Rule-Based Prediction Models of Cytochrome P450 Inhibition

Abstract

Hepatotoxicity, drug-induced liver injury, and competitive Cytochrome P-450 (CYP) isozyme binding are serious problems associated with drug use. It would be favorable to avoid or to understand potential CYP inhibition at the developmental stages. However, current in silico CYP prediction models or available public prediction servers can provide only yes/no classification results for just one or a few CYP enzymes. In this study, we utilized a rule-based C5.0 algorithm with different descriptors, including PaDEL, Mold(2), and PubChem fingerprints, to construct rule-based inhibition prediction models for five major CYP enzymes-CYP1A2, CYP2C9, CYP2C19, CYP2D6 and CYP3A4-that account for 90% of drug oxidation or hydrolysis. We also developed a rational sampling algorithm for the selection of compounds in the training data set, to enhance the performance of these CYP prediction models. The optimized models include several improved features. First, the final models significantly outperformed all of the currently available models. Second, the final models can also be used for rapid virtual screening of a large set of compounds due to their ruleset-based nature. Moreover, such rule-based prediction models can provide rulesets for structural features related to the five major CYP enzymes. The five most significant rules for CYP inhibition were identified for each CYP enzymes and discussed. An example was chosen for each of the five CYP enzymes to demonstrate how rule-based models can be used to gain insights into structural features that correspond with CYP inhibitions. A newer version of the freely accessible CYP prediction server, CypRules, is presented here as a result of the aforementioned improvements.

Pharmacophore-Based Virtual Screening of Novel Inhibitors and Docking Analysis for CYP51A from Penicillium italicum

“…In the present pharmacophore-based virtual screening system, the hydrophobic amino acid residues Y112, Y126, F120, F219 and V125 composed a large hydrophobic cleft in the PiCYP51A active site (Figure 4). The aromatic group of the ligands formed hydrophobic interactions with the hydrophobic cleft which fixed the orientation of the inhibitors in the active site [21,26]. The N atoms of the azole ring or hexatomic ring of ligands were bound to heme iron with distances from 2.2 Å to 2.9 Å, respectively (Figure 4).…”

“…DISCOtech module of the SYBYL 7.3 program package [26,31] was used to identify structural features. Further, 3D alignments of the pharmacophore features in desirable molecules with benzene ligand(s) and/or structure core of nitrogen heterocyclic ring, i.e.…”

Advances in Computational Prediction of Regioselective and Isoform-Specific Drug Metabolism Catalyzed by CYP450s.

“…Su et al. have develop a rule based model (CypRules) for prediction of inhibitory potential for CYP3A4, CYP2D6, CYP2C9, CYP2C19 and CYP1A2 ligands . A total of 64,312 compounds containing actives and inactives were extracted from the PubChem BioAssay Database.…”

Getting the most out of PubChem for virtual screening

“…Using a rule-based C5.0 decision tree algorithm with several molecular descriptors, Su et al . 29 developed an improved prediction model, which can classify CYP inhibitors and non-inhibitors with an 81.4-93.0% accuracy.…”