#9494th of 105 in ML frameworks and librariesFor science, health and research
deepchem
Python library for deep learning on molecules, materials and biological data
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 7k
- License
- MIT
- Last commit
- Aug 2026
- Last release
- Apr 2024
- Language
- Python
Missed the latest GitHub check; these facts may be older.
Overview
DeepChem is a Python toolchain for machine learning in drug discovery, materials science, quantum chemistry and biology. It offers models with TensorFlow, PyTorch and JAX backends, built on rdkit, scikit-learn and NumPy. Colab-ready tutorials and examples take users from beginner level up.
Who it is for: Researchers applying machine learning to chemistry, materials and biology
Strengths
- Supports TensorFlow, PyTorch and JAX through separate pip extras
- Large set of tutorials and examples that run on Google Colab
- Installable via pip, conda-forge or deepchemio Docker images
- Integrates with Weights & Biases for tracking training metrics
Weaknesses
- README lists Python 3.7 through 3.10 only
- Last tagged release is 2024-04-03, though commits continue
- Some features need extra soft dependencies installed by hand
- GPU use requires installing CUDA and the framework separately
What it needs
- GPU optional
- Docker
- Needs rdkit, NumPy, pandas, scikit-learn, SciPy, joblib
- Models: TensorFlow, PyTorch, JAX
Also in ML frameworks and libraries
See all 105| Rank | Project | Score |
|---|---|---|
| 1 | transformersPython library defining open models for text, vision, audio and multimodal tasks | 94 out of 100 |
| 2 | pytorchPython tensor library with GPU support and tape-based autograd for deep learning | 94 out of 100 |
| 3 | ultralyticsPython library and CLI for training and running YOLO vision models | 93 out of 100 |
| #4 | pytorch-image-modelsPyTorch library of image models, pretrained weights and reference training scripts | 92 out of 100 |
| #5 | supervisionPython toolkit for loading, annotating and counting computer vision detections | 91 out of 100 |