Cytochtome P450 inhibition (five isoforms)

Dataset profile

The dataset used for the presented CYP inibition models is a cytochrome = panel assay with activity outcomes [Comprehe= nsive Characterization of Cytochrome P450 Isozyme Selectivity across Chemic= al Libraries; Henrike Veith, Noel Southall, et al.] deposited in the Pu= bChem BioAsssay database under identifier AID1851.

The study determined potency values for 17,143 compounds agains= t five CYP isozymes (1A2, 2C9, 2C19, 2D6 and 3A4) using an in vitro biolumi= nescent assay. The compounds included libraries of US FDA-approved drugs an= d screening libraries. Among these molecules 8,019 were the compou= nds from the Molecular Libraries Small Molecule Repository, including compo= unds chosen for diversity and rule-of-five compliance, synthetic tractabili= ty and availability; 6,144 compounds were from biofocused librarie= s, which included 1,114 FDA-approved drugs; and the rest 2,980= compounds were from combinatorial chemistry libraries, containing pri= vileged structures targeted at G protein=E2=80=93coupled receptors and kina= ses and containing purified natural products or related structures.
This assay used various human CYP isozymes to measure the dealkylation = of various pro-luciferin substrates to luciferin. The luciferin was then me= asured by luminescence after the addition of a luciferase detection reagent= . Pro-luciferin substrate concentration in the assay was equal to its Micha= elis constant for its cytochrome P450 isozyme. Inhibitors and somesubstrate= s limit the production of luciferin, and decrease measured luminescence. To= address potential artifacts due to the assay format, particularly importan= t for panactive compounds, the authors of the assay used a database of pote= ncy values determined for the variant of the firefly luciferase used in the= assay to remove any compounds that interfered with luciferase detection (o= nly 0.7% were found to be interfering in the compound collection used for t= he assay).

The activators and compounds marked as inconclusive = where removed from the datasets before building the models.

The = threshold to differentiate between inhibitors and non-inhibitors is IC50 of= 10 µM / L.

Five models correspond to each of the five cytochrome P450 enzymes measu= red in the assay.

Data preprocessing

All chemical structures were cleaned using OCHEM cleaning protocol. The = standardization was performed in OCHEM. All salt counter ions were removed = and resulting ions were neutralized.

Descr= iptors

This models were built using EState desc= riptors (electrotopological EState indices) and ALogPS descriptors according to OCHEM implementation.

Valida= tion

The modes were built and validated using using the stratified bagging technique with 64 bags.

Statistical parameters

Predic= tion accuracy

The basic prediction accuracy parameters according to the bagging valida= tion procedure are:

Cytochrome	Total	Inhibitors	Noninhibitors	Accuracy	Balanced accuracy	MCC	AUC
CYP1A2	13,908 records	6,953	6,955	80.5% ± 0.3	80.5% ± 0.3	0.611 ± 0.007	0.887 ± 0.01
CYP2C9	13,246 records	4,429	8,817	80.2% ± 0.3	78.9% ± 0.4	0.566 ± 0.008	0.874 ± 0.01
CYP2C19	13,122 records	5,494	7,634	80.6% ± 0.3	80.2% ± 0.3	0.596 ± 0.007	0.88 ± 0.01
CYP2D6	14,059 records	2,837	11,222	83% ± 0.3	76.8% ± 0.5	0.506 ± 0.009	0.839 ± 0.01
CYP3A4	15,334 records	5,819	9,515	80.6% ± 0.3	80.2% ± 0.3	0.596 ± 0.007	0.88 ± 0.01

Appli= cability domain

The prediction accuracy is estimated using PROB-STD distance to model an= d sliding window based accuracy averaging.