Refine
Year of publication
Document Type
- Article (76)
- Preprint (35)
- Part of a Book (1)
- Conference Proceeding (1)
Language
- English (113) (remove)
Has Fulltext
- yes (113)
Is part of the Bibliography
- no (113)
Keywords
- LHC (7)
- ALICE (3)
- ALICE experiment (3)
- Hadron-Hadron Scattering (3)
- pp collisions (3)
- Beauty production (2)
- Breast cancer (2)
- Single electrons (2)
- 900 GeV (1)
- Adolescence (1)
Institute
- Physik (82)
- Frankfurt Institute for Advanced Studies (FIAS) (68)
- Informatik (68)
- Medizin (25)
- Biochemie und Chemie (2)
- Geowissenschaften (2)
- Biowissenschaften (1)
- ELEMENTS (1)
- Georg-Speyer-Haus (1)
- Pharmazie (1)
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.
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. ...
Introduction: Reliable predictive and prognostic markers for routine diagnostic purposes are needed for breast cancer patients treated with neoadjuvant chemotherapy. We evaluated protein biomarkers in a cohort of 116 participants of the GeparDuo study on anthracycline/taxane-based neoadjuvant chemotherapy for operable breast cancer to test for associations with pathological complete response (pCR) and disease-free survival (DFS). Particularly, we evaluated if interactions between hormone receptor (HR) and human epidermal growth factor receptor 2 (HER2) expression might lead to a different clinical behavior of HR+/HER2+ coexpressing and HR+/HER2- tumors and whether subgroups of triple negative tumors might be identified by the help of Ki67 labeling index, cytokeratin 5/6 (CK5/6), as well as cyclooxygenase-2 (COX-2), and Y-box binding protein 1 (YB-1) expression. Methods: Expression analysis was performed using immunohistochemistry and silver-enhanced in situ hybridization on tissue microarrays (TMAs) of pretherapeutic core biopsies. Results: pCR rates were significantly different between the biology-based tumor types (P = 0.044) with HR+/HER2+ and HR-/HER2- tumors having higher pCR rates than HR+/HER2-tumors. Ki67 labeling index, confirmed as significant predictor of pCR in the whole cohort (P = 0.001), identified HR-/HER- (triple negative) carcinomas with a higher chance for a pCR (P = 0.006). Biology-based tumor type (P = 0.046 for HR+/HER2+vs. HR+/HER2-), Ki67 labeling index (P = 0.028), and treatment arm (P = 0.036) were independent predictors of pCR in a multivariate model. DFS was different in the biology-based tumor types (P < 0.0001) with HR+/HER2- and HR+/HER2+ tumors having the best prognosis and HR-/HER2+ tumors showing the worst outcome. Biology-based tumor type was an independent prognostic factor for DFS in multivariate analysis (P < 0.001). Conclusions: Our data demonstrate that a biology-based breast cancer classification using estrogen receptor (ER), progesterone receptor (PgR), and HER2 bears independent predictive and prognostic potential. The HR+/HER2+ coexpressing carcinomas emerged as a group of tumors with a good response rate to neoadjuvant chemotherapy and a favorable prognosis. HR+/HER2- tumors had a good prognosis irrespective of a pCR, whereas patients with HR-/HER- and HR-/HER+ tumors, especially if they had not achieved a pCR, had an unfavorable prognosis and are in need of additional treatment options. Trial registration ClinicalTrials.gov identifier: NCT00793377