Predicting drug-protein interactions by preserving the node connectivity and topological structure based on the multi source data
Authors:
Preprint
- 7 November 2023
- preprint
- Published by Springer Nature in Research Square
Abstract
Examining potential drug-target interactions (DTIs) is a pivotal component of drug discovery and repurposing.Recently, there has been a significant rise in the use of computational techniques to predict DTIs. Nevertheless, previous investigations have predominantly concentrated on assessing either the connections between nodes or the consistency of the network’s topological structure in isolation. Such one-sided approaches could severely hinder the accuracy of DTI predictions. In this study, we propose a novel method called TTGCN, which combines heterogeneous graph convolutional neural networks (GCN) and graph attention networks (GAT) to address the task of DTI prediction. TTGCN employs a two-tiered feature learning strategy, utilizing GAT and residual GCN (R-GCN) to extract drug and target embeddings from the diverse network, respectively. These drug and target embeddings are then fused through a mean-pooling layer. Finally, we employ an inductive matrix completion technique to forecast DTIs while preserving the network’s node connectivity and topological structure.Our approach demonstrates superior performance in terms of Area Under the Curve (AUC) and Area Under the Precision-Recall Curve (AUPR) in experimental comparisons, highlighting its significant advantages in predicting DTIs. Furthermore, case studies provide additional evidence of its ability to identify potential DTIs.Keywords
All Related Versions
- Version 1, 2023-11-07, Research Square
- Published version: BMC Bioinformatics, 25 (1), 1.
This publication has 26 references indexed in Scilit:
- An integrative drug repositioning framework discovered a potential therapeutic agent targeting COVID-19Signal Transduction and Targeted Therapy, 2021
- DTI-CDF: a cascade deep forest model towards the prediction of drug-target interactions based on hybrid featuresBriefings in Bioinformatics, 2019
- Bioinformatics approaches for new drug discovery: a reviewBiotechnology and Genetic Engineering Reviews, 2018
- A network integration approach for drug-target interaction prediction and computational drug repositioning from heterogeneous informationNature Communications, 2017
- Similarity-based machine learning methods for predicting drug–target interactions: a brief reviewBriefings in Bioinformatics, 2013
- Large-scale prediction and testing of drug activity on side-effect targetsNature, 2012
- Predicting new molecular targets for known drugsNature, 2009
- Relating protein pharmacology by ligand chemistryNature Biotechnology, 2007
- Structure-based maximal affinity model predicts small-molecule druggabilityNature Biotechnology, 2007
- Keynote review: In vitro safety pharmacology profiling: an essential tool for successful drug developmentDrug Discovery Today, 2005