Skip to main content

Table 3 Performance evaluation of Decision Tree models by 10 fold Cross Validation.

From: Developing and validating predictive decision tree models from mining chemical structural fingerprints and high–throughput screening data in PubChem

  

Active compounds

  

Inactive compounds

    

Bioassay

PubChem Assay ID

TP

FN

Sensitivity

TN

FP

Specificity

Overall accuracy

MCC

5HT1a agonist

567

295

71

80.5%

63913

627

99.0%

98.9%

0.50

5HT1a antagonist

612

268

148

64.5%

60656

534

99.1%

98.9%

0.46

HIV-1 RT RNase H inhibitor

565

940

310

75.2%

62269

1698

97.3%

96.9%

0.50

HIV-1 RT RNase H inhibitor

372

441

329

57.2%

97923

1075

98.9%

98.6%

0.40

  1. TP = true positives, the number of correctly recognized active compounds;
  2. FN = false negative, the number of active compounds that the model is unable to recognize;
  3. TN = true negative, the number of inactive compounds that successfully recognized by the model;
  4. FP = false positive, the number of inactive compounds that the model is unable to recognize.
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us