The ability to make sense of the massive amounts of high-dimensional data generated from molecular dynamics simulations is heavily dependent on the knowledge of a low-dimensional manifold (parameterized by a reaction coordinate or RC) that typically distinguishes between relevant metastable states, and which captures the relevant slow dynamics of interest. Methods based on machine learning and artificial intelligence have been proposed over the years to deal with learning such low-dimensional manifolds, but they are often criticized for a disconnect from more traditional and physically interpretable approaches. To deal with such concerns, in this work we propose a deep learning based state predictive information bottleneck approach to learn the RC from high-dimensional molecular simulation trajectories. We demonstrate analytically and numerically how the RC learnt in this approach is connected to the committor in chemical physics and can be used to accurately identify transition states. A crucial hyperparameter in this approach is the time delay or how far into the future the algorithm should make predictions about. Through careful comparisons for benchmark systems, we demonstrate that this hyperparameter choice gives useful control over how coarse-grained we want the metastable state classification of the system to be. We thus believe that this work represents a step forward in systematic application of deep learning based ideas to molecular simulations.
While AlphaFold2 is rapidly being adopted as a new standard in protein structure predictions, it is limited to single structures. This can be insufficient for the inherently dynamic world of biomolecules. In this Letter, we propose AlphaFold2-RAVE, an efficient protocol for obtaining Boltzmann-ranked ensembles from sequence. The method uses structural outputs from AlphaFold2 as initializations for artificial intelligence-augmented molecular dynamics. We release the method as an open-source code and demonstrate results on different proteins.
In the short time since it has appeared, AlphaFold2 (AF2) has been widely adopted as a new standard in accurate and fast protein structure prediction starting from any arbitrary sequence of amino acids. However, AF2 maps a single sequence to a single structure, and even with recently proposed modifications that add conformational diversity, it is arguably devoid of thermodynamics. In this working paper we demonstrate an efficient protocol that uses the structural diversity from AF2 as a starting point to perform Artificial Intelligence augmented enhanced molecular dynamics simulations. Specifically we use the “Reweighted Autoencoded Variational Bayes for Enhanced Sampling (RAVE)” method as post-processing on AF2, and thus the protocol shown here is called AlphaFold2-RAVE. These simulations expand upon the results from AF2 ranking them as per their correct Boltzmann weights. This schema for going from sequence to Boltzmann weighted ensemble of structures is demonstrated here for a small cold-shock protein, and will be expanded to include many more sequences together with an easy-to-use open-source code.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.