Prediction of ADMET Properties of Anti-Breast Cancer Compounds Using Three Machine Learning Algorithms

In recent years, machine learning methods have been applied successfully in many fields. In this paper, three machine learning algorithms, including partial least squares-discriminant analysis (PLS-DA), adaptive boosting (AdaBoost), and light gradient boosting machine (LGBM), were applied to establish models for predicting the Absorption, Distribution, Metabolism, Excretion, and Toxicity (ADMET for short) properties, namely Caco-2, CYP3A4, hERG, HOB, MN of anti-breast cancer compounds. To the best of our knowledge, the LGBM algorithm was applied to classify the ADMET property of anti-breast cancer compounds for the first time. We evaluated the established models in the prediction set using accuracy, precision, recall, and F1-score. Compared with the performance of the models established using the three algorithms, the LGBM yielded most satisfactory results (accuracy > 0.87, precision > 0.72, recall > 0.73, and F1-score > 0.73). According to the obtained results, it can be inferred that LGBM can establish reliable models to predict the molecular ADMET properties and provide a useful tool for virtual screening and drug design researchers.

Automated summary

In this study, machine learning algorithms including PLS-DA, AdaBoost, and LGBM were applied to establish models for predicting the ADMET properties of anti-breast cancer compounds. The LGBM algorithm yielded the best results compared to the other two algorithms, with high accuracy, precision, recall, and F1-score. The findings suggest that LGBM can be a reliable tool for predicting molecular ADMET properties in virtual screening and drug design research.