molML / MoleculeACE

A tool for evaluating the predictive performance on activity cliff compounds of machine learning models
MIT License
151 stars 19 forks source link

code issues #9

Closed githubXin123 closed 1 year ago

githubXin123 commented 1 year ago

Hi I want to ask if there is an issue with this line of code? Why are we using sigmoid function after obtaining the atomic mass features? https://github.com/molML/MoleculeACE/blob/27f26ebae652e5f4101218ac7a27b25558d2db33/MoleculeACE/benchmark/featurization.py#L280

smiles724 commented 1 year ago

Interesting point! I want to know why as well.