puc-header

Coupling Molecular Dynamics and Deep Learning to Mine Protein Conformational Space

34 Pages Posted: 18 Jan 2019 Sneak Peek Status: Published

See all articles by Matteo T. Degiacomi

Matteo T. Degiacomi

Durham University - Department of Chemistry

More...

Abstract

Flexibility is often a key determinant of protein function. In order to elucidate the link between their molecular structure and role in an organism, computational techniques such as molecular dynamics can be leveraged to characterize their conformational space. Extensive sampling is however required to obtain reliable results, useful to rationalize experimental data or predict outcomes before experiments are carried out. We demonstrate that a generative neural network trained on protein structures produced by molecular simulation can be used to obtain new, plausible conformations complementing and extending pre-existing ones. To demonstrate this, we show that a trained neural network can be exploited in a protein-protein docking scenario to predict large conformational changes upon binding. Overall, this work shows that neural networks can be used as an exploratory tool for the study of molecular conformational space.

Suggested Citation

Degiacomi, Matteo T., Coupling Molecular Dynamics and Deep Learning to Mine Protein Conformational Space (2018). Available at SSRN: https://ssrn.com/abstract=3213915 or http://dx.doi.org/10.2139/ssrn.3213915
This is a paper under consideration at Cell Press and has not been peer-reviewed.

Matteo T. Degiacomi (Contact Author)

Durham University - Department of Chemistry ( email )

Old Elvet
Mill Hill Lane
Durham, DH1 3HP
United Kingdom

Click here to go to Cell.com

Go to Cell.com

Paper statistics

Abstract Views
456
Downloads
25