Scalable framework for adaptive in-silico knowledge discovery and decision-making out of genomic big data

This paper presents the concept and the modern advances of big data analytics and its influence in the area of genomics for adaptive in-silico knowledge discovery and decision-making with respect to precision and personalized medicine. The goal of the paper is to build up the scalable framework, providing a set of software tools for applying the methods in research and experimental activities for precision medicine support, establishing a modern research infrastructure that will allow for significant scientific outcomes, development of new methods and algorithms to manage big data streams, deployment of new streaming and parallel processing technologies of large sets of scientific data obtained from experiments. The scalability of the working framework reduces computational time and support optimization by involving resource reconfiguration and parallel processing. The proposed scalable framework is verified for the case studies of Multiple Sequence Alignment (MSA) based on social behavior model, enhancer-promotor interactions and early detection of breast cancer. Finally, some conclusions and future work are summarized.