0000000000109857
AUTHOR
J. Burton
Comparative performances of machine learning methods for classifying Crohn Disease patients using genome-wide genotyping data
Crohn Disease (CD) is a complex genetic disorder for which more than 140 genes have been identified using genome wide association studies (GWAS). However, the genetic architecture of the trait remains largely unknown. The recent development of machine learning (ML) approaches incited us to apply them to classify healthy and diseased people according to their genomic information. The Immunochip dataset containing 18,227 CD patients and 34,050 healthy controls enrolled and genotyped by the international Inflammatory Bowel Disease genetic consortium (IIBDGC) has been re-analyzed using a set of ML methods: penalized logistic regression (LR), gradient boosted trees (GBT) and artificial neural ne…
Breeding annual legumes for sustainable agricultures must target for new and more complex variety ideotypes
International audience; Although yield and total biomass produced by annual legumes remain major objectives for breeders, environment-friendly, resource use efficient including symbiotic performance, resilient production in the context of climate change, adaptation to sustainable cropping systems (reducing leaching and glasshouse gas emissions), adaptation to diverse uses (seeds for feeds foods, non-food, forage or green manures), and finally new ecological services such as pollinator protection, imply the development of innovative genotypes, definition of new ideotypes and acceptance of their commercialisation. Taken as a whole, this means more complex and integrated objectives for breeder…