Skip to main content

Table 1 Performance comparison of SMFF-DTA and state-of-the-art methods on benchmark datasets

From: SMFF-DTA: using a sequential multi-feature fusion method with multiple attention mechanisms to predict drug-target binding affinity

 

Davis

KIBA

Method

MSE

\(R_{m}^2\)

CI

MSE

\(R_{m}^2\)

CI

KronRLS (2015)

0.379

0.407

0.871

0.411

0.342

0.782

SimBoost (2017)

0.282

0.644

0.872

0.222

0.629

0.836

DeepDTA (2018)

0.261

0.630

0.878

0.194

0.673

0.863

GANsDTA (2020)

0.276

0.653

0.881

0.224

0.675

0.866

TF-DTA (2023)

0.231

0.670

0.886

0.177

0.734

0.877

MultiDTA (2024)

0.231

0.694

0.893

0.156

0.761

0.890

LLMDTA (2024)

0.226

0.717

0.884

0.162

0.768

0.872

SMFF-DTA (our)

0.206

0.733

0.897

0.151

0.780

0.894

  1. The best results in the metrics are highlighted in bold, and the second-best results are italicized
Back to article page

BMC Biology

ISSN: 1741-7007

Contact us