Adrien Coulet, Kevin Dalleau, Patrice Ringot, Sébastien Da Silva, Ndeye Coumba Ndiaye, Yassine Marzougui, Knowledge representation, reasonning (ORPAILLEUR), Inria Nancy - Grand Est, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Department of Natural Language Processing & Knowledge Discovery (LORIA - NLPKD), Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL), Ecole Nationale Supérieure des Mines de Nancy (ENSMN), Institut Mines-Télécom [Paris] (IMT)-Université de Lorraine (UL), Interactions Gène-Environnement en Physiopathologie Cardio-Vasculaire (IGE-PCV), Institut National de la Santé et de la Recherche Médicale (INSERM)-Université de Lorraine (UL), ANR PractiKPharma project, grant ANR-15-CE23-0028, funded by the French National Research Agency (http://practikpharma.loria.fr/) and *Snowflake, an Inria associate team (http://snowflake.loria.fr/), Snowflake Inria Associate Team, Inria@SiliconValley, Snowball Inria Associate Team, ANR-15-CE23-0028,PractiKPharma,Confrontation entre connaissances de l'état de l'art et connaissances extraites de dossiers patients en pharmacogénomique(2015), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS), Coulet, Adrien, and Interactions humain-machine, objets connectés, contenus numériques, données massives et connaissance - Confrontation entre connaissances de l'état de l'art et connaissances extraites de dossiers patients en pharmacogénomique - - PractiKPharma2015 - ANR-15-CE23-0028 - AAPG2015 - VALID
Background A standard task in pharmacogenomics research is identifying genes that may be involved in drug response variability, i.e., pharmacogenes. Because genomic experiments tended to generate many false positives, computational approaches based on the use of background knowledge have been proposed. Until now, only molecular networks or the biomedical literature were used, whereas many other resources are available. Method We propose here to consume a diverse and larger set of resources using linked data related either to genes, drugs or diseases. One of the advantages of linked data is that they are built on a standard framework that facilitates the joint use of various sources, and thus facilitates considering features of various origins. We propose a selection and linkage of data sources relevant to pharmacogenomics, including for example DisGeNET and Clinvar. We use machine learning to identify and prioritize pharmacogenes that are the most probably valid, considering the selected linked data. This identification relies on the classification of gene–drug pairs as either pharmacogenomically associated or not and was experimented with two machine learning methods –random forest and graph kernel–, which results are compared in this article. Results We assembled a set of linked data relative to pharmacogenomics, of 2,610,793 triples, coming from six distinct resources. Learning from these data, random forest enables identifying valid pharmacogenes with a F-measure of 0.73, on a 10 folds cross-validation, whereas graph kernel achieves a F-measure of 0.81. A list of top candidates proposed by both approaches is provided and their obtention is discussed. Electronic supplementary material The online version of this article (doi:10.1186/s13326-017-0125-1) contains supplementary material, which is available to authorized users.