KBbox: Methods

Introduction

Reweighted autoencoded variational Bayes for enhanced sampling is an enhanced sampling method based on deep learning.

Reweighted autoencoded variational Bayes for enhanced sampling (RAVE) uses iterations between short molecular dynamics simulations and deep learning to learn a probability distribution along a latent space and a physically interpretable progress coordinate to enhance sampling. The iterations are performed until converged estimates of thermodynamic observables are obtained.

Example Cases

For examples of previously performed studies in which Reweighted autoencoded variational Bayes for enhanced sampling was the primary method used, see the following example cases:

Toward Achieving Efficient and Accurate Ligand-Protein Unbinding with Deep Learning and Molecular Dynamics through RAVE.
Reweighted autoencoded variational Bayes for enhanced sampling (RAVE).

Reweighted autoencoded variational Bayes for enhanced sampling was also used in the following examples:

A combination of machine learning and infrequent metadynamics to efficiently predict kinetic rates, transition states, and molecular determinants of drug dissociation from G protein-coupled receptors.

Molecular Simulation

Reweighted autoencoded variational Bayes for enhanced sampling

Introduction

Example Cases