Table 5 Predicted active compounds by the five models using XGBoost algorithm.

From: Unveiling potent xanthine oxidase inhibitors in two Balanophora spp. using machine learning-based virtual screening and molecular docking approach

Fingerprint

Decoy compounds found

Predicted active compounds

MACCS-167bits

20/20

1-(3,4-dihydroxyphenyl)-6,7-dihydroxy-1,2-dihydro-2,3-naphthalenedicarboxylic acid

taxifolin

ECFP4-1024bits

20/20

1-O-caffeoyl-6-O-(S)-brevifolincarboxyl-β-D-glucopyranose

taxifolin

ECFP4-2048bits

20/20

1-O-caffeoyl-6-O-(S)-brevifolincarboxyl-β-D-glucopyranose

taxifolin

ECFP6-1024bits

20/20

none

ECFP6-2048bits

20/20

1-O-caffeoyl-6-O-(S)-brevifolincarboxyl-β-D-glucopyranose

taxifolin

Back to article page