The familiar quotation 'garbage in, garbage out' is particularly applicable to data mining and machine learning projects. Real-world data are often incomplete, inconsistent and are likely containing many errors. Relying on experience gained from many hundreds of data sets, our portfolio includes a number of tools for the efficient detection of these inconsistencies and errors (e.g. detection of outliers or artifacts). Application of adequate correction and normalization strategies leads to a standardized and well structured data set, thus paving the way for further analysis.
Based on our large experience in exploring data from various sources, we offer you the most outstanding data analysis for almost any data type. Besides artificial intelligence methods we employ a broad spectrum of statistical methods. Our methods comprise parametric and non-parametric testing methods just as tools for solving single- or multi-variate classification or regression problems, like support vector machines and ensemble based decision trees (random forest). We also provide solutions for meta analyses like gene set enrichment analysis (GSEA) or functional characterization.
Artificial intelligence (AI) in healthcare is the use of complex algorithms and software to emulate human cognition in the analysis of complicated medical data. What distinguishes AI technology from traditional technologies in health care is the ability to gain information, process it and give a well-defined output to the end-user. We offer to assist you in the analysis for large datasets with state-of-the-art convolutional neuronal networks.
Data Integration and Data Management
We offer you solutions for storage and maintenance of data sets e.g. generated within a research project or scientific consortium. A special focus is put on the integration of data derived from different technologies or biological layers.