Employing Automated Machine Learning (AutoML) Methods to Facilitate the ADMET Properties Prediction.

Journal: Journal of chemical information and modeling
PMID:

Abstract

The rationale for using ADMET prediction tools in the early drug discovery paradigm is to guide the design of new compounds with favorable ADMET properties and ultimately minimize the attrition rates of drug failures. Artificial intelligence (AI) in ADMET modeling has gained momentum due to its high-throughput and low-cost attributes. In this study, we developed a machine learning model capable of predicting 11 ADMET properties of chemical compounds. Each model was constructed by combining one of 40 classification algorithms including random forest (RF), extreme gradient boosting (XGB), support vector machine (SVM), and gradient boosting (GB) with one of three predefined hyperparameter configurations. This process can be efficiently performed using automated machine learning (AutoML) methods, which automatically search for the best combination of model algorithms and optimized hyperparameters. We developed optimal predictive models for 11 different ADMET properties using the Hyperopt-sklearn AutoML method. All of the developed models depicted an area under the ROC curve (AUC) >0.8. Furthermore, our developed models outperformed most of the ADMET properties and showed comparable performance in other properties when evaluated on external data sets and compared with published predictive models. Our results support the applicability of AutoML in ADMET prediction and will be helpful for ADMET prediction in early-stage drug discovery.

Authors

  • Herim Han
    Digital Bio R&D Center, Mediazen, Seoul, 07789, Republic of Korea.
  • Bilal Shaker
    84 Heukseok-ro, Dongjak-gu, Department of Biomedical Engineering, Chung-Ang University, Seoul 06974, Republic of Korea.
  • Jin Hee Lee
    Department of Radiology, Keimyung University Dongsan Hospital, Daegu, Republic of Korea.
  • Sunghwan Choi
    Division of National Supercomputing, Korea Institute of Science and Technology Information, Daejeon, 34141, Republic of Korea.
  • Sanghee Yoon
    Global AI Drug Discovery Center, College of Pharmacy and Graduate School of Pharmaceutical Sciences, Ewha Womans University, Seoul 03760, Republic of Korea.
  • Maninder Singh
    Molecular and Structural Biology Division, CSIR-Central Drug Research Institute (CSIR-CDRI), Lucknow, India.
  • Shaherin Basith
    Department of Physiology, Ajou University School of Medicine, Suwon, Korea.
  • Minghua Cui
    Global AI Drug Discovery Center, College of Pharmacy and Graduate School of Pharmaceutical Sciences, Ewha Womans University, Seoul 03760, Republic of Korea.
  • Sunil Ahn
    Korea Institute of Science and Technology Information, Daejeon 34141, Republic of Korea.
  • Junyoung An
    Global AI Drug Discovery Center, College of Pharmacy and Graduate School of Pharmaceutical Sciences, Ewha Womans University, Seoul 03760, Republic of Korea.
  • Soosung Kang
    Global AI Drug Discovery Center, College of Pharmacy and Graduate School of Pharmaceutical Sciences, Ewha Womans University, Seoul 03760, Republic of Korea.
  • Min Sun Yeom
    NamuICT R&D Center, NamuICT, Seoul 07793, Republic of Korea.
  • Sun Choi
    Global AI Drug Discovery Center, School of Pharmaceutical Sciences, College of Pharmacy and Graduate, Ewha Womans University, Seoul 03760, Korea.