Systemic　lupus　erythematosus　(SLE)　is　a　complex　autoimmune　disease　with　heterogeneous　clinical　manifestations.　Understanding　the　molecular　mechanisms　of　SLE　is　crucial　for　developing　effective　therapeutic　strategies.　This　study　downloaded　microarray　datasets　from　the　Gene　Expression　Omnibus　(GEO)　database.　Single-cell　RNA　sequencing　(scRNA-seq)　data　was　processed　to　identify　19　clusters　and　annotated　five　major　cell　types.　Then　we　calculated　mitochondrial-related　genes　(MRGs)　and　ferroptosis-related　genes　(FRGs)　scores.　FRGs　scored　the　highest　in　Megakaryocytes,　while　MRGs　scored　the　highest　in　B　cells.　By　employing　pseudotime　analysis,　cell-cell　communication　analysis,　and　Single-Cell　Regulatory　Network　Inference　and　Clustering　(SCENIC)　analysis,　we　explored　the　heterogeneity　of　cells　in　SLE.　Hub　genes　were　identified　using　high-dimensional　weighted　correlation　network　analysis　(hdWGNCA)　and　machine　learning　algorithms,　leading　to　the　development　of　a　predictive　diagnostic　model　with　high　predictive　accuracy.　Immune　infiltration　analysis　revealed　significant　correlations　between　diagnostic　biomarkers　and　various　immune　cells.　Lastly,　molecular　docking　studies　suggested　Doxorubicin　may　exert　therapeutic　effects　by　affecting　these　diagnostic　biomarkers.　This　study　offers　new　insights　into　the　pathogenesis　of　SLE　and　provide　valuable　directions　for　future　therapeutic　research.