Closed peizhenbai closed 3 years ago
hey, thanks. So FCS is a relatively general algorithm and is discussed in detail in our workshop paper (https://static1.squarespace.com/static/58f7aae1e6f2e1a0f9a56616/t/5e370e2d12092f15876d5753/1580666413389/paper.pdf). It can be applied in any datasets; although we found applying on a larger dataset help identify higher quality substructures. I remembered for MolTrans, we use all drugs in ChEMBL, which can be quickly downloaded here: https://tdcommons.ai/generation_tasks/molgen/#chembl. The FCS algorithm can be found here: https://github.com/kexinhuang12345/ESPF. We use canonical SMILES.
Got it, thanks!
Hi @kexinhuang12345 , I have several questions about your FCS algorithm in MolTrans paper:
This is a great job and inspire me a a lot. Many thanks!