Utilizing public and private sector data to build better machine learning models for the prediction of pharmacokinetic parameters. Issue 11 (November 2022)

• Record Type: Journal Article
• Authors: Kuroda, Masataka; Watanabe, Reiko; Esaki, Tsuyoshi; Kawashima, Hitoshi; Ohashi, Rikiya; Sato, Tomohiro; Honma, Teruki; Komura, Hiroshi; Mizuguchi, Kenji
• Is Part Of: Drug discovery today. Volume 27:Issue 11(2022)
• Publication Date: 2022-11
• Subjects: Pharmacokinetic prediction -- Database -- Descriptor -- Prediction model -- Machine learning -- Data collection; ANN artificial neural network -- AutoML automated machine learning -- CLint intrinsic clearance -- DruMAP drug metabolism and pharmacokinetics analysis platform -- fu, brain fraction unbound in brain homogenate -- fu, p fraction unbound in plasma -- GB gradient boosting -- MSE mean square error -- P-gp P-glycoprotein net efflux ratio -- QSAR quantitative structure–activity relationship -- RF random forest -- SlogP calculated octanol–water partition coefficient -- SVM support vector machine -- 2D two-dimensional -- 3D three-dimensional; Drugs -- Design -- Periodicals; Drugs -- Research -- Periodicals; 615.1
• DOI: 10.1016/j.drudis.2022.103339
• Languages: English
• ISSNs: 1359-6446

Abstract

Highlights: Assessment of PK parameters of drug candidates is crucial for lead optimization. We review problems in building machine learning models for PK parameter prediction. In silico predictions by machine learning are useful for designing compounds. Prediction models can be constructed with diverse data without calibration. Merging public and private sector datasets improve prediction performance. Abstract : One solution to compensate for the shortage of publicly available data is to collect more quality-controlled data from the private sector through public–private partnerships. However, several issues must be resolved before implementing such a system. Here, we review the technical aspects of public–private partnerships using our initiative in Japan as an example. In particular, we focus on the procedure for collecting data from multiple private sector companies and building prediction models and discuss how merging public and private sector datasets will help to improve the chemical space coverage and prediction performance. Teaser : Japan's first public–private consortium in pharmacokinetics has incorporated data from multiple pharmaceutical companies to create useful predictive models.