Naomi Wakayama1, Kota Toshimoto2,3, Kazuya Maeda4, Shun Hotta2, Takashi Ishida2, Yutaka Akiyama2, Yuichi Sugiyama5. 1. Drug Metabolism and Pharmacokinetics Japan, Biopharmaceutical Assessment Core Function Unit, Medicine Development Center, Eisai Co., Ltd., Tokyo, Japan. 2. Department of Computer Science, Graduate School of Information Science and Engineering, Tokyo Institute of Technology, Tokyo, Japan. 3. Sugiyama Laboratory, RIKEN Baton Zone Program, RIKEN Cluster for Science, Technology and Innovation Hub, RIKEN, Yokohama, Japan. 4. Laboratory of Molecular Pharmacokinetics, Graduate School of Pharmaceutical Sciences, the University of Tokyo, Tokyo, Japan. 5. Sugiyama Laboratory, RIKEN Baton Zone Program, RIKEN Cluster for Science, Technology and Innovation Hub, RIKEN, Yokohama, Japan. ychi.sugiyama@riken.jp.
Abstract
PURPOSE: The clearance pathways of drugs are critical elements for understanding the pharmacokinetics of drugs. We previously developed in silico systems to predict the five clearance pathway using a rectangular method and a support vector machine (SVM). In this study, we improved our classification system by increasing the number of clearance pathways available for our prediction (CYP1A2, CYP2C8, CYP2C19, and UDP-glucuronosyl transferases (UGTs)) and by accepting multiple major pathways. METHODS: Using the four default descriptors (charge, molecular weight, logD at pH 7.0, and unbound fraction in plasma), three kinds of SVM-based predictors based on traditional single-step approach or two-step focusing approaches with subset or partition clustering were developed. The two-step approach with subset clustering resulted in the highest prediction performance. The feature-selection of additional descriptors based on a greedy algorithm was employed to further improve the predictability. RESULTS: The prediction accuracy for each pathway was increased to more than 0.83 with the exception of CYP2C19 and UGTs pathways, whose accuracies were below 0.7. Prediction performance of CYP1A2, CYP3A4 and renal excretion pathways were found to be acceptable using external dataset. CONCLUSIONS: We successfully constructed a novel SVM-based predictor for the multiple major clearance pathways based on chemical structures.
PURPOSE: The clearance pathways of drugs are critical elements for understanding the pharmacokinetics of drugs. We previously developed in silico systems to predict the five clearance pathway using a rectangular method and a support vector machine (SVM). In this study, we improved our classification system by increasing the number of clearance pathways available for our prediction (CYP1A2, CYP2C8, CYP2C19, and UDP-glucuronosyl transferases (UGTs)) and by accepting multiple major pathways. METHODS: Using the four default descriptors (charge, molecular weight, logD at pH 7.0, and unbound fraction in plasma), three kinds of SVM-based predictors based on traditional single-step approach or two-step focusing approaches with subset or partition clustering were developed. The two-step approach with subset clustering resulted in the highest prediction performance. The feature-selection of additional descriptors based on a greedy algorithm was employed to further improve the predictability. RESULTS: The prediction accuracy for each pathway was increased to more than 0.83 with the exception of CYP2C19 and UGTs pathways, whose accuracies were below 0.7. Prediction performance of CYP1A2, CYP3A4 and renal excretion pathways were found to be acceptable using external dataset. CONCLUSIONS: We successfully constructed a novel SVM-based predictor for the multiple major clearance pathways based on chemical structures.
Entities:
Keywords:
UDP-glucuronosyltransferase; clearance pathway; cytochrome P450; in silico prediction; support vector machine
Authors: Manthena V S Varma; Bo Feng; R Scott Obach; Matthew D Troutman; Jonathan Chupka; Howard R Miller; Ayman El-Kattan Journal: J Med Chem Date: 2009-08-13 Impact factor: 7.446
Authors: J Andrew Williams; Ruth Hyland; Barry C Jones; Dennis A Smith; Susan Hurst; Theunis C Goosen; Vincent Peterkin; Jeffrey R Koup; Simon E Ball Journal: Drug Metab Dispos Date: 2004-08-10 Impact factor: 3.922
Authors: Sophie Stotz; Johannes Kinzler; Anne T Nies; Matthias Schwab; Andreas Maurer Journal: Eur J Nucl Med Mol Imaging Date: 2021-09-06 Impact factor: 9.236