Skip to content
/ FCD Public

Fréchet ChemNet Distance: A quality measure for generative models for molecules

License

Notifications You must be signed in to change notification settings

bioinf-jku/FCD

Folders and files

NameName
Last commit message
Last commit date

Latest commit

375216c · Apr 1, 2024

History

38 Commits
Apr 1, 2024
Apr 1, 2024
Mar 22, 2018
Apr 1, 2024
Apr 23, 2020
Nov 6, 2018
Aug 22, 2023
Apr 1, 2024
Apr 1, 2024
Apr 1, 2024

Repository files navigation

Fréchet ChemNet Distance

PyPI Tests (master) Tests (dev) PyPI - Downloads GitHub release (latest by date) GitHub release date GitHub

Code for the paper "Fréchet ChemNet Distance: A Metric for Generative Models for Molecules in Drug Discovery" JCIM / ArXiv

Installation

You can install FCD using

pip install fcd

or run the example notebook on Google Colab .

Requirements

numpy
torch
scipy
rdkit

Updates

Version 1.1 changes

  • Got rid of unneeded imports
  • load_ref_model doesn't need an argument any more to load a model.
  • canonical and canonical_smiles now return None for invalid smiles.
  • Added get_fcd as a quick way to get a the fcd score from two lists of smiles.

Version 1.2 changes