Past Awardee

Protein Structure Prediction using Deep Neural Networks

Jian Peng

College: Grainger College of Engineering
Award year: 2016-2017

The overall goal of this project is to develop a data-driven, deep-learning approach for protein structure prediction. Traditional approaches for protein 3D structure prediction are either based on comparative modeling or through ab initio folding. Instead, Peng proposes a research plan aiming to largely explore the protein conformational space and infer an accurate scoring function for evaluating predicted protein structures. Applying the existing protein structure prediction algorithms will generate a massive dataset including predicted protein models and randomly perturbed near-native decoys for all single-domain protein. Based on this dataset, we will develop a novel structure motif-based deep neural network to infer the hidden sequence-structure relationship and assess the structural quality of predictions. Further, we will apply this deep neural network to boost existing structure prediction algorithms.