Identification of consensus biomarkers for predicting non-genotoxic hepatocarcinogens

Shan Han Huang, Chun Wei Tung

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

The assessment of non-genotoxic hepatocarcinogens (NGHCs) is currently relying on two-year rodent bioassays. Toxicogenomics biomarkers provide a potential alternative method for the prioritization of NGHCs that could be useful for risk assessment. However, previous studies using inconsistently classified chemicals as the training set and a single microarray dataset concluded no consensus biomarkers. In this study, 4 consensus biomarkers of A2m, Ca3, Cxcl1, and Cyp8b1 were identified from four large-scale microarray datasets of the one-day single maximum tolerated dose and a large set of chemicals without inconsistent classifications. Machine learning techniques were subsequently applied to develop prediction models for NGHCs. The final bagging decision tree models were constructed with an average AUC performance of 0.803 for an independent test. A set of 16 chemicals with controversial classifications were reclassified according to the consensus biomarkers. The developed prediction models and identified consensus biomarkers are expected to be potential alternative methods for prioritization of NGHCs for further experimental validation.

Original languageEnglish
Article number41176
JournalScientific Reports
Volume7
DOIs
Publication statusPublished - Jan 24 2017
Externally publishedYes

Fingerprint

Biomarkers
Toxicogenetics
Decision Trees
Maximum Tolerated Dose
Biological Assay
Area Under Curve
Rodentia
Datasets

ASJC Scopus subject areas

  • General

Cite this

Identification of consensus biomarkers for predicting non-genotoxic hepatocarcinogens. / Huang, Shan Han; Tung, Chun Wei.

In: Scientific Reports, Vol. 7, 41176, 24.01.2017.

Research output: Contribution to journalArticle

@article{da692ffd55774d5cb75c671eccb989c8,
title = "Identification of consensus biomarkers for predicting non-genotoxic hepatocarcinogens",
abstract = "The assessment of non-genotoxic hepatocarcinogens (NGHCs) is currently relying on two-year rodent bioassays. Toxicogenomics biomarkers provide a potential alternative method for the prioritization of NGHCs that could be useful for risk assessment. However, previous studies using inconsistently classified chemicals as the training set and a single microarray dataset concluded no consensus biomarkers. In this study, 4 consensus biomarkers of A2m, Ca3, Cxcl1, and Cyp8b1 were identified from four large-scale microarray datasets of the one-day single maximum tolerated dose and a large set of chemicals without inconsistent classifications. Machine learning techniques were subsequently applied to develop prediction models for NGHCs. The final bagging decision tree models were constructed with an average AUC performance of 0.803 for an independent test. A set of 16 chemicals with controversial classifications were reclassified according to the consensus biomarkers. The developed prediction models and identified consensus biomarkers are expected to be potential alternative methods for prioritization of NGHCs for further experimental validation.",
author = "Huang, {Shan Han} and Tung, {Chun Wei}",
year = "2017",
month = "1",
day = "24",
doi = "10.1038/srep41176",
language = "English",
volume = "7",
journal = "Scientific Reports",
issn = "2045-2322",
publisher = "Nature Publishing Group",

}

TY - JOUR

T1 - Identification of consensus biomarkers for predicting non-genotoxic hepatocarcinogens

AU - Huang, Shan Han

AU - Tung, Chun Wei

PY - 2017/1/24

Y1 - 2017/1/24

N2 - The assessment of non-genotoxic hepatocarcinogens (NGHCs) is currently relying on two-year rodent bioassays. Toxicogenomics biomarkers provide a potential alternative method for the prioritization of NGHCs that could be useful for risk assessment. However, previous studies using inconsistently classified chemicals as the training set and a single microarray dataset concluded no consensus biomarkers. In this study, 4 consensus biomarkers of A2m, Ca3, Cxcl1, and Cyp8b1 were identified from four large-scale microarray datasets of the one-day single maximum tolerated dose and a large set of chemicals without inconsistent classifications. Machine learning techniques were subsequently applied to develop prediction models for NGHCs. The final bagging decision tree models were constructed with an average AUC performance of 0.803 for an independent test. A set of 16 chemicals with controversial classifications were reclassified according to the consensus biomarkers. The developed prediction models and identified consensus biomarkers are expected to be potential alternative methods for prioritization of NGHCs for further experimental validation.

AB - The assessment of non-genotoxic hepatocarcinogens (NGHCs) is currently relying on two-year rodent bioassays. Toxicogenomics biomarkers provide a potential alternative method for the prioritization of NGHCs that could be useful for risk assessment. However, previous studies using inconsistently classified chemicals as the training set and a single microarray dataset concluded no consensus biomarkers. In this study, 4 consensus biomarkers of A2m, Ca3, Cxcl1, and Cyp8b1 were identified from four large-scale microarray datasets of the one-day single maximum tolerated dose and a large set of chemicals without inconsistent classifications. Machine learning techniques were subsequently applied to develop prediction models for NGHCs. The final bagging decision tree models were constructed with an average AUC performance of 0.803 for an independent test. A set of 16 chemicals with controversial classifications were reclassified according to the consensus biomarkers. The developed prediction models and identified consensus biomarkers are expected to be potential alternative methods for prioritization of NGHCs for further experimental validation.

UR - http://www.scopus.com/inward/record.url?scp=85010297253&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85010297253&partnerID=8YFLogxK

U2 - 10.1038/srep41176

DO - 10.1038/srep41176

M3 - Article

C2 - 28117354

AN - SCOPUS:85010297253

VL - 7

JO - Scientific Reports

JF - Scientific Reports

SN - 2045-2322

M1 - 41176

ER -