0000000001167233
AUTHOR
G. Mahy
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…
No performance reduction at the present northern edge of Ambrosia artemisiifolia L. invasion range
Plant populations at range edges may exhibit reduction of performances and fitness. In the case of biological invasions, such a reduction could be associated with a slowing down of the spread and explain the non-naturalization of a species outside its present invasion range. Common ragweed (Ambrosia artemisiifolia L.) is an ideal model to investigate such processes, since it is invasive in France but not naturalized in northern countries, such as Belgium and the Netherlands. In this study, we test if the performances of ragweed populations vary among different invasion zones. Three populations were selected in each of four invasion zones in Western Europe: 1) French invasion area; 2) northe…