3 research outputs found
Root foraging : the consequences for nutrient acquisition and competition in heterogeneous environments
No full textIn natural habitats, the availability of essential mineral nutrients may vary widely from place to place and from time to time, at scales relevant to individual plants. Plants have developed root foraging mechanisms that enable them to acquire adequate amounts of nutrients in these heterogeneous environments. The ability of plants to proliferate roots in nutrient-rich patches has been shown frequently, but both the timing and the degree of root proliferation varied widely. Species from inherently nutrient-rich habitats in general display a higher relative increase in root density in nutrient-rich patches than species from inherently nutrient-poor habitats. This observation prompted the hypothesis that root foraging mechanisms differ between species from habitats of different nutrient availability.Overall, the results described in this thesis contradict this hypothesis. The higher degree of selective root placement displayed by species from more nutrient-rich habitats compared to species from more nutrient-poor habitats may result from differences in growth rate rather than from differences in root morphological plasticity. The results further indicate that selective root placement may confer an advantage in terms of nutrient acquisition in heterogeneous environments in the short-term, but in the long-term the increased root density may result in a lower rather than a higher biomass production in heterogeneous environments. However, root foraging abilities by which local nutrient patches are exploited may still be profitable when plants are grown in competition. The ability to rapidly exploit nutrient-rich patches due to root foraging characteristics seems to confer a competitive advantage in heterogeneous environments, even in the long-term.</p
Time series predictions for bank account balances
No full textFor our bachelor project we have been using machine learning to predict account balances for a large Dutch bank holding company. The company’s main interest is the integration of machine learning techniques in their systems. To enable this we have been asked to develop a product to predict account balances for the clients of associated banks. With the clients interest in machine learning in mind we have developed a framework enabling the user to implement different machine learning and non machine learning models. The framework makes it easy to compare the implemented models using different error measures, parameters of inputs and lets the user visualize the results easily. In this framework we have implemented our own models for the account prediction. To compare our models we started with implementing a baseline, next to this baseline we have implemented two non machine learning and one machine learning model. The data we used to train and validate our models has been derived from the clients data warehouse. We have cut the accounts on different criteria like activity and the period they have been with the bank. After that we have normalized the data to be able to better interpreted and process it. The machine learning techniques we want to implement require a lot of training examples, this made us decide implement a clustering model as well to create more data to train our models on. Eventually the clustering did not give us the expected results and we decided not to use it for our final model. To give our client a suited recommendation about the machine learning libraries to use on their systems, we have implemented the same clustering method with two different libraries. After this comparison we were able to recommend our client the Scikit-learn library over the more low level Tensorflow library. From this point on we used the Scikit-learn library as well for the implementation of SVM model. For the regression we implemented the L-1 prediction, OLS method and an SVM. Compared to the baseline, our SVM model gave the best results, however the results of the L-1 prediction closely followed the results of our SVM model. After a better comparison we have discovered that in some cases the SVM model makes a prediction is almost exactly the same as the L-1 prediction, one the other hand, various other predictions are not based on this pattern at all. We therefore assume that after tweaking the SVM more, it will preform better and show significantly better results than the L-1 prediction. For now we did not have time to tweak our SVM, but we have tried different inputs and parameters. As a future improvement these parameters can be tested in more detail and it would be interesting to take a closer look at different militarization methods and error measures. In conclusion we were able to test machine learning techniques with the client’s data by implementing a well working SMV model for account balance prediction. This model works on the clients systems and is validated on real client data. Furthermore we provided our client with a framework that allows them to easily implement machine learning and non machine learning models. This framework provides the user with interfaces to build models, standard data operations and error measures. This allows the user to quickly research many different con- figurations. We used this framework ourselves during this project to compare our machine learning and non machine learning models.Electrical Engineering, Mathematics and Computer ScienceComputer Scienc
Expanding the clinical spectrum of biglycan-related Meester-Loeys syndrome
No full textPathogenic loss-of-function variants in BGN, an X-linked gene encoding biglycan, are associated with Meester-Loeys syndrome (MRLS), a thoracic aortic aneurysm/dissection syndrome. Since the initial publication of five probands in 2017, we have considerably expanded our MRLS cohort to a total of 18 probands (16 males and 2 females). Segregation analyses identified 36 additional BGN variant-harboring family members (9 males and 27 females). The identified BGN variants were shown to lead to loss-of-function by cDNA and Western Blot analyses of skin fibroblasts or were strongly predicted to lead to loss-of-function based on the nature of the variant. No (likely) pathogenic missense variants without additional (predicted) splice effects were identified. Interestingly, a male proband with a deletion spanning the coding sequence of BGN and the 5' untranslated region of the downstream gene (ATP2B3) presented with a more severe skeletal phenotype. This may possibly be explained by expressional activation of the downstream ATPase ATP2B3 (normally repressed in skin fibroblasts) driven by the remnant BGN promotor. This study highlights that aneurysms and dissections in MRLS extend beyond the thoracic aorta, affecting the entire arterial tree, and cardiovascular symptoms may coincide with non-specific connective tissue features. Furthermore, the clinical presentation is more severe and penetrant in males compared to females. Extensive analysis at RNA, cDNA, and/or protein level is recommended to prove a loss-of-function effect before determining the pathogenicity of identified BGN missense and non-canonical splice variants. In conclusion, distinct mechanisms may underlie the wide phenotypic spectrum of MRLS patients carrying loss-of-function variants in BGN.</p
