Skip to main content

Table 3 Average AUPRC results (and standard deviations)

From: MOKPE: drug–target interaction prediction via manifold optimization based kernel preserving embedding

Methods

Data set

NR

GPCR

IC

E

Nearest Profile

0.427* (0.017)

0.275* (0.017)

0.209* (0.014)

0.225* (0.023)

Weighted Profile

0.380* (0.022)

0.231* (0.006)

0.193* (0.007)

0.116* (0.003)

LapRLS

0.367* (0.026)

0.219* (0.006)

0.177* (0.007)

0.110* (0.002)

DLapRLS

0.415* (0.026)

0.386 (0.008)

0.320 (0.017)

0.365 (0.018)

RLS-WNN

0.558 (0.023)

0.369 (0.012)

0.342 (0.019)

0.380 (0.022)

KBMF2K

0.491* (0.020)

0.380 (0.010)

0.316 (0.016)

0.249 (0.017)

CMF

0.528* (0.019)

0.400 (0.008)

0.355 (0.018)

0.391 (0.016)

WGRMF

0.592 (0.018)

0.420 (0.011)

0.378 (0.022)

0.409 (0.019)

GRGMF

0.506* (0.015)

0.367 (0.009)

0.366 (0.023)

0.363 (0.026)

HGBI

0.275* (0.024)

0.204* (0.011)

0.115* (0.009)

0.107* (0.006)

MOKPE

0.578 (0.023)

0.374 (0.008)

0.321 (0.015)

0.244 (0.016)

  1. * indicates that MOKPE significantly outperforms this method with \(p < 0.05\) using Mann–Whitney test. The highest result in each column is bolded and the second best is underlined
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us