search

DeepGraphLearning / torchdrug

A powerful and flexible machine learning platform for drug discovery
https://torchdrug.ai/
Apache License 2.0
1.43k stars 199 forks source link

How to use the generation model to generate specific molecules? #165

Open gogakg opened 1 year ago

gogakg commented 1 year ago

Hello,

I was wondering how can I use the generation model to generate specific molecules? For example, 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

KiddoZhu commented 1 year ago

Hi! The pretraining dataset determines what kind of molecules you are interested in generating, so you may use your small dataset to train the GraphAF model. If that is too small, a possible solution is to first train on ZINC250k, then finetune on your small dataset and finally finetune on property optimization.