The key immunologic signatures associated with clinical outcomes after posttransplant cyclophosphamide (PTCy)-based HLA-haploidentical (haplo) and HLA-matched bone marrow transplantation (BMT) are largely unknown. To address this gap in knowledge, we used machine learning to decipher clinically relevant signatures from immunophenotypic, proteomic, and clinical data and then examined transcriptome changes in the lymphocyte subsets that predicted major posttransplant outcomes. Kinetics of immune subset reconstitution after day 28 were similar for 70 patients undergoing haplo and 75 patients undergoing HLA-matched BMT. Machine learning based on 35 candidate factors (10 clinical, 18 cellular, and 7 proteomic) revealed that combined elevations in effector CD4⁺ conventional T cells (Tconv) and CXCL9 at day 28 predicted acute graft-versus-host disease (aGVHD). Furthermore, higher NK cell counts predicted improved overall survival (OS) due to a reduction in both nonrelapse mortality and relapse. Transcriptional and flow-cytometric analyses of recovering lymphocytes in patients with aGVHD identified preserved hallmarks of functional CD4⁺ regulatory T cells (Tregs) while highlighting a Tconv-driven inflammatory and metabolic axis distinct from that seen with conventional GVHD prophylaxis. Patients developing early relapse displayed a loss of inflammatory gene signatures in NK cells and a transcriptional exhaustion phenotype in CD8⁺ T cells. Using a multimodality approach, we highlight the utility of systems biology in BMT biomarker discovery and offer a novel understanding of how PTCy influences alloimmune responses. Our work charts future directions for novel therapeutic interventions after these increasingly used GVHD prophylaxis platforms. Specimens collected on NCT0079656226 and NCT0080927627 https://clinicaltrials.gov/.