MétaCan
Menu
Back to cohort
Record W4408553729 · doi:10.1101/2025.03.17.643783

ImmuniT Platform for Improved Neoantigen Prediction in Lung Cancer

2025· preprint· en· W4408553729 on OpenAlexaff
Stephanie J. Hachey, Alexander G. Forsythe, Hari B. Keshava, Christopher C.W. Hughes

Bibliographic record

VenuebioRxiv (Cold Spring Harbor Laboratory) · 2025
Typepreprint
Languageen
FieldBiochemistry, Genetics and Molecular Biology
Topicvaccines and immunoinformatics approaches
Canadian institutionsSimon Fraser University
Fundersnot available
KeywordsLung cancerComputer scienceMedicineComputational biologyOncologyBiology

Abstract

fetched live from OpenAlex

Introduction: 1.1Lung cancer remains the leading cause of cancer-related deaths, with most patients presenting with advanced, treatment-resistant disease. While immunotherapy has improved outcomes for some, most patients fail to mount an effective immune response due to inadequate tumor recognition. Neoantigen-based therapies offer a promising approach to personalized immunotherapy, but current discovery methods can miss immunogenic targets, particularly those with low or heterogeneous expression. To address this, we developed the ImmuniT platform, which enhances neoantigen identification by amplifying patient-specific targets from primary tumor samples, improving prediction accuracy for more precise immunotherapy. Methods: 1.2Patients with lung cancer were recruited under an IRB-approved protocol, and freshly resected tumor tissue and matched blood samples were collected. Tumors were processed into single-cell suspensions, enriched for EpCAM+ epithelial cells, and treated to enhance neoantigen expression. Peripheral blood and tumor-infiltrating lymphocytes were co-cultured with cancer cells to expand neoantigen-reactive T cells. The nextneopi pipeline integrated tumor mutational burden (TMB), HLA typing, and transcriptomic data to predict immunogenic targets. MHC:epitope complexes were validated via tetramer staining to identify patient-derived, neoantigen-specific T cells. Results: 1.3The ImmuniT platform demonstrated superior neoantigen prediction and T cell activation in vitro compared to conventional methods across five NSCLC patients. In one patient, it identified two neoantigens missed by standard approaches, which were validated based on their ability to stimulate tumor-infiltrating and peripheral blood lymphocytes. Across all tested samples, the platform identified a broader spectrum of immunogenic targets. These findings highlight its potential to enhance neoantigen discovery and improve personalized immunotherapy strategies. Conclusion: 1.4Our findings indicate that the ImmuniT platform improves neoantigen detection in NSCLC by identifying a wider range of tumor-specific antigens, including those overlooked by conventional methods. By expanding the pool of targetable neoantigens, this technology has the potential to enhance T cell activation and optimize immunotherapy. The ImmuniT platform represents a promising advancement towards more effective, personalized treatment strategies for lung cancer patients, particularly those who do not respond to current immunotherapies.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: Bench or experimental
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.139
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.001
Research integrity0.0010.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.012
GPT teacher head0.236
Teacher spread0.224 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

Study designBench or experimental
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venuebioRxiv (Cold Spring Harbor Laboratory)Same topicvaccines and immunoinformatics approachesFrench-language works237,207