Functional Protein Structure Annotation Using a Deep Convolutional Generative Adversarial Network

TL;DR

This paper presents a novel application of Deep Convolutional Generative Adversarial Networks (DCGANs) to classify and annotate functional protein structures from 3D data, improving robustness and aiding protein structure prediction.

Contribution

The study introduces a DCGAN-based method for classifying protein structures by encoding them in a grid format, demonstrating effective discrimination between native and decoy structures.

Findings

DCGAN can classify protein structures robustly.

Loss converges to a local minimum during training.

The method discriminates native from decoy structures effectively.

Abstract

Identifying novel functional protein structures is at the heart of molecular engineering and molecular biology, requiring an often computationally exhaustive search. We introduce the use of a Deep Convolutional Generative Adversarial Network (DCGAN) to classify protein structures based on their functionality by encoding each sample in a grid object structure using three features in each object: the generic atom type, the position atom type, and its occupancy relative to a given atom. We train DCGAN on 3-dimensional (3D) decoy and native protein structures in order to generate and discriminate 3D protein structures. At the end of our training, loss converges to a local minimum and our DCGAN can annotate functional proteins robustly against adversarial protein samples. In the future we hope to extend the novel structures we found from the generator in our DCGAN with more samples to explore more granular functionality with varying functions. We hope that our effort will advance the field of protein structure prediction.