The application of reverse translational medicine allows for the understanding of immune pathogenesis via therapeutic intervention. We applied this approach to the MuSK subtype of myasthenia gravis. Treatment with the CD20-specific B cell depletion therapy (BCDT) demonstrated that MuSK MG patients respond remarkably well; the majority invariably reach remission accompanied by a remarkable drop in autoantibody levels. Circulating antibodies are primarily produced by bone marrow resident plasma cells, which do not express CD20. So, how does BCDT diminish MuSK autoantibodies and induce rapid remission? We developed a mechanistic model, which hypothesized that plasmablasts, which are short-lived antibody secreting B cell populations, produce MuSK-specific autoantibodies. Anti-CD20-mediated BCDT is expected to deplete CD20-expressing plasmablasts or CD20 expressing memory cells that supply the plasmablast population. To test this hypothesis, we performed a series of investigations, which were reported over the last seven years and are summarized in this review. First, we isolated plasmablasts from patients and generated human recombinant monoclonal autoantibodies (mAb) which bound MuSK and had pathogenic capacity, demonstrating that MuSK autoantibodies can be produced by this specific cell population. The characterization of the mAbs showed that MuSK autoantibodies can include unique properties including unusually high antigen binding affinity, and an elevated frequency of N-linked glycosylation in their binding domains. Further characterization suggested that MuSK autoantibody-producing cells may form in the early stages of B cell development due to defective tolerance mechanisms. Finally, we sought to determine how these pathogenic B cell clones behave over time. High throughput B cell receptor sequencing was applied to investigate longitudinally collected samples from patients treated with anti-CD20-mediated BCDT. MuSK-specific clonal variants were detected at multiple timepoints spanning more than five years and reemerged after BCDT-induced remission, predating disease relapse by several months. These collective investigations provide a more detailed mechanistic understanding that MuSK MG, the key features of which include production of autoantibodies by circulating plasmablasts that can be targeted by CD20-specific BCDT, and that pathogenic clones can survive BCDT and reemerge prior to manifestation of clinical relapse.