Related Experiment Video
Updated: Jul 22, 2026
Using RNA-sequencing to Detect Novel Splice Variants Related to Drug Resistance in In Vitro Cancer Models
Published on: December 9, 2016
Pan-Cancer Drug Sensitivity Prediction from Gene Expression using Deep Learning
Beronica A Ocasio1,2,3, Jiaming Hu1,3, Vasileios Stathias2,3
1Dr. John T. Macdonald Foundation Department of Human Genetics and John P. Hussman Institute for Human Genomics, Miller School of Medicine, University of Miami, Miami, FL 33136, USA.
Abstract:
Cancer is a group of complex diseases, with tumor heterogeneity, durable drug efficacy, emerging resistance, and host toxicity presenting major challenges to the development of effective cancer therapeutics. While traditionally used methods have remained limited in their capacity to overcome these challenges in cancer drug development, efforts have been made in recent years toward applying "big data" to cancer research and precision oncology. By curating, standardizing, and integrating data from various databases, we developed deep learning architectures that use perturbation and baseline transcriptional signatures to predict efficacious small molecule compounds and genetic dependencies in cancer. A series of internal validations followed by prospective validation in prostate cancer cell lines were performed to ensure consistent performance and model applicability. We report SensitivitySeq, a novel bioinformatics tool for prioritizing small molecule compounds and gene dependencies in silico to drive the development of targeted therapies for cancer. To the best of our knowledge, this is the first supervised deep learning approach, validated in vitro, to predict drug sensitivity using baseline cancer cell line gene expression alongside cell line-independent perturbation-response consensus signatures.
Insights
This study introduces SensitivitySeq, a novel deep learning tool that predicts effective small molecule compounds and gene targets for cancer therapy. It utilizes big data to overcome challenges in precision oncology drug development.
Area of Science:
- Bioinformatics
- Computational Biology
- Genomics
Background:
- Cancer drug development faces challenges like tumor heterogeneity and drug resistance.
- Traditional methods struggle to overcome these complexities in precision oncology.
- Big data approaches are emerging to advance cancer research and therapeutic strategies.
Purpose of the Study:
- To develop a novel bioinformatics tool for predicting efficacious small molecule compounds and gene dependencies in cancer.
- To leverage deep learning and big data for improved cancer drug discovery.
- To address limitations in current cancer therapeutic development.
Main Methods:
- Developed deep learning architectures integrating curated, standardized, and diverse datasets.
- Utilized perturbation and baseline transcriptional signatures for prediction.
- Performed internal and prospective validation in prostate cancer cell lines.
Main Results:
- Reported SensitivitySeq, a novel bioinformatics tool for *in silico* prioritization of drug candidates and gene targets.
- Demonstrated the tool's ability to predict drug sensitivity using gene expression and perturbation-response signatures.
- Achieved validation of the deep learning approach *in vitro*.
Conclusions:
- SensitivitySeq offers a powerful new method for identifying targeted cancer therapies.
- The tool enhances precision oncology by predicting drug efficacy and genetic dependencies.
- This represents a significant advancement in applying supervised deep learning to cancer drug discovery.
Related Concept Videos
01:11Pharmacogenetics of Drug Targets: β₂-Adrenergic Receptors, Apo E, Thymidylate Synthase
01:29Pharmacogenomics: Identification of New Drug Targets