Skip to content

Commit

Permalink
arxiv submission
Browse files Browse the repository at this point in the history
  • Loading branch information
bengioe committed Jun 7, 2021
0 parents commit 45dd2f9
Show file tree
Hide file tree
Showing 28 changed files with 22,727 additions and 0 deletions.
26 changes: 26 additions & 0 deletions README.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,26 @@
# Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation

Implementation for [[add arxiv link]], submitted to NeurIPS 2021.

This is a minimum working version of the code used for the paper, which is extracted from the internal repository of the [Mila Molecule Discovery](https://mila.quebec/en/ai-society/exascale-search-of-molecules/) project. Original commits are lost here, but the credit for this code goes to [@bengioe](https://github.com/bengioe), [@MJ10](https://github.com/MJ10) and [@MKorablyov](https://github.com/MKorablyov/) (see paper).

## Grid experiments

Requirements for base experiments:
- `torch numpy scipy tqdm`

Additional requirements for active learning experiments:
- `botorch gpytorch`


## Molecule experiments

Additional requirements:
- `pandas rdkit torch_geometric h5py`
- a few biochemistry programs, see `mols/Programs/README`

For `rdkit` in particular we found it to be easier to install through (mini)conda. [`torch_geometric`](https://github.com/rusty1s/pytorch_geometric) has non-trivial installation instructions.

We compress the 300k molecule dataset for size. To uncompress it, run `cd mols/data/; gunzip docked_mols.h5.gz`.

We omit docking routines since they are part of a separate contribution still to be submitted. These are available on demand, please do reach out to [email protected] or [email protected].
Loading

0 comments on commit 45dd2f9

Please sign in to comment.