1. |
- Glasbey, JC, et al.
(författare)
-
- 2021
-
swepub:Mat__t
|
|
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. |
- Thomas, HS, et al.
(författare)
-
- 2019
-
swepub:Mat__t
|
|
8. |
|
|
9. |
|
|
10. |
- Drinnenberg, IA, et al.
(författare)
-
EvoChromo: towards a synthesis of chromatin biology and evolution
- 2019
-
Ingår i: Development (Cambridge, England). - : The Company of Biologists. - 1477-9129 .- 0950-1991. ; 146:19
-
Tidskriftsartikel (refereegranskat)abstract
- Over the past few years, interest in chromatin and its evolution has grown. To further advance these interests, we organized a workshop with the support of The Company of Biologists to debate the current state of knowledge regarding the origin and evolution of chromatin. This workshop led to prospective views on the development of a new field of research that we term ‘EvoChromo’. In this short Spotlight article, we define the breadth and expected impact of this new area of scientific inquiry on our understanding of both chromatin and evolution.
|
|
11. |
- Hacke, W, et al.
(författare)
-
Effects of alteplase for acute stroke according to criteria defining the European Union and United States marketing authorizations: Individual-patient-data meta-analysis of randomized trials
- 2018
-
Ingår i: International journal of stroke : official journal of the International Stroke Society. - : SAGE Publications. - 1747-4949. ; 13:2, s. 175-189
-
Tidskriftsartikel (refereegranskat)abstract
- The recommended maximum age and time window for intravenous alteplase treatment of acute ischemic stroke differs between the Europe Union and United States. Aims We compared the effects of alteplase in cohorts defined by the current Europe Union or United States marketing approval labels, and by hypothetical revisions of the labels that would remove the Europe Union upper age limit or extend the United States treatment time window to 4.5 h. Methods We assessed outcomes in an individual-patient-data meta-analysis of eight randomized trials of intravenous alteplase (0.9 mg/kg) versus control for acute ischemic stroke. Outcomes included: excellent outcome (modified Rankin score 0–1) at 3–6 months, the distribution of modified Rankin score, symptomatic intracerebral hemorrhage, and 90-day mortality. Results Alteplase increased the odds of modified Rankin score 0–1 among 2449/6136 (40%) patients who met the current European Union label and 3491 (57%) patients who met the age-revised label (odds ratio 1.42, 95% CI 1.21−1.68 and 1.43, 1.23−1.65, respectively), but not in those outside the age-revised label (1.06, 0.90−1.26). By 90 days, there was no increased mortality in the current and age-revised cohorts (hazard ratios 0.98, 95% CI 0.76−1.25 and 1.01, 0.86–1.19, respectively) but mortality remained higher outside the age-revised label (1.19, 0.99–1.42). Similarly, alteplase increased the odds of modified Rankin score 0-1 among 1174/6136 (19%) patients who met the current US approval and 3326 (54%) who met a 4.5-h revised approval (odds ratio 1.55, 1.19−2.01 and 1.37, 1.17−1.59, respectively), but not for those outside the 4.5-h revised approval (1.14, 0.97−1.34). By 90 days, no increased mortality remained for the current and 4.5-h revised label cohorts (hazard ratios 0.99, 0.77−1.26 and 1.02, 0.87–1.20, respectively) but mortality remained higher outside the 4.5-h revised approval (1.17, 0.98–1.41). Conclusions An age-revised European Union label or 4.5-h-revised United States label would each increase the number of patients deriving net benefit from alteplase by 90 days after acute ischemic stroke, without excess mortality.
|
|
12. |
|
|
13. |
|
|
14. |
|
|
15. |
|
|
16. |
|
|
17. |
|
|
18. |
|
|
19. |
|
|
20. |
|
|
21. |
|
|
22. |
|
|
23. |
|
|
24. |
|
|
25. |
|
|