Abstract
Motivation
In silico drug–target interaction (DTI) prediction is important for drug discovery and drug repurposing. Approaches to predict DTIs can proceed indirectly, top-down, using phenotypic effects of drugs to identify potential drug targets, or they can be direct, bottom-up and use molecular information to directly predict binding affinities. Both approaches can be combined with information about interaction networks.
Results
We developed DTI-Voodoo as a computational method that combines molecular features and ontology-encoded phenotypic effects of drugs with protein–protein interaction networks, and uses a graph convolutional neural network to predict DTIs. We demonstrate that drug effect features can exploit information in the interaction network whereas molecular features do not. DTI-Voodoo is designed to predict candidate drugs for a given protein; we use this formulation to show that common DTI datasets contain intrinsic biases with major effects on performance evaluation and comparison of DTI prediction methods. Using a modified evaluation scheme, we demonstrate that DTI-Voodoo improves significantly over state of the art DTI prediction methods.
Original language | English (US) |
---|---|
Journal | Bioinformatics |
DOIs | |
State | Published - Jul 28 2021 |
Bibliographical note
KAUST Repository Item: Exported on 2021-08-05Acknowledged KAUST grant number(s): URF/1/3790-01-01 and URF/1/4355-01-01
Acknowledgements: This work was supported by funding from King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research (OSR)
under Award No. URF/1/3790-01-01 and URF/1/4355-01-01.
ASJC Scopus subject areas
- Biochemistry
- Computational Theory and Mathematics
- Computational Mathematics
- Molecular Biology
- Statistics and Probability
- Computer Science Applications