Classification models for CYP450 3A4 inhibitors and non-inhibitors

Inhee Choi, Sun Young Kim, Hanjo Kim, Nam Sook Kang, Myung Ae Bae, Seung Eun Yoo, Jihoon Jung, Kyoung Tai No

Research output: Contribution to journalArticle

19 Citations (Scopus)

Abstract

Cytochrome P450 3A4 (CYP3A4) is the predominant enzyme involved in the oxidative metabolic pathways of many drugs. The inhibition of this enzyme in many cases leads to an undesired accumulation of the administered therapeutic agent. The purpose of this study is to develop in silico model that can effectively distinguish human CYP3A4 inhibitors from non-inhibitors. Structural diversity of the drug-like compounds CYP3A4 inhibitors and non-inhibitors was obtained from Fujitsu Database and Korea Research Institute of Chemical Technology (KRICT) as training and test sets, respectively. Recursive Partitioning (RP) method was introduced for the classification of inhibitor and non-inhibitor of CYP3A4 because it is an easy and quick classification method to implement. The 2D molecular descriptors were used to classify the compounds into respective inhibitors and non-inhibitors by calculation of the physicochemical properties of CYP3A4 inhibitors such as molecular weights and fractions of 2D VSA chargeable groups. The RP tree model reached 72.33% of accuracy and exceeded this percentage for the sensitivity (75.82%) parameter. This model is further validated by the test set where both accuracy and sensitivity were 72.58% and 82.64%, respectively. The accuracy of the random forest model was increased to 73.8%. The 2D descriptors sufficiently represented the molecular features of CYP3A4 inhibitors. Our model can be used for the prediction of either CYP3A4 inhibitors or non-inhibitors in the early stages of the drug discovery process.

Original languageEnglish
Pages (from-to)2354-2360
Number of pages7
JournalEuropean Journal of Medicinal Chemistry
Volume44
Issue number6
DOIs
Publication statusPublished - 2009 Jun 1

Fingerprint

Cytochrome P-450 CYP3A
Enzymes
Drug Discovery
Korea
Metabolic Networks and Pathways
Pharmaceutical Preparations
Computer Simulation
Molecular Weight
Molecular weight
Databases
Technology

All Science Journal Classification (ASJC) codes

  • Pharmacology
  • Drug Discovery
  • Organic Chemistry

Cite this

Choi, Inhee ; Kim, Sun Young ; Kim, Hanjo ; Kang, Nam Sook ; Bae, Myung Ae ; Yoo, Seung Eun ; Jung, Jihoon ; No, Kyoung Tai. / Classification models for CYP450 3A4 inhibitors and non-inhibitors. In: European Journal of Medicinal Chemistry. 2009 ; Vol. 44, No. 6. pp. 2354-2360.
@article{31dbf59176784e2db2ba73f941a1d6b6,
title = "Classification models for CYP450 3A4 inhibitors and non-inhibitors",
abstract = "Cytochrome P450 3A4 (CYP3A4) is the predominant enzyme involved in the oxidative metabolic pathways of many drugs. The inhibition of this enzyme in many cases leads to an undesired accumulation of the administered therapeutic agent. The purpose of this study is to develop in silico model that can effectively distinguish human CYP3A4 inhibitors from non-inhibitors. Structural diversity of the drug-like compounds CYP3A4 inhibitors and non-inhibitors was obtained from Fujitsu Database and Korea Research Institute of Chemical Technology (KRICT) as training and test sets, respectively. Recursive Partitioning (RP) method was introduced for the classification of inhibitor and non-inhibitor of CYP3A4 because it is an easy and quick classification method to implement. The 2D molecular descriptors were used to classify the compounds into respective inhibitors and non-inhibitors by calculation of the physicochemical properties of CYP3A4 inhibitors such as molecular weights and fractions of 2D VSA chargeable groups. The RP tree model reached 72.33{\%} of accuracy and exceeded this percentage for the sensitivity (75.82{\%}) parameter. This model is further validated by the test set where both accuracy and sensitivity were 72.58{\%} and 82.64{\%}, respectively. The accuracy of the random forest model was increased to 73.8{\%}. The 2D descriptors sufficiently represented the molecular features of CYP3A4 inhibitors. Our model can be used for the prediction of either CYP3A4 inhibitors or non-inhibitors in the early stages of the drug discovery process.",
author = "Inhee Choi and Kim, {Sun Young} and Hanjo Kim and Kang, {Nam Sook} and Bae, {Myung Ae} and Yoo, {Seung Eun} and Jihoon Jung and No, {Kyoung Tai}",
year = "2009",
month = "6",
day = "1",
doi = "10.1016/j.ejmech.2008.08.013",
language = "English",
volume = "44",
pages = "2354--2360",
journal = "European Journal of Medicinal Chemistry",
issn = "0223-5234",
publisher = "Elsevier Masson SAS",
number = "6",

