Skip to main content

Table 8 The representative fragments whose counts are equal or larger than 2 in the 50 misclassified compounds

From: ADMET evaluation in drug discovery. 20. Prediction of breast cancer resistance protein inhibition through machine learning

FragmentNameCount1aCount2aCount3aOR1a (%)OR2a (%)OR3a (%)
Pyridine1254355.587.6910.00
Tetrahydro-2H-pyran37631.651.076.00
Adamantane6320.270.544.00
(E)-prop-1-ene-1,3-diyldibenzene581632.592.866.00
1H-indole822533.664.476.00
4H-chromene1101744.913.048.00
Furan1753727.816.624.00
Piperazine982234.383.946.00
Quinazoline1503926.706.984.00
Quinoline581632.592.866.00
Thiophene1092534.874.476.00
1,2,3,4-tetrahydroi561432.502.506.00
2-(4-((quinolin-3-ylmethyl)amino)phenethyl)-1,2,3,4-tetrahydroi0220.000.364.00
  1. aCount1, 2, and 3 represent the number of the training compounds, testing compounds and misclassified compounds containing the fragment, respectively, and OR1, 2 and 3 represent the occurrence ratio of the fragment in the training compounds, testing compounds and misclassified compounds, respectively