Related Experiment Video
Updated: Feb 28, 2026
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
GenReP: An Ensemble Model for Predicting TP53 in Response to Pharmaceutical Compounds
Austin Spadaro1, Alok Sharma2,3,4, Iman Dehzangi1,5,6
1Center for Computational and Integrative Biology, Rutgers University, Camden, NJ 08102, USA.
Abstract:
TP53 is a tumor-suppressor gene involved in regulating apoptosis, DNA repair, and genomic stability. Mutations in TP53 are implicated in approximately half of all detected cancers, including breast, lung, colorectal, and ovarian cancers, making it a significant target for therapeutic interventions. Many pharmaceutical drugs aim to restore TP53 function, and there is a need for predictive tools to assess how compounds may affect TP53 expression. In this study, we propose a new ensemble machine-learning model to predict the direction of TP53 relative gene expression in response to pharmaceutical compounds. Our model utilizes molecular fingerprints, descriptors, and scaffold-based features extracted from SMILES representations of compounds concatenated into a single feature vector. Trained using our newly generated benchmark dataset based on the Connectivity Map (CMap) database and addressing class imbalance with the Synthetic Minority Over-sampling Technique (SMOTE), our model achieves 62.9%, 93.9%, 40.3%, and 0.39 in terms of accuracy, sensitivity, specificity, and Matthews Correlation Coefficient (MCC), respectively. As the first-of-its-kind TP53 gene regulation prediction, our study serves as a convincing proof-of-concept that paves the way for future investigation. GenReP as a stand-alone predictor, its source code, and our newly generated benchmark dataset are publicly available.
Insights
This study introduces a novel machine-learning model to predict how drugs affect the TP53 tumor-suppressor gene. This tool aids in developing new cancer therapies by understanding gene expression changes.
Area of Science:
- Genomics
- Computational Biology
- Pharmacology
Background:
- TP53 is a critical tumor-suppressor gene regulating apoptosis, DNA repair, and genomic stability.
- TP53 mutations are found in about half of all cancers, making it a key therapeutic target.
- Predictive tools are needed to assess drug effects on TP53 gene expression.
Purpose of the Study:
- To develop an ensemble machine-learning model for predicting TP53 relative gene expression changes in response to pharmaceutical compounds.
- To create a novel predictor for TP53 gene regulation by drugs.
Main Methods:
- Utilized molecular fingerprints, descriptors, and scaffold-based features from SMILES representations.
- Concatenated features into a single vector for model input.
- Trained the model on a new benchmark dataset from the Connectivity Map (CMap) database.
- Addressed class imbalance using the Synthetic Minority Over-sampling Technique (SMOTE).
Main Results:
- The model achieved 62.9% accuracy, 93.9% sensitivity, 40.3% specificity, and a 0.39 Matthews Correlation Coefficient (MCC).
- Demonstrated proof-of-concept for predicting TP53 gene regulation.
- The predictor, source code, and dataset are publicly available.
Conclusions:
- The developed machine-learning model is a novel tool for predicting TP53 gene expression changes induced by drugs.
- This work provides a foundation for future research in personalized cancer therapy and drug development.
- Public availability of the predictor and dataset facilitates further scientific investigation.
Related Concept Videos
01:27Pharmacodynamic Models: Overview
01:29Pharmacodynamic Models: Direct Effect Model and Indirect Response Model
01:09Pharmacodynamic Models: Additive and Proportional Drug Effect Model
01:14Pharmacokinetic–Pharmacodynamic Relationship: Model Components
01:18Pharmacodynamic Models: Emax Drug–Concentration Effect Model
01:13Physiological Pharmacokinetic Models: Assumption with Protein Binding