MODEL OVERVIEW: Molecular property prediction is one of the fundamental issues in chemoinformatics and vital for many applications in chemistry and drug discovery. Lipophilicity is one of the factors determining the permeability of the cell membrane to a drug molecule. Accurate lipophilicity prediction is an essential step in the development of new drugs. Utilizing deep learning and generalized atomic features we were able to achieve a new state-of-the-art result at the task of prediction of two main lipophilicity coefficients, namely logP (the partition coefficient) and logD (the distribution coefficient) descriptors. Model supports both symmetric and asymmetric molecule prediction.
