TY - JOUR
T1 - The present state and challenges of active learning in drug discovery
AU - Wang, Lei
AU - Zhou, Zhenran
AU - Yang, Xixi
AU - Shi, Shaohua
AU - Zeng, Xiangxiang
AU - Cao, Dongsheng
N1 - This work was supported by the National Key Research and Development Program of China, China (2021YFF1201400), the National Natural Science Foundation of China, China (22173118, 22220102001), the Hunan Provincial Science Fund for Distinguished Young Scholars, China; Science and Technology Innovation Program of Hunan Province, China (2021RC4011), the Natural Science Foundation of Hunan Province, China (2022JJ80104), and The 2020 Guangdong Provincial Science and Technology Innovation Strategy Special Fund, China (2020B1212030006, Guangdong-Hong Kong-Macau Joint Lab). We also acknowledge the support of Haikun Xu and the Centre for High Performance Computing at Central South University, China.
Publisher Copyright:
© 2024 Elsevier Ltd
PY - 2024/6
Y1 - 2024/6
N2 - 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.
AB - 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.
KW - active learning
KW - compounds–target interaction prediction
KW - molecular generation and optimization
KW - molecular properties prediction
KW - virtual screening
UR - http://www.scopus.com/inward/record.url?scp=85191855422&partnerID=8YFLogxK
U2 - 10.1016/j.drudis.2024.103985
DO - 10.1016/j.drudis.2024.103985
M3 - Journal article
C2 - 38642700
AN - SCOPUS:85191855422
SN - 1359-6446
VL - 29
JO - Drug Discovery Today
JF - Drug Discovery Today
IS - 6
M1 - 103985
ER -