Prediction of Interacting Protein Pairs from Sequence Using a Bayesian Method
With the development of bioinformatics, more and more protein sequence information has become available. Meanwhile, the number of known protein–protein interactions (PPIs) is still very limited. In this article, we propose a new method for predicting interacting protein pairs using a Bayesian method based on a new feature representation. We trained our model using data on 6,459 PPI pairs from the yeast Saccharomyces cerevisiae core subset. Using six species of DIP database, our model demonstrates an average prediction accuracy of 93.67%. The result showed that our method is superior to other methods in both computing time and prediction accuracy.
KeywordsProtein–protein interactions Feature vector Bayesian method Amino acid composition
Database of interacting proteins
Protein data bank
Support vector machine
Expression profile reliability
Paralogous verification method
Receiver operating characteristics
The area under the curve
This work was supported partially by the Project of Provincial Natural Scientific Fund from the Bureau of Education of AnHui Provience(Nos. KJ2007B066, KJ2007A087).
- 4.Cooper GF, Herskovits E (1992) Mach Learn 9(4):309–347Google Scholar
- 10.Krigbaum WR, Komoriya A (1979) Biochim Biophys Acta 576(1):204–228Google Scholar
- 15.Wang CS, Cheng JX, Su SB, Xu DZ (2008) ADMA 2008, LNAI 5139:207–216Google Scholar
- 16.Witten IH, Frank E (2005) Data mining: practical machine learning tools and techniques, 2nd edn. Morgan Kaufmann, San FranciscoGoogle Scholar