Surface pattered with 3D soft mushroom features showing adhesion via mechanical interlocking of mushroom features onto a textile fabric. Copyright: Wageningen University & Research
3D Printed Bioinspired Surface Patterning for Soft Robotics
7th August 2020
Experimental maps of the local dynamics over 1 s for a biopolymer under creep, measured by time- and space-resolved dynamic light scattering. Labels: time before failure. Copyright: University of Montpellier and CNRS
Creep Dynamics and Failure of a Biopolymer Gel
26th October 2021

Proteins occur in nature in enormous numbers and fulfil a huge range of biological tasks. Yet they are all simply made up of the same 20 amino acid building blocks, assembled into polymers and folded into a wide variety of shapes that determine their function. Proteins should however not be considered as a single atomic arrangement: they are flexible, exploring a continuous conformational space often described as a set of low energy states connected by higher energy transition paths. Current experimental techniques provide a good picture of the most stable conformations, but little on the transition path or intermediate states. Computational techniques such as molecular dynamics simulations can be used to characterize protein dynamics by sampling their conformational space. However, the odds a simulation will sample a specific conformation are inversely proportional to its energy, making the discovery of transition states a rare event.

Given the remarkable success of deep generative neural networks in generating believable synthetic images, videos and texts, we designed a neural network that, trained with a discrete set of structures produced via molecular simulations, can generate protein conformations. To ensure the network produces structures respecting physical laws, we also designed a new training procedure whereby we penalise high-energy conformations generated outside of the sampled space. As a result, our network attempts to generate transition paths of minimal energy. To demonstrate the usefulness of our approach, called molearn, we successfully challenged it with the prediction of the transition path between known conformations of the bacterial protein MurD.

Free access to molearn : www.github.com/degiacom/molearn

Read more:
Ramaswamy V.K. et al.,
Phys. Rev. X 11, 011052 (2021)

SoftComp partner:
Durham University

 

 

 

Schematic representation of our modelling pipeline. A neural network trained with an ensemble of protein conformations learns an internal model of their conformational space. This model can then be interrogated to generate new, plausible conformations. Copyright: Durham University
Schematic representation of our modelling pipeline. A neural network trained with an ensemble of protein conformations learns an internal model of their conformational space. This model can then be interrogated to generate new, plausible conformations. Copyright: Durham University
Interpolation between the open and closed state of the protein MurD, described in spherical coordinates. Unlike predictions based on principal components analysis (PCA), molearn generates a non-linear transition path closely resembling a known intermediate. Copyright: Durham University
Interpolation between the open and closed state of the protein MurD, described in spherical coordinates. Unlike predictions based on principal components analysis (PCA), molearn generates a non-linear transition path closely resembling a known intermediate. Copyright: Durham University
Research Gate
Research Gate