Abstract
The prediction of drug–target affinity (DTA) is a crucial step for drug screening and discovery. In this study, a new graph-based prediction model named SAG-DTA (self-attention graph drug–target affinity) was implemented. Unlike previous graph-based methods, the proposed model utilized self-attention mechanisms on the drug molecular graph to obtain effective representations of drugs for DTA prediction. Features of each atom node in the molecular graph were weighted using an attention score before being aggregated as molecule representation. Various self-attention scoring methods were compared in this study. In addition, two pooing architectures, namely, global and hierarchical architectures, were presented and evaluated on benchmark datasets. Results of comparative experiments on both regression and binary classification tasks showed that SAG-DTA was superior to previous sequence-based or other graph-based methods and exhibited good generalization ability.
Highlights
Developing a new drug that gains marketing approval is estimated to cost USD 2.6 billion, and the approval rate for drugs entering clinical development is less than 12% [1,2]
It can be seen that the SMILES of the drug molecule was used to build a molecular graph, and the graph was sent to the graph convolutional network (GCN) network with SAGPooling layers to learn drug features
The proposed SAG-drug–target affinity (DTA) model contains a number of hyperparameters, and combinations of these hyperparameters form a vast search space
Summary
Developing a new drug that gains marketing approval is estimated to cost USD 2.6 billion, and the approval rate for drugs entering clinical development is less than 12% [1,2] Such massive investments and high risks drive scientists to explore novel and more efficient approaches in drug discovery. In the SimBoost model, He et al defined three types of features separately for the drug, target, and the drug–target pair, each of which contained multiple hand-crafted features [6] These approaches, despite achieving good performance in the DTA prediction task, depend on chemical insights or expert experiences, which, in turn, restrict further optimizations of these models
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
