Unsupervised and Supervised Structure Learning for Protein Contact Prediction

TL;DR

This paper explores both unsupervised graphical models and supervised deep learning techniques to improve protein contact prediction, introducing a novel scoring system to evaluate contact prediction novelty.

Contribution

It presents a combined approach of unsupervised and supervised methods for protein contact prediction, along with a new scoring system for assessing prediction novelty.

Findings

Unsupervised graphical models with topology constraints improve contact prediction.

Supervised deep learning further enhances prediction accuracy.

A novel diversity score effectively measures the novelty of contact predictions.

Abstract

Protein contacts provide key information for the understanding of protein structure and function, and therefore contact prediction from sequences is an important problem. Recent research shows that some correctly predicted long-range contacts could help topology-level structure modeling. Thus, contact prediction and contact-assisted protein folding also proves the importance of this problem. In this thesis, I will briefly introduce the extant related work, then show how to establish the contact prediction through unsupervised graphical models with topology constraints. Further, I will explain how to use the supervised deep learning methods to further boost the accuracy of contact prediction. Finally, I will propose a scoring system called diversity score to measure the novelty of contact predictions, as well as an algorithm that predicts contacts with respect to the new scoring system.