Cross-modal transfer enables zero-shot prediction of drug responses across cell types
- 1Tsinghua University
Abstract
Genetic perturbation responses capture the functional consequences of gene-level interventions, providing functional information for drug-response prediction beyond baseline gene expression. Within the same cellular context, genetic and chemical perturbations engage shared regulatory networks, providing a biological basis for transferring response information between perturbation modalities. Here we introduce GRAFT, a framework that combines genetic-to-chemical transfer with cross-context prediction to infer drug-induced transcriptional responses without drug measurements in the target context. Across benchmarked LINCS and external contexts, GRAFT improved response correlation, directional agreement and magnitude reconstruction over competing methods, particularly for drugs with context-dependent responses. GRAFT-Adapt further refines predictions of unmeasured responses using a small number of drug measurements from the target context. GRAFT-Atlas spans 13 cellular contexts and 7,856 drug catalog entries, comprising 102,128 predictions for drug-context combinations. The atlas captured recognizable pharmacological neighborhoods, shared functional programs, context-dependent transcriptional changes and structural-functional associations supported by molecular docking. Across ten iPSC lines from distinct donors, GRAFT identified candidate inter-donor differences, with functional support for selected candidates from measured genetic perturbation responses. Together, GRAFT enables perturbation-informed prediction and comparison of drug responses across cellular contexts.
Related
- Agentic Discovery Transfer Enables Cross-Cancer Discovery at Scale
- Hierarchical Temporal Transformer for Cancer Grade Prediction and Cross-Cancer Transfer Learning from Pathology Reports
- Hierarchical temporal transformer for cancer grade prediction and cross cancer transfer learning from pathology reports
- Cross-cancer knowledge transfer for lymph node metastasis prediction: Applicability of an axillary lymph node-based deep learning model
- Cross-omics mapping of the human HIV restrictome across clinical states, immune-cell compartments, and protein responses
BibTeX
@misc{luo2026crossmodal,
title = {{Cross-modal transfer enables zero-shot prediction of drug responses across cell types}},
author = {C. Luo and M. Hu and Y. Wu and D. Guo and S. Wang and Q. R. Lyu and X. Liu},
howpublished = {bioRxiv},
year = {2026},
month = oct,
doi = {10.64898/2026.10.27.762107},
url = {https://www.biorxiv.org/content/10.64898/2026.10.27.762107v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Cross-modal transfer enables zero-shot prediction of drug responses across cell types
AU - C. Luo
AU - M. Hu
AU - Y. Wu
AU - D. Guo
AU - S. Wang
AU - Q. R. Lyu
AU - X. Liu
PY - 2026
DA - 2026/10/27
PB - bioRxiv
DO - 10.64898/2026.10.27.762107
UR - https://www.biorxiv.org/content/10.64898/2026.10.27.762107v1
AB - Genetic perturbation responses capture the functional consequences of gene-level interventions, providing functional information for drug-response prediction beyond baseline gene expression. Within the same cellular context, genetic and chemical perturbations engage shared regulatory networks, providing a biological basis for transferring response information between perturbation modalities. Here we introduce GRAFT, a framework that combines genetic-to-chemical transfer with cross-context prediction to infer drug-induced transcriptional responses without drug measurements in the target context. Across benchmarked LINCS and external contexts, GRAFT improved response correlation, directional agreement and magnitude reconstruction over competing methods, particularly for drugs with context-dependent responses. GRAFT-Adapt further refines predictions of unmeasured responses using a small number of drug measurements from the target context. GRAFT-Atlas spans 13 cellular contexts and 7,856 drug catalog entries, comprising 102,128 predictions for drug-context combinations. The atlas captured recognizable pharmacological neighborhoods, shared functional programs, context-dependent transcriptional changes and structural-functional associations supported by molecular docking. Across ten iPSC lines from distinct donors, GRAFT identified candidate inter-donor differences, with functional support for selected candidates from measured genetic perturbation responses. Together, GRAFT enables perturbation-informed prediction and comparison of drug responses across cellular contexts.
ER -