| 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. |
- Barnes, Paul W., et al.
(författare)
-
The importance and direction of current and future plant-UV research
- 2018
-
Ingår i: UV4Plants Bulletin. - : The UV4Plants International Association. - 2343-323X. ; 2, s. 19-32
-
Tidskriftsartikel (refereegranskat)abstract
- BackgroundTo stimulate how to move the field of plant-UV research forward, and create a coherent framework to highlight valuable future directions in plant UV research we had a group discussion of the most prescient questions and how to address them.The following sections are broken-down into those from the molecular, biochemical and physiological discussions followed by those from the ecological and plant production discussions. In each case, first basic research questions are considered and then applications and methodological considerations put forward. Finally, some common ground bringing together the two perspectives is proposed, aimed at solving scaling problems and ways in which the UV4Plants network might be put to good use.
|
|
| 3. |
- Brelsford, Craig C., et al.
(författare)
-
Do UV‐A radiation and blue light during growth prime leaves to cope with acute high light in photoreceptor mutants of Arabidopsis thaliana?
- 2019
-
Ingår i: Physiologia Plantarum. - : Blackwell Publishing. - 0031-9317 .- 1399-3054. ; 165:3, s. 537-554
-
Tidskriftsartikel (refereegranskat)abstract
- We studied how plants acclimated to growing conditions that included combinations of blue light (BL) and ultraviolet (UV)‐A radiation, and whether their growing environment affected their photosynthetic capacity during and after a brief period of acute high light (as might happen during an under‐canopy sunfleck). Arabidopsis thaliana Landsberg erecta wild‐type were compared with mutants lacking functional blue light and UV photoreceptors: phototropin 1, cryptochromes (CRY1 and CRY2) and UV RESISTANT LOCUS 8 (uvr8). This was achieved using light‐emitting‐diode (LED) lamps in a controlled environment to create treatments with or without BL, in a split‐plot design with or without UV‐A radiation. We compared the accumulation of phenolic compounds under growth conditions and after exposure to 30 min of high light at the end of the experiment (46 days), and likewise measured the operational efficiency of photosystem II (ϕPSII, a proxy for photosynthetic performance) and dark‐adapted maximum quantum yield (Fv/Fm to assess PSII damage). Our results indicate that cryptochromes are the main photoreceptors regulating phenolic compound accumulation in response to BL and UV‐A radiation, and a lack of functional cryptochromes impairs photosynthetic performance under high light. Our findings also reveal a role for UVR8 in accumulating flavonoids in response to a low UV‐A dose. Interestingly, phototropin 1 partially mediated constitutive accumulation of phenolic compounds in the absence of BL. Low‐irradiance BL and UV‐A did not improve ϕPSII and Fv/Fm upon our acute high‐light treatment; however, CRYs played an important role in ameliorating high‐light stress.
|
|
| 4. |
- Siipola, Sari M., et al.
(författare)
-
Epidermal UV-A absorbance and whole leaf flavonoid composition in pea respond more to solar blue light than solar UV radiation
- 2015
-
Ingår i: Plant, Cell and Environment. - : Blackwell Publishing. - 0140-7791 .- 1365-3040. ; 38:5, s. 941-952
-
Tidskriftsartikel (refereegranskat)abstract
- Plants synthesize phenolic compounds in response to certain environmental signals or stresses. One large group of phenolics, flavonoids, is considered particularly responsive to ultraviolet (UV) radiation. However, here we demonstrate that solar blue light stimulates flavonoid biosynthesis in the absence of UV‐A and UV‐B radiation. We grew pea plants (Pisum sativum cv. Meteor) outdoors, in Finland during the summer, under five types of filters differing in their spectral transmittance. These filters were used to (1) attenuate UV‐B; (2) attenuate UV‐B and UV‐A < 370 nm; (3) attenuate UV‐B and UV‐A; (4) attenuate UV‐B, UV‐A and blue light; and (5) as a control not attenuating these wavebands. Attenuation of blue light significantly reduced the flavonoid content in leaf adaxial epidermis and reduced the whole‐leaf concentrations of quercetin derivatives relative to kaempferol derivatives. In contrast, UV‐B responses were not significant. These results show that pea plants regulate epidermal UV‐A absorbance and accumulation of individual flavonoids by perceiving complex radiation signals that extend into the visible region of the solar spectrum. Furthermore, solar blue light instead of solar UV‐B radiation can be the main regulator of phenolic compound accumulation in plants that germinate and develop outdoors.
|
|
