Learning interpretable protein dynamics using Geometric Deep Learning

Project Webpage | Paper Version

MSc Project 2 for Bioinformatics degree at Imperial College London looking into learning interpretable protein dynamics using Geometric Deep Learning.

Getting Started

Inspiration

With work is large inspired by two papers and I give much credit to the authors:

1. Greener, Joe G., and David T. Jones. "Differentiable molecular simulation can learn all the parameters in a coarse-grained force field for proteins." bioRxiv (2021). - paper

   This work showed that

2. Sanchez-Gonzalez, Alvaro, et al. "Learning to simulate complex physics with graph networks." International Conference on Machine Learning. PMLR, 2020. - paper

Prerequisites used

Python packages used for this project

matplotlib
pandas
numpy
biopython

Author

• Charles Harris - cch1999 - [email protected]

License

Distributed under the MIT License. See LICENSE for more information.

Acknowledgments

• My thanks go to Michael Bronstein and Bruno Correia for their supervision and generous access to computational resources.

• I would also like to thank Freyr Sverrisson for his guidance throughout the project, Fabrizio Frasca for the discussions on simplicial complexes, and Joe Greener for providing the RMSF data for his model.