| 1. |
|
|
| 2. |
|
|
| 3. |
|
|
| 4. |
|
|
| 5. |
|
|
| 6. |
|
|
| 7. |
- 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.
|
|
| 8. |
- Wang, HD, et al.
(författare)
-
Global, regional, national, and selected subnational levels of stillbirths, neonatal, infant, and under-5 mortality, 1980-2015: a systematic analysis for the Global Burden of Disease Study 2015
- 2016
-
Ingår i: Lancet (London, England). - : Elsevier. - 1474-547X .- 0140-6736. ; 388:10053, s. 1725-1774
-
Tidskriftsartikel (refereegranskat)
|
|
| 9. |
- Thomas, HS, et al.
(författare)
-
- 2019
-
swepub:Mat__t
|
|
| 10. |
|
|
| 11. |
|
|
| 12. |
|
|
| 13. |
|
|
| 14. |
|
|
| 15. |
|
|
| 16. |
|
|
| 17. |
|
|
| 18. |
|
|
| 19. |
|
|
| 20. |
- Eklund, E, et al.
(författare)
-
Serum complexed and free prostate specific antigen levels are lower in female elite athletes in comparison to control women
- 2017
-
Ingår i: F1000Research. - : F1000 Research Ltd. - 2046-1402. ; 6, s. 1131-
-
Tidskriftsartikel (refereegranskat)abstract
- Background: We hypothesize that prostate specific antigen (PSA), a protein that it is under regulation by androgens, may be differentially expressed in female elite athletes in comparison to control women.Methods: We conducted a cross-sectional study of 106 female athletes and 114 sedentary age-matched controls. Serum from these women was analyzed for complexed prostate specific antigen (cPSA) and free prostate specific antigen (fPSA), by fifth generation assays with limits of detection of around 6 and 140 fg/mL, respectively. A panel of estrogens, androgens and progesterone in the same serum was also quantified by tandem mass spectrometry. Results: Both components of serum PSA (cPSA and fPSA) were lower in the elite athletes vs the control group (P=0.033 and 0.013, respectively). Furthermore, estrone (p=0.003) and estradiol (p=0.004) were significantly lower, and dehydroepiandrosterone (p=0.095) and 5-androstene-3β, 17β-diol (p=0.084) tended to be higher in the athletes vs controls. Oral contraceptive use was similar between groups and significantly associated with increased cPSA and fPSA in athletes (p= 0.046 and 0.009, respectively). PSA fractions were not significantly associated with progesterone changes. The Spearman correlation between cPSA and fPSA in both athletes and controls was 0.75 (P < 0.0001) and 0.64 (P < 0.0001), respectively. Conclusions: Elite athletes have lower complexed and free PSA, higher levels of androgen precursors and lower levels of estrogen in their serum than sedentary control women.Abbreviations: cPSA, complexed PSA; fPSA, free PSA; PCOS, polycystic ovarian syndrome; E1, estrone; E2, estradiol; DHEA, dehydroepiandrosterone, Testo, testosterone; DHT, dihydrotestosterone; PROG, progesterone; Delta 4, androstenedione; Delta 5, androst-5-ene-3β, 17β-diol; BMD, body mineral density; LLOQ, lower limit of quantification; ULOQ, upper limit of quantification; LOD, limit of detection; ACT, α1-antichymotrypsin
|
|
| 21. |
|
|
| 22. |
- Lopez-Isac, E, et al.
(författare)
-
GWAS for systemic sclerosis identifies multiple risk loci and highlights fibrotic and vasculopathy pathways
- 2019
-
Ingår i: Nature communications. - : Springer Science and Business Media LLC. - 2041-1723. ; 10:1, s. 4955-
-
Tidskriftsartikel (refereegranskat)abstract
- Systemic sclerosis (SSc) is an autoimmune disease that shows one of the highest mortality rates among rheumatic diseases. We perform a large genome-wide association study (GWAS), and meta-analysis with previous GWASs, in 26,679 individuals and identify 27 independent genome-wide associated signals, including 13 new risk loci. The novel associations nearly double the number of genome-wide hits reported for SSc thus far. We define 95% credible sets of less than 5 likely causal variants in 12 loci. Additionally, we identify specific SSc subtype-associated signals. Functional analysis of high-priority variants shows the potential function of SSc signals, with the identification of 43 robust target genes through HiChIP. Our results point towards molecular pathways potentially involved in vasculopathy and fibrosis, two main hallmarks in SSc, and highlight the spectrum of critical cell types for the disease. This work supports a better understanding of the genetic basis of SSc and provides directions for future functional experiments.
|
|
| 23. |
|
|
| 24. |
|
|
| 25. |
|
|
