Imputation of assay bioactivity data using deep learning
This article describes a novel deep learning neural network method and its application for the imputation of bioactivity data, such…
The Nova ideas generated depend on the parameters set by users’ input, which are based on over 200 commonly known transformations. The proposed compounds generated would make ‘sense’ to a chemist in terms of their properties. Chapter 10 of the reference guide* describes the properties of the resulting predicted compounds and the most promising ideas are prioritised for further consideration to identify those that are most likely to have a good balance of the properties required in a high quality drug.
This example goes through the generation of new compound ideas using ‘Med. Chem. transformations’ and prioritised against a project’s requirements. This is based on an example we published in J. Chem. Inf. Model. 2011, 51 (11), pp. 2967-2976.
Just follow the step-by-step guidelines in this PDF and download the associated example files to try it yourself.
*Reference guide can be access in StarDrop Help menu
More predictive modelling resources
Automatic generation of new compound ideas
During this example we will consider three compounds from a lead series which we would like to try to evolve into a candidate. The compound has a good profile of ADME properties but insufficient inhibition of the target, the Serotonin transporter. In this example we will use StarDrop’s Nova module to generate new ideas for compounds to improve the potency while maintaining the balance of other properties.
