Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

 
 
DownloadE-Mail
  Multi-task learning for pKa prediction

Skolidis, G., Hansen, K., Sanguinetti, G., & Rupp, M. (2012). Multi-task learning for pKa prediction. Journal of Computer-Aided Molecular Design, 26(7), 883-895. doi:10.1007/s10822-012-9582-x.

Item is

Externe Referenzen

einblenden:

Urheber

einblenden:
ausblenden:
 Urheber:
Skolidis, Grigorios1, Autor
Hansen, Katja2, 3, Autor           
Sanguinetti, Guido 4, Autor
Rupp, Matthias3, 5, Autor
Affiliations:
1Department of Statistical Science, University College London,, Gower Street, London WC1E 6BT, UK, ou_persistent22              
2Theory, Fritz Haber Institute, Max Planck Society, Faradayweg 4-6, 14195 Berlin, DE, ou_634547              
3Machine Learning Group, TU Berlin, Franklinstr. 28/29, 10587 Berlin, Germany, ou_persistent22              
4School of Informatics, University of Edinburgh,, 10 Crichton Street, EH8 9AB Edinburgh, Scotland, ou_persistent22              
5Institute of Pharmaceutical Sciences, ETH Zurich,, Wolfgang-Pauli-Str. 10, 8093 Zürich, Switzerland, ou_persistent22              

Inhalt

einblenden:
ausblenden:
Schlagwörter: -
 Zusammenfassung: Many compound properties depend directly on the dissociation constants of its acidic and basic groups. Significant effort has been invested in computational models to predict these constants. For linear regression models, compounds are often divided into chemically motivated classes, with a separate model for each class. However, sometimes too few measurements are available for a class to build a reasonable model, e.g., when investigating a new compound series. If data for related classes are available, we show that multi-task learning can be used to improve predictions by utilizing data from these other classes. We investigate performance of linear Gaussian process regression models (single task, pooling, and multitask models) in the low sample size regime, using a published data set (n = 698, mostly monoprotic, in aqueous solution) divided beforehand into 15 classes. A multi-task regression model using the intrinsic model of co-regionalization and incomplete Cholesky decomposition performed best in 85 % of all experiments. The presented approach can be applied to estimate other molecular properties where few measurements are available.

Details

einblenden:
ausblenden:
Sprache(n): eng - English
 Datum: 2011-11-152012-05-112012-06-20
 Publikationsstatus: Online veröffentlicht
 Seiten: 13
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: Expertenbegutachtung
 Identifikatoren: DOI: 10.1007/s10822-012-9582-x
 Art des Abschluß: -

Veranstaltung

einblenden:

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: Journal of Computer-Aided Molecular Design
Genre der Quelle: Zeitschrift
 Urheber:
Affiliations:
Ort, Verlag, Ausgabe: Leiden, The Netherlands : ESCOM Science Publishers
Seiten: - Band / Heft: 26 (7) Artikelnummer: - Start- / Endseite: 883 - 895 Identifikator: ISSN: 0920-654X
CoNE: https://pure.mpg.de/cone/journals/resource/954925564670