Abstract
The use of virtual drug screening can be beneficial to research teams, enabling them to narrow down potentially useful compounds for further study. A variety of virtual screening methods have been developed, typically with machine learning classifiers at the center of their design. In the present study, we created a virtual screener for protein kinase inhibitors. Experimental compound–target interaction data were obtained from the IDG-DREAM Drug-Kinase Binding Prediction Challenge. These data were converted and fed as inputs into two multi-input recurrent neural networks (RNNs). The first network utilized data encoded in one-hot representation, while the other incorporated embedding layers. The models were developed in Python, and were designed to output the IC50 of the target compounds. The performance of the models was assessed primarily through analysis of the Q2 values produced from runs of differing sample and epoch size; recorded loss values were also reported and graphed. The performance of the models was limited, though multiple changes are proposed for potential improvement of a multi-input recurrent neural network-based screening tool.
Highlights
Drug development is a long and costly process
As machine learning grows in popularity, the idea of virtual drug screening has been brought to drug developers
Identifier (InChI) representations were tried; all simplified molecular-input line-entry system (SMILES) implementations resulted in predictions consisting entirely of zeros or NaNs
Summary
Drug development is a long and costly process. A 2014 study found that the cost of developing a prescription drug is, on average, US$2.87 billion [1], and has likely since increased. High-throughput screening requires all compounds to be purchased or synthesized, and requires repeated menial assaying work on the part of chemists. It typically has a low yield relative to the amount of required effort. As machine learning grows in popularity, the idea of virtual drug screening has been brought to drug developers. Virtual screening saves researchers time and money, and because it allows for the testing of a much greater number of compounds, it hugely increases yield. The processes for conducting virtual screening vary, and methods include molecular dynamics simulations (which require enormous amounts of computation) and machine learning.
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.
