About property computation

[tszslovewanpu]

Hello, and great job! I have a question regarding property computation. For instance, in Table 1, how do we compute the PENALIZED LOGP and QED for the generated molecules using different methods? Do we employ RDKit or the trained property prediction model gθ? If we use the property prediction model gθ, how do other methods compute their properties? Do they calculate the PENALIZED LOGP and QED using their own respective property prediction models?(if so, how about the fairity) Thank you very much!

[PeterEckmann1]

Hi,

Thanks for your interest! The penalized logP and QED property computation is done using RDKit for all methods. The property prediction models are only used in the generation process, not the actual evaluation. Therefore, the outputs from generate_molecules.py are computed using RDKit.

[tszslovewanpu]

Got it, thanks!