Big Data methods to uncover the impact of fusion genes on generating phenotypic plasticity in human cells

Technological advancements provide opportunities to quickly create, store, and analyze data that, until recently, would have taken years to compile and interpret. New biomedical techniques, such as next-generation genome sequencing, are generating large volumes of data and leading to uncover novel fusion genes as well as coding and non-coding RNAs. Particularly, precision medicine is a novel approach to healthcare that uses personal information, including genetic, environmental, and lifestyle data, to help prevent, diagnose, and treat common and complex diseases. Fusion genes have the potential to create chimeric RNAs, which can generate the phenotypic diversity of human cells, and could be associated with novel molecular functions, protein-protein interactions related to changes in a clinical phenotype.

We use Machine learning (ML), a part of AI, for the research of chimeric RNAs and other features in whole genome sequencing of patients for their clinical outcomes. It uses data-analysis techniques that are applied to multi-dimensional datasets of mutations, fusions, coding and non-coding RNAs, so that predictive models can be built and insights gained for disease diagnostics and personal treatment.

Thus, we are targeting chimeric RNAs in the content of Big Data, including next-generation sequencing (NGS) data, clinical measurements, drugs used by patients, disease development history and therapies that could be useful for uncovering phenotypes vs. genotype associations for the precision medicine using druggable fusions as biomarkers.