A type-2 fuzzy data fusion approach for building reliable weighted protein interaction networks with application in protein complex detection

Detecting the protein complexes is an important task in analyzing the protein interaction network. Although many algorithms predict protein complexes in different ways, surveys on the interaction networks indicate that about 50 percent of detected interactions are false positives. Consequently, the accuracy of existing methods needs to be improved. In this paper we propose a novel algorithm to detect the protein complexes in ‘noisy’ protein interaction data. First, we integrate several biological data sources to determine the reliability of each interaction and determine more accurate weights for the interactions.
Source: Computers in Biology and Medicine - Category: Bioinformatics Authors: Source Type: research