DL4Proteins Jupyter Notebooks Teach how to use Artificial Intelligence for Biomolecular Structure Prediction and Design

TL;DR

DL4Proteins provides interactive Jupyter notebooks that teach AI-based biomolecular structure prediction and design, making advanced tools accessible for educational purposes and broadening participation in protein research.

Contribution

It introduces a comprehensive series of notebooks that teach fundamental ML concepts and demonstrate cutting-edge AI tools for protein structure prediction and design.

Findings

Accessible educational resources for AI in protein science

Interactive notebooks cover training ML models for proteins

Enables broader participation in AI-driven protein research

Abstract

Computational methods for predicting and designing biomolecular structures are increasingly powerful. While previous approaches relied on physics-based modeling, modern tools, such as AlphaFold2 in CASP14, leverage artificial intelligence (AI) to achieve significantly improved performance. The growing impact of AI-based tools in protein science necessitates enhanced educational materials that improve AI literacy among both established scientists seeking to deepen their expertise and new researchers entering the field. To address this need, we developed DL4Proteins, a series of ten interactive notebook modules that introduce fundamental machine learning (ML) concepts, guide users through training ML models for protein-related tasks, and ultimately present cutting-edge protein structure prediction and design pipelines. With nothing more than a web browser, learners can now access state-of-the-art computational tools employed by professional protein engineers - ranging from all-atom protein design to fine-tuning protein language models for biophysically relevant functional tasks. By increasing accessibility, this notebook series broadens participation in AI-driven protein research. The complete notebook series is publicly available at https://github.com/Graylab/DL4Proteins-notebooks.