Back to Programs

Science and medicine

DeepChem

Democratize AI for drug discovery.

data sciencedeep learninghuggingfacemachine learningnumpypythonpytorch

Participation history

3 GSoC years

2026

5 projects

Official year page

Implement RFDiffusion and RFDiffusion All-Atom in DeepChem

RFDiffusion (Watson et al., Nature 2023) is the state-of-the-art protein backbone diffusion model but DeepChem currently has no protein structure...

OLMo Support For 7B models In DeepChem

According to the Google Summer of Code (GSoC) project ideas listed for One proposed DeepChem project involves adding support for the OLMo Large...

Machine Learning Interatomic Potentials (MLIP) in DeepChem using E(3)-Equivariant Neural Networks

This project aims to develop a native PyTorch-based Machine Learning Interatomic Potential (MLIP) framework within DeepChem, enabling efficient...

DeepChem-Compatible RFDiffusion Implementation

This project aims to implement state-of-the-art protein design models, RFDiffusion and RFDiffusion-2, within the DeepChem framework using a clean,...

Single Cell and DNA Foundation Models

DeepChem supports transformer-based foundation models for chemistry (ChemBERTa, MolFormer) but has no equivalent for genomic data. This project fills...

2025

6 projects

Official year page

Hamiltonian Neural Networks

This project aims to implement Hamiltonian Neural Networks (HNN) within the DeepChem framework using PyTorch. HNNs are designed to model physical...

Model-Parallel DeepChem Model Training

This project aims to significantly enhance the DeepChem library by integrating PyTorch Lightning to enable efficient multi-GPU training. Currently,...

Porting Chemception Model to PyTorch

This project ports the Chemception model—a deep CNN for molecular property prediction—from TensorFlow to PyTorch.DeepChem has been shifting its...

Integrating Single Cell RNA-seq modeling into Deepchem

This project proposes integrating ACTINN, a neural network for automated cell type identification in single-cell RNA sequencing (scRNA-seq) data,...

Implement a Wishlist Model - Fourier Neural Operator

This project aims to implement the Fourier Neural Operator (FNO) in DeepChem, expanding its support for solving complex partial differential...

Developing Modality Support for Antibody Drug Conjugates (ADCs)

Antibody-Drug Conjugates (ADCs) represent a promising class of cancer therapeutics designed to selectively target cancer cells while minimizing...

2024

8 projects

Official year page

Protein Language Modeling

The project aims to integrate a protein language model (PLM) into the DeepChem library through HuggingFace APIs and PyTorch. The project would...

Developing Modality Support for PROTACs

PROTACs represent a very promising emerging drug modalities. Traditional modalities, small-molecule drugs, for example, or monoclonal antibodies, are...

Target Conditioned Antibody Sequence Generation Using Protein Language Models

Monoclonal antibodies (mAbs) are a potent therapeutic because of their ability to precisely target molecular surfaces at a sub-protein level...

Torch compile and PyTorch 2.2.0

This project aims to integrate the torch.compile function released in PyTorch 2.0 into DeepChem's PyTorch models, unlocking significant performance...

Porting the Smiles2Vec Model from Tensorflow to Pytorch

In this project, we aim to port DeepChem Models from Tensorflow to Pytorch. I want to select Chemnet Models model to work with. I want to put the...

Incorporating Polymer Representation in DeepChem for Drug Delivery and Material Science Support

Current methods in the DeepChem library struggle to understand complex polymers, limiting their application in drug delivery and materials science....

DeepChem meets Hugging Face pLM ESM-2: Predicting protein binding sites. A tutorial.

Protein-ligand interactions play a crucial role in various biological processes, and accurately predicting protein binding sites, where ligand...

Drug Target Selection and Validation

The project aims to integrate ConPLex for target selection and ESM for target validation into DeepChem, addressing the need for target selection and...