Deep Neural Network learning of physicochemical properties

The aim is to learn physicochemical properties of interest from simple structural representations, using deep neural networks: in particular I would like to investigate how much can be learned from molecular fingerprints generated by using the SMILES molecular representation.

Representation of a molecular substructure fingerprint with a substructure fingerprint dictionary of given substructure patterns. This molecule is represented in a series of binary bits that represent the presence or absence of particular substructures in the molecules. SOURCE : https://www.researchgate.net/publication/235919348_manual_for_chemopy/figures

This project was initiated in 0ctober 2017 during the IPAM’s long program “Complex High-Dimensional Energy Landscapes”