The development of different high-throughput omics technologies over the past two decades has completely revolutionized our ability to measure molecular entities in biological systems. This unprecedented rate of data generation has given rise to the era of biomedical big data, where the main challenges lie in how to integrate and interpret large-scale heterogeneous data of different types and from different sources. This project will explore different AI and machine leaning approaches for analysis and integration of multi-omics and image data from the biological domain. A key research question addressed is whether deep learning models, like convolution neural networks, can be successfully applied to classify stem cell culture microscopy images and MRI images from multiple sclerosis patients. Single-cell RNA-seq and other types of omics data may also be generated, and used for classification and clustering analysis.