neoag
Neoantigen × AI
Daily research signal
TOPICS / MODALITY

TCR & T-cell receptor

T-cell-receptor biology and TCR-engineered cell therapy directed at tumor neoantigens — the readout side of antigen recognition.

Topic17 items2026-07-09 – 2026-10-21
Modalities
mRNA vaccines78Peptide vaccines26TCR & T-cell receptor17Dendritic-cell vaccines12Shared & off-the-shelf8Lipid nanoparticles7DNA vaccines4Viral-vector vaccines4
01
AI / Methods

EMBER: Predicting TCR--pMHC Binding Without a Docked Complex

EMBER is a structure-based TCR-pMHC binding predictor that folds the TCR and pMHC independently and compares SE(3)-invariant residue-graph representations without constructing a shared coordinate frame, eliminating the docked-complex placement error that propagates through traditional predictors while cutting preprocessing from O(NM) to O(N+M). Under epitope-disjoint evaluation against six retrained baselines across four folding tools, it ranked first on every metric: gains of 0.9-14.4% in micro-AUROC, 18.5-25.3% in micro-AUPRC, and 10.6-24.1% in MCC, with rankings up to 85% more stable across folding tools. For vaccine developers, immunogenicity prediction is the upstream constraint on neoantigen selection, so folding-tool-agnostic accuracy directly bears on target-prioritization reliability.

arxiv · brief 2026-10-21 · published 2026-10-19
02
AI / Methods

Auditing Tool Traces in Agentic LLMs: Source Localization and Counterfactual Dependence Testing

A methods paper introduces a two-stage audit for agentic LLM pipelines: Per-Tool TF-IDF Decomposition (PT2D) localizes label-predictive patterns to individual tool results, and Token-Class Redaction counterfactually tests whether the model actually depends on them. Applied to TCR-pMHC binding, tool augmentation initially looked like it beat a no-evidence baseline, but the audit traced the signal to identifiers in one tool result, and redacting them dropped performance to chance. Since TCR-pMHC prediction underpins neoantigen prioritization, this is a concrete warning that shortcut-driven gains can masquerade as biological reasoning in LLM-based discovery workflows, and an actionable template for auditing them before such results inform vaccine design or diligence claims.

arxiv · brief 2026-10-20 · published 2026-10-18
03
Clinical

Discovery of frameshift-associated TCRs following personalized neoantigen vaccination in a patient with osteosarcoma

A case report in locally recurrent osteosarcoma demonstrates an end-to-end immune monitoring workflow after personalized neoantigen vaccination: in vitro peptide stimulation plus IFN-gamma ELISPOT detected post-vaccination responses to 12 of 15 tested peptides, and 10x single-cell TCR sequencing yielded 26 candidate TCRs, of which 25 generated functional TCR-T cells. Only 4 were specific to vaccine peptides, and all 4 proved MHC class-II restricted — a key constraint for anyone planning to spin vaccine-discovered TCRs into conventional (class I-targeted) TCR-T assets. For the field, this validates single-cell TCR discovery as a pharmacodynamic readout of whether a vaccine actually elicited trackable antigen-specific clones, not just bulk ELISPOT signal.

Peptide vaccines
biorxiv · brief 2026-10-16 · published 2026-10-15
04
Clinical

HLA Typing & Tumor Neoantigen Identification for Phase I/II Study of Autologous TCR-T Cells in Subjects With Solid Tumors

Alaunos Therapeutics terminated its screening study (NCT05124743), the data-collection protocol that HLA-typed and somatic-mutation-profiled patients with ovarian/endometrial, colorectal, pancreatic, NSCLC, and cholangiocarcinoma tumors to match them against the company's TCR library as the entry funnel into the TCR001-201 Phase I/II autologous TCR-T study. No therapy was administered under this protocol, and patients without a TCR match were discontinued. Termination closes the screening pipeline that fed the Phase I/II study — a meaningful operational signal for a library-matching approach where match rates gate enrollment.

Pancreatic cancerLung cancer (NSCLC)Colorectal cancerOvarian cancer
clinicaltrials · brief 2026-10-15 · published 2026-10-15
05
Clinical

Long-Term Follow-up Study of Subjects Treated With Autologous T Cells Using the Sleeping Beauty System to Express TCRs

Alaunos completed the long-term follow-up study (NCT05292859) for subjects treated in its Phase I/II study of autologous T cells engineered with the non-viral Sleeping Beauty system to express TCRs reactive against cancer-specific mutations in solid tumors. Completion means the extended-safety and durability dataset for this Sleeping Beauty-based TCR-T program is now closed out. For industry watchers, this finalizes the long-term record on a non-viral TCR engineering platform targeting tumor neoantigens.

clinicaltrials · brief 2026-10-15 · published 2026-10-15
06
AI / Methods

HeteroTCR: A heterogeneous graph neural network-based method for predicting peptide-TCR interaction - Nature

HeteroTCR, a heterogeneous graph neural network for predicting peptide-TCR interaction, appears in Nature. Peptide-TCR prediction sits at the heart of neoantigen prioritization, separating predicted binders from antigens T cells actually recognize, so a graph-based method landing in a top journal is a relevant addition to the in-silico selection stack used across vaccine and TCR-therapy developers.

