Machine learning vs protein conformational spaces - 31 May 2022

Speaker Dr Matteo Degiacomi, Associate Professor, EPSRC Research Fellow, Department of Physics, Durham University

Title Machine learning vs protein conformational spaces

Host Franca Fraternali

Abstract Determining the different conformational states of a protein and the transition paths between them is key to fully understanding the relationship between biomolecular structure and function. In this seminar, I will discuss how a neural network can learn a continuous conformational space representation from example structures produced by molecular dynamics simulations. I will then show how such representation, obtained via our software molearn (1), can be leveraged to predict putative protein transition states (2), or to generate conformations useful in the context of flexible protein-protein docking (3).

1. ^{https://github.com/Degiacomi-Lab/molearn}
2. ^{V.K. Ramaswamy et al., Learning Protein Conformational Space with Convolutions and Latent Interpolations. Physical Review X (2021).}
3. ^{M.T. Degiacomi, Coupling Molecular Dynamics and Deep Learning to Mine Protein Conformational Space. Structure (2019).}