Recent advances in cloud-based resources and technologies for imaging and multi-omics analysis have created new opportunities for exploring relationships between medical images, molecular events, and clinical outcomes using quantitative methods. However, the unprecedented scale and complexity of imaging and multi-omics data have presented critical computational bottlenecks requiring new concepts and enabling tools. The objective of this proposal is to address the computational challenges in integrative analysis of imaging and multi-omics data from The Cancer Genome Atlas (TCGA), Clinical Proteomic Tumor Analysis Consortium (CPTAC), and The Cancer Imaging Archive (TCIA) via an innovative AI-powered, scalable, and cloud-based data analytics platform to fully unlock the potential of the Cancer Research Data Commons (CRDC). This will be accomplished by building a computational framework that integrates novel data analysis algorithms including deep learning into a cloud-based platform for revealing complex relationships between medical images, multi-omics, and phenotypic outcomes. This project not only facilitates the development of new data analysis techniques, but also addresses emerging scientific questions in cancer research via a cloud-based data analytics pipeline that consists of innovative modules interfaced with CRDC. The proposed computational methods and pipeline are expected to impact cancer research and enable investigators to effectively test their scientific hypothesis.