README.md

---
license: mit
tags:
  - biology
  - protein
  - protein-dynamics
  - molecular-dynamics
  - structural-biology
library_name: pytorch
pipeline_tag: other
---

# DynaProt

Checkpoints for [**"Learning residue level protein dynamics with multiscale Gaussians"**](https://arxiv.org/pdf/2509.01038)
(Mihir Bafna, Bowen Jing, Bonnie Berger — CSAIL, MIT).


| Folder | Model | Params | Output |
|---|---|---|---|
| `dynaprot-M` | DynaProt-M (marginal) | 955K | per-residue 3×3 covariances — anisotropic flexibility, and RMSF as `sqrt(Tr(Σᵢ))` |
| `dynaprot-J` | DynaProt-J (joint) | 1.9M | N×N scalar residue–residue coupling matrix |


Both were trained on the [ATLAS](https://www.dsimb.inserm.fr/ATLAS/) MD dataset (3 × 100 ns per
protein) using the AlphaFlow train/val/test split, with no large-scale PDB pretraining.

## Usage

```bash
pip install "dynaprot[hub] @ git+https://github.com/MihirBafna/dynaprot"
dynaprot predict my_protein.pdb -o out/ --num-samples 250
```

Weights download automatically on first use. In Python:

```python
from dynaprot.inference import DynaProtPredictor

predictor  = DynaProtPredictor.from_pretrained(device="cuda:0")
prediction = predictor.predict("my_protein.pdb", chain_id="A")

prediction.rmsf                  # (N,)     per-residue flexibility, Å
prediction.marginal_covariances  # (N,3,3)  anisotropic Gaussian blobs, global frame
prediction.correlation           # (N,N)    residue-residue coupling
prediction.joint_covariance      # (3N,3N)  composed joint covariance
prediction.sample_ensemble(250)  # (250,N,3)
```

## Citation

```bibtex
@inproceedings{bafna2026dynaprot,
  title     = {Learning residue level protein dynamics with multiscale Gaussians},
  author    = {Bafna, Mihir and Jing, Bowen and Berger, Bonnie},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year      = {2026}
}
```