Visual anaalytics for Personalized Medizine

VIPEM is an interactive data exploration system for the visualization of and navigation in molecular and clinical data in the field of personalized medicine. A multidimensional space consisting of molecular and clinical data is screened and hierarchically structured by applying algorithmic methods and direct user interaction. The essential but to date unsolved problem VIPEM addresses in the emerging field of personalized medicine is the question of how to identify connections between genetic variants and their corresponding diseases or the response to certain drugs and treatments, respectively. It is therefore necessary, to e.g. connect gene data and clinical data in order to categorise specific subgroups of patients with certain diseases. The huge amount of data provided by molecular analytical methods (genetic polymorphisms, gene expression data, proteomics) can only be accomplished by applying bioinformatical and statistical methods. However, even standard methods of statistics and bioinformatics fail when the data are inhomogeneous as is the case with clinical data and when data structures are obscured by noise and dominant patterns. VIPEM should make the structure of the data spaces visible by using visualisation methods and allow an interactive navigation and structuring of both molecular and clinical data. VIPEM is based on fundamental results in the fields of information visualisation and multimodal user interfaces. Through a close link between several input channels, which are simultaneously active, and by immediate visualisation of the steps of the analysis, the expert is provided with a tool for the interactive exploration of complex data spaces. As input parameter for analysis algorithms VIPEM makes use of the human capacity to grasp complex patterns and correlations and therefore allows to reveal hidden structures. VIPEM aims to address the high demand for visual analytics in the field of bioinformatics. The innovative approach of VIPEM can be a unique selling proposition in this market, in such a way that we can see a promising commercial prospect for VIPEM and a marketable product within the period of two to three years. The VIPEM team aims at exploiting results either through a spin-off company or as strategic partner of an existing biomedical company. technology supplier of an existing biomedical company.

In the VIPEM project we developed an interactive data exploration system for the "visualization of" and "navigation in" molecular and clinical data. The main problem in the emerging field of personalized medicine to be dealt with is the question of how to identify connections between genetic variants and their corresponding diseases or the response to certain drugs and treatments, respectively. The huge amount of data provided by molecular analytical methods (genetic polymorphisms, gene expression data, proteomics) can only be accomplished by applying bioinformatical and statistical methods. However, even standard methods of statistics and bioinformatics fail when the data are inhomogeneous - as is the case with clinical data - and when data structures are obscured by noise and dominant patterns. We therefore make the structure of the data space visible by using visualisation methods. This makes interactive navigation and structuring of both molecular and clinical data possible. As input parameter for analysis of algorithms we make use of the human capacity to grasp complex patterns and correlations. This allows revealing hidden structures that might lead to new scientific hypotheses.