This study focusses on using new machine learning approaches to study cell contents at different levels, called omics. Evaluating tissue specific patterns of different omics and the relation between the different levels, could hold significant promise in several sectors. Understanding how various omics work together to create tissue specific functions, can pave the way for breakthroughs in biomarker discovery and for the diagnosis of cancers. Accurate and early diagnosis of cancer, means faster access to personalized treatment plans, potentially saving lives. Robust and accurate models, built with multi-omics data, that better understand tissue-specific characteristics, would have a valuable impact on health outcomes. Patients and medical professionals could both benefit from these advancements. For the pharmaceutical and biotechnical industry, understanding tissue specific characteristics, can also help discovery of new drug targets, and streamline drug development. The broader public would also stand to gain through these enhanced healthcare services which could provide a higher quality of life. The focus in this research lies on the tissue specificity of DNA methylation (methylomics) and protein expression (proteomics). By further expanding the research to include more omics types, a better understanding of how the body functions as a system could be reached. This fundamental research can be translated into tangible benefits for medical professionals, the pharmaceutical and biotechnical industry and society as a whole. This potential highlights the transformative power multi-omics and machine learning can have on modern medicine.