Integrating in silico models to enhance predictivity for developmental toxicity

Marco Marzo, Sunil Kulkarni, Alberto Manganaro, Alessandra Roncaglioni, Shengde Wu, Tara S. Barton-Maclaren, Cathy Lester, Emilio Benfenati

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

Application of in silico models to predict developmental toxicity has demonstrated limited success particularly when employed as a single source of information. It is acknowledged that modelling the complex outcomes related to this endpoint is a challenge; however, such models have been developed and reported in the literature. The current study explored the possibility of integrating the selected public domain models (CAESAR, SARpy and P&G model) with the selected commercial modelling suites (Multicase, Leadscope and Derek Nexus) to assess if there is an increase in overall predictive performance. The results varied according to the data sets used to assess performance which improved upon model integration relative to individual models. Moreover, because different models are based on different specific developmental toxicity effects, integration of these models increased the applicable chemical and biological spaces. It is suggested that this approach reduces uncertainty associated with in silico predictions by achieving a consensus among a battery of models. The use of tools to assess the applicability domain also improves the interpretation of the predictions. This has been verified in the case of the software VEGA, which makes freely available QSAR models with a measurement of the applicability domain.

Original languageEnglish
Pages (from-to)127-137
Number of pages11
JournalToxicology
Volume370
DOIs
Publication statusPublished - Aug 31 2016

Fingerprint

Computer Simulation
Toxicity
Quantitative Structure-Activity Relationship
Public Sector
Uncertainty
Software
Datasets
Nexus

Keywords

  • Developmental toxicity
  • In silico
  • In vitro and alternatives
  • QSAR
  • VEGA

ASJC Scopus subject areas

  • Toxicology

Cite this

Integrating in silico models to enhance predictivity for developmental toxicity. / Marzo, Marco; Kulkarni, Sunil; Manganaro, Alberto; Roncaglioni, Alessandra; Wu, Shengde; Barton-Maclaren, Tara S.; Lester, Cathy; Benfenati, Emilio.

In: Toxicology, Vol. 370, 31.08.2016, p. 127-137.

Research output: Contribution to journalArticle

Marzo, M, Kulkarni, S, Manganaro, A, Roncaglioni, A, Wu, S, Barton-Maclaren, TS, Lester, C & Benfenati, E 2016, 'Integrating in silico models to enhance predictivity for developmental toxicity', Toxicology, vol. 370, pp. 127-137. https://doi.org/10.1016/j.tox.2016.09.015
Marzo, Marco ; Kulkarni, Sunil ; Manganaro, Alberto ; Roncaglioni, Alessandra ; Wu, Shengde ; Barton-Maclaren, Tara S. ; Lester, Cathy ; Benfenati, Emilio. / Integrating in silico models to enhance predictivity for developmental toxicity. In: Toxicology. 2016 ; Vol. 370. pp. 127-137.
@article{8b8914f806a541ef8e4245f579834149,
title = "Integrating in silico models to enhance predictivity for developmental toxicity",
abstract = "Application of in silico models to predict developmental toxicity has demonstrated limited success particularly when employed as a single source of information. It is acknowledged that modelling the complex outcomes related to this endpoint is a challenge; however, such models have been developed and reported in the literature. The current study explored the possibility of integrating the selected public domain models (CAESAR, SARpy and P&G model) with the selected commercial modelling suites (Multicase, Leadscope and Derek Nexus) to assess if there is an increase in overall predictive performance. The results varied according to the data sets used to assess performance which improved upon model integration relative to individual models. Moreover, because different models are based on different specific developmental toxicity effects, integration of these models increased the applicable chemical and biological spaces. It is suggested that this approach reduces uncertainty associated with in silico predictions by achieving a consensus among a battery of models. The use of tools to assess the applicability domain also improves the interpretation of the predictions. This has been verified in the case of the software VEGA, which makes freely available QSAR models with a measurement of the applicability domain.",
keywords = "Developmental toxicity, In silico, In vitro and alternatives, QSAR, VEGA",
author = "Marco Marzo and Sunil Kulkarni and Alberto Manganaro and Alessandra Roncaglioni and Shengde Wu and Barton-Maclaren, {Tara S.} and Cathy Lester and Emilio Benfenati",
year = "2016",
month = "8",
day = "31",
doi = "10.1016/j.tox.2016.09.015",
language = "English",
volume = "370",
pages = "127--137",
journal = "Toxicology",
issn = "0300-483X",
publisher = "Elsevier Ireland Ltd",

}

TY - JOUR

T1 - Integrating in silico models to enhance predictivity for developmental toxicity

AU - Marzo, Marco

AU - Kulkarni, Sunil

AU - Manganaro, Alberto

AU - Roncaglioni, Alessandra

AU - Wu, Shengde

AU - Barton-Maclaren, Tara S.

AU - Lester, Cathy

AU - Benfenati, Emilio

PY - 2016/8/31

Y1 - 2016/8/31

N2 - Application of in silico models to predict developmental toxicity has demonstrated limited success particularly when employed as a single source of information. It is acknowledged that modelling the complex outcomes related to this endpoint is a challenge; however, such models have been developed and reported in the literature. The current study explored the possibility of integrating the selected public domain models (CAESAR, SARpy and P&G model) with the selected commercial modelling suites (Multicase, Leadscope and Derek Nexus) to assess if there is an increase in overall predictive performance. The results varied according to the data sets used to assess performance which improved upon model integration relative to individual models. Moreover, because different models are based on different specific developmental toxicity effects, integration of these models increased the applicable chemical and biological spaces. It is suggested that this approach reduces uncertainty associated with in silico predictions by achieving a consensus among a battery of models. The use of tools to assess the applicability domain also improves the interpretation of the predictions. This has been verified in the case of the software VEGA, which makes freely available QSAR models with a measurement of the applicability domain.

AB - Application of in silico models to predict developmental toxicity has demonstrated limited success particularly when employed as a single source of information. It is acknowledged that modelling the complex outcomes related to this endpoint is a challenge; however, such models have been developed and reported in the literature. The current study explored the possibility of integrating the selected public domain models (CAESAR, SARpy and P&G model) with the selected commercial modelling suites (Multicase, Leadscope and Derek Nexus) to assess if there is an increase in overall predictive performance. The results varied according to the data sets used to assess performance which improved upon model integration relative to individual models. Moreover, because different models are based on different specific developmental toxicity effects, integration of these models increased the applicable chemical and biological spaces. It is suggested that this approach reduces uncertainty associated with in silico predictions by achieving a consensus among a battery of models. The use of tools to assess the applicability domain also improves the interpretation of the predictions. This has been verified in the case of the software VEGA, which makes freely available QSAR models with a measurement of the applicability domain.

KW - Developmental toxicity

KW - In silico

KW - In vitro and alternatives

KW - QSAR

KW - VEGA

UR - http://www.scopus.com/inward/record.url?scp=84991730726&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84991730726&partnerID=8YFLogxK

U2 - 10.1016/j.tox.2016.09.015

DO - 10.1016/j.tox.2016.09.015

M3 - Article

AN - SCOPUS:84991730726

VL - 370

SP - 127

EP - 137

JO - Toxicology

JF - Toxicology

SN - 0300-483X

ER -