Molecular partition coefficient from machine learning with polarization and entropy embedded atom-centered symmetry functions
Qiang Zhu, Qingqing Jia, Ziteng Liu, Yang Ge, Xu Gu, Ziyi Cui, Mengting Fan, Jing Ma
Abstract
-carboxylic acids with the number of carbons ranging from 2 to 14 and 54 kinds of organic solvent. It is easy to apply the present method to arbitrary sized systems and give a transferable atom-based partition coefficient.
Topics & Concepts
Partition coefficientPolarEmbeddingAtom (system on chip)Statistical physicsChemistryBoltzmann machineEntropy (arrow of time)Polarization (electrochemistry)Boltzmann constantArtificial neural networkThermodynamicsPhysicsQuantum mechanicsPhysical chemistryComputer scienceArtificial intelligenceOrganic chemistryEmbedded systemComputational Drug Discovery MethodsCrystallography and molecular interactionsMachine Learning in Materials Science