Machine learning approach for accurate backmapping of coarse-grained models to all-atom models
Yaxin An, Sanket A. Deshmukh
Abstract
Four different machine learning (ML) regression models: artificial neural network, k-nearest neighbors, Gaussian process regression and random forest were built to backmap coarse-grained models to all-atom models. The ML models showed better predictions than the existing backmapping approaches for selected structures, suggesting the applications of the ML models for backmapping.
Topics & Concepts
Atom (system on chip)Computer scienceArtificial intelligenceChemistryParallel computingMachine Learning in Materials ScienceX-ray Diffraction in CrystallographyBlock Copolymer Self-Assembly