In　this　paper,　we　propose　a　framework　for　privacy-preserving　outsourced　drug　discovery　in　the　cloud,　which　we　refer　to　as　POD.　Specifically,　POD　is　designed　to　allow　the　cloud　to　securely　use　multiple　drug　formula　providers'　drug　formulas　to　train　Support　Vector　Machine　(SVM)　provided　by　the　analytical　model　provider.　In　our　approach,　we　design　secure　computation　protocols　to　allow　the　cloud　server　to　perform　commonly　used　integer　and　fraction　computations.　To　securely　train　the　SVM,　we　design　a　secure　SVM　parameter　selection　protocol　to　select　two　SVM　parameters　and　construct　a　secure　sequential　minimal　optimization　protocol　to　privately　refresh　both　selected　SVM　parameters.　The　trained　SVM　classifier　can　be　used　to　determine　whether　a　drug　chemical　compound　is　active　or　not　in　a　privacy-preserving　way.　Lastly,　we　prove　that　the　proposed　POD　achieves　the　goal　of　SVM　training　and　chemical　compound　classification　without　privacy　leakage　to　unauthorized　parties,　as　well　as　demonstrating　its　utility　and　efficiency　using　three　real-world　drug　datasets.　IEEE