Classification of Breast Cancer Resistant Protein (BCRP) Inhibitors and Non-Inhibitors Using Machine Learning
Vilas Belekar, Karthik Lingineni, Prabha Garg1
1Department of Pharmacoinformatics, National Institute of Pharmaceutical Education and Research (NIPER), Sector-67, S.A.S. Nagar, Mohali, Punjab-160062, India. prabhagarg@niper.ac.in.
Abstract:
The breast cancer resistant protein (BCRP) is an important transporter and its inhibitors play an important role in cancer treatment by improving the oral bioavailability as well as blood brain barrier (BBB) permeability of anticancer drugs. In this work, a computational model was developed to predict the compounds as BCRP inhibitors or non-inhibitors. Various machine learning approaches like, support vector machine (SVM), k-nearest neighbor (k-NN) and artificial neural network (ANN) were used to develop the models. The Matthews correlation coefficients (MCC) of developed models using ANN, k-NN and SVM are 0.67, 0.71 and 0.77, and prediction accuracies are 85.2%, 88.3% and 90.8% respectively. The developed models were tested with a test set of 99 compounds and further validated with external set of 98 compounds. Distribution plot analysis and various machine learning models were also developed based on druglikeness descriptors. Applicability domain is used to check the prediction reliability of the new molecules.
Insights
This study developed computational models to predict breast cancer resistant protein (BCRP) inhibitors, crucial for enhancing anticancer drug efficacy. Machine learning models achieved high accuracy, aiding in the discovery of potential BCRP-targeting cancer therapeutics.
Area of Science:
- Computational chemistry
- Pharmacology
- Biochemistry
Background:
- The breast cancer resistant protein (BCRP) is a key transporter influencing drug efficacy.
- BCRP inhibitors can improve oral bioavailability and blood-brain barrier (BBB) permeability of anticancer agents.
- Predictive models for BCRP inhibitors are essential for drug development.
Purpose of the Study:
- To develop and validate computational models for predicting BCRP inhibitors.
- To assess the performance of various machine learning algorithms in BCRP inhibitor prediction.
- To establish an applicability domain for reliable prediction of new molecules.
Main Methods:
- Development of predictive models using Support Vector Machine (SVM), k-nearest neighbor (k-NN), and Artificial Neural Network (ANN).
- Utilized drug-likeness descriptors for model development and analysis.
- Validated models using test and external compound sets.
- Implemented applicability domain analysis for prediction reliability.
Main Results:
- Support Vector Machine (SVM) model achieved the highest prediction accuracy (90.8%) and Matthews correlation coefficient (MCC) of 0.77.
- k-NN and ANN models also demonstrated strong performance with MCCs of 0.71 and 0.67, respectively.
- Models were successfully validated on independent test and external datasets.
- Applicability domain analysis confirmed the reliability of predictions for new molecules.
Conclusions:
- Computational models, particularly SVM, can reliably predict BCRP inhibitors.
- These models can aid in the rational design and discovery of novel anticancer drugs targeting BCRP.
- The developed approach enhances the efficiency of identifying compounds with improved pharmacokinetic properties.
More Related Videos
07:15Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
07:13Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
Published on: April 18, 2025
