| 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. |
- Cronin, M. F., et al.
(författare)
-
Developing an Observing Air-Sea Interactions Strategy (OASIS) for the global ocean
- 2022
-
Ingår i: Ices Journal of Marine Science. - : Oxford University Press (OUP). - 1054-3139 .- 1095-9289. ; 80:2, s. 367-73
-
Tidskriftsartikel (refereegranskat)abstract
- The Observing Air-Sea Interactions Strategy (OASIS) is a new United Nations Decade of Ocean Science for Sustainable Development programme working to develop a practical, integrated approach for observing air-sea interactions globally for improved Earth system (including ecosystem) forecasts, CO2 uptake assessments called for by the Paris Agreement, and invaluable surface ocean information for decision makers. Our "Theory of Change" relies upon leveraged multi-disciplinary activities, partnerships, and capacity strengthening. Recommendations from >40 OceanObs'19 community papers and a series of workshops have been consolidated into three interlinked Grand Ideas for creating #1: a globally distributed network of mobile air-sea observing platforms built around an expanded array of long-term time-series stations; #2: a satellite network, with high spatial and temporal resolution, optimized for measuring air-sea fluxes; and #3: improved representation of air-sea coupling in a hierarchy of Earth system models. OASIS activities are organized across five Theme Teams: (1) Observing Network Design & Model Improvement; (2) Partnership & Capacity Strengthening; (3) UN Decade OASIS Actions; (4) Best Practices & Interoperability Experiments; and (5) Findable-Accessible-Interoperable-Reusable (FAIR) models, data, and OASIS products. Stakeholders, including researchers, are actively recruited to participate in Theme Teams to help promote a predicted, safe, clean, healthy, resilient, and productive ocean.
|
|
| 3. |
|
|
| 4. |
- Lønborg, C., et al.
(författare)
-
A global database of dissolved organic matter (DOM) concentration measurements in coastal waters (CoastDOM v1)
- 2024
-
Ingår i: Earth System Science Data. - : Copernicus Publications. - 1866-3508 .- 1866-3516. ; 16:2, s. 1107-1119
-
Tidskriftsartikel (refereegranskat)abstract
- Measurements of dissolved organic carbon (DOC), nitrogen (DON), and phosphorus (DOP) concentrations are used to characterize the dissolved organic matter (DOM) pool and are important components ofbiogeochemical cycling in the coastal ocean. Here, we present the first edition of a global database (CoastDOMv1; available at https://doi.org/10.1594/PANGAEA.964012, Lønborg et al., 2023) compiling previously published and unpublished measurements of DOC, DON, and DOP in coastal waters. These data are complementedby hydrographic data such as temperature and salinity and, to the extent possible, other biogeochemical variables(e.g. chlorophyll a, inorganic nutrients) and the inorganic carbon system (e.g. dissolved inorganic carbon andtotal alkalinity). Overall, CoastDOM v1 includes observations of concentrations from all continents. However,most data were collected in the Northern Hemisphere, with a clear gap in DOM measurements from the SouthernHemisphere. The data included were collected from 1978 to 2022 and consist of 62 338 data points for DOC,20 356 for DON, and 13 533 for DOP. The number of measurements decreases progressively in the sequenceDOC > DON > DOP, reflecting both differences in the maturity of the analytical methods and the greater focuson carbon cycling by the aquatic science community. The global database shows that the average DOC concentration in coastal waters (average ± standard deviation (SD): 182±314 µmolC L−1; median: 103 µmolC L−1) is13-fold higher than the average coastal DON concentration (13.6 ± 30.4 µmol N L−1; median: 8.0 µmol N L−1),which is itself 39-fold higher than the average coastal DOP concentration (0.34 ± 1.11 µmol P L−1; median:0.18 µmol P L−1). This dataset will be useful for identifying global spatial and temporal patterns in DOM and willhelp facilitate the reuse of DOC, DON, and DOP data in studies aimed at better characterizing local biogeochemical processes; closing nutrient budgets; estimating carbon, nitrogen, and phosphorous pools; and establishing abaseline for modelling future changes in coastal waters.
|
|
| 5. |
|
|
| 6. |
|
|
| 7. |
- Craddock, Nick, et al.
(författare)
-
Genome-wide association study of CNVs in 16,000 cases of eight common diseases and 3,000 shared controls
- 2010
-
Ingår i: Nature. - : Springer Science and Business Media LLC. - 0028-0836 .- 1476-4687. ; 464:7289, s. 713-720
-
Tidskriftsartikel (refereegranskat)abstract
- Copy number variants (CNVs) account for a major proportion of human genetic polymorphism and have been predicted to have an important role in genetic susceptibility to common disease. To address this we undertook a large, direct genome-wide study of association between CNVs and eight common human diseases. Using a purpose-designed array we typed,19,000 individuals into distinct copy-number classes at 3,432 polymorphic CNVs, including an estimated similar to 50% of all common CNVs larger than 500 base pairs. We identified several biological artefacts that lead to false-positive associations, including systematic CNV differences between DNAs derived from blood and cell lines. Association testing and follow-up replication analyses confirmed three loci where CNVs were associated with disease-IRGM for Crohn's disease, HLA for Crohn's disease, rheumatoid arthritis and type 1 diabetes, and TSPAN8 for type 2 diabetes-although in each case the locus had previously been identified in single nucleotide polymorphism (SNP)-based studies, reflecting our observation that most common CNVs that are well-typed on our array are well tagged by SNPs and so have been indirectly explored through SNP studies. We conclude that common CNVs that can be typed on existing platforms are unlikely to contribute greatly to the genetic basis of common human diseases.
|
|
| 8. |
|
|
| 9. |
|
|
| 10. |
|
|
