End-to-End Differentiable Learning of Protein Structure

• Published in: Cell systems Vol. 8; no. 4; pp. 292 - 301.e3
• Main Author: AlQuraishi, Mohammed
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 24.04.2019
• Subjects: biophysics; co-evolution; deep learning; geometric deep learning; homology modeling; machine learning; protein design; protein folding; protein structure prediction; structural biology; deep learning; homology modeling; geometric deep learning; protein folding; structural biology; machine learning; protein structure prediction; biophysics; protein design; co-evolution
• ISSN: 2405-4712; 2405-4720; 2405-4720
• DOI: 10.1016/j.cels.2019.03.006

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 Å; 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. [Display omitted] •Neural network predicts protein structure from sequence without using co-evolution•Model replaces structure prediction pipelines with one mathematical function•Achieves state-of-the-art performance on novel protein folds•Learns a low-dimensional representation of protein sequence space Prediction of protein structure from sequence is important for understanding protein function, but it remains very challenging, especially for proteins with few homologs. Existing prediction methods are human engineered, with many complex parts developed over decades. We introduce a new approach based entirely on machine learning that predicts protein structure from sequence using a single neural network. The model achieves state-of-the-art accuracy and does not require co-evolution information or structural homologs. It is also much faster, making predictions in milliseconds versus hours or days, which enables new applications in drug discovery and protein design.