Multi-task learning for pKa prediction

Lade...
Vorschaubild
Dateien
Zu diesem Dokument gibt es keine Dateien.
Datum
2012
Autor:innen
Skolidis, Grigorios
Hansen, Katja
Sanguinetti, Guido
Herausgeber:innen
Kontakt
ISSN der Zeitschrift
Electronic ISSN
ISBN
Bibliografische Daten
Verlag
Schriftenreihe
Auflagebezeichnung
URI (zitierfähiger Link)
ArXiv-ID
Internationale Patentnummer
EU-Projektnummer
DFG-Projektnummer
Projekt
Open Access-Veröffentlichung
Gesperrt bis
Titel in einer weiteren Sprache
Forschungsvorhaben
Organisationseinheiten
Zeitschriftenheft
Publikationstyp
Zeitschriftenartikel
Publikationsstatus
Published
Erschienen in
Journal of Computer-Aided Molecular Design. Springer. 2012, 26(7), pp. 883-895. ISSN 0920-654X. eISSN 1573-4951. Available under: doi: 10.1007/s10822-012-9582-x
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 multi-task 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.

Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
004 Informatik
Schlagwörter
pKa prediction, Multi-task learning, Quantitative structure–property relationships, Gaussian processes
Konferenz
Rezension
undefined / . - undefined, undefined
Zitieren
ISO 690SKOLIDIS, Grigorios, Katja HANSEN, Guido SANGUINETTI, Matthias RUPP, 2012. Multi-task learning for pKa prediction. In: Journal of Computer-Aided Molecular Design. Springer. 2012, 26(7), pp. 883-895. ISSN 0920-654X. eISSN 1573-4951. Available under: doi: 10.1007/s10822-012-9582-x
BibTex
@article{Skolidis2012-07Multi-52163,
  year={2012},
  doi={10.1007/s10822-012-9582-x},
  title={Multi-task learning for pK<sub>a</sub> prediction},
  number={7},
  volume={26},
  issn={0920-654X},
  journal={Journal of Computer-Aided Molecular Design},
  pages={883--895},
  author={Skolidis, Grigorios and Hansen, Katja and Sanguinetti, Guido and Rupp, Matthias}
}
RDF
<rdf:RDF
    xmlns:dcterms="http://purl.org/dc/terms/"
    xmlns:dc="http://purl.org/dc/elements/1.1/"
    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
    xmlns:bibo="http://purl.org/ontology/bibo/"
    xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#"
    xmlns:foaf="http://xmlns.com/foaf/0.1/"
    xmlns:void="http://rdfs.org/ns/void#"
    xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > 
  <rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/52163">
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2020-12-17T14:24:15Z</dcterms:available>
    <dc:contributor>Rupp, Matthias</dc:contributor>
    <dcterms:abstract xml:lang="eng">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 multi-task 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.</dcterms:abstract>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:creator>Hansen, Katja</dc:creator>
    <dcterms:title>Multi-task learning for pK&lt;sub&gt;a&lt;/sub&gt; prediction</dcterms:title>
    <dc:creator>Sanguinetti, Guido</dc:creator>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/52163"/>
    <dc:creator>Skolidis, Grigorios</dc:creator>
    <dc:creator>Rupp, Matthias</dc:creator>
    <dc:contributor>Sanguinetti, Guido</dc:contributor>
    <dc:language>eng</dc:language>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dc:rights>terms-of-use</dc:rights>
    <dc:contributor>Skolidis, Grigorios</dc:contributor>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:contributor>Hansen, Katja</dc:contributor>
    <dcterms:issued>2012-07</dcterms:issued>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2020-12-17T14:24:15Z</dc:date>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
  </rdf:Description>
</rdf:RDF>
Interner Vermerk
xmlui.Submission.submit.DescribeStep.inputForms.label.kops_note_fromSubmitter
Kontakt
URL der Originalveröffentl.
Prüfdatum der URL
Prüfungsdatum der Dissertation
Finanzierungsart
Kommentar zur Publikation
Allianzlizenz
Corresponding Authors der Uni Konstanz vorhanden
Internationale Co-Autor:innen
Universitätsbibliographie
Nein
Begutachtet
Ja