Few-shot meta-learning applied to whole brain activity maps improves systems neuropharmacology and drug discovery
Xuan Luo,
Yanyun Ding,
Yi Cao,
Zhen Liu,
Wenchong Zhang,
Shangzhi Zeng,
Shuk Han Cheng,
Honglin Li,
Stephen J. Haggarty,
Xin Wang,
Jin Zhang,
Peng Shi
Affiliations
Xuan Luo
Department of Biomedical Engineering, City University of Hong Kong, Kowloon 999077, Hong Kong SAR, China; National Center for Applied Mathematics Shenzhen, Shenzhen 518000, China; Department of Mathematics, Southern University of Science and Technology, Shenzhen 518055, China
Yanyun Ding
National Center for Applied Mathematics Shenzhen, Shenzhen 518000, China; Institute of Applied Mathematics, Shenzhen Polytechnic University, Shenzhen 518055, China
Yi Cao
Department of Biomedical Sciences, City University of Hong Kong, Kowloon 999077, Hong Kong SAR, China
Zhen Liu
Department of Biomedical Engineering, City University of Hong Kong, Kowloon 999077, Hong Kong SAR, China
Wenchong Zhang
Department of Biomedical Engineering, City University of Hong Kong, Kowloon 999077, Hong Kong SAR, China
Shangzhi Zeng
National Center for Applied Mathematics Shenzhen, Shenzhen 518000, China
Shuk Han Cheng
Department of Biomedical Sciences, City University of Hong Kong, Kowloon 999077, Hong Kong SAR, China
Honglin Li
Innovation Center for AI and Drug Discovery, East China Normal University, Shanghai 200062, China
Stephen J. Haggarty
Chemical Neurobiology Laboratory, Precision Therapeutics Unit, Center for Genomic Medicine, Massachusetts General Hospital, Department of Neurology, Harvard Medical School, Boston, MA 02114, USA
Xin Wang
Department of Surgery, Chinese University of Hong Kong, Kowloon 999077, Hong Kong SAR, China
Jin Zhang
National Center for Applied Mathematics Shenzhen, Shenzhen 518000, China; Department of Mathematics, Southern University of Science and Technology, Shenzhen 518055, China; Corresponding author
Peng Shi
Department of Biomedical Engineering, City University of Hong Kong, Kowloon 999077, Hong Kong SAR, China; National Center for Applied Mathematics Shenzhen, Shenzhen 518000, China; Shenzhen Research Institute, City University of Hong Kong, Shenzhen 518057, China; Corresponding author
Summary: 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.
