Technical report: Improving the properties of molecules generated by LIMO
This work addresses molecule generation for computational chemistry, but it is incremental as it focuses on ablative studies of existing methods.
The authors investigated variants of the Latent Inceptionism on Molecules (LIMO) framework to enhance generated molecule properties, finding that an autoregressive Transformer decoder with GroupSELFIES yields the best average properties in random generation tasks.
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.