Skip to main content

Table 5 Results of deep models on KIBA and Davis dataset with multi-granularity representations as inputs

From: Multi-scaled self-attention for drug–target interaction prediction based on multi-granularity representation

 

Deep models

CI

MSE

\(r^2_m\)

KIBA

CNNs

0.863 (0.002)

0.194

0.673 (0.009)

SANs

0.875 (0.003)

0.179

0.691 (0.019)

Multi-scaled SANs

0.890 (0.002)

0.155

0.742 (0.010)

Davis

CNNs

0.878 (0.004)

0.261

0.630 (0.017)

SANs

0.888 (0.004)

0.232

0.689 (0.007)

Multi-scaled SANs

0.890 (0.005)

0.233

0.681(0.014)

  1. Bold values indicate the best results on the datasets
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us