Hey everyone! I am Atreya. I participated in Google Summer of Code 2021 under Deepchem. The goal of my project was to primarily implement the Molecular Attention Transformer.
Main Contributions:
- Added a new featurizer: MATFeaturizer
- Added a new dataset to MoleculeNet: Freesolv
- Added a way to implement and call deepchem layers written in pytorch (deepchem.models.torch_models.layers).
- Implemented the Molecular Attention Transformer as a regression model for the freesolv dataset.
A quick and short summary of my progress can be found in the Deepchem forums page.
Here is a list of PRs I sent for the project that have been merged or are currently under review:
- https://github.com/deepchem/deepchem/pull/2544
- https://github.com/deepchem/deepchem/pull/2576
- https://github.com/deepchem/deepchem/pull/2601
- https://github.com/deepchem/deepchem/pull/2622
- https://github.com/deepchem/deepchem/pull/2623
- https://github.com/deepchem/deepchem/pull/2624
- https://github.com/deepchem/deepchem/pull/2652
- https://github.com/deepchem/deepchem/pull/2676
There are also a few other utility fix, documentation and pre-GSoC PRs which I have not listed above.
Future Work
I plan on continuing to work on optimizing my contributions and adding a few more features. Currently I plan on optimizing the MAT model by converting it to a more 2-D focussed implementation so that training speed can be increased.
The addition of D-MPNN is also something that I would really like to work on.
Acknowledgements
This was my first proper deep dive into open-source, and it would be an understatement to say that I loved it. @bharath @Vignesh @hanig were really helpful and supportive, and I learnt a great deal from them. I have been able to expand my knowledge of both Deep Learning and Chemistry. The mentorship provided to me by my mentors was amazing, and their feedback has helped me become a better and more mindful developer.
I would like to thank everyone involved in the project, and I hope we continue to work together!