Skip to main content
Fig. 7 | BMC Bioinformatics

Fig. 7

From: Integration of probabilistic functional networks without an external Gold Standard

Fig. 7

ssNet evaluation. The functional prediction performance of ssNet, BioSystems and Gene Ontology-scored networks as measured by area under curve of AUC of receiver operator characteristic (ROC) plots. The error of the AUC was calculated using the standard error of the Wilcoxon statistic SE(W): not statistically significant (NSS); statistically significant (SS). A. BioSystems-derived (MP_GS) Gold Standard. Of 298 Gene Ontology biological processes, 325 had improved prediction using the ssNet network, and 73 using the MP_GS network. Of these changes 127 were statistically significant with 124 (98%) improved using LTP_GS. B. Gene ontology biological process terms annotating <10% of the genome (BP10_GS) Gold Standard. Of 398 Gene Ontology biological processes, 128 had improved prediction using the LTP_GS network, compared to 270 using BP10_GS. Of the changes just 20 were significant with 2 (10%) improved using LTP_GS. C. Gene ontology biological process terms annotating annotation <100 genes (BP100_GS) Gold Standard. Of 398 Gene Ontology biological processes, 102 had improved prediction using the LTP_GS network, compared to 296 using BP100_GS. Of the changes only 2 were significant, both of which were improved using BP100_GS

Back to article page