Related Experiment Video
Updated: Oct 4, 2025
Testing Targeted Therapies in Cancer using Structural DNA Alteration Analysis and Patient-Derived Xenografts
Published on: July 25, 2020
A community challenge for a pancancer drug mechanism of action inference from perturbational profile data
Eugene F Douglass1,2, Robert J Allaway3, Bence Szalai4
1Department of Systems Biology, Columbia University Irving Medical Center, 1130 Saint Nicholas Ave., New York, NY 10032, USA.
Abstract:
The Columbia Cancer Target Discovery and Development (CTD2) Center is developing PANACEA, a resource comprising dose-responses and RNA sequencing (RNA-seq) profiles of 25 cell lines perturbed with ∼400 clinical oncology drugs, to study a tumor-specific drug mechanism of action. Here, this resource serves as the basis for a DREAM Challenge assessing the accuracy and sensitivity of computational algorithms for de novo drug polypharmacology predictions. Dose-response and perturbational profiles for 32 kinase inhibitors are provided to 21 teams who are blind to the identity of the compounds. The teams are asked to predict high-affinity binding targets of each compound among ∼1,300 targets cataloged in DrugBank. The best performing methods leverage gene expression profile similarity analysis as well as deep-learning methodologies trained on individual datasets. This study lays the foundation for future integrative analyses of pharmacogenomic data, reconciliation of polypharmacology effects in different tumor contexts, and insights into network-based assessments of drug mechanisms of action.
Insights
Researchers developed PANACEA, a drug discovery resource, to predict drug polypharmacology. Computational algorithms accurately identified drug targets using gene expression and deep learning, advancing cancer drug development.
Area of Science:
- Pharmacology
- Computational Biology
- Genomics
Background:
- The Columbia Cancer Target Discovery and Development (CTD2) Center created PANACEA, a comprehensive resource for studying drug mechanisms of action.
- PANACEA includes dose-response and RNA sequencing (RNA-seq) data for 25 cell lines treated with approximately 400 clinical oncology drugs.
Purpose of the Study:
- To assess the accuracy and sensitivity of computational algorithms for predicting drug polypharmacology using the PANACEA resource.
- To evaluate predictive models in a DREAM Challenge format, where 21 teams predicted drug targets for 32 kinase inhibitors.
Main Methods:
- Utilized dose-response and RNA-seq profiles from the PANACEA resource.
- Employed a DREAM Challenge framework where computational teams predicted high-affinity binding targets for kinase inhibitors from a list of ~1,300 DrugBank targets.
- Teams used computational algorithms, including gene expression profile similarity analysis and deep learning methodologies.
Main Results:
- The best performing computational methods successfully predicted drug polypharmacology.
- Methods leveraging gene expression profile similarity and deep learning demonstrated high accuracy.
- The study validated the utility of the PANACEA resource for drug target prediction challenges.
Conclusions:
- This study establishes a foundation for future integrative analyses of pharmacogenomic data.
- The findings enable reconciliation of polypharmacology effects across different tumor contexts.
- The research provides insights into network-based assessments of drug mechanisms of action.
