DTI-Voodoo: machine learning over interaction networks and ontology-based background knowledge predicts drug-target interactions
KAUST Department1Computational Bioscience Research Center, Computer, Electrical and Mathematical Sciences & Engineering Division, King Abdullah University of Science and Technology, 4700 King Abdullah University of Science and Technology, Thuwal 23955, Saudi Arabia.
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Computer Science Program
Computational Bioscience Research Center (CBRC)
KAUST Grant NumberURF/1/3790-01-01 and URF/1/4355-01-01
Permanent link to this recordhttp://hdl.handle.net/10754/669064
MetadataShow full item record
AbstractMotivation: 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 potentials. 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 neural networks 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 affects on performance evaluation and comparison of DTI prediction methods. Using a modified evaluation scheme, we demonstrate that DTI-Voodoo improves substantially over state of the art DTI prediction methods.
CitationHinnerichs, T., & Hoehndorf, R. (2021). DTI-Voodoo: machine learning over interaction networks and ontology-based background knowledge predicts drug-target interactions. doi:10.1101/2021.04.28.441733
SponsorsWe acknowledge the use of computational resources from the KAUST Supercomputing Core Laboratory
Funding 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 Supercomputing Core Laboratory
PublisherCold Spring Harbor Laboratory
RelationsIs Supplemented By: