RS-predictor: a new tool for predicting sites of cytochrome P450-mediated metabolism applied to CYP 3A4

Research output: Contribution to journalJournal articleResearchpeer-review

Standard

RS-predictor : a new tool for predicting sites of cytochrome P450-mediated metabolism applied to CYP 3A4. / Zaretzki, Jed; Bergeron, Charles; Rydberg, Patrik; Huang, Tao-wei; Bennett, Kristin P; Breneman, Curt M.

In: Journal of Chemical Information and Modeling, Vol. 51, No. 7, 25.07.2011, p. 1667-1689.

Research output: Contribution to journalJournal articleResearchpeer-review

Harvard

Zaretzki, J, Bergeron, C, Rydberg, P, Huang, T, Bennett, KP & Breneman, CM 2011, 'RS-predictor: a new tool for predicting sites of cytochrome P450-mediated metabolism applied to CYP 3A4', Journal of Chemical Information and Modeling, vol. 51, no. 7, pp. 1667-1689. https://doi.org/10.1021/ci2000488

APA

Zaretzki, J., Bergeron, C., Rydberg, P., Huang, T., Bennett, K. P., & Breneman, C. M. (2011). RS-predictor: a new tool for predicting sites of cytochrome P450-mediated metabolism applied to CYP 3A4. Journal of Chemical Information and Modeling, 51(7), 1667-1689. https://doi.org/10.1021/ci2000488

Vancouver

Zaretzki J, Bergeron C, Rydberg P, Huang T, Bennett KP, Breneman CM. RS-predictor: a new tool for predicting sites of cytochrome P450-mediated metabolism applied to CYP 3A4. Journal of Chemical Information and Modeling. 2011 Jul 25;51(7):1667-1689. https://doi.org/10.1021/ci2000488

Author

Zaretzki, Jed ; Bergeron, Charles ; Rydberg, Patrik ; Huang, Tao-wei ; Bennett, Kristin P ; Breneman, Curt M. / RS-predictor : a new tool for predicting sites of cytochrome P450-mediated metabolism applied to CYP 3A4. In: Journal of Chemical Information and Modeling. 2011 ; Vol. 51, No. 7. pp. 1667-1689.

Bibtex

@article{8932f2d0250442ffaaecf4039de7b195,
title = "RS-predictor: a new tool for predicting sites of cytochrome P450-mediated metabolism applied to CYP 3A4",
abstract = "This article describes RegioSelectivity-Predictor (RS-Predictor), a new in silico method for generating predictive models of P450-mediated metabolism for drug-like compounds. Within this method, potential sites of metabolism (SOMs) are represented as {"}metabolophores{"}: A concept that describes the hierarchical combination of topological and quantum chemical descriptors needed to represent the reactivity of potential metabolic reaction sites. RS-Predictor modeling involves the use of metabolophore descriptors together with multiple-instance ranking (MIRank) to generate an optimized descriptor weight vector that encodes regioselectivity trends across all cases in a training set. The resulting pathway-independent (O-dealkylation vs N-oxidation vs Csp(3) hydroxylation, etc.), isozyme-specific regioselectivity model may be used to predict potential metabolic liabilities. In the present work, cross-validated RS-Predictor models were generated for a set of 394 substrates of CYP 3A4 as a proof-of-principle for the method. Rank aggregation was then employed to merge independently generated predictions for each substrate into a single consensus prediction. The resulting consensus RS-Predictor models were shown to reliably identify at least one observed site of metabolism in the top two rank-positions on 78{\%} of the substrates. Comparisons between RS-Predictor and previously described regioselectivity prediction methods reveal new insights into how in silico metabolite prediction methods should be compared.",
keywords = "Former Faculty of Pharmaceutical Sciences",
author = "Jed Zaretzki and Charles Bergeron and Patrik Rydberg and Tao-wei Huang and Bennett, {Kristin P} and Breneman, {Curt M}",
year = "2011",
month = "7",
day = "25",
doi = "10.1021/ci2000488",
language = "English",
volume = "51",
pages = "1667--1689",
journal = "Journal of Chemical Information and Modeling",
issn = "1549-9596",
publisher = "American Chemical Society",
number = "7",

}

RIS

TY - JOUR

T1 - RS-predictor

T2 - a new tool for predicting sites of cytochrome P450-mediated metabolism applied to CYP 3A4

AU - Zaretzki, Jed

AU - Bergeron, Charles

AU - Rydberg, Patrik

AU - Huang, Tao-wei

AU - Bennett, Kristin P

AU - Breneman, Curt M

PY - 2011/7/25

Y1 - 2011/7/25

N2 - This article describes RegioSelectivity-Predictor (RS-Predictor), a new in silico method for generating predictive models of P450-mediated metabolism for drug-like compounds. Within this method, potential sites of metabolism (SOMs) are represented as "metabolophores": A concept that describes the hierarchical combination of topological and quantum chemical descriptors needed to represent the reactivity of potential metabolic reaction sites. RS-Predictor modeling involves the use of metabolophore descriptors together with multiple-instance ranking (MIRank) to generate an optimized descriptor weight vector that encodes regioselectivity trends across all cases in a training set. The resulting pathway-independent (O-dealkylation vs N-oxidation vs Csp(3) hydroxylation, etc.), isozyme-specific regioselectivity model may be used to predict potential metabolic liabilities. In the present work, cross-validated RS-Predictor models were generated for a set of 394 substrates of CYP 3A4 as a proof-of-principle for the method. Rank aggregation was then employed to merge independently generated predictions for each substrate into a single consensus prediction. The resulting consensus RS-Predictor models were shown to reliably identify at least one observed site of metabolism in the top two rank-positions on 78% of the substrates. Comparisons between RS-Predictor and previously described regioselectivity prediction methods reveal new insights into how in silico metabolite prediction methods should be compared.

AB - This article describes RegioSelectivity-Predictor (RS-Predictor), a new in silico method for generating predictive models of P450-mediated metabolism for drug-like compounds. Within this method, potential sites of metabolism (SOMs) are represented as "metabolophores": A concept that describes the hierarchical combination of topological and quantum chemical descriptors needed to represent the reactivity of potential metabolic reaction sites. RS-Predictor modeling involves the use of metabolophore descriptors together with multiple-instance ranking (MIRank) to generate an optimized descriptor weight vector that encodes regioselectivity trends across all cases in a training set. The resulting pathway-independent (O-dealkylation vs N-oxidation vs Csp(3) hydroxylation, etc.), isozyme-specific regioselectivity model may be used to predict potential metabolic liabilities. In the present work, cross-validated RS-Predictor models were generated for a set of 394 substrates of CYP 3A4 as a proof-of-principle for the method. Rank aggregation was then employed to merge independently generated predictions for each substrate into a single consensus prediction. The resulting consensus RS-Predictor models were shown to reliably identify at least one observed site of metabolism in the top two rank-positions on 78% of the substrates. Comparisons between RS-Predictor and previously described regioselectivity prediction methods reveal new insights into how in silico metabolite prediction methods should be compared.

KW - Former Faculty of Pharmaceutical Sciences

U2 - 10.1021/ci2000488

DO - 10.1021/ci2000488

M3 - Journal article

C2 - 21528931

VL - 51

SP - 1667

EP - 1689

JO - Journal of Chemical Information and Modeling

JF - Journal of Chemical Information and Modeling

SN - 1549-9596

IS - 7

ER -

ID: 35458079