Refine
Document Type
- Article (4)
Language
- English (4)
Has Fulltext
- yes (4)
Is part of the Bibliography
- no (4)
Keywords
- Gaussian Process (1)
- Germany (1)
- JAK2V617F (1)
- Multiple Kernel (1)
- Support Vector Regression (1)
- Support Vector Regression Model (1)
- Virtual Screening (1)
- adolescents’ health (1)
- bleeding (1)
- chronic kidney disease (1)
Institute
- Biochemie und Chemie (2)
- Medizin (2)
- Pharmazie (1)
For a virtual screening study, we introduce a combination of machine learning techniques, employing a graph kernel, Gaussian process regression and clustered cross-validation. The aim was to find ligands of peroxisome-proliferator activated receptor gamma (PPAR-y). The receptors in the PPAR family belong to the steroid-thyroid-retinoid superfamily of nuclear receptors and act as transcription factors. They play a role in the regulation of lipid and glucose metabolism in vertebrates and are linked to various human processes and diseases. For this study, we used a dataset of 176 PPAR-y agonists published by Ruecker et al. ...
Objectives: It is known that transition, as a shift of care, marks a vulnerable phase in the adolescents’ lives with an increased risk for non-adherence and allograft failure. Still, the transition process of adolescents and young adults living with a kidney transplant in Germany is not well defined. The present research aims to assess transition-relevant structures for this group of young people. Special attention is paid to the timing of the process.
Setting: In an observational study, we visited 21 departments of paediatric nephrology in Germany. Participants were doctors (n=19), nurses (n=14) and psychosocial staff (n=16) who were responsible for transition in the relevant centres. Structural elements were surveyed using a short questionnaire. The experiential viewpoint was collected by interviews which were transcribedverbatim before thematic analysis was performed.
Results: This study highlights that professionals working within paediatric nephrology in Germany are well aware of the importance of successful transition. Key elements of transitional care are well understood and mutually agreed on. Nonetheless, implementation within daily routine seems challenging, and the absence of written, structured procedures may hamper successful transition.
Conclusions: While professionals aim for an individual timing of transfer based on medical, social, emotional and structural aspects, rigid regulations on transfer age as given by the relevant health authorities add on to the challenge.
Trial registration: number ISRCTN Registry no 22988897; results (phase I) and pre-results (phase II).
Poster presentation at 5th German Conference on Cheminformatics: 23. CIC-Workshop Goslar, Germany. 8-10 November 2009 We demonstrate the theoretical and practical application of modern kernel-based machine learning methods to ligand-based virtual screening by successful prospective screening for novel agonists of the peroxisome proliferator-activated receptor gamma (PPARgamma) [1]. PPARgamma is a nuclear receptor involved in lipid and glucose metabolism, and related to type-2 diabetes and dyslipidemia. Applied methods included a graph kernel designed for molecular similarity analysis [2], kernel principle component analysis [3], multiple kernel learning [4], and, Gaussian process regression [5]. In the machine learning approach to ligand-based virtual screening, one uses the similarity principle [6] to identify potentially active compounds based on their similarity to known reference ligands. Kernel-based machine learning [7] uses the "kernel trick", a systematic approach to the derivation of non-linear versions of linear algorithms like separating hyperplanes and regression. Prerequisites for kernel learning are similarity measures with the mathematical property of positive semidefiniteness (kernels). The iterative similarity optimal assignment graph kernel (ISOAK) [2] is defined directly on the annotated structure graph, and was designed specifically for the comparison of small molecules. In our virtual screening study, its use improved results, e.g., in principle component analysis-based visualization and Gaussian process regression. Following a thorough retrospective validation using a data set of 176 published PPARgamma agonists [8], we screened a vendor library for novel agonists. Subsequent testing of 15 compounds in a cell-based transactivation assay [9] yielded four active compounds. The most interesting hit, a natural product derivative with cyclobutane scaffold, is a full selective PPARgamma agonist (EC50 = 10 ± 0.2 microM, inactive on PPARalpha and PPARbeta/delta at 10 microM). We demonstrate how the interplay of several modern kernel-based machine learning approaches can successfully improve ligand-based virtual screening results.
Simple Summary: In patients with myeloproliferative neoplasms (MPN) and in patients with kidney dysfunction, a higher rate of thrombosis has been reported compared with the general population. Furthermore, MPN patients are more prone to develop kidney dysfunction. In our study, we assessed the importance of specific risk factors for kidney dysfunction and thrombosis in MPN patients. We found that the rate of thrombosis is correlated with the degree of kidney dysfunction, especially in myelofibrosis. Significant associations for kidney dysfunction included arterial hypertension, MPN treatment, and increased inflammation, and those for thrombosis comprised arterial hypertension, non-excessive platelet counts, and antithrombotic therapy. The identified risk factor associations varied between MPN subtypes. Our data suggest that kidney dysfunction in MPN patients is associated with an increased risk of thrombosis, mandating closer monitoring, and, possibly, early thromboprophylaxis.
Abstract: Inflammation-induced thrombosis represents a severe complication in patients with myeloproliferative neoplasms (MPN) and in those with kidney dysfunction. Overlapping disease-specific attributes suggest common mechanisms involved in MPN pathogenesis, kidney dysfunction, and thrombosis. Data from 1420 patients with essential thrombocythemia (ET, 33.7%), polycythemia vera (PV, 38.5%), and myelofibrosis (MF, 27.9%) were extracted from the bioregistry of the German Study Group for MPN. The total cohort was subdivided according to the calculated estimated glomerular filtration rate (eGFR, (mL/min/1.73 m2)) into eGFR1 (≥90, 21%), eGFR2 (60–89, 56%), and eGFR3 (<60, 22%). A total of 29% of the patients had a history of thrombosis. A higher rate of thrombosis and longer MPN duration was observed in eGFR3 than in eGFR2 and eGFR1. Kidney dysfunction occurred earlier in ET than in PV or MF. Multiple logistic regression analysis identified arterial hypertension, MPN treatment, increased uric acid, and lactate dehydrogenase levels as risk factors for kidney dysfunction in MPN patients. Risk factors for thrombosis included arterial hypertension, non-excessive platelet counts, and antithrombotic therapy. The risk factors for kidney dysfunction and thrombosis varied between MPN subtypes. Physicians should be aware of the increased risk for kidney disease in MPN patients, which warrants closer monitoring and, possibly, early thromboprophylaxis.