RdkitConformerFeaturizer

[tonydavis629]

Description

This PR implements a featurizer which uses RDkit to generate conformers and 3d coordinates

Type of change

Please check the option that is related to your PR.

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
  • In this case, we recommend to discuss your modification on GitHub issues before creating the PR
• Documentations (modification for documents)

Checklist

• My code follows the style guidelines of this project
• Run yapf -i <modified file> and check no errors (yapf version must be 0.32.0)
• Run mypy -p deepchem and check no errors
• Run flake8 <modified file> --count and check no errors
• Run python -m doctest <modified file> and check no errors
• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• I have added tests that prove my fix is effective or that my feature works
• New unit tests pass locally with my changes
• I have checked my code and corrected any misspellings

[tonydavis629]

The main issue which I think we need to discuss is the handling of conformers in the featurization. We input one smiles, and get get out n number of conformers. How are those packaged? I think what makes the most sense is a list of GraphData objects. This requires a little bit different handling when doing batching, this is handled by flattening the batch and then forming a BatchGraphData, as seen in the doctest and unit test. The other alternative is a BatchGraphData object, but batching multiple BatchGraphData objects will require a change to GraphData, so I opted out of that.

The other question is whether we want to enable limits on the RMSD error for a conformer to be returned, because if you set self.num_conformers too high you will get unrealistic molecules. Not sure how important that is, or if we can leave that up to the user to decide.

[rbharath]

Can you a docstring?

[tonydavis629]

done

[rbharath]

Documenting offline discussion, @tonydavis629 to proceed with fixed number of conformers, a quality rejection threshold for conformers, and to either round-robin repeat or use Nones in the case that there are insufficient high quality conformers.

[rbharath]

LGTM, feel free to merge in once CI is clear