swMATH ID: 32927
Software Authors: Andreas Mardt, Luca Pasquali, Hao Wu, Frank Noé
Description: VAMPnets: Deep learning of molecular kinetics. There is an increasing demand for computing the relevant structures, equilibria and long-timescale kinetics of biomolecular processes, such as protein-drug binding, from high-throughput molecular dynamics simulations. Current methods employ transformation of simulated coordinates into structural features, dimension reduction, clustering the dimension-reduced data, and estimation of a Markov state model or related model of the interconversion rates between molecular structures. This handcrafted approach demands a substantial amount of modeling expertise, as poor decisions at any step will lead to large modeling errors. Here we employ the variational approach for Markov processes (VAMP) to develop a deep learning framework for molecular kinetics using neural networks, dubbed VAMPnets. A VAMPnet encodes the entire mapping from molecular coordinates to Markov states, thus combining the whole data processing pipeline in a single end-to-end framework. Our method performs equally or better than state-of-the art Markov modeling methods and provides easily interpretable few-state kinetic models.
Homepage: https://arxiv.org/abs/1710.06012
Source Code: https://github.com/markovmodel/deeptime/tree/master/vampnet
Keywords: Machine Learning; arXiv_stat.ML; Biological Physics; arXiv_physics.bio-ph; Chemical Physics; arXiv_physics.chem-ph; arXiv_physics.comp-ph
Related Software: PDE-Net; torchdiffeq; TensorFlow; SINDy; GAIO; PRMLT; Adam; AlexNet; ImageNet; SINDy-PI; DeepXDE; HODMD; odmd; DeepONet; PyDMD; rsvd; EnKF; U-Net; PyEMMA; MCTDH
Cited in: 22 Publications

Citations by Year