# ROCKET User Guide

ROCKET refines protein structure predictions against **X-ray** and **cryo-EM/ET** data.

It combines OpenFold prediction, Phenix preprocessing, and gradient-based maximum-likelihood refinement.

{% hint style="success" %}
New to ROCKET? Install first. Then follow the setup tutorial for your data type.
{% endhint %}

Read our [paper in *Nature Methods*](https://www.nature.com/articles/s41592-026-03047-4).

{% embed url="<https://github.com/alisiafadini/ROCKET>" %}

### Start here

{% hint style="info" %}
Keeping it simple: install once, preprocess datasets, then iterate in `rk.refine`.
{% endhint %}

<table data-view="cards"><thead><tr><th>Title</th><th data-card-target data-type="content-ref">Target</th></tr></thead><tbody><tr><td>Install ROCKET</td><td><a href="/spaces/k7qcAL69XMMAPrtIDoGr/pages/dogmOsjGr1VNjyBsK51m">/spaces/k7qcAL69XMMAPrtIDoGr/pages/dogmOsjGr1VNjyBsK51m</a></td></tr><tr><td>Set up with X-ray data</td><td><a href="/spaces/k7qcAL69XMMAPrtIDoGr/pages/VRekUTJg5zIwTJeTULS5">/spaces/k7qcAL69XMMAPrtIDoGr/pages/VRekUTJg5zIwTJeTULS5</a></td></tr><tr><td>Set up with cryo-EM data</td><td><a href="/spaces/k7qcAL69XMMAPrtIDoGr/pages/KPRh3sQ8v8vPRaUHAaDq">/spaces/k7qcAL69XMMAPrtIDoGr/pages/KPRh3sQ8v8vPRaUHAaDq</a></td></tr><tr><td>CLI reference</td><td><a href="/spaces/k7qcAL69XMMAPrtIDoGr/pages/Ii0ZO8KBv1fKfhM9pK9y">/spaces/k7qcAL69XMMAPrtIDoGr/pages/Ii0ZO8KBv1fKfhM9pK9y</a></td></tr></tbody></table>

### Example workflows

<table data-view="cards"><thead><tr><th>Title</th><th data-card-target data-type="content-ref">Target</th></tr></thead><tbody><tr><td>MSA subsampling with data-based scoring</td><td><a href="/spaces/k7qcAL69XMMAPrtIDoGr/pages/YPvodjGiln3gaWx0Swyt">/spaces/k7qcAL69XMMAPrtIDoGr/pages/YPvodjGiln3gaWx0Swyt</a></td></tr><tr><td>Low-resolution cryo-EM refinement</td><td><a href="/spaces/k7qcAL69XMMAPrtIDoGr/pages/Am7XlfyWF4JG6rMXA20h">/spaces/k7qcAL69XMMAPrtIDoGr/pages/Am7XlfyWF4JG6rMXA20h</a></td></tr></tbody></table>

## Citing

```bibtex
@article{fadini2025alphafold,
  title={AlphaFold as a Prior: Experimental Structure Determination Conditioned on a Pretrained Neural Network},
  author={Fadini, Alisia and Li, Minhuan and McCoy, Airlie J and Terwilliger, Thomas C and Read, Randy J and Hekstra, Doeke and AlQuraishi, Mohammed},
  journal={bioRxiv},
  year={2025}
}
```


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://rocket-9.gitbook.io/rocket-docs/rocket-user-guide.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.