ABSTRACT

ADME influences the performance and pharmacological activity of the compound as a drug.Poor compound solubility, chemical instability  and inability to permeate the intestinal wall can all reduce bioavailability of a drug. Drugs that absorb poorly when taken orally must be administered in some less desirable way, like intravenously or by inhalation. Machine learning methods are useful tool in prediction of ADME properties.In this project we study performance of  machine learning model  Message Passing Neural Network (MPNN) as ADME predictor.