Deep Learning for Proteins (DL4Proteins) Workshops
January 21, 2026 · View on GitHub
Welcome to DL4Proteins!
The goal of the DL4Proteins notebook series is to democratize deep learning for protein design and prediction, arriving at a transformative moment in science. With the 2024 Nobel Prize in Chemistry awarded to David Baker, Demis Hassabis, and John Jumper for breakthroughs in computational protein design and structural prediction, this resource provides an accessible, hands-on introduction to the very tools and methodologies that shaped this revolution. By blending foundational machine learning principles with state-of-the-art approaches such as AlphaFold, RFDiffusion, and ProteinMPNN, DL4Proteins equips researchers, educators, and students with the knowledge to contribute to the future of protein engineering. These open-source notebooks bridge the gap between cutting-edge research and classroom learning, fostering a new generation of innovators in synthetic biology and therapeutics.
The associated preprint presents a detailed pedagogical framework for this notebook series, describing the motivation, learning outcomes, and deep-learning principles underlying each notebook.
Preprint:
The Jupyter notebooks below provide an introduction to the fundamental machine learning concepts and models currently utilized in the protein design space. Notebooks can be run in Google Colaboratory.
**For figures and questions to render correctly, please set colab notebooks to light mode.
Table of contents
Chapter 1: Neural Networks with NumPy
Chapter 2: Neural Networks with PyTorch
Chapter 3: Convolutional Neural Networks
Chapter 4: Language Models for Shakespeare and Proteins
Chapter 5: Language model embeddings transfer learning for downstream task
Chapter 6: Introduction to AlphaFold
Chapter 7: Graph Neural Networks for Proteins
Chapter 8: Denoising Diffusion Probabilistic Models
Chapter 9: Putting it All Together - From RFDiffusion to ProteinMPNN to Alphafold
Chapter 10: Introduction to RFDiffusion - All Atom
If you have any issues, please put into Issues tab. This is a living repository - we are actively incorporating feedback!
Authors: Michael F. Chungyoun, Sreevarsha Puvada, Gabriel Au, Courtney Thomas, Britnie J. Carpentier, Jeffrey J. Gray
Acknowledgments: Sergey Lyskov, Sergey Ovchinnikov, Johns Hopkins students of 2023 540.614/414 Protein Structure Prediction course, and the Johns Hopkins Center for Teaching Excellence and Innovation - Instructional Enhancement Grant.
Citations and Additional Resources: Each notebook in this repository draws inspiration and methodologies from various cutting-edge resources, including prominent online tools, education resources, publications, and open-source repositories. Key resources include YouTube series by Harrison Kinsley, Andrej Karpathy, and Petar Veličković. These are cited within their respective notebooks, and we encourage users to explore these foundational works for deeper insights.