Skip to Main content Skip to Navigation

Modélisation de la stéréochimie : une application à la chémoinformatique

Pierre-Anthony Grenier 1 
1 Equipe Image - Laboratoire GREYC - UMR6072
GREYC - Groupe de Recherche en Informatique, Image et Instrumentation de Caen
Abstract : In the framework of prediction of molecule’s properties, graph kernels allow to combine a natural encoding of a molecule by a graph with classical statistical tools. 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. This work aims to take into account stereoisomerism into graph kernels method. In this document we first present the main methods of prediction of molecule’s properties, and we focus on methods based on graph kernels. Based on this state of the art, we present stereoisomers and a state of the art of methods which take into account those molecules. Then we propose to encode stereoisomers by ordered graphs. We define minimal stereo subgraphs, which are subgraphs that locally characterizes the stereochemistry. Those subgraphs are used to define a kernel that take into account the stereochemistry. Finally we propose three extensions for this kernel. Those extensions allow to consider the neighbourhoods of minimal stereo subgraphs and to compare different minimal stereo subgraphs.
Complete list of metadata

Cited literature [46 references]  Display  Hide  Download
Contributor : Greyc Référent Connect in order to contact the contributor
Submitted on : Thursday, January 7, 2016 - 1:59:10 PM
Last modification on : Saturday, June 25, 2022 - 9:50:15 AM
Long-term archiving on: : Friday, April 8, 2016 - 1:24:00 PM


  • HAL Id : tel-01252296, version 1


Pierre-Anthony Grenier. Modélisation de la stéréochimie : une application à la chémoinformatique. Vision par ordinateur et reconnaissance de formes [cs.CV]. Université de Caen Normandie, 2015. Français. ⟨tel-01252296⟩



Record views


Files downloads