DeepSPInN – deep reinforcement learning for molecular structure prediction from infrared and <sup>13</sup> C NMR spectra
Sriram Devata, Bhuvanesh Sridharan, Sarvesh Mehta, Yashaswi Pathak, Siddhartha Laghuvarapu, Girish Varma, U. Deva Priyakumar
Abstract
DeepSPInI is a deep reinforcement learning method that predicts the molecular structure when given infrared and 13 C nuclear magnetic resonance spectra with an accuracy of 91.5%.
Topics & Concepts
Carbon-13 NMRReinforcement learningNuclear magnetic resonanceInfraredSpectral lineArtificial intelligenceMaterials scienceComputer sciencePhysicsOpticsQuantum mechanicsSpectroscopy and Chemometric Analyses