How to use the generation model to optimize specific molecules about torchdrug

[shichence]

For the first question, you could hack the code in task/generation.py/reinforce_forward, and replace the graph generated from scratch by your own molecules.

For the second question, please check out the colab.

[Yongrui-Wang]

THANKS

[gogakg]

shichence @shichence shichence

Hello,

I have similar question but I was wondering how can I use the generation model to generate specific molecules? I have a small dataset of molecules I am interested in generating, should I use ZINC250k dataset to train GraphAF model on and then use property optimization to generate novel molecules with desired QED, logP properties or should I use my small dataset(around 4k) to train the GraphAF model?

Thank you kindly,

Looking forward for your reply