Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
DRUG SIDE EFFECT PREDICTION METHOD BASED ON RESTRICTED BOLTZMANN MACHINE WITH PENALTY REGULARIZATION TERM
Document Type and Number:
WIPO Patent Application WO/2024/021368
Kind Code:
A1
Abstract:
Disclosed in the present invention are a drug side effect prediction method, apparatus, and device based on a restricted Boltzmann machine with a penalty regularization term. The method comprises: constructing a target drug similarity matrix, a target side effect similarity matrix, and a drug side effect association matrix; constructing a drug restricted Boltzmann machine model and a side effect restricted Boltzmann machine model; constructing a maximum likelihood function on the basis of initial model parameters, the target drug similarity matrix, the target side effect similarity matrix, and the drug side effect association matrix, adding a penalty term into the maximum likelihood function for iterative training until a preset number of iterations is reached, so as to obtain optimal model parameters; finally, utilizing the trained models for prediction. According to the present invention, by training the optimal parameters of the models by means of a gradient descent algorithm of the maximum likelihood function with the penalty term, fitting in the training process is avoided, and the prediction precision of the models is improved, such that the prediction result is more accurate.

Inventors:
QIAN YUQING (CN)
DING YIJIE (CN)
ZHAN XIAOTONG (CN)
WU HONGJIE (CN)
Application Number:
PCT/CN2022/132125
Publication Date:
February 01, 2024
Filing Date:
November 16, 2022
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
UNIV SUZHOU SCI & TECHNOLOGY (CN)
International Classes:
G16H70/40
Foreign References:
CN111477344A2020-07-31
CN113140327A2021-07-20
CN113793696A2021-12-14
EP3089060A12016-11-02
Other References:
QIAN YUQING, DING YIJIE, ZOU QUAN, GUO FEI: "Identification of drug-side effect association via restricted Boltzmann machines with penalized term", BRIEFINGS IN BIOINFORMATICS, OXFORD UNIVERSITY PRESS, OXFORD., GB, vol. 23, no. 6, 19 November 2022 (2022-11-19), GB , XP093133578, ISSN: 1467-5463, DOI: 10.1093/bib/bbac458
Attorney, Agent or Firm:
CENTRAL SOUTH WELL INTELLECTUAL PROPERTY OFFICE (CN)
Download PDF: