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 language | English |
|---|---|
| Pages (from-to) | 127-137 |
| Number of pages | 11 |
| Journal | Toxicology |
| Volume | 370 |
| DOIs | |
| Publication status | Published - Aug 31 2016 |
Fingerprint
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 journal › Article
}
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 -