B‐factor profile prediction for RNA flexibility using support vector machines. Issue 8 (21st November 2017)

• Record Type: Journal Article
• Authors: Guruge, Ivantha; Taherzadeh, Ghazaleh; Zhan, Jian; Zhou, Yaoqi; Yang, Yuedong
• Is Part Of: Journal of computational chemistry. Volume 39:Issue 8(2018)
• Page Start: 407
• Page End: 411
• Publication Date: 2017-11-21
• Subjects: RNA flexibility -- temperature B‐factor -- support vectors regression; Chemistry -- Data processing -- Periodicals; 542.85
• DOI: 10.1002/jcc.25124
• Languages: English
• ISSNs: 0192-8651

Abstract

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 athttp://sparks-lab.org/server/RNAflex . © 2017 Wiley Periodicals, Inc. Abstract : Similar to proteins, dynamics of RNAs plays a significant role in their functions. One measure of RNA structural flexibility is temperature B ‐factor of RNA structures determined by X‐ray crystallography. Here, we developed a sequence‐based prediction of RNA B ‐factor called RNAflex with reasonable accuracy. The method should be useful for locating RNA flexible regions directly from sequences. This is important as most RNAs do not have known structures.