A Graph Kernel incorporating molecule's stereisomerism information

Abstract : The prediction of molecule's properties through Quantitative Structure Activity (resp. Property) Relationships are two active research fields named QSAR and QSPR. Within these frameworks Graph kernels allow to combine a natural encoding of a molecule by a graph with classical statistical tools such as SVM or kernel ridge regression. Unfortunately some molecules encoded by a same graph and differing only by the three dimensional orientations of their atoms in space have different properties. Such molecules are called stereoisomers. These latter properties can not be predicted by usual graph methods which do not encode stereoisomerism. In this paper we propose a new graph encoding of molecules taking explicitly into account stereoisomerism and propose a new kernel between these structures in order to predict properties related to stereoisomerism.
Type de document :
Communication dans un congrès
22nd International Conference on Pattern Recognition (ICPR) 2014, Aug 2014, Stockholm, Sweden. 2014
Liste complète des métadonnées

Littérature citée [10 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01059530
Contributeur : Pierre-Anthony Grenier <>
Soumis le : lundi 1 septembre 2014 - 11:14:36
Dernière modification le : jeudi 7 février 2019 - 17:27:44
Document(s) archivé(s) le : mardi 2 décembre 2014 - 10:15:17

Fichier

article.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01059530, version 1

Citation

Pierre-Anthony Grenier, Luc Brun, Didier Villemin. A Graph Kernel incorporating molecule's stereisomerism information. 22nd International Conference on Pattern Recognition (ICPR) 2014, Aug 2014, Stockholm, Sweden. 2014. 〈hal-01059530〉

Partager

Métriques

Consultations de la notice

277

Téléchargements de fichiers

162