Skip to main content

Table 2 Results for the active/inactive discrimination task, and Training scheme 2

From: Convolutional architectures for virtual screening

Architecture Bal. Accuracy Sensitivity Loss AUC F1-score MCC
Tuned-MLP-Out 0.9644 0.9625 0.0983 0.9875 0.5519 0.5989
Voting 0.9639 0.9500 0.1523 0.9889 0.6379 0.6694
CNN 1D (F) 0.9579 0.9625 0.1398 0.9854 0.4709 0.5336
CNN 2D (T-L-E) 0.9525 0.9375 0.1054 0.9841 0.5192 0.5920
Random Forest (F) 0.8789 0.7750 0.6221 0.9541 0.6528 0.6540
SVM (F) 0.9208 0.8625 0.6221 0.9682 0.6699 0.6524
  1. Fingerprint types: (F) eatMorgan, (T) orsion, (L) ayered, (E)CFP4