Designing Data-Driven Learning Algorithms: A Necessity to Ensure Effective Post-Genomic Medicine and Biomedical Research

Advances in sequencing technology have significantly contributed to shaping the area of genetics and enabled the identification of genetic variants associated with complex traits through genome-wide association studies. This has provided insights into genetic medicine, in which case, genetic factors influence variability in disease and treatment outcomes. On the other side, the missing or hidden heritability has suggested that the host quality of life and other environmental factors may also influence differences in disease risk and drug/treatment responses in genomic medicine, and orient biomedical research, even though this may be highly con-strained by genetic capabilities. It is expected that combining these different factors can yield a paradigm-shift of personalized medicine and lead to a more effective medical treatment. With existing “big data” initiatives and high-performance computing infrastructures, there is a need for data-driven learning algorithms and models that enable the selection and prioritization of relevant genetic variants (post-genomic medicine) and trigger effective translation into clinical practice. In this chapter, we survey and discuss existing machine learning algorithms and post-genomic analysis models supporting the process of identifying valuable markers.