Abstract
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.
Competing Interest Statement
The authors declare the following competing financial interest: P.T. is a consultant to Schrodinger, Inc.