| 1. |
|
|
| 2. |
- Romagnoni, A, et al.
(författare)
-
Comparative performances of machine learning methods for classifying Crohn Disease patients using genome-wide genotyping data
- 2019
-
Ingår i: Scientific reports. - : Springer Science and Business Media LLC. - 2045-2322. ; 9:1, s. 10351-
-
Tidskriftsartikel (refereegranskat)abstract
- 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 networks (NN). The main score used to compare the methods was the Area Under the ROC Curve (AUC) statistics. The impact of quality control (QC), imputing and coding methods on LR results showed that QC methods and imputation of missing genotypes may artificially increase the scores. At the opposite, neither the patient/control ratio nor marker preselection or coding strategies significantly affected the results. LR methods, including Lasso, Ridge and ElasticNet provided similar results with a maximum AUC of 0.80. GBT methods like XGBoost, LightGBM and CatBoost, together with dense NN with one or more hidden layers, provided similar AUC values, suggesting limited epistatic effects in the genetic architecture of the trait. ML methods detected near all the genetic variants previously identified by GWAS among the best predictors plus additional predictors with lower effects. The robustness and complementarity of the different methods are also studied. Compared to LR, non-linear models such as GBT or NN may provide robust complementary approaches to identify and classify genetic markers.
|
|
| 3. |
|
|
| 4. |
|
|
| 5. |
|
|
| 6. |
|
|
| 7. |
|
|
| 8. |
|
|
| 9. |
- Hugot, JP, et al.
(författare)
-
Clustering of Crohn's disease within affected sibships
- 2003
-
Ingår i: European Journal of Human Genetics. - : Springer Science and Business Media LLC. - 1018-4813 .- 1476-5438. ; 11:2, s. 179-184
-
Tidskriftsartikel (refereegranskat)abstract
- Crohn's disease (CD) is a complex genetic disorder for which aetiology is unknown. Recently, genetic factors for susceptibility have been described. Several genetic loci have been mapped and partially explain the familial aggregations of the disease. However, environmental factors may also contribute to these aggregations. We considered that if the role of non-genetic factors was negligible, CD patients would be randomly distributed in sibships with multiple affected siblings. On the other hand if there was a significant environmental contribution, the siblings would be affected non-randomly over exposure status. In order to test this hypothesis, we studied 102 sibships with two or more affected siblings. A statistical test, named Cluster of Affected Sibling Test or CAST, was developed, based on the exact calculation of the probability of observing a given number of clusters of affected siblings in multiplex families. The null hypothesis of a random distribution of affected siblings was rejected (P=0,005). The observed excess of affected sibling clusters indicates that birth order influences the disease status. Considering that an adjacent order of birth is a global estimate of environmental sharing, this observation strongly suggests that environmental factors contribute to the observed familial aggregations of the disease. This observation provides evidence that familial CD is a relevant tool for further studies of environmental factors and gene-environment interaction. More generally, the CAST statistics may be widely applicable to estimate the involvement of environmental factors in the aetiology of other binary traits which may be observed in multiple members of the same sibship.
|
|
| 10. |
|
|
