> For the complete documentation index, see [llms.txt](https://jwliaomath.gitbook.io/cocofold2/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://jwliaomath.gitbook.io/cocofold2/user_guide.md).

# CoCoFold2 User Guide

CoCoFold2 refines protein structure predictions from limited-particle cryo-EM observations using a frozen Protenix-v1 diffusion prior. This guide covers installation, input preparation, refinement and inspection of saved results.

[Project website](https://jwliaomath.github.io/CoCoFold2/) · [Source code](https://github.com/jwliaomath/CoCoFold2) · [Releases](https://github.com/jwliaomath/CoCoFold2/releases)

## Start here

1. Follow [Installation](/cocofold2/getting-started/installation.md) and validate your environment.
2. Read [Input data requirements](/cocofold2/getting-started/data_requirements.md), including the coordinate frame and particle-path conventions. For fixed-frame refinement, choose the required 3D [projection origin](/cocofold2/reference/parameter_guide.md#choosing-the-projection-origin) before starting a new run.
3. Run the [7ZDT/7ZD5 minimal example](/cocofold2/getting-started/7zdt_7zd5.md) before adapting the workflow to your own data.
4. Inspect the exported structure and [structured run records](/cocofold2/reference/outputs_and_restart.md).

Run shell commands from the cloned CoCoFold2 repository root unless a tutorial explicitly says otherwise. Replace example paths with your own paths. Weights, common resources and sequence/MSA inputs are separate from the source checkout.

## Choose a workflow

| Task                                               | Guide                                                                                                                    |
| -------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |
| Refine a complete structure on one GPU             | [Single-GPU 6ZBH tutorial](/cocofold2/refinement-workflows/particle_tutorial_6zbh.md)                                    |
| Refine components across two GPUs                  | [Parallel 6ZBH example](/cocofold2/refinement-workflows/6zbh_parallel.md)                                                |
| Prepare Independent or Contextual component caches | [Component preparation](/cocofold2/refinement-workflows/component_parallel_tutorial.md)                                  |
| Use separate rigid transforms for chains or blocks | [Alignment guide](/cocofold2/refinement-workflows/block_rigid_alignment.md)                                              |
| Understand options and saved states                | [Parameters](/cocofold2/reference/parameter_guide.md) and [outputs/restart](/cocofold2/reference/outputs_and_restart.md) |

## Interpreting results

A successful smoke test checks execution and output consistency; it does not establish structural accuracy for a new target. Inspect agreement with your experimental map and, when appropriate, compare matched atoms with an independent reference. Read the [validation scope](/cocofold2/reference/release_validation.md) for the tested workflows and their limits.

For errors, start with [Troubleshooting](/cocofold2/reference/troubleshooting.md). Report reproducible issues through [GitHub Issues](https://github.com/jwliaomath/CoCoFold2/issues), including the command, environment and relevant error messages.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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, and the optional `goal` query parameter:

```
GET https://jwliaomath.gitbook.io/cocofold2/user_guide.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.