Description du projet
Tirer les leçons du passé constitue une nouvelle façon de réduire le bruit dans les images cryo-EM
Il y a quelques années encore, il était difficile d’obtenir des images des molécules biologiques sans les cristalliser, et toutes les molécules ne peuvent pas être formées en grands cristaux. La microscopie cryo-électronique (cryo-EM) permet de surmonter cet obstacle, en imagerie des molécules gelées en solution avec des faisceaux d’électrons, une technique récompensée par le prix Nobel de chimie en 2017. Le projet EM-PRIOR, financé par l’Union européenne, entend améliorer encore ce qui se fait de mieux en faisant appel à une technique du passé qui permettra d’améliorer la résolution du signal dans le bruit. La stratégie de débruitage informatique s’appuiera sur des réseaux neuronaux convolutionnels pour «apprendre» une grande partie de ce qui est déjà connu sur les structures biologiques. Cela permettra en fin de compte de mieux focaliser l’objet en question.
Objectif
Electron cryo-microscopy (cryo-EM) is the fastest growing technique to explore the structure of biological macromolecules. To limit radiation damage, images are recorded under low-dose conditions, which leads to high levels of experimental noise. To reduce the noise, one averages over many images, but this requires alignment and classification algorithms that are robust to the high levels of noise. When signal-to-noise ratios drop, cryo-EM 3D reconstruction algorithms become susceptible to overfitting, ultimately limiting their applicability. The algorithms can be improved by incorporating prior knowledge. The most widely used approaches in the field to date incorporate the prior knowledge that cryo-EM reconstructions are smooth in a Bayesian approach. However, in terms of information content, the smoothness prior reflects poorly compared to the vast amount of prior knowledge that structural biology has gathered in the past 50 years. I aim to develop a computational pipeline that can exploit much more of the existing knowledge about biological structures in the cryo-EM structure determination process. I will express this prior knowledge through convolutional neural networks that have been trained on many reconstructions, and use these networks in novel algorithms that optimise a regularised likelihood function. Similar approaches have excelled in image denoising and reconstruction in related areas. Preliminary results with simulated data suggest that significant improvements beyond the existing methods are possible, both in computational speed and in signal recovery capabilities. The proposed methods will enable faster computations with less user involvement, but most importantly, they will extend the applicability of cryo-EM structure determination to many more samples, alleviating the existing experimental requirements of particle size, ice thickness and sample purity.
Champ scientifique
Programme(s)
Régime de financement
MSCA-IF - Marie Skłodowska-Curie Individual Fellowships (IF)Coordinateur
SN2 1FL Swindon
Royaume-Uni