A machine learning approach for the prediction of aqueous solubility of pharmaceuticals: a comparative model and dataset analysis
Mohammad Amin Ghanavati, Soroush Ahmadi, Sohrab Rohani
Abstract
Three ML models and their ensemble predict aqueous solubility of small organic molecules using different representations: GCN with molecular graphs, EdgeConv with ESP maps, and XGBoost with tabular features from ESP and Mordred descriptors.
Topics & Concepts
SolubilityAqueous solutionMachine learningComputer scienceArtificial intelligenceChemistryBiochemical engineeringEngineeringOrganic chemistryComputational Drug Discovery MethodsAnalytical Chemistry and ChromatographyProcess Optimization and Integration