2-AIN-506 a 2-AIN-252: Seminár z bioinformatiky (2) a (4)
Leto 2020

Mohammed AlQuraishi. End-to-End Differentiable Learning of Protein Structure. Cell Syst, 8(4):292-301. 2019.

Download preprint: not available

Download from publisher: https://www.biorxiv.org/content/10.1101/265231v2 PubMed

Related web page: not available

Bibliography entry: BibTeX


Predicting protein structure from sequence is a central challenge of
biochemistry. Co-evolution methods show promise, but an explicit
sequence-to-structure map remains elusive. Advances in deep learning that replace
complex, human-designed pipelines with differentiable models optimized end to end
suggest the potential benefits of similarly reformulating structure prediction.
Here, we introduce an end-to-end differentiable model for protein structure
learning. The model couples local and global protein structure via geometric
units that optimize global geometry without violating local covalent chemistry.
We test our model using two challenging tasks: predicting novel folds without
co-evolutionary data and predicting known folds without structural templates. In 
the first task, the model achieves state-of-the-art accuracy, and in the second, 
it comes within 1-2 A; competing methods using co-evolution and experimental
templates have been refined over many years, and it is likely that the
differentiable approach has substantial room for further improvement, with
applications ranging from drug discovery to protein design.