Sigma profiles in deep learning: towards a universal molecular descriptor
Dinis O. Abranches, Yong Zhang, Edward J. Maginn, Yamil J. Colón
Abstract
This work showcases the remarkable ability of sigma profiles to function as molecular descriptors in deep learning. The sigma profiles of 1432 compounds are used to train convolutional neural networks that accurately correlate and predict a wide range of physicochemical properties. The architectures developed are then exploited to include temperature as an additional feature.
Topics & Concepts
SigmaConvolutional neural networkDeep learningArtificial intelligenceFeature (linguistics)Function (biology)Range (aeronautics)Computer sciencePattern recognition (psychology)Biological systemMaterials sciencePhysicsBiologyQuantum mechanicsPhilosophyComposite materialEvolutionary biologyLinguisticsComputational Drug Discovery MethodsMachine Learning in Materials ScienceCrystallography and molecular interactions