Journal
BMC BIOINFORMATICS
Volume 19, Issue -, Pages -Publisher
BIOMED CENTRAL LTD
DOI: 10.1186/s12859-018-2031-7
Keywords
Torsion angle; Intrinsically disordered region; Model quality assessment; Deep learning neural network
Categories
Funding
- National Natural Science Foundation of China (NSFC) [11701296]
- National Natural Science Foundation of China [U1611261, 61772566]
- program for Guangdong Introducing Innovative and Entrepreneurial Teams [2016ZT06D211]
- National Health and Medical Research Council of Australia [1059775, 1083450]
- Australian Research Council's Linkage Infra-structure, Equipment and Facilities funding scheme [LE150100161]
- ARC Discovery grant [DP180102060]
Ask authors/readers for more resources
Background: Protein structure can be described by backbone torsion angles: rotational angles about the N-C alpha bond (phi) and the C alpha-C bond (psi) or the angle between C alpha(i-1)-C alpha(i)-C alpha(i + 1) (theta) and the rotational angle about the C alpha(i)-C alpha(i + 1) bond (tau). Thus, their accurate prediction is useful for structure prediction and model refinement. Early methods predicted torsion angles in a few discrete bins whereas most recent methods have focused on prediction of angles in real, continuous values. Real value prediction, however, is unable to provide the information on probabilities of predicted angles. Results: Here, we propose to predict angles in fine grids of 5 degrees by using deep learning neural networks. We found that this grid-based technique can yield 2-6% higher accuracy in predicting angles in the same 5 degrees bin than existing prediction techniques compared. We further demonstrate the usefulness of predicted probabilities at given angle bins in discrimination of intrinsically disorder regions and in selection of protein models. Conclusions: The proposed method may be useful for characterizing protein structure and disorder. The method is available at http://sparks-lab.org/server/SPIDER2/ as a part of SPIDER2 package.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available