Skip to main content

Table 4 Results of ablation experiments on Human and Davis datasets

From: MCL-DTI: using drug multimodal information and bi-directional cross-attention learning method for predicting drug–target interaction

Dataset

Method

ROC–AUC

PR–AUC

Recall

Human

MCL-DTI

0.987

0.989

0.961

Image + SMILES

0.983

0.982

0.926

Text

0.963

0.966

0.910

Image

0.983

0.985

0.935

-MCA

0.984

0.984

0.897

 MCA, image

0.968

0.971

0.919

 MCA,text

0.980

0.982

0.945

Davis

MCL-DTI

0.922

0.492

0.895

Iimage + SMILES

0.917

0.462

0.874

Text

0.917

0.481

0.842

Iimage

0.916

0.466

0.884

 MCA

0.914

0.471

0.835

 MCA, image

0.912

0.473

0.839

 MCA, text

0.913

0.453

0.839

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us