Kernel Methods, Pattern Analysis and Computational Metabolomics (KEPACO)
The KEPACO group develops machine learning methods, models and tools for data science, in particular computational metabolomics. The methodological backbone of the group is formed by kernel methods and regularized learning.
The group particularly focuses in learning with multiple and structured targets, multiple views and ensembles. Machine learning applications of interest include metabolite identification, metabolic network reconstruction and pathway analysis, chemogenomics as well as biomarker discovery.
See overview of KEPACO research (in PDF)
Check out the CSI:FingerID server for metabolite identification from MS/MS data, running the methods we developed with Sebastian Boecker's group in Friedrich-Schiller-Universitat Jena.