Title:
METHOD AND DEVICE FOR PREDICTING INTERMOLECULAR BINDING ACTIVITY
Document Type and Number:
WIPO Patent Application WO/2021/089008
Kind Code:
A1
Abstract:
A method for predicting intermolecular binding activity, comprising: obtaining an original matrix of a protein and an original matrix of a small molecule (S101), extracting a first feature vector corresponding to the original matrix of the protein and a second feature vector corresponding to the original matrix of small molecule (S102), and then interlocking the first feature vector and the second feature vector and performing calculation, to obtain a prediction result of the binding activity between the protein and the small molecule output by a prediction model (S103). This method uses a convolutional neural network model to extract characteristics of a one-dimensional sequence of the protein and the small molecule to obtain the binding activity between the protein and the small molecule, avoiding errors in research resulting from an unclear structure of large molecules such as proteins, improving the efficiency of drug research and development by scientific and technical means, effectively shortening the research and development time, and ensuring the stability of the research process and results.
Inventors:
HU FAN (CN)
JIANG JIAXIN (CN)
YIN PENG (CN)
JIANG JIAXIN (CN)
YIN PENG (CN)
Application Number:
PCT/CN2020/127249
Publication Date:
May 14, 2021
Filing Date:
November 06, 2020
Export Citation:
Assignee:
SHENZHEN INST ADV TECH (CN)
International Classes:
G16C10/00
Foreign References:
| CN110910964A | 2020-03-24 | |||
| CN109887541A | 2019-06-14 | |||
| US20160196480A1 | 2016-07-07 | |||
| CN110444250A | 2019-11-12 |
Attorney, Agent or Firm:
BEIJING ZHONG XUN TONG DA INTELLECTUAL PROPERTY AGENCY CO., LTD. (CN)
Download PDF: