Transfer Learning for Protein Structure Classification at Low Resolution
This provides a proof of concept for high-speed, low-cost protein structure classification, which could benefit researchers in structural biology by reducing reliance on costly analytical methods.
The study tackled the problem of expensive protein structure determination by demonstrating accurate (≥80%) predictions of protein class and architecture from low-resolution (>3Å) structures using a deep convolutional neural network trained on high-resolution data.
Structure determination is key to understanding protein function at a molecular level. Whilst significant advances have been made in predicting structure and function from amino acid sequence, researchers must still rely on expensive, time-consuming analytical methods to visualise detailed protein conformation. In this study, we demonstrate that it is possible to make accurate ($\geq$80%) predictions of protein class and architecture from structures determined at low ($>$3A) resolution, using a deep convolutional neural network trained on high-resolution ($\leq$3A) structures represented as 2D matrices. Thus, we provide proof of concept for high-speed, low-cost protein structure classification at low resolution, and a basis for extension to prediction of function. We investigate the impact of the input representation on classification performance, showing that side-chain information may not be necessary for fine-grained structure predictions. Finally, we confirm that high-resolution, low-resolution and NMR-determined structures inhabit a common feature space, and thus provide a theoretical foundation for boosting with single-image super-resolution.