| 1. |
- Romagnoni, A, et al.
(author)
-
Comparative performances of machine learning methods for classifying Crohn Disease patients using genome-wide genotyping data
- 2019
-
In: Scientific reports. - : Springer Science and Business Media LLC. - 2045-2322. ; 9:1, s. 10351-
-
Journal article (peer-reviewed)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. |
|
|
| 4. |
|
|
| 5. |
|
|
| 6. |
|
|
| 7. |
|
|
| 8. |
|
|
| 9. |
|
|
| 10. |
- Wojdacz, TK, et al.
(author)
-
Clinical significance of DNA methylation in chronic lymphocytic leukemia patients: results from 3 UK clinical trials
- 2019
-
In: Blood advances. - : American Society of Hematology. - 2473-9537 .- 2473-9529. ; 3:16, s. 2474-2481
-
Journal article (peer-reviewed)abstract
- Chronic lymphocytic leukemia patients with mutated immunoglobulin heavy-chain genes (IGHV-M), particularly those lacking poor-risk genomic lesions, often respond well to chemoimmunotherapy (CIT). DNA methylation profiling can subdivide early-stage patients into naive B-cell–like CLL (n-CLL), memory B-cell–like CLL (m-CLL), and intermediate CLL (i-CLL), with differing times to first treatment and overall survival. However, whether DNA methylation can identify patients destined to respond favorably to CIT has not been ascertained. We classified treatment-naive patients (n = 605) from 3 UK chemo and CIT clinical trials into the 3 epigenetic subgroups, using pyrosequencing and microarray analysis, and performed expansive survival analysis. The n-CLL, i-CLL, and m-CLL signatures were found in 80% (n = 245/305), 17% (53/305), and 2% (7/305) of IGHV-unmutated (IGHV-U) cases, respectively, and in 9%, (19/216), 50% (108/216), and 41% (89/216) of IGHV-M cases, respectively. Multivariate Cox proportional analysis identified m-CLL as an independent prognostic factor for overall survival (hazard ratio [HR], 0.46; 95% confidence interval [CI], 0.24-0.87; P = .018) in CLL4, and for progression-free survival (HR, 0.25; 95% CI, 0.10-0.57; P = .002) in ARCTIC and ADMIRE patients. The analysis of epigenetic subgroups in patients entered into 3 first-line UK CLL trials identifies m-CLL as an independent marker of prolonged survival and may aid in the identification of patients destined to demonstrate prolonged survival after CIT.
|
|
