End-to-End Differentiable Learning of Protein Structure

37 Pages Posted: 28 Aug 2018 Publication Status: Review Complete

See all articles by Mohammed AlQuraishi

Mohammed AlQuraishi

Harvard University - Department of Systems Biology



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 report the first end-to-end differentiable model of protein structure. 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 1-2Å; 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.

Suggested Citation

AlQuraishi, Mohammed, End-to-End Differentiable Learning of Protein Structure (2018). Available at SSRN: https://ssrn.com/abstract=3239970 or http://dx.doi.org/10.2139/ssrn.3239970
This version of the paper has not been formally peer reviewed.

Mohammed AlQuraishi (Contact Author)

Harvard University - Department of Systems Biology ( email )

Boston,, MA 02115
United States

Click here to go to Cell.com

Paper statistics

Abstract Views
PlumX Metrics