}

Classification models for CYP450 3A4 inhibitors and non-inhibitors. / Choi, Inhee; Kim, Sun Young; Kim, Hanjo; Kang, Nam Sook; Bae, Myung Ae; Yoo, Seung Eun; Jung, Jihoon; No, Kyoung Tai.

In: European Journal of Medicinal Chemistry, Vol. 44, No. 6, 01.06.2009, p. 2354-2360.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Classification models for CYP450 3A4 inhibitors and non-inhibitors

AU - Choi, Inhee

AU - Kim, Sun Young

AU - Kim, Hanjo

AU - Kang, Nam Sook

AU - Bae, Myung Ae

AU - Yoo, Seung Eun

AU - Jung, Jihoon

AU - No, Kyoung Tai

PY - 2009/6/1

Y1 - 2009/6/1

N2 - Cytochrome P450 3A4 (CYP3A4) is the predominant enzyme involved in the oxidative metabolic pathways of many drugs. The inhibition of this enzyme in many cases leads to an undesired accumulation of the administered therapeutic agent. The purpose of this study is to develop in silico model that can effectively distinguish human CYP3A4 inhibitors from non-inhibitors. Structural diversity of the drug-like compounds CYP3A4 inhibitors and non-inhibitors was obtained from Fujitsu Database and Korea Research Institute of Chemical Technology (KRICT) as training and test sets, respectively. Recursive Partitioning (RP) method was introduced for the classification of inhibitor and non-inhibitor of CYP3A4 because it is an easy and quick classification method to implement. The 2D molecular descriptors were used to classify the compounds into respective inhibitors and non-inhibitors by calculation of the physicochemical properties of CYP3A4 inhibitors such as molecular weights and fractions of 2D VSA chargeable groups. The RP tree model reached 72.33% of accuracy and exceeded this percentage for the sensitivity (75.82%) parameter. This model is further validated by the test set where both accuracy and sensitivity were 72.58% and 82.64%, respectively. The accuracy of the random forest model was increased to 73.8%. The 2D descriptors sufficiently represented the molecular features of CYP3A4 inhibitors. Our model can be used for the prediction of either CYP3A4 inhibitors or non-inhibitors in the early stages of the drug discovery process.

AB - Cytochrome P450 3A4 (CYP3A4) is the predominant enzyme involved in the oxidative metabolic pathways of many drugs. The inhibition of this enzyme in many cases leads to an undesired accumulation of the administered therapeutic agent. The purpose of this study is to develop in silico model that can effectively distinguish human CYP3A4 inhibitors from non-inhibitors. Structural diversity of the drug-like compounds CYP3A4 inhibitors and non-inhibitors was obtained from Fujitsu Database and Korea Research Institute of Chemical Technology (KRICT) as training and test sets, respectively. Recursive Partitioning (RP) method was introduced for the classification of inhibitor and non-inhibitor of CYP3A4 because it is an easy and quick classification method to implement. The 2D molecular descriptors were used to classify the compounds into respective inhibitors and non-inhibitors by calculation of the physicochemical properties of CYP3A4 inhibitors such as molecular weights and fractions of 2D VSA chargeable groups. The RP tree model reached 72.33% of accuracy and exceeded this percentage for the sensitivity (75.82%) parameter. This model is further validated by the test set where both accuracy and sensitivity were 72.58% and 82.64%, respectively. The accuracy of the random forest model was increased to 73.8%. The 2D descriptors sufficiently represented the molecular features of CYP3A4 inhibitors. Our model can be used for the prediction of either CYP3A4 inhibitors or non-inhibitors in the early stages of the drug discovery process.

UR - http://www.scopus.com/inward/record.url?scp=64249130918&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=64249130918&partnerID=8YFLogxK

U2 - 10.1016/j.ejmech.2008.08.013

DO - 10.1016/j.ejmech.2008.08.013

M3 - Article

C2 - 19026469

AN - SCOPUS:64249130918

VL - 44

SP - 2354

EP - 2360

JO - European Journal of Medicinal Chemistry

JF - European Journal of Medicinal Chemistry

SN - 0223-5234

IS - 6

ER -