DeepChem 2025 Targets

Here are some early musings on goals I’d like us to hit as a community in 2025:

  • Swapping to all Torch defaults for models
  • Deprecating all TensorFlow/Jax code formally
  • First equivariant models (SE(3) transformers, E3NN style models): Adding equivariance to DeepChem has been tricky. I want us to mature this engineering effort and get it into DeepChem core
  • First RNA-seq/ATAC-seq models: Single cell deep learning has been booming. I’d like to see us get some models into

Suggest more below!

2 Likes

Hello Bharath, I am Chirag Sindhwani, B.Tech student in Electrical Engineering from IIT BHU Varanasi. I have experience working with NequIP, Allegro, and other equivariant models. I am eager to begin contributing to DeepChem by incorporating equivariance. Do you have a plan in mind for this?

Hi Bharath, I am Rishi Das from NIT Rourkela. I am very eager to contribute in the above said targets that you have in mind for 2025. I am working in the field of Machine Learning for 2 years now. I have actively participated in several competitions and challenges on Kaggle and I have worked extensively on the Leash BELKA dataset during such a competition. During my research of that time, I came to know about DeepChem and check the objectives and goals. So, I will like to work for this organization and contribute my best as much as possible.