| 1. |
|
|
| 2. |
|
|
| 3. |
|
|
| 4. |
|
|
| 5. |
- 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.
|
|
| 6. |
|
|
| 7. |
|
|
| 8. |
- Beaney, KE, et al.
(författare)
-
Functional Analysis of the Coronary Heart Disease Risk Locus on Chromosome 21q22
- 2017
-
Ingår i: Disease markers. - : Hindawi Limited. - 1875-8630 .- 0278-0240. ; 2017, s. 1096916-
-
Tidskriftsartikel (refereegranskat)abstract
- Background. The coronary heart disease (CHD) risk locus on 21q22 (lead SNP rs9982601) lies within a “gene desert.” The aim of this study was to assess if this locus is associated with CHD risk factors and to identify the functional variant(s) and gene(s) involved.Methods. A phenome scan was performed with UCLEB Consortium data. Allele-specific protein binding was studied using electrophoretic mobility shift assays. Dual-reporter luciferase assays were used to assess the impact of genetic variation on expression. Expression quantitative trait analysis was performed with Advanced Study of Aortic Pathology (ASAP) and Genotype-Tissue Expression (GTEx) consortium data.Results. A suggestive association between QT interval and the locus was observed (rs9982601 p=0.04). One variant at the locus, rs28451064, showed allele-specific protein binding and its minor allele showed 12% higher luciferase expression (p= 4.82 × 10−3) compared to the common allele. The minor allele of rs9982601 was associated with higher expression of the closest upstream genes (SLC5A31.30-fold increasep= 3.98 × 10−5;MRPS61.15-fold increasep= 9.60 × 10−4) in aortic intima media in ASAP. Both rs9982601 and rs28451064 showed a suggestive association withMRPS6expression in relevant tissues in the GTEx data.Conclusions. A candidate functional variant, rs28451064, was identified. Future work should focus on identifying the pathway(s) involved.
|
|
| 9. |
|
|
| 10. |
|
|
