A Molecular Graph Representation Learning Method Based on Contrastive Learning

Abstract

The invention discloses a molecular graph representation learning method based on comparative learning, which includes: obtaining the molecular fingerprint representation of each molecule, and calculating the similarity between every two molecular fingerprints; Each atom matches the corresponding functional group; the molecular graph is modeled with the heterogeneous graph; the representation of each atom in the molecule and the representation of its functional group are encoded using the RGCN in the structure-aware molecular encoder, and the molecule is mapped to the feature through the aggregation function According to the fingerprint similarity between molecules, select positive and negative samples, and carry out comparative learning in the feature space; use the method of comparative learning to train on large sample molecular data sets, and obtain Structure-aware molecular encoders for downstream molecular property prediction tasks. The invention helps to capture richer molecular structure information and solve the problem of molecular attribute prediction.

Description

technical field [0001] The invention belongs to the field of graph representation learning, in particular to a molecular graph representation learning method based on contrastive learning. Background technique [0002] Over the past few years, Graph Representation Learning has become a popular research area for analyzing graph-structured data. Graph representation learning aims to learn an encoding function that takes full advantage of graph data to transform graph data with complex structures into dense representations in low-dimensional spaces that preserve diverse graph properties and structural features. [0003] The traditional unsupervised graph representation learning method uses the random walk method to convert the graph into a node sequence, and models the co-occurrence relationship between the central node and the neighbor nodes. However, this type of learning framework has two obvious disadvantages: one is the lack of parameter sharing between encoders, which wi...

AI Technical Summary

Problems solved by technology

[0009] The invention provides a molecular graph representation learning method based on comparative learning, which can obtain domain information and differentiated molecular graph representations, and solve problems such as molecular attribute prediction.

Images