PFP-RFSM: Protein fold prediction by using random forests and sequence motifsReport as inadecuate




PFP-RFSM: Protein fold prediction by using random forests and sequence motifs - Download this document for free, or read online. Document in PDF available to download.

Proteintertiary structure is indispensible in revealing the biological functions ofproteins. De novo perdition ofprotein tertiary structure is dependent on protein fold recognition. This studyproposes a novel method for prediction of protein fold types which takes primarysequence as input. The proposed method, PFP-RFSM, employsa random forest classifier and a comprehensive feature representation, includingboth sequence and predicted structure descriptors. Particularly, wepropose a method for generation of features based on sequence motifs and thosefeatures are firstly employed in protein fold prediction. PFP-RFSM and tenrepresentative protein fold predictors are validated in a benchmark datasetconsisting of 27 fold types. Experiments demonstrate that PFP-RFSM outperformsall existing protein fold predictors and improves the success rates by 2%-14%.The results suggest sequence motifs are effective in classification andanalysis of protein sequences.

 

KEYWORDS

Protein Fold; Structure Analysis; Random Forest; Sequence Motifs

Cite this paper

Li, J. , Wu, J. and Chen, K. 2013 PFP-RFSM: Protein fold prediction by using random forests and sequence motifs. Journal of Biomedical Science and Engineering, 6, 1161-1170. doi: 10.4236-jbise.2013.612145.





Author: Junfei Li, Jigang Wu, Ke Chen

Source: http://www.scirp.org/



DOWNLOAD PDF




Related documents