Variant-informed multimodal tissue-state modeling reveals an NRF2 stress niche and dependency axis in KEAP1/NFE2L2-altered cancer
6 affiliations
- 1Department of Cardiology, The Affiliated Hospital of Southwest Medical University
- 2Key Laboratory of Medical Electrophysiology, Ministry of Education, Institute of Cardiovascular Research
- 3The Key Laboratory of Optimal Utilization of Natural Medicine Resources (The Union Key Laboratory of Guiyang City-Guizhou Medical University), School of Pharmaceutical Sciences, Guizhou Medical University
- 4School of Medical Information and Engineering, Southwest Medical University
- 5Basic Medicine Research Innovation Center for Cardiometabolic Diseases, Ministry of Education, Southwest Medical University
- 6Nucleic Acid Medicine of Luzhou Key Laboratory
Abstract
Introduction: Cancer genotypes influence transcriptional programs, spatial organization, histopathology, and treatment-response states, yet these molecular and tissue-level features are often analyzed separately in public-data studies. VISTA was developed as a variant-informed, multimodal framework for modeling genotype-linked tissue states and prioritizing validation-ready biological hypotheses.
Methods: VISTA integrates somatic variants, protein-region and AlphaMissense-informed priors, RNA-state scoring, whole-slide image embeddings, immunotherapy cohorts, spatial and single-cell references, cell-line dependency maps, and pharmacogenomic screens. We evaluated the framework in KEAP1/NFE2L2-altered lung cancer and melanoma, using the NRF2 stress axis as a biologically defined test case. Analyses incorporated project-adjusted modeling, bootstrap confidence intervals, permutation testing, leave-project sensitivity analyses, independent tumor-level validation cohorts, fixed-effect external meta-analysis, model-system analyses using DepMap/CCLE, tissue-context analyses, immunotherapy cohorts, and exploratory whole-slide image analyses.
Results: In TCGA LUAD, LUSC, and SKCM pilot cohorts, KEAP1 and NFE2L2 alterations were consistently associated with NRF2 stress activation across project-adjusted models and sensitivity analyses. Independent analyses of CPTAC LUAD, CPTAC LSCC, and non-TCGA LUAD cohorts reproduced higher NRF2-state scores in KEAP1/NFE2L2-altered tumors. Fixed-effect external meta-analysis supported associations with both KEAP1 mutation and combined KEAP1-or-NFE2L2 alteration status. DepMap/CCLE analyses provided complementary model-system evidence: KEAP1/NFE2L2-mutant models had higher NRF2 scores, while NRF2-high or KEAP1/NFE2L2-mutant contexts showed stronger NFE2L2 dependency. Tissue-context analyses positioned NRF2 stress near hypoxic, stromal, myeloid, and immune programs. Immunotherapy cohorts supported the relevance of NRF2-associated states to treatment-response biology, while also indicating limited utility for static pan-cancer prediction. Exploratory whole-slide image analyses using pathology foundation-model embeddings identified morphology associations with myeloid, hypoxic, and CAF/TGF-beta barrier programs.
Discussion: VISTA provides an evidence-layered approach to variant-informed tissue-state modeling. By integrating genomic, transcriptomic, imaging, spatial, cellular, dependency, and pharmacogenomic evidence, it can help prioritize genotype-linked cancer states and validation-ready hypotheses. VISTA is not intended to function as a stand-alone clinical predictor; its claims are bounded by the evidence available in each data layer and by the biological and clinical context of the analyzed cohorts.
