| 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. |
- Alvarez-Madrazo, S., et al.
(författare)
-
Common Polymorphisms in the CYP11B1 and CYP11B2 Genes: Evidence for a Digenic Influence on Hypertension
- 2013
-
Ingår i: Hypertension. - : Ovid Technologies (Wolters Kluwer Health). - 0194-911X .- 1524-4563. ; 61:1, s. 232-239
-
Tidskriftsartikel (refereegranskat)abstract
- The locus encompassing the corticosteroidogenic genes CYP11B2 and CYP11B1 is of potential importance in essential hypertension. We analyzed the association of polymorphisms at this locus with risk of essential hypertension, using 2 white case-control collections for discovery (n = 3340) and confirmation (n = 2929). Single-marker and haplotype analyses were performed, with the CYP11B2 Intron 2 Conversion polymorphism showing strongest association with hypertension in both cohorts and in combined analysis (odds ratio = 1.16, P = 8.54x10(-5)). The CYP11B1 ACA haplotype associated with increased risk of hypertension relative to the alternative, GTC (odds ratio = 1.11; P = 7.4x10(-3)), whereas the CYP11B2 TWtC haplotype seemed protective relative to the contrasting CConvT (odds ratio = 0.88, P = 2.2x10(-3)). Analysis spanning the whole CYP11B1/CYP11B2 locus showed that haplotypes associated with raised risk of hypertension tend to coexist. Functional analysis of heterozygous human adrenal tissue demonstrated decreased CYP11B2 expression and increased CYP11B1 expression for those alleles associating with reduced risk of hypertension. These results confirm the hypertensive influence of this locus, with data suggesting a complex digenic mechanism whereby altered relative CYP11B1 and CYP11B2 gene expression could have a chronic effect on enzyme activity and corticosteroid synthesis.
|
|
| 8. |
|
|
| 9. |
|
|
| 10. |
|
|
