From: Complementary PLS and KNN algorithms for improved 3D-QSDAR consensus modeling of AhR binding
Chemical class | Endpoint | Dataset size | Data processing algorithm* | Descriptor type | Statistical parameters | Reference |
---|---|---|---|---|---|---|
PCBs, PCDDs and PCDFs | logEC50 | 52 | MLR | 13C-NMR | R2 = 0.85; q2 = 0.71 | [13] |
PCBs, PCDDs and PCDFs | logEC50 | 52 | MLR | 13C-NMR, atom-to-atom distances | R2 = 0.85; q2 = 0.52 | [14] |
PCDFs | log(1/EC50) | 33 | MLR | Quantum mechanical; logP | R2 = 0.720; s = 0.723 | [15] |
PCDFs | log(1/EC50) | 34 | MLR | Quantum mechanical | R2 = 0.747; R2adj = 0.669; q2 = 0.572 | [16] |
PCDDs and PCDFs | log(1/EC50) | 90 | PLS | CoMFA - 10 latent variables | R2 = 0.838; q2 = 0.624; SEP = 0.903 | [17] |
PCDFs | log(1/EC50) | 34 | MLR | Quantum mechanical | R2 = 0.863; R2adj = 0.839; q2 = 0.807; SE = 0.558 ; F = 35.389 | [18] |
PCDDs | log(1/EC50) | 47 | MLR | Quantum mechanical | R2 = 0.729; R2adj = 0.703; SE = 0.797; F = 28.269 | [19] |
PHDDs | log(1/EC50) | 25 | MLR | Quantum mechanical | R2 = 0.768; R2adj = 0.721; q2 = 0.635; S.E. = 0.762; F = 16.529 | [20] |
PHDDs | log(1/EC50) | 25 | MLR | WHIM | R2 = 0.915; R2adj = 0.902; q2 = 0.880; S.E. = 0.451; F = 75.032 | [20] |
PCDDs and PCDFs | log(1/EC50) | 60 | MLR | Quantum mechanical | R2 = 0.687; R2adj = 0.686; q2 = 0.603; S.E. = 0.870 | [21] |