Peptide vaccines
news · brief 2026-10-02 · published 2024-06-04
07
AI / Methods

Functional Deorphanization of Tumor-reactive TCRs Uncovers a Landscape of Shared, Immune Dominant Antigens across Cancers

A biorxiv preprint introduces TWISTAR, a platform that deorphanizes single-cell-derived TCRs by screening them against tumor transcriptomes, validating actual TCR engagement so only functionally immunogenic antigens are recovered. Applied to melanoma, breast, and hepatocellular carcinoma patients responding to immune checkpoint blockade, it shows tumor-reactive TCRs recognize targets beyond neoantigens—including peptides from unannotated coding sequences and novel transcripts—many shared across patients and cancer types, with multiple clones converging on a few immune-dominant epitopes. Why it matters: shared, immune-dominant antigens are the prerequisite for off-the-shelf or pan-cancer vaccines, and the finding that the immunogenic landscape is broader than the neoantigen set expands the addressable target space. The work is method-stage and retrospective on ICB responders; no prospective vaccine validation is reported, so watch for independent replication and whether the platform is productized by an antigen-discovery player.

Peptide vaccinesShared & off-the-shelfMelanomaLiver cancer (HCC)
biorxiv · brief 2026-09-30 · published 2026-09-29
09
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.

Peptide vaccines
biorxiv · brief 2026-08-30 · published 2026-08-28
11
Clinical

Identification of pre-existing ubiquitous neoantigen-reactive tumor-infiltrating T-cells in a patient with metastatic pancreatic neuroendocrine tumor

A preprint investigates whether ubiquitous neoantigens—mutations shared across all metastatic sites—can overcome inter-site heterogeneity in pancreatic neuroendocrine tumors. Using whole-exome and RNA sequencing on 14 samples from a treatment-naive patient, researchers identified ubiquitous mutations and validated immunogenicity via IFN-gamma ELISpot and single-cell TCR sequencing. This approach targets durable immune responses by focusing on neoantigens present in both primary and metastatic lesions.

Pancreatic cancer
biorxiv · brief 2026-08-07 · published 2026-08-04
12
AI / Methods

Engineering antigen-driven co-stimulation and T helper cell activity into TCR-T cells with CD8-41BB fusion receptors enhances anti-tumor activity

Researchers engineered TCR-T cells with CD8-41BB fusion receptors to overcome the lack of co-stimulation and helper activity typical in TCR therapies. While wild-type CD8beta promoted CD4+ T cell activity, it failed to drive durable responses against WT1 in mouse models, suggesting further optimization is needed for high-affinity targets.

biorxiv · brief 2026-07-29 · published 2026-07-28
13
Clinical

Intermediate-size IND for Treatment of Patients With Advanced Cancer Using T Cells Engineered to Express TCR Targeting Mutant KRAS

Providence Health & Services is operating an expanded access program (NCT07614048) for T-cells engineered to express TCRs targeting mutant KRAS-G12D. The intermediate-size IND treats advanced pancreatic and colorectal cancers in patients with specific HLA types. This provides real-world data on the feasibility of manufacturing and administering KRAS-targeted adoptive cell therapy outside of traditional trial structures.

Shared & off-the-shelfPancreatic cancerColorectal cancer
clinicaltrials · brief 2026-07-25 · published 2026-07-23
15
AI / Methods

Spatial Compartmentalization of TCR Repertoires Between Primary Melanomas and Sentinel Lymph Nodes Reveals Distinct Clonal Architectures and Shared Antigen Recognition

Primary tumors and their sentinel lymph nodes are functionally linked sites of anti-tumor immunity, yet how T cell receptor (TCR) repertoires are organized across these compartments remains incompletely understood. We thus performed TCR{beta} sequencing on paired primary melanoma…

Shared & off-the-shelfMelanoma
biorxiv · brief 2026-07-11 · published 2026-07-08
16
AI / Methods

IgGM2: An All-Atom Foundation Model for Adaptive Immune Receptor Design

IgGM2 is a new all-atom foundation model for adaptive immune receptor design that jointly generates CDR residue identities and full-atom structures. Unlike modular pipelines, it uses a structure-to-design strategy to allow framework geometry to adapt to designed CDRs without separate inverse folding. This unified approach aims to improve accuracy in modeling the coupled variation of sequence, conformation, and binding geometry for antibodies and TCRs.

biorxiv · brief 2026-07-10 · published 2026-07-09
17
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.

Peptide vaccines
biorxiv · brief 2026-07-09 · published 2026-07-06
Where nextAll topicsToday’s briefTrials tracker