Related
- Genome-wide CRISPR screening reveals a chromatin-to-mitochondrial dependency architecture underlying Galunisertib-induced OXPHOS vulnerability
- Beyond the Black Box: Physics-Based and Conservation-Informed Evidence for ACVRL1 Variant Classification in Hereditary Hemorrhagic Telangiectasia and Pulmonary Arterial Hypertension
- Replication-independent eviction of the histone variant H2B.8 reveals chromatin reprogramming during seed imbibition
- A structure-informed deep learning framework for modeling TCR-peptide-HLA interactions
- LEMON-ZEST: Evolution-Informed Tokenization for Efficient Protein Language Modeling
BibTeX
@article{kong2026variantinformed,
title = {{Variant-informed multimodal tissue-state modeling reveals an NRF2 stress niche and dependency axis in KEAP1/NFE2L2-altered cancer}},
author = {Mowei Kong and Qiuing Li and Xingwei Zhao and Yu Wang and Yamei Luo and Yang Yu and Chunxiang Zhang},
journal = {Frontiers in Immunology},
year = {2026},
month = oct,
doi = {10.3389/fimmu.2026.1957511},
url = {https://www.frontiersin.org/articles/10.3389/fimmu.2026.1957511/full},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Variant-informed multimodal tissue-state modeling reveals an NRF2 stress niche and dependency axis in KEAP1/NFE2L2-altered cancer
AU - Mowei Kong
AU - Qiuing Li
AU - Xingwei Zhao
AU - Yu Wang
AU - Yamei Luo
AU - Yang Yu
AU - Chunxiang Zhang
PY - 2026
DA - 2026/10/06
JO - Frontiers in Immunology
DO - 10.3389/fimmu.2026.1957511
UR - https://www.frontiersin.org/articles/10.3389/fimmu.2026.1957511/full
AB - Introduction: Cancer genotypes influence transcriptional programs, spatial organization, histopathology, and treatment-response states, yet these molecular and tissue-level features are often analyzed separately in public-data studies. VISTA was developed as a variant-informed, multimodal framework for modeling genotype-linked tissue states and prioritizing validation-ready biological hypotheses. Methods: VISTA integrates somatic variants, protein-region and AlphaMissense-informed priors, RNA-state scoring, whole-slide image embeddings, immunotherapy cohorts, spatial and single-cell references, cell-line dependency maps, and pharmacogenomic screens. We evaluated the framework in KEAP1/NFE2L2-altered lung cancer and melanoma, using the NRF2 stress axis as a biologically defined test case. Analyses incorporated project-adjusted modeling, bootstrap confidence intervals, permutation testing, leave-project sensitivity analyses, independent tumor-level validation cohorts, fixed-effect external meta-analysis, model-system analyses using DepMap/CCLE, tissue-context analyses, immunotherapy cohorts, and exploratory whole-slide image analyses. Results: In TCGA LUAD, LUSC, and SKCM pilot cohorts, KEAP1 and NFE2L2 alterations were consistently associated with NRF2 stress activation across project-adjusted models and sensitivity analyses. Independent analyses of CPTAC LUAD, CPTAC LSCC, and non-TCGA LUAD cohorts reproduced higher NRF2-state scores in KEAP1/NFE2L2-altered tumors. Fixed-effect external meta-analysis supported associations with both KEAP1 mutation and combined KEAP1-or-NFE2L2 alteration status. DepMap/CCLE analyses provided complementary model-system evidence: KEAP1/NFE2L2-mutant models had higher NRF2 scores, while NRF2-high or KEAP1/NFE2L2-mutant contexts showed stronger NFE2L2 dependency. Tissue-context analyses positioned NRF2 stress near hypoxic, stromal, myeloid, and immune programs. Immunotherapy cohorts supported the relevance of NRF2-associated states to treatment-response biology, while also indicating limited utility for static pan-cancer prediction. Exploratory whole-slide image analyses using pathology foundation-model embeddings identified morphology associations with myeloid, hypoxic, and CAF/TGF-beta barrier programs. Discussion: VISTA provides an evidence-layered approach to variant-informed tissue-state modeling. By integrating genomic, transcriptomic, imaging, spatial, cellular, dependency, and pharmacogenomic evidence, it can help prioritize genotype-linked cancer states and validation-ready hypotheses. VISTA is not intended to function as a stand-alone clinical predictor; its claims are bounded by the evidence available in each data layer and by the biological and clinical context of the analyzed cohorts.
SN - 1664-3224
ER -