A comparison of DEMETRA individual QSARs with an index for evaluation of uncertainty

Chiara Porcelli, Alessandra Roncaglioni, Antonio Chana, Emilio Benfenati

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Quantitative structure-activity relationships (QSARs) urgently need to be applied in regulatory programs. Many QSAR models can predict the effect of a wide range of substances to different endpoints, particularly in the case of ecotoxicity, but it is difficult to choose the most appropriate model on the basis of the requirements of the application. During the EC-funded project DEMETRA (www.demetra-tox.net) a huge number of QSAR models have been developed for the prediction of different ecotoxicological endpoints. DEMETRA individual models on rainbow trout LC50 after 96 h, water flea LC50 after 48 h and honey bee LD50 after 48 h have been used as a QSAR database to test the advantages of a new index for evaluating model uncertainty. This index takes into consideration the number of outliers (weighted on the total number of compounds) and their root mean square error. Application on the DEMETRA QSAR database indicated that the index can identify the models with the best performance with regard to outliers, and can be used, together with other classical statistical measures (e.g., the squared correlation coefficient), to support the evaluation of QSAR models.

Original languageEnglish
Pages (from-to)1845-1852
Number of pages8
JournalChemosphere
Volume71
Issue number10
DOIs
Publication statusPublished - May 2008

Fingerprint

Quantitative Structure-Activity Relationship
Uncertainty
outlier
Cladocera
Databases
Honey
Oncorhynchus mykiss
Bees
Lethal Dose 50
honey
evaluation
comparison
index
structure-activity relationship
bee
Mean square error
rainbow
Water
prediction

Keywords

  • DEMETRA
  • Ecotoxicity
  • Index
  • QSAR
  • REACH
  • Uncertainty

ASJC Scopus subject areas

  • Environmental Chemistry
  • Environmental Science(all)

Cite this

A comparison of DEMETRA individual QSARs with an index for evaluation of uncertainty. / Porcelli, Chiara; Roncaglioni, Alessandra; Chana, Antonio; Benfenati, Emilio.

In: Chemosphere, Vol. 71, No. 10, 05.2008, p. 1845-1852.

Research output: Contribution to journalArticle

@article{817c3b7eba9642a49f9d616999474f3f,
title = "A comparison of DEMETRA individual QSARs with an index for evaluation of uncertainty",
abstract = "Quantitative structure-activity relationships (QSARs) urgently need to be applied in regulatory programs. Many QSAR models can predict the effect of a wide range of substances to different endpoints, particularly in the case of ecotoxicity, but it is difficult to choose the most appropriate model on the basis of the requirements of the application. During the EC-funded project DEMETRA (www.demetra-tox.net) a huge number of QSAR models have been developed for the prediction of different ecotoxicological endpoints. DEMETRA individual models on rainbow trout LC50 after 96 h, water flea LC50 after 48 h and honey bee LD50 after 48 h have been used as a QSAR database to test the advantages of a new index for evaluating model uncertainty. This index takes into consideration the number of outliers (weighted on the total number of compounds) and their root mean square error. Application on the DEMETRA QSAR database indicated that the index can identify the models with the best performance with regard to outliers, and can be used, together with other classical statistical measures (e.g., the squared correlation coefficient), to support the evaluation of QSAR models.",
keywords = "DEMETRA, Ecotoxicity, Index, QSAR, REACH, Uncertainty",
author = "Chiara Porcelli and Alessandra Roncaglioni and Antonio Chana and Emilio Benfenati",
year = "2008",
month = "5",
doi = "10.1016/j.chemosphere.2008.02.038",
language = "English",
volume = "71",
pages = "1845--1852",
journal = "Chemosphere",
issn = "0045-6535",
publisher = "Elsevier Limited",
number = "10",

}

TY - JOUR

T1 - A comparison of DEMETRA individual QSARs with an index for evaluation of uncertainty

AU - Porcelli, Chiara

AU - Roncaglioni, Alessandra

AU - Chana, Antonio

AU - Benfenati, Emilio

PY - 2008/5

Y1 - 2008/5

N2 - Quantitative structure-activity relationships (QSARs) urgently need to be applied in regulatory programs. Many QSAR models can predict the effect of a wide range of substances to different endpoints, particularly in the case of ecotoxicity, but it is difficult to choose the most appropriate model on the basis of the requirements of the application. During the EC-funded project DEMETRA (www.demetra-tox.net) a huge number of QSAR models have been developed for the prediction of different ecotoxicological endpoints. DEMETRA individual models on rainbow trout LC50 after 96 h, water flea LC50 after 48 h and honey bee LD50 after 48 h have been used as a QSAR database to test the advantages of a new index for evaluating model uncertainty. This index takes into consideration the number of outliers (weighted on the total number of compounds) and their root mean square error. Application on the DEMETRA QSAR database indicated that the index can identify the models with the best performance with regard to outliers, and can be used, together with other classical statistical measures (e.g., the squared correlation coefficient), to support the evaluation of QSAR models.

AB - Quantitative structure-activity relationships (QSARs) urgently need to be applied in regulatory programs. Many QSAR models can predict the effect of a wide range of substances to different endpoints, particularly in the case of ecotoxicity, but it is difficult to choose the most appropriate model on the basis of the requirements of the application. During the EC-funded project DEMETRA (www.demetra-tox.net) a huge number of QSAR models have been developed for the prediction of different ecotoxicological endpoints. DEMETRA individual models on rainbow trout LC50 after 96 h, water flea LC50 after 48 h and honey bee LD50 after 48 h have been used as a QSAR database to test the advantages of a new index for evaluating model uncertainty. This index takes into consideration the number of outliers (weighted on the total number of compounds) and their root mean square error. Application on the DEMETRA QSAR database indicated that the index can identify the models with the best performance with regard to outliers, and can be used, together with other classical statistical measures (e.g., the squared correlation coefficient), to support the evaluation of QSAR models.

KW - DEMETRA

KW - Ecotoxicity

KW - Index

KW - QSAR

KW - REACH

KW - Uncertainty

UR - http://www.scopus.com/inward/record.url?scp=42049106408&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=42049106408&partnerID=8YFLogxK

U2 - 10.1016/j.chemosphere.2008.02.038

DO - 10.1016/j.chemosphere.2008.02.038

M3 - Article

VL - 71

SP - 1845

EP - 1852

JO - Chemosphere

JF - Chemosphere

SN - 0045-6535

IS - 10

ER -