What question did this study set out to answer?

The aim is to improve protein secondary structure prediction accuracy beyond current predictors using a novel deep learning approach.

January 11, 2016Open Access

Protein Secondary Structure Prediction Using Deep Convolutional Neural Fields

Key Points

The aim is to improve protein secondary structure prediction accuracy beyond current predictors using a novel deep learning approach.
Developed DeepCNF, a deep learning model integrating conditional neural fields for SS prediction.
Evaluated DeepCNF on CASP and CAMEO test datasets.
Compared performance with popular existing predictors.
Achieved ~84% Q3 accuracy, ~85% SOV score, and ~72% Q8 accuracy on test proteins.
Outperformed current leading predictors significantly, showing both improved accuracy and robustness.

Abstract

Protein secondary structure (SS) prediction is important for studying protein structure and function. When only the sequence (profile) information is used as input feature, currently the best predictors can obtain ~80% Q3 accuracy, which has not been improved in the past decade. Here we present DeepCNF (Deep Convolutional Neural Fields) for protein SS prediction. DeepCNF is a Deep Learning extension of Conditional Neural Fields (CNF), which is an integration of Conditional Random Fields (CRF) and shallow neural networks. DeepCNF can model not only complex sequence-structure relationship by a deep hierarchical architecture, but also interdependency between adjacent SS labels, so it is much more powerful than CNF. Experimental results show that DeepCNF can obtain ~84% Q3 accuracy, ~85% SOV score, and ~72% Q8 accuracy, respectively, on the CASP and CAMEO test proteins, greatly outperforming currently popular predictors. As a general framework, DeepCNF can be used to predict other protein structure properties such as contact number, disorder regions, and solvent accessibility.

Bookmark

View Full Paper