Protein Secondary Structure Assignments and Their Usefulness for Dihedral Angle Prediction
We present and compare different protein secondary structure assignment methods and the effect of their use in dihedral angle prediction. It is found that consensus reassignment of secondary structure tends to improve the accuracy of secondary structure prediction. However, it is less useful for the prediction of the dihedral angles than a better defined reassignment method based on angle values. Considering reassigned residues, we find them to be hard to predict. We find the most significant improvement for reassigned residues is due to our new reassignment method. This method also reassigns a smaller number of residues as compared to consensus methods. We additionally find that improvements to the accuracy of dihedral angle prediction is due both to single residue and local-neighborhood effects.
KeywordsDihedral angle prediction Secondary structure prediction Secondary structure assignment Protein structure Machine learning
We gratefully acknowledge support from National Science Foundation grant DBI 1661391, and Bridge funds provided by The Research Institute at Nationwide Children’s Hospital.
- 5.Sikorski, A.: Prediction of protein secondary structure by neural networks: Encoding short and long range patterns of amino acid packing. Acta. Biochim. Pol., 39(4), (1992)Google Scholar
- 7.Rost, B., Sander, C., Schneider, R.: Phd-an automatic mail server for protein secondary structure prediction. Comput. Appl. Biosci.: CABIOS 10(1), 53–60 (1994)Google Scholar
- 16.Kolinski, A.: Protein modeling and structure prediction with a reduced representation. Acta Biochim. Pol.-English Edition- 51, 349–372 (2004)Google Scholar
- 26.Kouza, M., Faraggi, E., Kolinski, A., Kloczkowski, A.: The gor method of protein secondary structure prediction and its application as a protein aggregation prediction tool. In: Prediction of Protein Secondary Structure, pp. 7–24. Springer (2017 )Google Scholar
- 27.Rost, B.: TOPITS: threading one-dimensional predictions into three-dimensional structures. In: Third international conference on intelligent systems for molecular biology, pp. 314–321. AAAI Press (1995)Google Scholar