Abstract A023: Spatially resolved drug response predictions reveal fibroblast-associated resistances in <i>in situ</i> lung cancer samples
Bibliographic record
Abstract
Abstract The tumor microenvironment (TME) plays a pivotal role in shaping therapeutic outcomes in lung cancer, with cancer-associated fibroblasts (CAFs) emerging as key mediators of drug resistance. In situ sequencing enables spatial resolution of tumor architecture, offering insight into heterogeneity and the influence of CAFs on tumor cell biology. However, directly translating these microenvironmental effects on tumor cell behavior into drug response predictions remains a major challenge. In this work, we leveraged spatial transcriptomics and in situ single-cell RNA sequencing to predict spatially resolved drug responses in non-small cell lung cancer (NSCLC) patient samples and investigated the impact of fibroblast density on therapeutic efficacy. We adapted our recently published scIDUC modeling approach—which integrates bulk RNA-seq from cancer cell lines with single-cell RNA-seq data to predict drug responses—for use with in situ data from eight NSCLC patients. Our spatial analysis revealed that tumor cells in high fibroblast-density regions exhibited distinct predicted drug sensitivities compared to those in low-fibroblast contexts. Notably, lapatinib—a dual EGFR/HER2 inhibitor—was consistently predicted to be less effective in tumor cells residing within fibroblast-rich niches. These predictions were validated experimentally using a co-culture model of CALU-3 lung cancer cells and IMR-90 fibroblasts. CALU-3 cells grown with fibroblasts, either in direct contact or separated by a transwell, showed significantly increased resistance to lapatinib compared to monoculture conditions, confirming our computational findings. Our study highlights the role of CAF-rich microenvironments in therapeutic response and proposes a CAF-informed framework for refining therapeutic strategies in NSCLC. By integrating spatial transcriptomics with predictive modeling, we provide a pathway to directly link microenvironmental context with functional drug response in tumors. Citation Format: Robert F. Gruener, Lilin Wang, Adam Lee, Weijie Zhang, R. Stephanie Huang. Spatially resolved drug response predictions reveal fibroblast-associated resistances in in situ lung cancer samples [abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: Artificial Intelligence and Machine Learning; 2025 Jul 10-12; Montreal, QC, Canada. Philadelphia (PA): AACR; Clin Cancer Res 2025;31(13_Suppl):Abstract nr A023.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".