Skip to main content

Table 6 AUC values of different algorithms under \(CV_d\) scenario

From: Graph regularized non-negative matrix factorization with \(L_{2,1}\) norm regularization terms for drug–target interactions prediction

Method

NR

GPCR

IC

E

iPALM-DLMF

0.886132 (0.0184)

0.87153 (0.0074)

0.814679 (0.0150)

0.834224 (0.0035)

iPALM-DLMF (without NNDSVD)

0.880843 (0.0264)

0.855862 (0.0074)

0.825428 (0.0167)

0.817143 (0.0085)

iPALM-DLMF ( \(\lambda _d\)=0)

0.620998 (0.0543)

0.639598 (0.0268)

0.592975 (0.0140)

0.547534 (0.0098)

iPALM-DLMF ( \(\lambda _t\)=0)

0.831302 (0.0180)

0.844522 (0.0048)

0.815958 (0.0140)

0.805771 (0.0049)

iPALM-DLMF ( \(\lambda _l\)=0)

0.859537 (0.0099)

0.853745 (0.0094)

0.811177 (0.0104)

0.824733 (0.0111)

PALM-DLMF

0.852378 (0.0262)

0.865187 (0.0072)

0.805869 (0.0062)

0.81903 (0.0031)

  1. The maximum AUC on each dataset is shown in bold. Standard deviation is shown in parentheses