Bet365 login title:Co-regularized variational autoencoders for Bet365 login prediction
Bet365 login Announcement Person:Bet365 login
Reporting location: Tencent Conference 643-361-958
Bet365 login time:November 202210 day Afternoon4：00
Master hold Person:Guo Fei
Bet365 login Introduction:Bet365 login has been a key step in drug discovery. In this talk, I will present our co-regularized variational autoencoders (Co-VAE) for predicting Bet365 login based on drug structures and target sequences. The Co-VAE model consists of two VAEs for generating drug SMILES strings and target sequences, respectively, and a co-regularization part for generating the binding affinities. We theoretically prove that the Co-VAE model is to maximize the lower bound of the joint likelihood of drug, protein and their affinity. The Co-VAE could predict drug-target affinity and generate new drugs which share similar targets with the input drugs. The experimental results on two datasets show that the Co-VAE could predict drug-target affinity better than existing affinity prediction methods such as DeepDTA and DeepAffinity, and could generate more new valid drugs than existing methods such as GAN and VAE.
Speaker introduction: Bet365 login，Xi’an TransportationProfessor of the Bet365 login School of Mathematics and Statistics,Doctoral Supervisor。Graduated from Zhejiang Bet365 login with bachelor’s degree and master’s degree，Graduated from the Bet365 login of Hong Kong with a Ph.D.。MainResearchMachine Learning and Statistical MethodsandThey are in biological Bet365 loginApplication in,includesBet365 logintargetProtein recognition,Cancer subType identification, cross-species predictionetc.. Published in related fields in recent yearsMultiple articlespaper,includesTPAMI, Briefings in Bioinformatics, SIAM Journal on Bet365 login Computing, TCBB etc.。Host the National Natural Science Foundation of China General Project and the Outstanding Youth Science Fund。
