Can I read Interpretable Embeddings From Molecular Simulations Using Gaussian Mixture Variational Autoencoders on EtoBox?

Interpretable Embeddings From Molecular Simulations Using Gaussian Mixture Variational Autoencoders by Varolgunes, Yasemin Bozkurt; Bereau, Tristan; Rudzinski, Joseph F. is a scholarly article available to read on EtoBox.

What is Interpretable Embeddings From Molecular Simulations Using Gaussian Mixture Variational Autoencoders about?

Extracting insight from the enormous quantity of data generated from molecular simulations requires the identification of a small number of collective variables whose corresponding low-dimensional free-energy landscape retains the essential features of the underlying system. Data-driven techniques provide a systematic route to constructing this landscape, without the need for extensive a priori intuition into the relevant driving forces. In particular, autoencoders are powerful tools for dimensionality reduction, as they naturally force an information bottleneck and, thereby, a low-dimensional embedding of the essential features. While variational autoencoders ensure continuity of the embedding by assuming a unimodal Gaussian prior, this is at odds with the multi-basin free-energy landscapes that typically arise from the identification of meaningful collective variables. In this work, we incorporate this physical intuition into the prior by employing a Gaussian mixture variational autoencoder (GMVAE), which encourages the separation of metastable states within the embedding. The GMVAE performs dimensionality reduction and clustering within a single unified framework, and is capable

Author

Varolgunes, Yasemin Bozkurt; Bereau, Tristan; Rudzinski, Joseph F.

Published

2019

Language

EN