| 1. |
|
|
| 2. |
- Didion, JP, et al.
(författare)
-
R2d2 Drives Selfish Sweeps in the House Mouse
- 2016
-
Ingår i: Molecular biology and evolution. - : Oxford University Press (OUP). - 1537-1719 .- 0737-4038. ; 33:6, s. 1381-1395
-
Tidskriftsartikel (refereegranskat)
|
|
| 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. |
- Bajunirwe, F, et al.
(författare)
-
Burden of depressive symptoms and non-alcohol substance abuse; and their association with alcohol use and partner violence: a cross-sectional study in four sub-Saharan Africa countries
- 2018
-
Ingår i: Global mental health (Cambridge, England). - : Cambridge University Press (CUP). - 2054-4251. ; 5, s. e31-
-
Tidskriftsartikel (refereegranskat)abstract
- In sub-Saharan Africa, there are limited data on burden of non-alcohol substance abuse (NAS) and depressive symptoms (DS), yet potential risk factors such as alcohol and intimate partner violence (IPV) are common and NAS abuse may be the rise. The aim of this study was to measure the burden of DS and NAS abuse, and determine whether alcohol use and IPV are associated with DS and/or NAS abuse. We conducted a cross-sectional study at five sites in four countries: Nigeria (nurses), South Africa (teachers), Tanzania (teachers) and two sites in Uganda (rural and peri-urban residents). Participants were selected by simple random sampling from a sampling frame at each of the study sites. We used a standardized tool to collect data on demographics, alcohol use and NAS use, IPV and DS and calculated prevalence ratios (PR). We enrolled 1415 respondents and of these 34.6% were male. DS occurred among 383 (32.3%) and NAS use among 52 (4.3%). In the multivariable analysis, being female (PR = 1.49, p = 0.008), NAS abuse (PR = 2.06, p = 0.02) and IPV (PR = 2.93, p < 0.001) were significantly associated with DS. Older age [odds ratio (OR) = 0.31, p < 0.001)], female (OR = 0.48, p = 0.036) were protective of NAS but current smokers (OR = 2.98, p < 0.001) and those reporting IPV (OR = 2.16, p = 0.024) were more likely to use NAS. Longitudinal studies should be done to establish temporal relationships with these risk factors to provide basis for interventions.
|
|
| 10. |
|
|
