With the ultimate goal of finding new polymorphs through targeted synthesis conditions and techniques, we outline a computational framework to select optimal substrates for epitaxial growth using first principle calculations of formation energies, elastic strain energy and topological information. To demonstrate the approach, we study the stabilization of metastable VO 2 compounds which provides a rich chemical as well as structural polymorph space. We find that common polymorph statistics, lattice matching and energy above hull considerations recommends homostructural growth on TiO 2 substrates, where the VO 2 brookite phase would be preferentially grown on the a -c TiO 2 brookite plane while the columbite and anatase structures favor the a -b 1 plane on the respective TiO 2 phases. Overall, we find that a model which incorporates a geometric unit cell area matching between the substrate and the target film as well as the resulting strain energy density of the film provide qualitative agreement with experimental observations for the heterostructural growth of known VO 2 polymorphs: rutile A-and B phases. The minimal interfacial geometry matching and estimated strain energy criteria provide several suggestions for substrates and substrate-film orientations for the heterostructural growth of the hitherto hypothetical anatase, brookite and columbite polymorphs. These criteria serve as a preliminary guidance for the experimental e↵orts stabilizing new materials and/or polymorphs through epitaxy. The current screening algorithm is being integrated within the Materials Project online framework and data and hence publicly available.