Skip to main content

Table 7 Selected association rules for the antiTB dataset

From: Fast rule-based bioactivity prediction using associative classification mining

Association rules Support Confidence
MDL
1 [#7]~[#6]~[#8] AND *!@[#8]!@* → class = active 23.10% 75.14%
2 Not [#7]~*~*~[#8] AND not [#7]!:*:* → class = inactive 21.38% 75. 50%
3 [#7]~[#6]~[#8] AND *~*(~*)(~*)~* → class = active 18.95% 81.98%
4 [#7]~*~[CH2]~* AND [#8]~[#6]~[#8] → class = active 18.37% 76.80%
Property   
5 ALogP[0.985 - 4.446] AND Num_RingBonds[>19] AND ADMET_CYP2D6[=0 ] → class = active 9.55% 74.64%
6 Num_Hydrogens[18–50] AND Molecular_Solubility[−12.036 - -7.198] AND Molecular_SASA[690.864 - 1058.920] → class = inactive 9.03% 78.31%
7 Molecular_FractionalPolarSASA[0.140 - 0.312] AND Molecular_Solubility[−12.036 - -7.198] AND ChemAxon_HBD[>3] → class = inactive 9.00% 91.84%
8 Num_Bonds[<30] AND ChemAxon_TPSA[<46.170] AND Molecular_FractionalPolarSASA[<0.140] → class = active 9.00% 81.57%