Machine learning of molecular electronic properties in chemical compound space

Lade...
Vorschaubild
Dateien
Montavon_2-r9g26xv1vvo45.pdf
Montavon_2-r9g26xv1vvo45.pdfGröße: 6.86 MBDownloads: 351
Datum
2013
Autor:innen
Montavon, Grégoire
Gobre, Vivekanand
Vazquez-Mayagoitia, Alvaro
Hansen, Katja
Tkatchenko, Alexandre
Müller, Klaus-Robert
von Lilienfeld, O. Anatole
Herausgeber:innen
Kontakt
ISSN der Zeitschrift
Electronic ISSN
ISBN
Bibliografische Daten
Verlag
Schriftenreihe
Auflagebezeichnung
ArXiv-ID
Internationale Patentnummer
Angaben zur Forschungsförderung
Projekt
Open Access-Veröffentlichung
Open Access Gold
Core Facility der Universität Konstanz
Gesperrt bis
Titel in einer weiteren Sprache
Forschungsvorhaben
Organisationseinheiten
Zeitschriftenheft
Publikationstyp
Zeitschriftenartikel
Publikationsstatus
Published
Erschienen in
New Journal of Physics. Institute of Physics Publishing (IOP). 2013, 15(9), 095003. eISSN 1367-2630. Available under: doi: 10.1088/1367-2630/15/9/095003
Zusammenfassung

The combination of modern scientific computing with electronic structure theory can lead to an unprecedented amount of data amenable to intelligent data analysis for the identification of meaningful, novel and predictive structure–property relationships. Such relationships enable high-throughput screening for relevant properties in an exponentially growing pool of virtual compounds that are synthetically accessible. Here, we present a machine learning model, trained on a database of ab initio calculation results for thousands of organic molecules, that simultaneously predicts multiple electronic ground- and excited-state properties. The properties include atomization energy, polarizability, frontier orbital eigenvalues, ionization potential, electron affinity and excitation energies. The machine learning model is based on a deep multi-task artificial neural network, exploiting the underlying correlations between various molecular properties. The input is identical to ab initio methods, i.e. nuclear charges and Cartesian coordinates of all atoms. For small organic molecules, the accuracy of such a 'quantum machine' is similar, and sometimes superior, to modern quantum-chemical methods—at negligible computational cost.

Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
004 Informatik
Schlagwörter
Konferenz
Rezension
undefined / . - undefined, undefined
Zitieren
ISO 690MONTAVON, Grégoire, Matthias RUPP, Vivekanand GOBRE, Alvaro VAZQUEZ-MAYAGOITIA, Katja HANSEN, Alexandre TKATCHENKO, Klaus-Robert MÜLLER, O. Anatole VON LILIENFELD, 2013. Machine learning of molecular electronic properties in chemical compound space. In: New Journal of Physics. Institute of Physics Publishing (IOP). 2013, 15(9), 095003. eISSN 1367-2630. Available under: doi: 10.1088/1367-2630/15/9/095003
BibTex
@article{Montavon2013-09-04Machi-53899,
  year={2013},
  doi={10.1088/1367-2630/15/9/095003},
  title={Machine learning of molecular electronic properties in chemical compound space},
  number={9},
  volume={15},
  journal={New Journal of Physics},
  author={Montavon, Grégoire and Rupp, Matthias and Gobre, Vivekanand and Vazquez-Mayagoitia, Alvaro and Hansen, Katja and Tkatchenko, Alexandre and Müller, Klaus-Robert and von Lilienfeld, O. Anatole},
  note={Article Number: 095003}
}
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/123456789/53899">
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dc:contributor>von Lilienfeld, O. Anatole</dc:contributor>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/53899/3/Montavon_2-r9g26xv1vvo45.pdf"/>
    <dc:contributor>Gobre, Vivekanand</dc:contributor>
    <dcterms:title>Machine learning of molecular electronic properties in chemical compound space</dcterms:title>
    <dc:contributor>Hansen, Katja</dc:contributor>
    <dc:creator>von Lilienfeld, O. Anatole</dc:creator>
    <dc:creator>Vazquez-Mayagoitia, Alvaro</dc:creator>
    <dc:creator>Müller, Klaus-Robert</dc:creator>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:contributor>Rupp, Matthias</dc:contributor>
    <dc:creator>Hansen, Katja</dc:creator>
    <dc:creator>Gobre, Vivekanand</dc:creator>
    <dc:rights>Attribution 3.0 Unported</dc:rights>
    <dc:creator>Tkatchenko, Alexandre</dc:creator>
    <dc:contributor>Müller, Klaus-Robert</dc:contributor>
    <dcterms:issued>2013-09-04</dcterms:issued>
    <dc:language>eng</dc:language>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2021-06-07T12:48:08Z</dc:date>
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/53899/3/Montavon_2-r9g26xv1vvo45.pdf"/>
    <dcterms:abstract xml:lang="eng">The combination of modern scientific computing with electronic structure theory can lead to an unprecedented amount of data amenable to intelligent data analysis for the identification of meaningful, novel and predictive structure–property relationships. Such relationships enable high-throughput screening for relevant properties in an exponentially growing pool of virtual compounds that are synthetically accessible. Here, we present a machine learning model, trained on a database of ab initio calculation results for thousands of organic molecules, that simultaneously predicts multiple electronic ground- and excited-state properties. The properties include atomization energy, polarizability, frontier orbital eigenvalues, ionization potential, electron affinity and excitation energies. The machine learning model is based on a deep multi-task artificial neural network, exploiting the underlying correlations between various molecular properties. The input is identical to ab initio methods, i.e. nuclear charges and Cartesian coordinates of all atoms. For small organic molecules, the accuracy of such a 'quantum machine' is similar, and sometimes superior, to modern quantum-chemical methods—at negligible computational cost.</dcterms:abstract>
    <dc:contributor>Tkatchenko, Alexandre</dc:contributor>
    <dc:contributor>Vazquez-Mayagoitia, Alvaro</dc:contributor>
    <dcterms:rights rdf:resource="http://creativecommons.org/licenses/by/3.0/"/>
    <dc:creator>Montavon, Grégoire</dc:creator>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2021-06-07T12:48:08Z</dcterms:available>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/53899"/>
    <dc:contributor>Montavon, Grégoire</dc:contributor>
    <dc:creator>Rupp, Matthias</dc:creator>
    <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
Diese Publikation teilen