lnu.sePublikationer
Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
A risk assessment perspective of current practice in characterizing uncertainties in QSAR regression predictions
Linnéuniversitetet, Fakultetsnämnden för naturvetenskap och teknik, Institutionen för naturvetenskap, NV.
Linnéuniversitetet, Fakultetsnämnden för naturvetenskap och teknik, Institutionen för naturvetenskap, NV.
Linnéuniversitetet, Fakultetsnämnden för naturvetenskap och teknik, Institutionen för naturvetenskap, NV.ORCID-id: 0000-0001-9382-9296
2011 (Engelska)Ingår i: Molecular Informatics, ISSN 1868-1751, Vol. 30, nr 6-7, s. 551-564Artikel i tidskrift (Refereegranskat) Published
Abstract [en]

The European REACH legislation accepts the use of non-testing methods, such as QSARs, to inform chemical risk assessment. In this paper, we aim to initiate a discussion on the characterization of predictive uncertainty from QSAR regressions. For the purpose of decision making, we discuss applications from the perspective of applying QSARs to support probabilistic risk assessment. Predictive uncertainty is characterized by a wide variety of methods, ranging from pure expert judgement based on variability in experimental data, through data-driven statistical inference, to the use of probabilistic QSAR models. Model uncertainty is dealt with by assessing confidence in predictions and by building consensus models. The characterization of predictive uncertainty would benefit from a probabilistic formulation of QSAR models (e.g. generalized linear models, conditional density estimators or Bayesian models). This would allow predictive uncertainty to be quantified as probability distributions, such as Bayesian predictive posteriors, and likelihood-based methods to address model uncertainty. QSAR regression models with point estimates as output may be turned into a probabilistic framework without any loss of validity from a chemical point of view. A QSAR model for use in probabilistic risk assessment needs to be validated for its ability to make reliable predictions and to quantify associated uncertainty.

Ort, förlag, år, upplaga, sidor
2011. Vol. 30, nr 6-7, s. 551-564
Nyckelord [en]
Decision making; Predictive uncertainty; Probabilistic risk assessment; REACH; Regression
Nationell ämneskategori
Naturvetenskap
Forskningsämne
Naturvetenskap, Miljövetenskap
Identifikatorer
URN: urn:nbn:se:lnu:diva-11414DOI: 10.1002/minf.201000177ISI: 000293847700006Scopus ID: 2-s2.0-79960573919OAI: oai:DiVA.org:lnu-11414DiVA, id: diva2:410526
Tillgänglig från: 2011-04-14 Skapad: 2011-04-14 Senast uppdaterad: 2016-11-15Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Övriga länkar

Förlagets fulltextScopus

Personposter BETA

Sahlin, UllrikaFilipsson, MonikaÖberg, Tomas

Sök vidare i DiVA

Av författaren/redaktören
Sahlin, UllrikaFilipsson, MonikaÖberg, Tomas
Av organisationen
Institutionen för naturvetenskap, NV
Naturvetenskap

Sök vidare utanför DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetricpoäng

doi
urn-nbn
Totalt: 131 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf