| 1. |
- 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.
|
|
| 2. |
|
|
| 3. |
- Bruder, CEG, et al.
(författare)
-
High resolution deletion analysis of constitutional DNA from neurofibromatosis type 2 (NF2) patients using microarray-CGH
- 2001
-
Ingår i: Human Molecular Genetics. - Oxford, United Kingdom : Oxford University Press. - 0964-6906 .- 1460-2083. ; 1, s. 271-
-
Tidskriftsartikel (refereegranskat)abstract
- Neurofibromatosis type 2 (NF2) is an autosomal dominant disorder whose hallmark is bilateral vestibular schwannoma. It displays a pronounced clinical heterogeneity with mild to severe forms. The NF2 tumor suppressor (merlin/schwannomin) has been cloned and extensively analyzed for mutations in patients with different clinical variants of the disease. Correlation between the type of the NF2 gene mutation and the patient phenotype has been suggested to exist. However, several independent studies have shown that a fraction of NF2 patients with various phenotypes have constitutional deletions that partly or entirely remove one copy of the NF2 gene. The purpose of this study was to examine a 7 Mb interval in the vicinity of the NF2 gene in a large series of NF2 patients in order to determine the frequency and extent of deletions. A total of 116 NF2 patients were analyzed using high-resolution array-comparative genomic hybridization (CGH) on an array covering at least 90% of this region of 22q around the NF2 locus. Deletions, which remove one copy of the entire gene or are predicted to truncate the schwannomin protein, were detected in 8 severe, 10 moderate and 6 mild patients. This result does not support the correlation between the type of mutation affecting the NF2 gene and the disease phenotype. This work also demonstrates the general usefulness of the array-CON methodology for rapid and comprehensive detection of small (down to 40 kb) heterozygous and/or homozygous deletions occurring in constitutional or tumor-derived DNA.
|
|
| 4. |
- Wang, Arthur, et al.
(författare)
-
Targeting mitochondria-derived reactive oxygen species to reduce epithelial barrier dysfunction and colitis
- 2014
-
Ingår i: American Journal of Pathology. - : Elsevier BV. - 0002-9440 .- 1525-2191. ; 184:9, s. 2516-2527
-
Tidskriftsartikel (refereegranskat)abstract
- Epithelial permeability is often increased in inflammatory bowel diseases. We hypothesized that perturbed mitochondrial function would cause barrier dysfunction and hence epithelial mitochondria could be targeted to treat intestinal inflammation. Mitochondrial dysfunction was induced in human colon-derived epithelial cell lines or colonic biopsy specimens using dinitrophenol, and barrier function was assessed by transepithelial flux of Escherichia coil with or without mitochondria-targeted antioxidant (MTA) cotreatment. The impact of mitochondria-targeted antioxidants on gut permeability and dextran sodium sulfate (DSS)-induced colitis in mice was tested. Mitochondrial superoxide evoked by dinitrophenol elicited significant internalization and transtocation of E. coil across epithelia and control colonic biopsy specimens, which was more striking in Crohn's disease biopsy specimens; the mitochondria-targeted antioxidant, MitoTEMPO, inhibited these barrier defects. Increased gut permeability and reduced epithelial mitochondrial voltage-dependent anion channel expression were observed 3 days after DSS. These changes and the severity of DSS-colitis were reduced by MitoTEMPO treatment. In vitro DSS-stimulated IL-8 production by epithelia was reduced by MitoTEMPO. Metabolic stress evokes significant penetration of commensal bacteria across the epithelium, which is mediated by mitochondria-derived superoxide acting as a signaling, not a cytotoxic, molecule. MitoTEMPO inhibited this barrier dysfunction and suppressed colitis in DSS-colitis, likely via enhancing barrier function and inhibiting proinflammatory cytokine production. These novel findings support consideration of MTAs in the maintenance of epithelial barrier function and the management of inflammatory bowel diseases.
|
|
