Skip to main content

Advertisement

Table 3 Cross verification with the yeast datasets

From: A domain-based approach to predict protein-protein interactions

Training set Test set   Explanation Ratio (%)a
867 pmt 344 pmt Positive 99.3
inclusive closed Negative 95.4
344 pmt 867 pmt Positive 69.9
closed inclusive Negative 64.3
2466 pmt 1216 pmt Positive 98.6
inclusive closed Negative 96.0
1216 pmt 2466 pmt Positive 76.7
closed inclusive Negative 66.5
5095 pmt 3060 pmt Positive 99.3
inclusive closed Negative 95.6
3060 pmt closed 5095 pmt inclusive Positive 84.5
   Negative 67.8
867 pmt Uetz et al. b Core 78
inclusive   Full 75
344 pmt Uetz et al. b Core 78
closed   Full 75
  1. a Explanation ratios were calculated by using the indicated yeast datasets as the testing data after the domain-domain interaction score parameters were optimized using the reported MIPS set as the training data in the DomainGA runs.
  2. b Explanation ratios were calculated by using the indicated closed Uetz et al. yeast datasets [1] as testing data. Uetz et al. datasets http://dip.doe-mbi.ucla.edu/dip/Download.cgi contain only positive PPIs so test statistics were computed only for the positive predictions. Yeast Core set originally contained 5952 positive PPIs of which 74 were retained after selecting the entries according to their relevance to the parameter set utilized in optimizations. In the Yeast Full dataset case the corresponding total and retained values were 17471 and 119.