3D chemical structures allow robust deep learning models for retention time prediction
Mark Zaretckii, Inga Bashkirova, Sergey Osipenko, Yury Kostyukevich, Е. Н. Николаев, Petr Popov
Abstract
We present a robust deep learning method CPORT to predict retention time from 3D molecular structures. It generates 4D tensor representations of 3D conformers, that are processed by a neural network with 3D convolutional and fully-connected layers.
Topics & Concepts
Deep learningConvolutional neural networkComputer scienceArtificial intelligenceRetention timeTensor (intrinsic definition)Pattern recognition (psychology)ChemistryMathematicsChromatographyGeometryMachine Learning in Materials ScienceComputational Drug Discovery MethodsProtein Structure and Dynamics