Predicting associations between drugs and G protein-coupled receptors using a multi-graph convolutional network

In this study, based on a multi-graph convolutional network, an end-to-end deep model was developed to efficiently and precisely discover latent drug-GPCR relationships by combining data from multi-sources. We demonstrated that our model, based on multi-graph convolutional networks, outperformed rival deep learning techniques as well as non-deep learning models in terms of inferring drug-GPCR relationships. Our results indicated that integrating data from multi-sources can lead to further advancement.PMID:38579550 | DOI:10.1016/j.compbiolchem.2024.108060

Source: Computational Biology and Chemistry - April 5, 2024 Category: Bioinformatics Authors: Yuxun Luo Shasha Li Li Peng Pingjian Ding Wei Liang Source Type: research