To Örebro University

oru.seÖrebro University Publications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Multitask Modeling with Confidence Using Matrix Factorization and Conformal Prediction
Swetox, Karolinska Institute, Unit of Toxicology Sciences, Södertälje, Sweden; Department of Computer and Systems Sciences, Stockholm University, Kista, Sweden.ORCID iD: 0000-0003-3107-331X
Alzheimer's Research UK UCL Drug Discovery Institute, University College, London, England; Francis Crick Institute, London, England.ORCID iD: 0000-0002-5556-8133
2019 (English)In: Journal of Chemical Information and Modeling, ISSN 1549-9596, E-ISSN 1549-960X, Vol. 59, no 4, p. 1598-1604Article in journal (Refereed) Published
Abstract [en]

Multitask prediction of bioactivities is often faced with challenges relating to the sparsity of data and imbalance between different labels. We propose class conditional (Mondrian) conformal predictors using underlying Macau models as a novel approach for large scale bioactivity prediction. This approach handles both high degrees of missing data and label imbalances while still producing high quality predictive models. When applied to ten assay end points from PubChem, the models generated valid models with an efficiency of 74.0-80.1% at the 80% confidence level with similar performance both for the minority and majority class. Also when deleting progressively larger portions of the available data (0-80%) the performance of the models remained robust with only minor deterioration (reduction in efficiency between 5 and 10%). Compared to using Macau without conformal prediction the method presented here significantly improves the performance on imbalanced data sets.

Place, publisher, year, edition, pages
Washington: American Chemical Society (ACS), 2019. Vol. 59, no 4, p. 1598-1604
National Category
Pharmacology and Toxicology Bioinformatics and Systems Biology Computer Sciences
Identifiers
URN: urn:nbn:se:oru:diva-83145DOI: 10.1021/acs.jcim.9b00027ISI: 000465644500030PubMedID: 30908915Scopus ID: 2-s2.0-85064354183OAI: oai:DiVA.org:oru-83145DiVA, id: diva2:1440452
Note

Forskningsfinansiärer:

Alzheimer's Research UK, Grant Number: 1077089, SC042474

Cancer Research UK, Grant Number: FC001002

UK Medical Research Council, Grant Number: FC001002

Wellcome Trust, Grant Number: FC001002

Available from: 2019-05-27 Created: 2020-06-15 Last updated: 2020-07-16Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textPubMedScopus

Authority records

Norinder, Ulf

Search in DiVA

By author/editor
Norinder, UlfSvensson, Fredrik
In the same journal
Journal of Chemical Information and Modeling
Pharmacology and ToxicologyBioinformatics and Systems BiologyComputer Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
pubmed
urn-nbn

Altmetric score

doi
pubmed
urn-nbn
Total: 59 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf