Technical report: Improving the properties of molecules generated by LIMO

This technical report investigates variants of the Latent Inceptionism on Molecules (LIMO) framework to improve the properties of generated molecules. We conduct ablative studies of molecular representation, decoder model, and surrogate model training scheme. The experiments suggest that an autogressive Transformer decoder with GroupSELFIES achieves the best average properties for the random generation task. LIMO (Eckmann et al. (2022)) is a molecular generation technique that improves a given set of properties by mapping molecules to a latent space and uses inexpensive property surrogates to turn a discrete space optimization problem into a continuous one. There are multiple components to this framework which are described below.