptide vaccine combined with pembrolizumab in advanced renal cell carcinoma. The study aims to enroll 5-8 patients across safety and expansion cohorts to address the high rate of primary or acquired resistance to pembrolizumab monotherapy.

Kidney cancer (RCC)
clinicaltrials · brief 2026-07-07 · published 2026-07-07
16
AI / Methods

Preclinical proof of concept for a personalized SNAP™-TIL (Specific Neo-Antigen Peptides-TIL) therapy platform.

Preclinical proof-of-concept data demonstrates a SNAP™-TIL platform that combines computational modeling with PepSeq screening to credential and enrich TILs for specific neoantigens. By isolating T cells with high affinity for patient-specific HLA class II proteins before expansion, the platform aims to overcome the rarity of neoantigen-reactive cells in less immunogenic tumors. The approach yielded products with 96% CD3+ content and a mix of effector and central memory subsets, suggesting improved precision in TIL manufacturing.

europepmc · brief 2026-07-06 · published 2026-07-05
17
AI / Methods

PRISM : Peptide-specificity annotation of T-cell receptors with uncertainty quantification

PRISM is a metric-learning framework that embeds TCR beta sequences into a peptide-organized latent space to predict pMHC ligands. By using structure-guided synthetic receptors to counter viral bias in training data, it abstains on out-of-distribution inputs via uncertainty modeling. Benchmarks show PRISM matches or exceeds existing models, particularly for rare epitopes.

TCR & T-cell receptor
biorxiv · brief 2026-07-05 · published 2026-07-04
18
Clinical

IDH1-mutant vaccine in newly diagnosed astrocytoma: final analysis of the multicenter, single-arm, open-label, first-in-human phase 1 NOA16 trial.

The NOA16 trial provides 8-year follow-up data for an IDH1-R132H peptide vaccine in newly diagnosed astrocytoma, demonstrating sustained immunogenicity and favorable long-term outcomes. Participants with grade IV disease achieved a median overall survival of 106.1 months, significantly outperforming historical controls. Sustained antibody responses to the neoepitope correlated with favorable clinical courses, validating the target for mutant IDH1-driven cancers.

europepmc · brief 2026-07-02 · published 2026-07-01
19
Clinical

Specific killing of Ewing sarcoma by TCR-T cells targeting public neogene-encoded antigens

Researchers identified neogenes (Ew_NGs) induced by the EWSR1::FLI1 fusion in Ewing sarcoma, which present peptides on HLA-I complexes. CD8+ T cells specific to these public antigens killed EwS cells in an HLA-I restricted manner, a process dependent on both the fusion and the neogene expression. Transduced TCR-T cells replicated this cytotoxicity in vivo without off-target or allogeneic activation, suggesting a viable cell therapy for relapsed/resistant cases.

TCR & T-cell receptor
biorxiv · brief 2026-06-28 · published 2026-06-25
20
AI / Methods

Measuring peptide-MHC generalization to unseen alleles across both HLA classes

Researchers demonstrate that reported peptide-MHC (pMHC) AUROCs of 0.85-0.95 overstate generalization due to data leakage from dense immunopeptidome data on well-studied alleles. Using a harmonized corpus of 5.8 million measurements, they show true generalization to unseen alleles is in the high 0.7s. They released an open benchmark and a new predictor that outperforms eight existing models by +0.22 to +0.37 AUROC on least-studied genes.

biorxiv · brief 2026-06-24 · published 2026-06-23
Where nextAll topicsToday’s briefTrials tracker