B-factor profile prediction for RNA flexibility using support vector machines.

Journal: Journal of computational chemistry
Published Date: Mar 30, 2018

Abstract

Determining the flexibility of structured biomolecules is important for understanding their biological functions. One quantitative measurement of flexibility is the atomic Debye-Waller factor or temperature B-factor. Most existing studies are limited to temperature B-factors of proteins and their prediction. Only one method attempted to predict temperature B-factors of ribosomal RNA. Here, we developed and compared machine-learning techniques in prediction of temperature B-factors of RNAs. The best model based on Support Vector Machines yields Pearson's correction coefficient at 0.51 for fivefold cross validation and 0.50 for the independent test. Analysis of the performance indicates that the model has the best performance on rRNAs, tRNAs, and protein-bound RNAs, for long chains in particular. The server is available at http://sparks-lab.org/server/RNAflex. © 2017 Wiley Periodicals, Inc.

Authors

  • Ivantha Guruge
    School of Information and Communication Technology and Institue for Glycomics, Griffith University, Parklands Drive, Southport, Queensland, 4215, Australia.
  • Ghazaleh Taherzadeh
    School of Information and Communication Technology, Griffith University, Parklands Drive, Southport, Queensland, 4215, Australia.
  • Jian Zhan
    School of Information and Communication Technology and Institue for Glycomics, Griffith University, Parklands Drive, Southport, Queensland, 4215, Australia.
  • Yaoqi Zhou
    Institute of Systems and Physical Biology, Shenzhen Bay Laboratory, Shenzhen, Guangdong, 518106, China. Electronic address: zhouyq@szbl.ac.cn.
  • Yuedong Yang
    Institute for Glycomics and School of Information and Communication Technique, Griffith University, Parklands Dr. Southport, QLD 4222, Australia.

Keywords

External Resources

Popular Topics
Recent Journals