| 1. |
|
|
| 2. |
|
|
| 3. |
- 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.
|
|
| 4. |
|
|
| 5. |
|
|
| 6. |
|
|
| 7. |
|
|
| 8. |
|
|
| 9. |
- Harbo, HF, et al.
(författare)
-
Two genome-wide linkage disequilibrium screens in Scandinavian multiple sclerosis patients
- 2003
-
Ingår i: Journal of Neuroimmunology. - : Elsevier BV. - 1872-8421 .- 0165-5728. ; 143:1-2, s. 101-106
-
Tidskriftsartikel (refereegranskat)abstract
- We report the first two genome-wide screens for linkage disequilibrium between putative multiple sclerosis (MS) susceptibility genes and genetic markers performed in the genetically homogenous Scandinavian population, using 6000 microsatellite markers and DNA pools of approximately 200 MS cases and 200 controls in each screen. Usable data were achieved from the same 3331 markers in both screens. Nine markers from eight genomic regions (1p33, 3q13, 6p21, 6q14, 7p22, 9p21, 9q21 and Xq22) were identified as potentially associated with MS in both screens. (C) 2003 Elsevier B.V. All rights reserved.
|
|
| 10. |
- Chen, Q, et al.
(författare)
-
Identification of Plasmodium falciparum erythrocyte membrane protein 1 (PfEMP1) as the rosetting ligand of the malaria parasite P. falciparum
- 1998
-
Ingår i: The Journal of experimental medicine. - : Rockefeller University Press. - 0022-1007 .- 1540-9538. ; 187:1, s. 15-23
-
Tidskriftsartikel (refereegranskat)abstract
- Severe Plasmodium falciparum malaria is characterized by excessive sequestration of infected and uninfected erythrocytes in the microvasculature of the affected organ. Rosetting, the adhesion of P. falciparum–infected erythrocytes to uninfected erythrocytes is a virulent parasite phenotype associated with the occurrence of severe malaria. Here we report on the identification by single-cell reverse transcriptase PCR and cDNA cloning of the adhesive ligand P. falciparum erythrocyte membrane protein 1 (PfEMP1). Rosetting PfEMP1 contains clusters of glycosaminoglycan-binding motifs. A recombinant fusion protein (Duffy binding-like 1–glutathione S transferase; Duffy binding-like-1–GST) was found to adhere directly to normal erythrocytes, disrupt naturally formed rosettes, block rosette reformation, and bind to a heparin-Sepharose matrix. The adhesive interactions could be inhibited with heparan sulfate or enzymes that remove heparan sulfate from the cell surface whereas other enzymes or similar glycosaminoglycans of a like negative charge did not affect the binding. PfEMP1 is suggested to be the rosetting ligand and heparan sulfate, or a heparan sulfate–like molecule, the receptor both for PfEMP1 binding and naturally formed erythrocyte rosettes.
|
|
