Development of QSAR models for predicting hepatocarcinogenic toxicity of chemicals

Ilaria Massarelli, Marcello Imbriani, Alessio Coi, Marilena Saraceno, Niccolò Carli, Anna Maria Bianucci

Research output: Contribution to journalArticle

17 Citations (Scopus)

Abstract

A dataset comprising 55 chemicals with hepatocarcinogenic potency indices was collected from the Carcinogenic Potency Database with the aim of developing QSAR models enabling prediction of the above unwanted property for New Chemical Entities. The dataset was rationally split into training and test sets by means of a sphere-exclusion type algorithm. Among the many algorithms explored to search regression models, only a Support Vector Machine (SVM) method led to a QSAR model, which was proved to pass rigorous validation criteria, in accordance with the OECD guidelines. The proposed model is capable to explain the hepatocarcinogenic toxicity and could be exploited for predicting this property for chemicals at the early stage of their development, so optimizing resources and reducing animal testing.

Original languageEnglish
Pages (from-to)3658-3664
Number of pages7
JournalEuropean Journal of Medicinal Chemistry
Volume44
Issue number9
DOIs
Publication statusPublished - Sep 2009

Fingerprint

Quantitative Structure-Activity Relationship
Toxicity
Databases
Guidelines
Support vector machines
Animals
Datasets
Testing
Support Vector Machine
Organisation for Economic Co-Operation and Development

Keywords

  • Carcinogenic potency database
  • Hepatocarcinogenic
  • Quantitative structure-activity relationship
  • Sphere-exclusion
  • WEKA

ASJC Scopus subject areas

  • Drug Discovery
  • Organic Chemistry
  • Pharmacology

Cite this

Development of QSAR models for predicting hepatocarcinogenic toxicity of chemicals. / Massarelli, Ilaria; Imbriani, Marcello; Coi, Alessio; Saraceno, Marilena; Carli, Niccolò; Bianucci, Anna Maria.

In: European Journal of Medicinal Chemistry, Vol. 44, No. 9, 09.2009, p. 3658-3664.

Research output: Contribution to journalArticle

Massarelli, Ilaria ; Imbriani, Marcello ; Coi, Alessio ; Saraceno, Marilena ; Carli, Niccolò ; Bianucci, Anna Maria. / Development of QSAR models for predicting hepatocarcinogenic toxicity of chemicals. In: European Journal of Medicinal Chemistry. 2009 ; Vol. 44, No. 9. pp. 3658-3664.
@article{ef06881b4bbc40c4bf7825081f7e7e4e,
title = "Development of QSAR models for predicting hepatocarcinogenic toxicity of chemicals",
abstract = "A dataset comprising 55 chemicals with hepatocarcinogenic potency indices was collected from the Carcinogenic Potency Database with the aim of developing QSAR models enabling prediction of the above unwanted property for New Chemical Entities. The dataset was rationally split into training and test sets by means of a sphere-exclusion type algorithm. Among the many algorithms explored to search regression models, only a Support Vector Machine (SVM) method led to a QSAR model, which was proved to pass rigorous validation criteria, in accordance with the OECD guidelines. The proposed model is capable to explain the hepatocarcinogenic toxicity and could be exploited for predicting this property for chemicals at the early stage of their development, so optimizing resources and reducing animal testing.",
keywords = "Carcinogenic potency database, Hepatocarcinogenic, Quantitative structure-activity relationship, Sphere-exclusion, WEKA",
author = "Ilaria Massarelli and Marcello Imbriani and Alessio Coi and Marilena Saraceno and Niccol{\`o} Carli and Anna Maria Bianucci",
year = "2009",
month = "9",
doi = "10.1016/j.ejmech.2009.02.014",
language = "English",
volume = "44",
pages = "3658--3664",
journal = "European Journal of Medicinal Chemistry",
issn = "0223-5234",
publisher = "Elsevier Masson SAS",
number = "9",

}

TY - JOUR

T1 - Development of QSAR models for predicting hepatocarcinogenic toxicity of chemicals

AU - Massarelli, Ilaria

AU - Imbriani, Marcello

AU - Coi, Alessio

AU - Saraceno, Marilena

AU - Carli, Niccolò

AU - Bianucci, Anna Maria

PY - 2009/9

Y1 - 2009/9

N2 - A dataset comprising 55 chemicals with hepatocarcinogenic potency indices was collected from the Carcinogenic Potency Database with the aim of developing QSAR models enabling prediction of the above unwanted property for New Chemical Entities. The dataset was rationally split into training and test sets by means of a sphere-exclusion type algorithm. Among the many algorithms explored to search regression models, only a Support Vector Machine (SVM) method led to a QSAR model, which was proved to pass rigorous validation criteria, in accordance with the OECD guidelines. The proposed model is capable to explain the hepatocarcinogenic toxicity and could be exploited for predicting this property for chemicals at the early stage of their development, so optimizing resources and reducing animal testing.

AB - A dataset comprising 55 chemicals with hepatocarcinogenic potency indices was collected from the Carcinogenic Potency Database with the aim of developing QSAR models enabling prediction of the above unwanted property for New Chemical Entities. The dataset was rationally split into training and test sets by means of a sphere-exclusion type algorithm. Among the many algorithms explored to search regression models, only a Support Vector Machine (SVM) method led to a QSAR model, which was proved to pass rigorous validation criteria, in accordance with the OECD guidelines. The proposed model is capable to explain the hepatocarcinogenic toxicity and could be exploited for predicting this property for chemicals at the early stage of their development, so optimizing resources and reducing animal testing.

KW - Carcinogenic potency database

KW - Hepatocarcinogenic

KW - Quantitative structure-activity relationship

KW - Sphere-exclusion

KW - WEKA

UR - http://www.scopus.com/inward/record.url?scp=67650456828&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67650456828&partnerID=8YFLogxK

U2 - 10.1016/j.ejmech.2009.02.014

DO - 10.1016/j.ejmech.2009.02.014

M3 - Article

VL - 44

SP - 3658

EP - 3664

JO - European Journal of Medicinal Chemistry

JF - European Journal of Medicinal Chemistry

SN - 0223-5234

IS - 9

ER -