Diffuse Project’s cover photo
Diffuse Project

Diffuse Project

Biotechnology Research

Infrastructure for learning and representing protein motions from structural data

About us

The era of static structure prediction is here. The next frontier lies in understanding dynamics. Macromolecules do not act as rigid entities; their functions emerge from ensembles of motions shaped by structure, environment, and interactions. We are only beginning to appreciate how these motions contribute to recognition, catalysis, and regulation. We are in a state of exponential growth of new methods for collecting, modeling, and possibly predicting the flexibility ensembles. One of the most exciting aspects of this emerging frontier is that the details of conformational ensembles are often embedded within the experimental data used to derive the static macromolecular structures we’ve been collecting for decades. By learning directly from this raw data, we may be able to better converge on a macromolecule’s conformational ensemble. Beyond this, correctly representing and encoding the outputs of structural modeling is essential for translating them into biological insight. To enable AI co-driven scientific discovery, these representations must be both machine-readable and human-interpretable. Achieving this will require a transformation in how we collect, encode, and interact with biological data, building infrastructure that allows algorithms to learn from the full complexity of experimental observations while remaining accessible to human reasoning.

Website
https://diffuse.science
Industry
Biotechnology Research
Company size
11-50 employees
Type
Nonprofit
Founded
2025

Updates

Similar pages