Transfer learning empowers accurate pharmacokinetics prediction of small samples

• Published in: Drug discovery today Vol. 29; no. 4; p. 103946
• Main Authors: Guo, Wenbo, Dong, Yawen, Hao, Ge-Fei
• Format: Journal Article
• Language: English
• Published: England Elsevier Ltd 01.04.2024
• Subjects: Cheminformatics; machine learning; multimodal learning; multitask learning; pharmacokinetics prediction; transfer learning; transfer learning; pharmacokinetics prediction; Cheminformatics; multimodal learning; machine learning; multitask learning
• ISSN: 1359-6446; 1878-5832
• DOI: 10.1016/j.drudis.2024.103946

•Transfer learning enhances PK prediction models by leveraging relevant knowledge transfer.•Transfer learning categorizes into three types based on domain and tasks.•Diverse toolkits offer user-friendly approaches to deploy transfer learning effectively.•Several case studies exhibit the process and outcomes of transfer learning in PK prediction. Accurate assessment of pharmacokinetic (PK) properties is crucial for selecting optimal candidates and avoiding downstream failures. Transfer learning is an innovative machine learning approach enabling high-throughput prediction with limited data. Recently, transfer learning methods showed promise in predicting ADME/PK parameters. Given the prolific growth of research on transfer learning for PK prediction, a comprehensive review of its advantages and challenges is imperative. This study explores the fundamentals, classifications, toolkits and applications of various transfer learning techniques for PK prediction, demonstrating their utility through three practical case studies. This work will serve as a reference for drug design researchers.