Relevant Cycle Hypergraph Representation for Molecules

Benoit Gaüzère 1 Luc Brun 1 Didier Villemin 2
1 Equipe Image - Laboratoire GREYC - UMR6072
GREYC - Groupe de Recherche en Informatique, Image, Automatique et Instrumentation de Caen
Abstract : Chemoinformatics aims to predict molecule's properties through informational methods. Some methods base their prediction model on the comparison of molecular graphs. Considering such a molecular representation, graph kernels provide a nice framework which allows to combine machine learning techniques with graph theory. Despite the fact that molecular graph encodes all structural information of a molecule, it does not explicitly encode cyclic information. In this paper, we propose a new molecular representation based on a hypergraph which explicitly encodes both cyclic and acyclic information into one molecular representation called relevant cycle hypergraph. In addition, we propose a similarity measure in order to compare relevant cycle hypergraphs and use this molecular representation in a chemoinformatics prediction problem.
Type de document :
Communication dans un congrès
9th IAPR-TC-15 Graph-Based Representations in Pattern Recognition, May 2013, Austria. pp.111, 2013
Liste complète des métadonnées

Littérature citée [13 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-00829227
Contributeur : Benoit Gaüzère <>
Soumis le : dimanche 2 juin 2013 - 21:46:43
Dernière modification le : jeudi 7 février 2019 - 15:43:37
Document(s) archivé(s) le : mardi 4 avril 2017 - 15:02:16

Fichier

GbR2013_014.pdf
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

  • HAL Id : hal-00829227, version 1

Citation

Benoit Gaüzère, Luc Brun, Didier Villemin. Relevant Cycle Hypergraph Representation for Molecules. 9th IAPR-TC-15 Graph-Based Representations in Pattern Recognition, May 2013, Austria. pp.111, 2013. 〈hal-00829227〉

Partager

Métriques

Consultations de la notice

157

Téléchargements de fichiers

246