Prediction of the disulphide bonding state of cysteines in proteins using Conditional Random Fields. (1st January 2011)

• Record Type: Journal Article
• Authors: Shoombuatong, Watshara; Traisathit, Patrinee; Prasitwattanaseree, Sukon; Tayapiwatana, Chatchai; Cutler, Robert; Chaijaruwanich, Jeerayut
• Is Part Of: International journal of data mining and bioinformatics. Volume 5:Number 4(2011)
• Page Start: 449
• Page End: 464
• Publication Date: 2011-01-01
• Subjects: cysteines-bonding state -- CRFs -- conditional random fields -- bioinformatics -- machine learning; Data mining -- Periodicals; Bioinformatics -- Periodicals; 006.312
• DOI: 10.1504/IJDMB.2011.041559
• Languages: English
• ISSNs: 1748-5673

Abstract

The formation of disulphide bonds between cysteines plays a major role in protein folding, structure, function and evolution. Many computational approaches have been used to predict the disulphide bonding state of cysteines. In our work, we developed a novel method based on Conditional Random Fields (CRFs) to predict the disulphide bonding state from protein primary sequence, predicted secondary structures and predicted relative solvent accessibilities (all-state information). Our experiments obtain 84% accuracy, 88% precision and 94% recall, using all-state information. However, our results show essentially identical results when using protein sequence and predicted relative solvent accessibilities in the absence of secondary structure.