If you have other models you'd like to see in DeepChem, please chime in below as well and I'll update the main wishlist at the top of the thread

Maybe seen and implementation of MolGAN (https://github.com/nicola-decao/MolGAN https://arxiv.org/abs/1805.11973) would be nice 😃

@nicola-decao We already have MolGAN in DeepChem! https://deepchem.readthedocs.io/en/latest/api_reference/models.html#basicmolganmodel. I hadn't realized you were the lead author :)

how about reinforcement learning, such as Reinvent. https://github.com/MolecularAI/Reinvent

@rbharat Oh WOW I did not know that! 😱 I'll proudly share that with people then!

MegaMolBART (released last month) would be interesting to compare against the other generative models: https://ngc.nvidia.com/catalog/models/nvidia:clara:megamolbart

We have some funding now to support people who want to implement models. Please apply following directions at https://forum.deepchem.io/t/deepchem-model-wishlist-internships/569 if you are interested!

Hi. I would love to take a crack at implementing SE(3) Transformer. Since it has a high quality implementation available already, it should give me a gentle intro to deepchem's repo!

Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation (https://arxiv.org/abs/2106.04399, https://github.com/bengioe/gflownet) paper proposes an approach for tasks like molecule synthesis. Maybe this can be added to the list.

Neural Flows (https://proceedings.neurips.cc/paper/2021/file/b21f9f98829dea9a48fd8aaddc1f159d-Paper.pdf) proposes an
alternative by directly modeling the solution curves — the flow of an ODE — with a neural network. This immediately eliminates the need for expensive numerical solvers while still maintaining the modeling capability of neural ODEs.

I'm currently working on adding a tutorial for scikit-learn's Gaussian Processes. However, I've been having trouble with getting calibrated uncertainty out of it. I plan to try again with a different implementation of Gaussian Processes like GPy.

Is someone still working on implementing ChemProp (D-MPNN)?

@TheRealSalmon I believe that @atreyamaj was working with a student on ChemProp but I'm not sure if that project is still proceeding. Perhaps it might be worth teaming up and discussing? I'd really like to see D-MPNN make it into ChemProp so I can help on the effort as well :)

@TheRealSalmon I believe that @atreyamaj was working with a student on ChemProp but I'm not sure if that project is still proceeding. Perhaps it might be worth teaming up and discussing? I'd really like to see D-MPNN make it into ChemProp so I can help on the effort as well :)

Hi! I'm really sorry for the delay, got caught up with my thesis project for this semester. Now that the project is almost over, I will be resuming working on DMPNN starting now.

@atreyamaj and @rbharath I would like to work on DPMNN project as well, can you please give me just a heads up how to proceed?

Many of these models (Neural ODEs, Lagrangian / Hamiltonian) and various neural operators are available in torchdyn and / or the DiffeqML ecosystem. We'd be happy to help deepchem adopt our API.

@Zymrael I believe @shivance and @VIGNESHinZONE are both working on different ODE/PDE/NODE models and might be interested in discussing with you

@Zymrael Can we please hop on a call sometime to discuss on the same or maybe you could talk during deepchem's office hours ?

@rbharath this also seems interesting!
https://astroautomata.com/paper/rediscovering-gravity/

@gusty1g Is this Model Wishlist updated?

@gusty1g Is this Model Wishlist updated?

Mostly. I am working on grover. If you are interested to work on some, post that you are working on it here.

Hey! Can I work on the Kalman Filter? Is it still available?

Hey @rbharath and fellow DeepChem contributors! Can I work on HM Models,if someone else isnt' working on it?

@rbharath can we add GFlowNet (https://papers.nips.cc/paper/2021/hash/e614f646836aaed9f89ce58e837e2310-Abstract.html), (https://openreview.net/pdf?id=JFSaHKNZ35b),(https://pubs.rsc.org/en/content/articlepdf/2023/dd/d3dd00002h) as a generative model

Hey @rbharath, can I work on implementing Neural ODEs under GSOC 2024.
Please let me know how to proceed