IMMUNIA: A Multi-LLM Reasoning Agent for Immunoregulatory Surfaceome Discovery
Park, N.; Lee, J. H.
Show abstract
Biomarker discovery for immunotherapy often requires reasoning across complex immune contexts. We present IMMUNIA, a multi-large-language-model (multi-LLM) reasoning agent designed to identify immunoregulatory surfaceome genes through interpretable, biologically grounded analysis. The term IMMUNIA originates from the fusion of Immune and Noeia (the Greek concept of perception and understanding), defining an AI system that perceives, reasons, and interprets the immune landscape with human-like cognition. IMMUNIA integrates structured prompting, contextual scoring across immunotherapy, inflammation, and NF-{kappa}B signaling, and consensus reasoning across GPT-4o, GPT-5, and Gemini 2.5 Pro. Benchmarking with positive (HLA) and negative (contactin) controls confirmed model consistency and contextual discrimination. Consensus evaluation prioritized IL1R1, BSG, CD276, ALCAM, B2M, PTPRS, VCAN, and MXRA5 as high-confidence candidates. Among these, PTPRS, VCAN, and MXRA5 emerged as previously unrecognized stromal immune checkpoint-like regulators, shaping tumor-immune crosstalk via phosphatase, ECM, and cytokine signaling networks. IMMUNIA thus establishes a reasoning-centric AI paradigm that bridges computational inference with biological plausibility, offering a scalable approach for precision immunotherapy biomarker discovery.
Matching journals
The top 10 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- TCCIA: A Comprehensive Resource for Exploring CircRNA in Cancer Immunotherapy 94%
- Tumor-agnostic transcriptome-based classifier identifies spatial infiltration patterns of CD8+ T cells in the tumor microenvironment and predicts clinical outcome in early- and late-phase clinical trials 94%
- Evaluation of tumor antigen-specific antibody responses in patients with metastatic triple negative breast cancer treated with cyclophosphamide and pembrolizumab 93%
Similar papers in this journal
- A Community Challenge to Predict Clinical Outcomes After Immune Checkpoint Blockade in Non-Small Cell Lung Cancer 93%
- Genomic Insights Guiding Personalized First-Line Immunotherapy Response in Lung and Bladder Tumors 92%
- A modular framework for the development of targeted Covid-19 blood transcript profiling panels 90%
Similar papers in this journal
- Tumor reactivity assessment using clonal expression (TRACE) reveals tumor reactive CD8+ T cell heterogeneity across solid tumors 94%
- Integrated immunogenomic analyses of high-grade serous ovarian cancer reveal vulnerability to combination immunotherapy 93%
- A three-gene expression score for predicting clinical benefit to anti-PD-1 blockade in advanced renal cell carcinoma 92%
Similar papers in this journal
- Personalized Cancer Therapy Prioritization Based on Driver Alteration Co-occurrence Patterns 93%
- Pan-cancer identification of clinically relevant genomic subtypes using outcome-weighted integrative clustering 92%
- Text-mining clinically relevant cancer biomarkers for curation into the CIViC database 92%
Similar papers in this journal
- Context-aware Multi-Property Antibody Predictor: a Novel Framework Integrating Text and Protein Language Models 92%
- Systems profiling reveals recurrently dysregulated cytokine signaling responses in ER+ breast cancer patients' blood 92%
- Identification of factors mediating the signaling convergenceof multiple receptors following cell-cell interaction 91%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.