deqiankong / sgds Goto Github PK

Hello!
As you mentioned in README.md
'''
We use selfies representations of ZINC250k with corresponding property values. All the property values can be computed either by RDKit or AutoDock-GPU.
'''
May i get the ZINC250k with corresponding property values, thank you very much!!!
My email is [email protected]
Thanks again!

Hello, and great job!
1、When generating the 10K molecules in Table 1、Table2, or Table3, etc.,
should we input some molecules, are they from the ZINK250K or MOSES?
OR
SGDS generates molecules in a manner of sampling from the latent vector $z$, after trained on the ZINK250K and MOSES datasets.
i.e., the inference process is from $z$ to $x$ in Figure 1.

2、I have this question because that other method such as LIMO in Table 1, generate molecules by giving an input from ZINK250K, and gives a better molecule with higher QED property.
So their generation process is actually an optimization process, does SGDS the same as them?

Thank you very much!

Hello, and fantastic work! I have a question regarding the optimization concept.

In the context of
SINGLE-OBJECTIVE OPTIMIZATION、MULTI-OBJECTIVE OPTIMIZATION、CONSTRAINED OPTIMIZATION, etc.
what is the target of optimization?

Is it the latent variable 'z,' or is it the prediction model 'pγ'?

I understand this might be a bit of a basic question, but I'm hoping you can help clarify this concept for me. Thank you so much! ^v^