Skip to main content

Table 5 Performance of best individual classifiers, errors are absolute (unsigned) and are measured in log S units

From: Can human experts predict solubility better than computers?

Compound MLP error Human 11 error Difference
4-Aminobenzoic acid 0.42 0.63 − 0.21
4-Aminosalicylic acid 0.39 0.04 0.35
Antipyrine 1.90 1.48 0.42
Chloramphenicol 0.78 0.89 − 0.11
Corticosterone 0.00 0.76 − 0.76
Dapsone 0.41 0.09 0.32
Primidone 1.45 0.36 1.09
Estrone 0.78 1.32 − 0.54
Alclofenac 0.02 1.13 − 1.11
5-Fluorouracil 0.07 0.97 − 0.90
Griseofulvin 0.90 1.25 − 0.35
Fluometuron 0.33 0.46 − 0.13
Fluconazole 0.22 0.20 0.02
Khellin 0.13 0.02 0.11
Clozapine 0.33 0.76 − 0.43
Norethisterone 1.53 0.37 1.16
Nicotinic acid 0.59 0.15 0.44
Perphenazine 0.53 0.84 − 0.31
Pteridine 1.00 0.02 0.98
Salicylamide 0.23 1.34 − 1.11
Sulfanilamide 0.71 0.14 0.57
Gliclazide 1.30 0.29 1.01
Trihexyphenidyl 2.93 2.20 0.73
Triphenylene 0.38 0.73 − 0.35
Mifepristone 0.86 1.90 − 1.04
Average 0.728 0.734 − 0.005
  1. The difference is meaningfully signed, with a positive value where the best human classifier performed better on that compound and a negative value where the best machine learning classifier performed better