Fig. 6
From: A novel method to predict essential proteins based on tensor and HITS algorithm
Jackknife curves of ten methods. The prediction performance of HEPT and nine other competing methods (DC, IC, SC, BC, CC, NC, PeC, CoEWC, and POEM) based on protein data are validated by the jackknife methodology. Moreover, the 10 random classifications were drawn for comparison. The x-axis represents the proteins in PPI network ranked by HEPT and nine other methods, ranked from left to right as strongest to weakest prediction of essentiality. The y-axis is the accumulated count of essential proteins encountered as moving from left to right through the ranked. The areas under the curve for HEPT and the other methods are used for comparing their prediction performance. a The comparison results of HEPT, DC, IC, and SC. b The comparison results of HEPT, BC, CC, and NC. c The comparison results of HEPT and other three methods: PeC, CoEWC, and POEM