Human nephrotoxicity prediction models for three types of kidney injury based on data sets of pharmacological compounds and their metabolites

Sehan Lee, Young Mook Kang, Hyejin Park, Mi Sook Dong, Jae Min Shin, Kyoung Tai No

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

The kidney is the most important organ for the excretion of pharmaceuticals and their metabolites. Among the complex structures of the kidney, the proximal tubule and renal interstitium are major targets of nephrotoxins. Despite its importance, there are only a few in silico models for predicting human nephrotoxicity for drug candidates. Here, we present quantitative structure-activity relationship (QSAR) models for three common patterns of drug-induced kidney injury, i.e., tubular necrosis, interstitial nephritis, and tubulo-interstitial nephritis. A support vector machine (SVM) was used to build the binary classification models of nephrotoxin versus non-nephrotoxin with eight fingerprint descriptors. To build the models, we constructed two types of data sets, i.e., parent compounds of pharmaceuticals (251 nephrotoxins and 387 non-nephrotoxins) and their major urinary metabolites (307 nephrotoxins and 233 non-nephrotoxins). Information on the nephrotoxicity of the pharmaceuticals was taken from clinical trial and postmarketing safety data. Though the mechanisms of nephrotoxicity are very complex, by using the metabolite information, the predictive accuracies of the best models for each type of kidney injury were better than 83% for external validation sets. Software to predict nephrotoxicity is freely available from our Web site at http://bmdrc.org/DemoDownload.

Original languageEnglish
Pages (from-to)1652-1659
Number of pages8
JournalChemical Research in Toxicology
Volume26
Issue number11
DOIs
Publication statusPublished - 2013 Nov 18

Fingerprint

Metabolites
Pharmacology
Kidney
Wounds and Injuries
Interstitial Nephritis
Proximal Kidney Tubule
Pharmaceutical Preparations
Quantitative Structure-Activity Relationship
Dermatoglyphics
Computer Simulation
Support vector machines
Websites
Necrosis
Software
Datasets
Clinical Trials
Safety

All Science Journal Classification (ASJC) codes

  • Toxicology

Cite this

Lee, Sehan ; Kang, Young Mook ; Park, Hyejin ; Dong, Mi Sook ; Shin, Jae Min ; No, Kyoung Tai. / Human nephrotoxicity prediction models for three types of kidney injury based on data sets of pharmacological compounds and their metabolites. In: Chemical Research in Toxicology. 2013 ; Vol. 26, No. 11. pp. 1652-1659.
@article{0e1414c83dff495ba2678ec9c9660d8d,
title = "Human nephrotoxicity prediction models for three types of kidney injury based on data sets of pharmacological compounds and their metabolites",
abstract = "The kidney is the most important organ for the excretion of pharmaceuticals and their metabolites. Among the complex structures of the kidney, the proximal tubule and renal interstitium are major targets of nephrotoxins. Despite its importance, there are only a few in silico models for predicting human nephrotoxicity for drug candidates. Here, we present quantitative structure-activity relationship (QSAR) models for three common patterns of drug-induced kidney injury, i.e., tubular necrosis, interstitial nephritis, and tubulo-interstitial nephritis. A support vector machine (SVM) was used to build the binary classification models of nephrotoxin versus non-nephrotoxin with eight fingerprint descriptors. To build the models, we constructed two types of data sets, i.e., parent compounds of pharmaceuticals (251 nephrotoxins and 387 non-nephrotoxins) and their major urinary metabolites (307 nephrotoxins and 233 non-nephrotoxins). Information on the nephrotoxicity of the pharmaceuticals was taken from clinical trial and postmarketing safety data. Though the mechanisms of nephrotoxicity are very complex, by using the metabolite information, the predictive accuracies of the best models for each type of kidney injury were better than 83{\%} for external validation sets. Software to predict nephrotoxicity is freely available from our Web site at http://bmdrc.org/DemoDownload.",
author = "Sehan Lee and Kang, {Young Mook} and Hyejin Park and Dong, {Mi Sook} and Shin, {Jae Min} and No, {Kyoung Tai}",
year = "2013",
month = "11",
day = "18",
doi = "10.1021/tx400249t",
language = "English",
volume = "26",
pages = "1652--1659",
journal = "Chemical Research in Toxicology",
issn = "0893-228X",
publisher = "American Chemical Society",
number = "11",

