Example showing how to use an ML model to tune pretrained generative models?

[PatWalters]

Is there an example showing how one can use an ML model to tune the output of the pre-trained generative models?

[mufeili]

What's your purpose of tuning a pre-trained generative model?

[PatWalters]

I want to fine-tune the pre-trained model to output molecules meeting a specific profile. For instance, outputting molecules that score highly using a target-specific regression model.

[mufeili]

I see. DGL-LifeSci does not support that. You may want to check the original codebase of JTVAE or other generative models.

[PatWalters]

Thanks for your quick response. I'm just curious about the use case for the pre-trained generative models.

[mufeili]

No problems! I'll close the issue for now. Feel free to reopen it if you have any further questions.