New Open-Source Package Makeshift Integrates NMR Data for Protein Dynamics Models

anshulkundaje · x · 2026-08-21

Researchers released Makeshift, a lightweight open-source Python package designed to lower the barrier for using Nuclear Magnetic Resonance (NMR) dynamics data in machine learning. The tool integrates data access, curation, and analysis, allowing users to retrieve and parse BMRB entries, perform chemical shift re-referencing, and predict secondary structure propensity. By re-implementing and validating several widely-used NMR calculations, Makeshift aims to pave the way for more NMR-based models like Dyna-1. A preprint is available on bioRxiv.

Original post →

More from Research

Research channel →