Abstract
The discovery of new medications in a cost-effective manner has become the top priority for many pharmaceutical companies. Despite decades of innovation, many of their processes arguably remain relatively inefficient. One such process is the prediction of biological activity. This paper describes a new deep learning model, capable of conducting a preliminary screening of chemical compounds in-silico. The model has been constructed using a variation autoencoder to generate chemical compound fingerprints, which have been used to create a regression model to predict their LogD property and a classification model to predict binding in selected assays from the ChEMBL dataset. The conducted experiments demonstrate accurate prediction of the properties of chemical compounds only using structural definitions and also provide several opportunities to improve upon this model in the future.
Highlights
Deep learning [24] has been successfully applied in a number of problem domains from natural language processing [39], medical imaging analysis [32] to finance [26]
This paper describes a new deep learning model, capable of conducting a preliminary screening of chemical compounds in-silico
The model has been constructed using a variation autoencoder to generate chemical compound fingerprints, which have been used to create a regression model to predict their LogD property and a classification model to predict binding in selected assays from the ChEMBL dataset
Summary
Deep learning [24] has been successfully applied in a number of problem domains from natural language processing [39], medical imaging analysis [32] to finance [26]. Deep learning architectures are successfully used for many predictive tasks in chemistry and biology domains [55]. One application of deep learning in the chemistry domain is to predict important properties of chemical compounds. It allows for the assessment of chemical compounds before committing to an expensive synthesis process [7, 8, 20, 43]. Deep learning theory is based on deep neural networks (DNN) which consist of many layers.
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 call
