An evaluation of unconditional 3D molecular generation methods

Unconditional molecular generation is a stepping stone for conditional molecular generation, which is important in de novo drug design. Recent unconditional 3D molecular generation methods report saturated benchmarks, suggesting it is time to re-evaluate our benchmarks and compare the latest models. We assess five recent high performing 3D molecular generation methods (EQGAT-diff, FlowMol, GCDM, GeoLDM, SemlaFlow), in terms of both standard benchmarks and chemical and physical validity. Overall, the best method, SemlaFlow, has an 87\% success rate in generating valid, unique, and novel molecules without post-processing; and GCDM has a 95\% success rate with post-processing.