Few-shot meta-learning applied to whole brain activity maps improves systems neuropharmacology and drug discovery

Luo, Xuan1,2,3; Ding, Yanyun2,9; Cao, Yi4; Liu, Zhen1; Zhang, Wenchong1; Zeng, Shangzhi2; Cheng, Shuk Han4; Li, Honglin5; Haggarty, Stephen J.6; Wang, Xin7; Zhang, Jin2,3; Shi, Peng1,2,8

2024-10-18

10.1016/j.isci.2024.110875

ISCIENCE   影响因子和分区

2589-0042

In this study, we present an approach to neuropharmacological research by integrating few-shot meta- learning algorithms with brain activity mapping (BAMing) to enhance the discovery of central nervous system (CNS) therapeutics. By utilizing patterns from previously validated CNS drugs, our approach facilitates the rapid identification and prediction of potential drug candidates from limited datasets, thereby accelerating the drug discovery process. The application of few-shot meta-learning algorithms allows us to adeptly navigate the challenges of limited sample sizes prevalent in neuropharmacology. The study reveals that our meta-learning-based convolutional neural network (Meta-CNN) models demonstrate enhanced stability and improved prediction accuracy over traditional machine-learning methods. Moreover, our BAM library proves instrumental in classifying CNS drugs and aiding in pharmaceutical repurposing and repositioning. Overall, this research not only demonstrates the effectiveness in overcoming data limitations but also highlights the significant potential of combining BAM with advanced meta-learning techniques in CNS drug discovery.

SCI

英语

通讯

National Natural Science Foundation of China["U20A20194","2222106","12326605","62331014"] ; Research Grants Council of Hong Kong SAR["11215920","11220024","11218522","11218523"] ; Guangdong Basic and Applied Basic Research Foundation[2022B1515020082] ; Shenzhen-Hong Kong-Macau Science and Technology Program[SGDX2020110309300502] ; Shenzhen Science and Tech-nology Program[RCYX20200714114700072] ; City University of Hong Kong["7005084","7005206","7005642","7020003","7020077","9680233","9240060"]

Science & Technology - Other Topics

Multidisciplinary Sciences

WOS:001317448300001

CELL PRESS

Web of Science

1.City Univ Hong Kong, Dept Biomed Engn, Kowloon, Hong Kong 999077, Peoples R China
2.Natl Ctr Appl Math Shenzhen, Shenzhen 518000, Peoples R China
3.Southern Univ Sci & Technol, Dept Math, Shenzhen 518055, Peoples R China
4.City Univ Hong Kong, Dept Biomed Sci, Kowloon, Hong Kong 999077, Peoples R China
5.East China Normal Univ, Innovat Ctr AI & Drug Discovery, Shanghai 200062, Peoples R China
6.Harvard Med Sch, Massachusetts Gen Hosp, Ctr Genom Med, Dept Neurol,Chem Neurobiol Lab,Precis Therapeut Un, Boston, MA 02114 USA
7.Chinese Univ Hong Kong, Dept Surg, Kowloon, Hong Kong 999077, Peoples R China
8.City Univ Hong Kong, Shenzhen Res Inst, Shenzhen 518057, Peoples R China
9.Shenzhen Polytech Univ, Inst Appl Math, Shenzhen 518055, Peoples R China

Luo, Xuan,Ding, Yanyun,Cao, Yi,et al. Few-shot meta-learning applied to whole brain activity maps improves systems neuropharmacology and drug discovery[J]. ISCIENCE,2024,27(10).

Luo, Xuan.,Ding, Yanyun.,Cao, Yi.,Liu, Zhen.,Zhang, Wenchong.,...&Shi, Peng.(2024).Few-shot meta-learning applied to whole brain activity maps improves systems neuropharmacology and drug discovery.ISCIENCE,27(10).

Luo, Xuan,et al."Few-shot meta-learning applied to whole brain activity maps improves systems neuropharmacology and drug discovery".ISCIENCE 27.10(2024).