BACKGROUND: The metastatic microenvironment is often rich in tumor-associated macrophages (TAMs). In uveal melanoma (UM), high levels of TAMs positively correlate with tumor progression and poorer prognosis. We hypothesize that the immunomodulation of TAMs can remodel the UM tumor microenvironment and make it more susceptible to therapeutic interventions. METHODS: In our work, we designed a novel computational pipeline that combines single-cell transcriptomics data, network analysis, multicriteria decision techniques, and pharmacophore-based docking simulations to select molecular targets and matching repurposable drugs for TAM immunomodulation. The method generates a ranking of drug-target interactions, the most promising of which are channeled towards experimental validation. RESULTS: To identify potential immunomodulatory targets, we created a network-based representation of the TAM interactome and extracted a regulatory core conditioned on UM expression data. Further, we selected 13 genes from this core (NLRP3, HMOX1, CASP1, GSTP1, NAMPT, HSP90AA1, B2M, ISG15, LTA4H, PTGS2, CXCL2, PLAUR, ZFP36, TANK) for pharmacophore-based virtual screening of FDA-approved compounds, followed by flexible molecular docking. Based on the ranked docking results, we chose the interaction between caspase-1 and clindamycin for experimental validation. Functional studies on macrophages confirmed that clindamycin inhibits caspase-1 activity and thereby inflammasome activation, leading to a decrease in IL-1β, IL-18, and gasdermin D cleavage products as well as a reduction in pyroptotic cell death. This clindamycin-mediated inhibition of caspase-1 was also observable in TAMs derived from the bone marrow of multiple myeloma patients. CONCLUSIONS: Our computational workflow for drug repurposing identified clindamycin as an efficacious inhibitor of caspase-1 that suppresses inflammasome activity and pyroptosis in vitro in TAMs.