The present state and challenges of active learning in drug discovery

Lei Wang, Zhenran Zhou, Xixi Yang, Shaohua Shi, Xiangxiang Zeng*, Dongsheng Cao*

*Corresponding author for this work

Research output: Contribution to journalJournal articlepeer-review

4 Citations (Scopus)

Abstract

Active learning (AL) is an iterative feedback process that efficiently identifies valuable data within vast chemical space, even with limited labeled data. This characteristic renders it a valuable approach to tackle the ongoing challenges faced in drug discovery, such as the ever-expanding explore space and the limitations of labeled data. Consequently, AL is increasingly gaining prominence in the field of drug development. In this paper, we comprehensively review the application of AL at all stages of drug discovery, including compounds–target interaction prediction, virtual screening, molecular generation and optimization, as well as molecular properties prediction. Additionally, we discuss the challenges and prospects associated with the current applications of AL in drug discovery.

Original languageEnglish
Article number103985
Number of pages14
JournalDrug Discovery Today
Volume29
Issue number6
DOIs
Publication statusPublished - Jun 2024

Scopus Subject Areas

  • Pharmacology
  • Drug Discovery

User-Defined Keywords

  • active learning
  • compounds–target interaction prediction
  • molecular generation and optimization
  • molecular properties prediction
  • virtual screening

Fingerprint

Dive into the research topics of 'The present state and challenges of active learning in drug discovery'. Together they form a unique fingerprint.

Cite this