}

Human nephrotoxicity prediction models for three types of kidney injury based on data sets of pharmacological compounds and their metabolites. / Lee, Sehan; Kang, Young Mook; Park, Hyejin; Dong, Mi Sook; Shin, Jae Min; No, Kyoung Tai.

In: Chemical Research in Toxicology, Vol. 26, No. 11, 18.11.2013, p. 1652-1659.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Human nephrotoxicity prediction models for three types of kidney injury based on data sets of pharmacological compounds and their metabolites

AU - Lee, Sehan

AU - Kang, Young Mook

AU - Park, Hyejin

AU - Dong, Mi Sook

AU - Shin, Jae Min

AU - No, Kyoung Tai

PY - 2013/11/18

Y1 - 2013/11/18

N2 - The kidney is the most important organ for the excretion of pharmaceuticals and their metabolites. Among the complex structures of the kidney, the proximal tubule and renal interstitium are major targets of nephrotoxins. Despite its importance, there are only a few in silico models for predicting human nephrotoxicity for drug candidates. Here, we present quantitative structure-activity relationship (QSAR) models for three common patterns of drug-induced kidney injury, i.e., tubular necrosis, interstitial nephritis, and tubulo-interstitial nephritis. A support vector machine (SVM) was used to build the binary classification models of nephrotoxin versus non-nephrotoxin with eight fingerprint descriptors. To build the models, we constructed two types of data sets, i.e., parent compounds of pharmaceuticals (251 nephrotoxins and 387 non-nephrotoxins) and their major urinary metabolites (307 nephrotoxins and 233 non-nephrotoxins). Information on the nephrotoxicity of the pharmaceuticals was taken from clinical trial and postmarketing safety data. Though the mechanisms of nephrotoxicity are very complex, by using the metabolite information, the predictive accuracies of the best models for each type of kidney injury were better than 83% for external validation sets. Software to predict nephrotoxicity is freely available from our Web site at http://bmdrc.org/DemoDownload.

AB - The kidney is the most important organ for the excretion of pharmaceuticals and their metabolites. Among the complex structures of the kidney, the proximal tubule and renal interstitium are major targets of nephrotoxins. Despite its importance, there are only a few in silico models for predicting human nephrotoxicity for drug candidates. Here, we present quantitative structure-activity relationship (QSAR) models for three common patterns of drug-induced kidney injury, i.e., tubular necrosis, interstitial nephritis, and tubulo-interstitial nephritis. A support vector machine (SVM) was used to build the binary classification models of nephrotoxin versus non-nephrotoxin with eight fingerprint descriptors. To build the models, we constructed two types of data sets, i.e., parent compounds of pharmaceuticals (251 nephrotoxins and 387 non-nephrotoxins) and their major urinary metabolites (307 nephrotoxins and 233 non-nephrotoxins). Information on the nephrotoxicity of the pharmaceuticals was taken from clinical trial and postmarketing safety data. Though the mechanisms of nephrotoxicity are very complex, by using the metabolite information, the predictive accuracies of the best models for each type of kidney injury were better than 83% for external validation sets. Software to predict nephrotoxicity is freely available from our Web site at http://bmdrc.org/DemoDownload.

UR - http://www.scopus.com/inward/record.url?scp=84888032163&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84888032163&partnerID=8YFLogxK

U2 - 10.1021/tx400249t

DO - 10.1021/tx400249t

M3 - Article

C2 - 24138086

AN - SCOPUS:84888032163

VL - 26

SP - 1652

EP - 1659

JO - Chemical Research in Toxicology

JF - Chemical Research in Toxicology

SN - 0893-228X

IS - 11

ER -