Machine learning for protein folding and dynamics

Abstract

Many aspects of the study of protein folding and dynamics have been affected by the recent advances in machine learning. Methods for the prediction of protein structures from their sequences are now heavily based on machine learning tools. The way simulations are performed to explore the energy landscape of protein systems is also changing as force-fields are started to be designed by means of machine learning methods. These methods are also used to extract the essential information from large simulation datasets and to enhance the sampling of rare events such as folding/unfolding transitions. While significant challenges still need to be tackled, we expect these methods to play an important role on the study of protein folding and dynamics in the near future. We discuss here the recent advances on all these fronts and the questions that need to be addressed for machine learning approaches to become mainstream in protein simulation.

DiffNets: deep learning the structural determinants of proteins biochemical properties by comparing different structural ensembles

“…Standard autoencoders have been used in many applications to MD simulation data. 4,[30][31][32][33][34][35][36][37][38][39][40][41] They connect two separate neural networks, an encoder network and a decoder network, to perform an unsupervised dimensionality reduction on input data (e.g. a protein structure from a frame of an MD simulation).…”

Confronting pitfalls of AI-augmented molecular dynamics using statistical physics

“…To conclude, we have introduced a new approach to sieve out the spurious solutions from AIaugmented enhanced sampling simulations. 37,38 AI-based approaches have had indisputable impact across sciences, including their use in enhancing the efficiency of molecular simulations.…”

“…35,36 Artificial intelligence (AI) potentially provides a systematic means to differentiate signal from noise in generic data, and thus discover relevant CVs to accelerate the simulations. [37][38][39][40][41] A number of such AI-based approaches have been proposed recently [37][38][39]42,43 and remain the subject of extensive research. A common underlying theme in these methods is to exploit AI tools to gradually uncover the underlying effective geometry, parametrize it on-the-fly, and exploit it to bias the design of experiments with the MD simulator by emphasizing informative configuration space areas that have not been explored before.…”

A Periodic System of Supramolecular Elements

“…[46] Furthermore,r ecent advances in machine learning have successfully provided reduced models to reproduce the equilibrium thermodynamics of macromolecules with less computational time compared to the computationally expensive atomistic or ab initio molecular dynamics simulations. [47] It is,i ndeed, expected that advances in artificial intelligence and machine learning will already open up entirely new perspectives in the next couple of years for the de novo design of synthetic macromolecules by reasonably accurate predictions of their energy landscapes. [48] With this information, synthetic chemists can avoid the time-consuming trial-anderror approach in the laboratory and directly synthesize the desired well-folded functional macromolecules predicted by theory.L ikewise,b ym eans of correctly predicted surface properties,t he intermolecular interactions and the selfassembly of larger molecules through multivalent interactions can be tailored, which will revolutionize both the life [47] and materials sciences.…”