When we analyse biological data in isolation, we only see one part of the picture. By bringing together genomic, epigenomic, and transcriptomic data, we can better understand how genetic variation and epigenetic regulation work together to influence gene expression and immune responses. Looking at these data collectively helps us identify disease-associated markers and biological pathways that we would likely miss if we analysed each data type separately. This gives us a more complete understanding of the biological mechanisms underlying health and disease.

What appeals to me most is the complexity of biological data and the challenge of making sense of it through data integration. No single data type can capture the whole picture, genetics provides the inherited variation, epigenetics adds a flexible layer shaped by environment and lifestyle, and gene expression reflects how cells respond under different conditions. Bringing these layers together helps us better understand why individuals respond differently to disease and identify the molecular mechanisms behind that variation.

Bringing research into clinical practice requires people from different fields to work closely together. Bioinformaticians, clinicians, and AI researchers all bring different expertise, and CAIMed creates an environment where they can collaborate to answer the same research questions. This makes it much easier to turn computational discoveries into findings that can eventually improve patient care.