DEPICT enables sample-centric therapeutic prioritization across evolving and spatially heterogeneous tumor states
- 1Peking University
Abstract
Accurate treatment selection remains a major challenge in precision oncology because tumors with similar genomic alterations can respond differently to therapy. Most drug-response models evaluate individual drugs or drug-sample pairs, whereas clinical decision-making requires therapies to be prioritized within each tumor context. Here we present DEPICT (Drug Efficacy Prediction via Integrated ConText), a sample-centric deep learning framework that reframes drug-response prediction as the relative prioritization of therapies within an individual tumor context. DEPICT integrates transcriptomic and mutational features with prior alteration-therapy relationship and was trained on 231,880 cell line-drug pairs comprising 941 cancer cell lines and 289 compounds. Without retraining, DEPICT retained predictive performance in independently profiled cell lines, experimentally induced drug-resistant states and matched primary lung tumors and patient-derived organoids. Representations learned exclusively from bulk pharmacogenomic data further captured progressive drug-response states at single-cell resolution and outperformed existing single-cell drug-response inference methods. Applied to spatial transcriptomic data, DEPICT resolved clone-associated therapeutic heterogeneity within individual lung tumors, and predicted regional differences were recapitulated in matched multiregional organoid drug-response assays. These findings establish sample-centric therapeutic prioritization as a transferable strategy for modeling dynamic and spatially heterogeneous drug vulnerabilities across biological scales.
Related
- Claustrum Morphometry Reveals Spatially Heterogeneous Alterations in 22q11DS
- Long-term biodiversity responses to anthropogenic change are spatially and taxonomically heterogeneous across coastal wetlands
- A heterogeneous biomedical knowledge network framework for rare disease drug candidate prioritization: integrating Orphadata and DisGeNET via gene-bridge harmonization
- ADMET-EvO: a self-evolving scientific agent for sustained research across heterogeneous tasks
- PathwayFinder enables linked exploration of cell types and gene modules in spatially resolved transcriptomics data
BibTeX
@misc{ma2026depict,
title = {{DEPICT enables sample-centric therapeutic prioritization across evolving and spatially heterogeneous tumor states}},
author = {S. Ma and S. Yan and X. Wen and C. Yu and H. Ma and W. Teng and X. Zhou and J. Gao and S. Wang and M. Li and K. Han and Y. Huang and N. Wu and B. Liu and C. Zheng},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.07.756157},
url = {https://www.biorxiv.org/content/10.64898/2026.10.07.756157v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - DEPICT enables sample-centric therapeutic prioritization across evolving and spatially heterogeneous tumor states
AU - S. Ma
AU - S. Yan
AU - X. Wen
AU - C. Yu
AU - H. Ma
AU - W. Teng
AU - X. Zhou
AU - J. Gao
AU - S. Wang
AU - M. Li
AU - K. Han
AU - Y. Huang
AU - N. Wu
AU - B. Liu
AU - C. Zheng
PY - 2026
DA - 2026/10/07
PB - bioRxiv
DO - 10.64898/2026.10.07.756157
UR - https://www.biorxiv.org/content/10.64898/2026.10.07.756157v1
AB - Accurate treatment selection remains a major challenge in precision oncology because tumors with similar genomic alterations can respond differently to therapy. Most drug-response models evaluate individual drugs or drug-sample pairs, whereas clinical decision-making requires therapies to be prioritized within each tumor context. Here we present DEPICT (Drug Efficacy Prediction via Integrated ConText), a sample-centric deep learning framework that reframes drug-response prediction as the relative prioritization of therapies within an individual tumor context. DEPICT integrates transcriptomic and mutational features with prior alteration-therapy relationship and was trained on 231,880 cell line-drug pairs comprising 941 cancer cell lines and 289 compounds. Without retraining, DEPICT retained predictive performance in independently profiled cell lines, experimentally induced drug-resistant states and matched primary lung tumors and patient-derived organoids. Representations learned exclusively from bulk pharmacogenomic data further captured progressive drug-response states at single-cell resolution and outperformed existing single-cell drug-response inference methods. Applied to spatial transcriptomic data, DEPICT resolved clone-associated therapeutic heterogeneity within individual lung tumors, and predicted regional differences were recapitulated in matched multiregional organoid drug-response assays. These findings establish sample-centric therapeutic prioritization as a transferable strategy for modeling dynamic and spatially heterogeneous drug vulnerabilities across biological scales.
ER -