Related Experiment Video
Updated: Nov 15, 2025
A Combined 3D Tissue Engineered In Vitro/In Silico Lung Tumor Model for Predicting Drug Effectiveness in Specific Mutational Backgrounds
Published on: April 6, 2016
Facilitating Drug Discovery in Breast Cancer by Virtually Screening Patients Using In Vitro Drug Response Modeling
Robert F Gruener1, Alexander Ling2, Ya-Fang Chang1
1Ben May Department for Cancer Research, University of Chicago, Chicago, IL 60637, USA.
Abstract:
(1) Background: Drug imputation methods often aim to translate in vitro drug response to in vivo drug efficacy predictions. While commonly used in retrospective analyses, our aim is to investigate the use of drug prediction methods for the generation of novel drug discovery hypotheses. Triple-negative breast cancer (TNBC) is a severe clinical challenge in need of new therapies. (2) Methods: We used an established machine learning approach to build models of drug response based on cell line transcriptome data, which we then applied to patient tumor data to obtain predicted sensitivity scores for hundreds of drugs in over 1000 breast cancer patients. We then examined the relationships between predicted drug response and patient clinical features. (3) Results: Our analysis recapitulated several suspected vulnerabilities in TNBC and identified a number of compounds-of-interest. AZD-1775, a Wee1 inhibitor, was predicted to have preferential activity in TNBC (p < 2.2 × 10-16) and its efficacy was highly associated with TP53 mutations (p = 1.2 × 10-46). We validated these findings using independent cell line screening data and pathway analysis. Additionally, co-administration of AZD-1775 with standard-of-care paclitaxel was able to inhibit tumor growth (p < 0.05) and increase survival (p < 0.01) in a xenograft mouse model of TNBC. (4) Conclusions: Overall, this study provides a framework to turn any cancer transcriptomic dataset into a dataset for drug discovery. Using this framework, one can quickly generate meaningful drug discovery hypotheses for a cancer population of interest.
Insights
This study developed a machine learning framework to predict drug efficacy from cancer transcriptomes, identifying AZD-1775 as a promising drug for triple-negative breast cancer (TNBC) and validating its effectiveness in preclinical models.
Area of Science:
- Computational Biology
- Drug Discovery
- Oncology
Background:
- Drug imputation methods typically predict in vitro drug response for in vivo efficacy.
- Novel therapeutic strategies are urgently needed for triple-negative breast cancer (TNBC).
Purpose of the Study:
- To investigate the utility of drug prediction models for generating novel drug discovery hypotheses.
- To identify potential drug candidates for triple-negative breast cancer (TNBC).
Main Methods:
- Machine learning models were trained on cell line transcriptome data to predict drug response.
- Models were applied to patient tumor data to generate drug sensitivity scores for over 1000 breast cancer patients.
- Predicted drug responses were correlated with patient clinical features.
Main Results:
- The analysis identified AZD-1775, a Wee1 inhibitor, as having predicted preferential activity in TNBC, strongly associated with TP53 mutations.
- Findings were validated using independent cell line screening data and pathway analysis.
- Co-administration of AZD-1775 with paclitaxel demonstrated significant tumor growth inhibition and increased survival in a TNBC xenograft mouse model.
Conclusions:
- A novel framework enables the transformation of cancer transcriptomic datasets into drug discovery resources.
- This approach facilitates rapid generation of drug discovery hypotheses for specific cancer populations.
- The study highlights AZD-1775 as a potential therapeutic agent for TNBC.
