Skip to main content
Fig. 1 | BMC Bioinformatics

Fig. 1

From: INBIA: a boosting methodology for proteomic network inference

Fig. 1

Inference Network Based on iRefIndex Analysis (INBIA) pipeline. We selected 14 inference methods and applied them to the 16 RPPA datasets in order to achieve PPI predictions (a). Networks are inferred following two approaches: (i) the predictions have been compared with the gold standard, iRefIndex, in order to obtain true positive (TP), false positive (FP), true negative (TN) and false negative (FN) values from which it was computed F-measure, a weighted combination of precision and recall (b). The best method for each cancer type was selected and its associated network was returned (c); (ii) for each cancer type, an ensemble network was created by computing all possible PPIs generated from genes associated to TCPA proteins and then a score from the ensemble of best methods (BM) that represents the percentage of BMs within the ensemble which have predicted that PPI (d). The methods named M1, M2, …M14 correspond to those reported in Additional file 1:Table S2

Back to article page