A huge volume of multidimensional data is generated by modern omics biotechnologies (microarray arrays, next generation sequence, Single Nucleotide Polymorphisms data, metabolomics, proteomics, etc.). The data can be used to construct predictive and diagnostic statistical models, identify possible pharmaceutical targets, biomarkers and bio-histograms, and develop statistical models for personalized therapeutic approaches. Unfortunately, the statistical analysis of these data requires a great deal of time for an expert bioinformatician and data analyst and significantly great computational power. At the same time, analyses of this kind raise open, challenging problems in the field of data analysis. We propose a specific research program on artificial intelligence and machine learning techniques for the automatic analysis of biomedical data, finding (multiple) biomarkers and biosignatures, Big Data visualization algorithms, and interpretation of the produced biostatistical models. This research will lead to a new generation of automated analysis tools that will expand our under-construction commercial product, Just Add Data Bio. Our goal is to increase by at least one order of magnitude the productivity in data analysis as well as to make analysis possible by non-experts.
JAD Bio will be offered in the cloud computing as Software as a Service (SaaS) in a market estimated at hundreds of millions of euros.