Target identification and combination screening uncover context-specific therapeutic vulnerabilities, characterize molecular determinants of target dependency, and identify rational combination strategies. While large-scale perturbation studies can be performed experimentally, systematically profiling diverse tumor models, molecular subtypes, and therapeutic contexts remains resource-intensive and limits exploration across broader biological landscapes. To address this challenge, we developed Virtual Assays (VAs) based on Turbine’s Virtual Lab platform — simulated experiments that predict wet-lab outcomes — enabling large-scale in silico target identification, biomarker discovery, pathway activity analysis, and combination screening across diverse molecular backgrounds. Our platform’s biosample library currently contains 1300+ cell lines, 50+ immune cell types, 100+ PDO and 1000+ PDX samples, where we can apply perturbations of ~16k genes and 5000+ drugs in mono- or combination setup.