Bitte benutzen Sie diese Referenz, um auf diese Ressource zu verweisen: doi:10.22028/D291-42667
Titel: Chemical representation learning for toxicity prediction
VerfasserIn: Born, Jannis
Markert, Greta
Janakarajan, Nikita
Kimber, Talia B.
Volkamer, Andrea
Martínez, María Rodríguez
Manica, Matteo
Sprache: Englisch
Titel: Digital Discovery
Bandnummer: 2
Heft: 3
Seiten: 674-691
Verlag/Plattform: Royal Society of Chemistry
Erscheinungsjahr: 2023
DDC-Sachgruppe: 004 Informatik
Dokumenttyp: Journalartikel / Zeitschriftenartikel
Abstract: Undesired toxicity is a major hindrance to drug discovery and largely responsible for high attrition rates in early stages. This calls for new, reliable, and interpretable molecular property prediction models that help prioritize compounds and thus reduce the high costs for development and the risk to humans, animals, and the environment. Here, we propose an interpretable chemical language model that combines attention with multiscale convolutions and relies on data augmentation. We first benchmark various molecular representations (e.g., fingerprints, different flavors of SMILES and SELFIES, as well as graph and graph kernel methods) revealing that SMILES coupled with augmentation overall yields the best performance. Despite its simplicity, our model is then shown to outperform existing approaches across a wide range of molecular property prediction tasks, including but not limited to toxicity. Moreover, the attention weights of the model allow for easy interpretation and show enrichment of known toxicophores even without explicit supervision. To introduce a notion of model reliability, we propose and combine two simple methods for uncertainty estimation (Monte-Carlo dropout and test-time-augmentation). These methods not only identify samples with high prediction uncertainty, but also allow formation of implicit model ensembles that improve accuracy. Last, we validate our model on a large-scale proprietary toxicity dataset and find that it outperforms previous work while giving similar insights into revealing cytotoxic substructures.
DOI der Erstveröffentlichung: 10.1039/D2DD00099G
URL der Erstveröffentlichung: https://doi.org/10.1039/D2DD00099G
Link zu diesem Datensatz: urn:nbn:de:bsz:291--ds-426678
hdl:20.500.11880/38271
http://dx.doi.org/10.22028/D291-42667
ISSN: 2635-098X
Datum des Eintrags: 14-Aug-2024
Bezeichnung des in Beziehung stehenden Objekts: Electronic supplementary information
In Beziehung stehendes Objekt: https://www.rsc.org/suppdata/d2/dd/d2dd00099g/d2dd00099g1.pdf
Fakultät: MI - Fakultät für Mathematik und Informatik
Fachrichtung: MI - Informatik
Professur: MI - Prof. Dr. Andrea Volkamer
Sammlung:SciDok - Der Wissenschaftsserver der Universität des Saarlandes

Dateien zu diesem Datensatz:
Datei Beschreibung GrößeFormat 
d2dd00099g.pdf2,36 MBAdobe PDFÖffnen/Anzeigen


Diese Ressource wurde unter folgender Copyright-Bestimmung veröffentlicht: Lizenz von Creative Commons Creative Commons