The remarkable genetic heterogeneity of Multiple Myeloma poses a significant challenge for proper prognostication and clinical management of patients. Here, we introduce MM-PSN, the first multi-omics Patient Similarity Network of Myeloma. MM-PSN enabled accurate dissection of the genetic and molecular landscape of the disease and determined twelve distinct sub-groups defined by five data types generated from genomic and transcriptomic patient profiling of 655 patients. MM-PSN revealed that 1q gain is the most important single lesion conferring high risk of relapse and that it can improve on the current International Staging Systems (ISS and R-ISS). Several sub-groups uncovered novel associations between the gain of 1q and other adverse secondary lesions, thereby identifying the chromosomal hallmarks of sub-clonal heterogeneity and tumor progression in MM. We also determined gene vulnerabilities and potential therapeutic options for each sub-group and validated our prognostic model in an independent dataset.