PCA-CMI: Path Consistency Algorithm based on Conditional Mutual Information

• Last updated: Jan. 18, 2013

Introduction#

Welcome to our website! This is a webpage for our paper "Inferring a protein interaction map of Mycobacterium tuberculosis based on sequences and interologs". Mycobacterium tuberculosis is a dangerous bacterium for human health. Extensive protein interactions will provide much information on biological processes to understand its living systems. In this paper, we constructed an integrated M. tuberculosis protein interaction network by machine learning and ortholog-based methods. Firstly, we developed a support vector machine (SVM) method to infer the protein interactions of tuberculosis H37Rv by gene sequence information. We tested our predictor in Escherichia coli and mapped the genetic codon features underlying protein interactions to M. tuberculosis. Moreover, the documented interactions of other 14 species are mapped to M. tuberculosis by the interolog method on protein sequence level. The ensemble protein interactions were validated by diverse functional linkages i.e., gene coexpression, evolutionary relationship and functional similarity, extracted from heterogeneous data sources. The accuracy and validation demonstrate the effectiveness and efficiency of our framework. Our methods can be straightforwardly extended to infer the protein interactions of other species.

Pay attention to the users: You can use and redistribute the data and software if you accept GNU General Public License (GPL).

Reference#

• Liu ZP, Wang J, Qiu YQ, Leung RK, Zhang XS, Tsui SK and Chen L: Inferring a protein interaction map of Mycobacterium tuberculosis based on sequences and interologs. BMC Bioinformatics, 13(Suppl 7):S6, 2012.

Software and Data:#

• mtbppi.rar