Intelligent prediction method for small molecule-protein binding affinity

An intelligent prediction, protein technology, applied in the analysis of two-dimensional or three-dimensional molecular structure, neural learning methods, instruments, etc., can solve the problems of easily overlooked proteins, the difficulty of mining spatial structure information, etc., and achieve rapid and accurate data processing. Effects of Small Molecule-Protein Affinity Prediction

Pending Publication Date: 2022-04-12
QINGDAO TECHNOLOGICAL UNIVERSITY
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] On the one hand, it is easy to ignore the structural information of proteins in the form of string-encoded sequences; on the other hand, it is difficult to mine spatial structure information from sequences

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Intelligent prediction method for small molecule-protein binding affinity
  • Intelligent prediction method for small molecule-protein binding affinity
  • Intelligent prediction method for small molecule-protein binding affinity

Examples

Experimental program
Comparison scheme
Effect test

Embodiment example 1

[0036] The overall structural framework of the invention is as figure 1 As shown, the input is the SMILES representation of protein sequence and small molecule respectively. First, the small molecule graph is constructed based on SMILES, and the protein weight graph is constructed based on the sequence. Secondly, two graph convolutional neural networks are used to extract the features of molecular graph and protein weight graph respectively. Finally, based on the extracted two vectors, binding affinity prediction is performed.

[0037] (1) Construction of protein weight graph

[0038] Sequences are represented by character strings. In order to fully describe sequence features, the present invention proposes a method for constructing protein weight graphs based on residue interactions. The construction process is as follows: figure 2 shown.

[0039] First, the ESM model is used to predict the interaction of protein residues. This model does not require sequence alignment, a...

Embodiment example 2

[0055] In addition, the method of the present invention and existing method performance comparison (Davis database), the result is as follows:

[0056] Method Protein rep. Compound rep. MSE CI Pearson KronRLS Smith-Waterman Pubchem Sim 0.379 0.871 - SimBoost Smith-Waterman Pubchem Sim 0.282 0.872 - Deep DTA Smith-Waterman Pubchem Sim 0.608 0.790 - Deep DTA Smith-Waterman CNN 0.420 0.886 - Deep DTA CNN Pubchem Sim 0.419 0.835 - Deep DTA CNN CNN 0.261 0.878 - Wide DTA CNN CNN 0.262 0.886 0.820 GraphDTA CNN GIN 0.229 0.893 - GANs DTA GAN GAN 0.276 0.881 - The method of the invention GCN GCN 0.208 0.902 0.862

[0057] The results show that the present invention realizes more accurate small molecule-protein affinity prediction.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention provides a protein weight graph-based small molecule-protein binding affinity intelligent prediction method, which comprises the following steps of: firstly, constructing a small molecule graph based on SMILES, constructing a protein weight graph based on a sequence, and secondly, respectively extracting the characteristics of the small molecule graph and the protein weight graph by adopting two graph convolutional neural networks; and constructing a graph convolutional neural network to extract the features of the two, splicing the obtained feature vectors, and further predicting the affinity of the two. According to the protein weight graph constructed by the invention, more accurate representation of the sequence is realized, and the interaction among amino acid residues is more intuitively and effectively represented by a graph structure; the constructed protein weight graph does not need to be subjected to an extremely complex sequence alignment process, so that data processing is quicker, the method is suitable for a virtual screening process of a large molecular database, and more accurate small molecule-protein affinity prediction can be realized.

Description

technical field [0001] The invention relates to an intelligent prediction method for small molecule-protein binding affinity, in particular to an intelligent prediction method for small molecule-protein binding affinity based on a protein weight graph. Background technique [0002] Proteins are the main bearers of the functional activities of the human body, and the combination of small molecules and proteins can inhibit or promote the functional activities of proteins. Therefore, candidate drugs that can bind to disease-related proteins (target proteins) are screened from many small molecule databases Molecules are the main ideas in drug development at present. Affinity is an important indicator to measure the binding activity of small molecules and proteins. It is time-consuming and costly to observe the binding affinity of small molecules and proteins through chemical experiments. In recent years, with the rapid development of computers, the use of computers to calculate...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G16B15/00G06N3/04G06N3/08
Inventor 江明建
Owner QINGDAO TECHNOLOGICAL UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap