# ColabFold MSA server (api.colabfold.com)

Adopt this skill: https://proskills.md/skills/biomodels/aipoch-open-science-resources-skills-alphafold2

Page: https://proskills.md/skills/biomodels/aipoch-open-science-resources-skills-alphafold2
This document is the public skill bundle for that page. It contains SKILL.md and every helper file the catalog carries. No login is required.

## File: resources/skills/alphafold2/SKILL.md
size: 5391
sha: 486fe3264eb577a267bdb0e2b624a31993c04d36
upstream: https://github.com/aipoch/open-science/blob/main/resources/skills/alphafold2/SKILL.md

````text
---
name: alphafold2
description: >
  Predict protein structure for monomers and multimers with AlphaFold2 via the
  ColabFold runner (Mirdita et al. 2022, github.com/sokrypton/ColabFold;
  AlphaFold2 Jumper et al. 2021). Reach for this skill to fold a sequence or
  complex with the AF2/AF2-Multimer evoformer, to validate designed sequences
  by self-consistency pLDDT, ipTM, and RMSD, or to run a quick MSA-backed
  prediction using the public MMseqs2 server.
license: Apache-2.0
category: biomodels
requirements: [gpu]
metadata:
  display-name: AlphaFold2
  # README #model-parameters-license: "AlphaFold parameters … CC BY 4.0".
  # SKILL.md body: "the public MMseqs2 server" (api.colabfold.com — user's
  # sequence is POSTed there for MSA). verified 2026-06-30
  third_party:
    - kind: weights
      name: AlphaFold2
      provider: Google DeepMind
      license: CC-BY-4.0
      terms_url: https://github.com/google-deepmind/alphafold#model-parameters-license
    # api.colabfold.com has no published ToS or privacy policy. The GitHub
    # wiki is the closest data-use reference (info_url, not terms_url).
    # Hostname in `name` so the user sees exactly where their sequence goes.
    - kind: service
      name: ColabFold MSA server (api.colabfold.com)
      provider: Steinegger Lab
      info_url: https://github.com/sokrypton/ColabFold/wiki
---

# AlphaFold2 (ColabFold runner)

This skill wraps AlphaFold2 and AlphaFold2-Multimer through `colabfold_batch`,
which replaces DeepMind's local-database MSA pipeline with a call to the public
MMseqs2 server — so a prediction is one command and one FASTA, not a 2 TB
database mount. AF2 remains the reference monomer predictor and the multimer
model is still a strong protein–protein validator, but it does not handle
ligands or nucleic acids; for those, route to `boltz`, `chai1`, or `openfold3`.
The ColabFold code is MIT (github.com/sokrypton/ColabFold) and the AlphaFold2
code is Apache-2.0 (github.com/google-deepmind/alphafold); the AF2 model
parameters are CC-BY-4.0 with DeepMind's terms of use.

## Running it

```bash
colabfold_batch input.fasta out \
  --num-recycle 3 \
  --model-type alphafold2_multimer_v3
```

The input is a plain FASTA. For a complex, put every chain on one sequence
line separated by `:` — `colabfold_batch` builds a paired MSA per segment and
runs the multimer model when it sees the colon (so the explicit `--model-type
alphafold2_multimer_v3` above is belt-and-braces). For monomers omit
`--model-type` and the colon. `--templates` and `--amber` add PDB templates
and OpenMM relaxation respectively; both are off by default and both add
minutes per model.

ColabFold runs all five AF2 model weights by default and ranks them by pLDDT
(pTM/ipTM for multimer), so output per query lands in `out/` as five ranked
PDBs `<name>_unrelaxed_rank_00{1..5}_*.pdb` (b-factor column carries pLDDT)
and a matching `<name>_scores_rank_00{N}_*.json` with `plddt`, `ptm`, and — for
multimer — `iptm` and the `pae` matrix. Rank-1 is the model to read first;
ipTM > 0.5 is the usual soft pass for an interface.

## Unified-memory defaults loop forever under gVisor — the env patches them out

`colabfold/batch.py` hard-sets `TF_FORCE_UNIFIED_MEMORY=1` and
`XLA_PYTHON_CLIENT_MEM_FRACTION=4.0` on import. Under a gVisor sandbox unified
memory is unsupported, so JAX's `device_put` loops indefinitely allocating
host RAM during AF2 parameter load — the job appears hung, never errors.
Override both before the import (`TF_FORCE_UNIFIED_MEMORY=0`, fraction
`0.95`), or `sed`-patch the two assignments out of `batch.py` in the image
build, or the first fold never starts.

## The MSA server is the wall-clock bottleneck, and it is shared

`colabfold_batch` defaults to `--msa-mode mmseqs2_uniref_env`, which posts your
sequence to `api.colabfold.com`. That server is a public, rate-limited
resource: the wait dominates short folds and occasionally times out under load.
For campaigns, run the MSA stage once with `--msa-only`, keep the resulting
`.a3m` files, and feed the directory back as the input on subsequent runs — the
GPU stage then starts immediately and the server is not hit again.

## Errors worth recognizing

| You see                                                            | It means / do this                                                                                                 |
| ------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------ |
| Job hangs silently during "Running model_1" with host RAM climbing | Unified-memory loop under gVisor — see the gotcha above; override or patch `batch.py`.                             |
| `RESOURCE_EXHAUSTED` / OOM during XLA compile                      | `XLA_PYTHON_CLIENT_MEM_FRACTION` too high for the GPU — drop below the `0.95` default to `0.9` or so.              |
| MSA stage hangs at `Submitting job`                                | Public MMseqs2 server is rate-limiting — wait, or pre-compute with `--msa-only` and re-run from the cached `.a3m`. |

---

**Next:** for designed-sequence validation, superpose the rank-1 model onto
the design backbone with US-align and gate on pLDDT/ipTM thresholds; for
ligand-bearing complexes, hand the same chains to `boltz` or `chai1`.
````

## File: resources/skills/alphafold2/.catalog_stamp
size: 13
sha: 267b449ac7af5326abcb1f5a532eb50b0e31d377
upstream: https://github.com/aipoch/open-science/blob/main/resources/skills/alphafold2/.catalog_stamp

```text
1782943770000
```

## File: README.md
upstream: https://github.com/aipoch/open-science/blob/main/README.md

````text
<h1 align="center">AIPOCH Open-Science</h1>

<p align="center">
  AIPOCH Open-Science is a local-first open-source AI research workbench for reproducible science, with flexible model backends. Share a portable <code>.science</code> Research Package so others can inspect the evidence behind a result, or export a Research Film to show how you reached it.
</p>

<p align="center">
  <a href="https://www.youtube.com/watch?v=to_BhE5DDMw">
    <img width="720" alt="AIPOCH Research Generation Demo — AIPOCH Open-Science .science Research Package" src="docs/images/readme/demo-full.webp" />
  </a>
</p>

<p align="center">Watch on YouTube: <a href="https://www.youtube.com/watch?v=to_BhE5DDMw">AIPOCH Open-Science: Generating .science Research Packages (Demo)</a></p>

<p align="center">
  <a href="https://aipoch.com/open-science/download">
    <img alt="Download AIPOCH Open-Science" src="https://img.shields.io/badge/Download-Latest%20Release-2f9e44?style=flat">
  </a>
  <a href="https://github.com/aipoch/open-science/releases/latest">
    <img alt="Latest AIPOCH Open-Science version" src="https://img.shields.io/github/v/release/aipoch/open-science?label=Version&style=flat&color=4dabf7">
  </a>
  <a href="https://doi.org/10.5281/zenodo.22252246">
    <img alt="AIPOCH Open-Science Zenodo DOI" src="https://img.shields.io/badge/DOI-10.5281%2Fzenodo.22252246-0b7285?style=flat">
  </a>
  <a href="https://arxiv.org/abs/2610.17110">
    <img alt="AIPOCH Open-Science preprint on arXiv: 2610.17110" src="docs/images/readme/arxiv-preprint.svg">
  </a>
  <a href="#benchmark-performance">
    <img alt="AIPOCH Open-Science — Benchmark results" src="docs/images/readme/benchmark-comparisons.svg">
  </a>
  <a href="https://github.com/aipoch/open-science/releases/latest">
    <img alt="Platforms macOS Windows Linux" src="https://img.shields.io/badge/platform-macOS%20%7C%20Windows%20%7C%20Linux-4263eb?style=flat">
  </a>
  <a href="LICENSE">
    <img alt="License Apache 2.0" src="https://img.shields.io/badge/license-Apache--2.0-7950f2?style=flat">
  </a>
  <a href="https://aipoch.com/open-science">
    <img alt="Website aipoch.com" src="https://img.shields.io/badge/website-aipoch.com-e8590c?style=flat">
  </a>
</p>

<p align="center">
  <a href="./README.md"><img alt="README in English" src="https://img.shields.io/badge/English-d9d9d9"></a>
  <a href="./docs/zh-Hans/README.md"><img alt="简体中文 README" src="https://img.shields.io/badge/简体中文-d9d9d9"></a>
  <a href="./docs/zh-Hant/README.md"><img alt="繁體中文 README" src="https://img.shields.io/badge/繁體中文-d9d9d9"></a>
  <a href="./docs/ja/README.md"><img alt="日本語 README" src="https://img.shields.io/badge/日本語-d9d9d9"></a>
  <a href="./docs/ko/README.md"><img alt="한국어 README" src="https://img.shields.io/badge/한국어-d9d9d9"></a>
  <a href="./docs/fr/README.md"><img alt="Français README" src="https://img.shields.io/badge/Français-d9d9d9"></a>
  <a href="./docs/ru/README.md"><img alt="README на русском" src="https://img.shields.io/badge/Русский-d9d9d9"></a>
  <a href="./docs/de/README.md"><img alt="German README" src="https://img.shields.io/badge/Deutsch-d9d9d9"></a>
  <a href="./docs/es/README.md"><img alt="Español README" src="https://img.shields.io/badge/Español-d9d9d9"></a>
</p>

### 💡 AIPOCH Open-Science v1.2.2 updates

_November 12, 2026_

- **Strict network mode**: Opt in to a Strict whitelist for Notebook networking — requests must match your rules by protocol, host, and port; unmatched requests are blocked without an authorization prompt.
- **Films resume**: Interrupted research-film generation continues from validated checkpoints with a five-step progress view; completed scenes and narration are reused.
- **PDF fidelity**: External PDFs keep native figures, tables, captions, and reading order, and translated documents preserve the original structure and layout.
- **Safer Windows grants**: Folder grants in protected mode are checked before saving, and update, uninstall, and handoff flows recover more reliably with diagnostics preserved.
- **Provider updates**: Qwen4 Max Preview joins Bailian Token Plans in Beijing and Singapore, and default models for official connections are refreshed.
- **Reliability fixes**: Session imports report their outcome, service recovery blocks the workspace until the connection returns, and dark-mode contrast is preserved across surfaces.

[View the full v1.2.2 release notes](https://github.com/aipoch/open-science/releases/tag/v1.2.2)

<a id="share-your-research"></a>

## A research record to share, a film to watch

**Hand off a result with a [`.science` package](https://aipoch.com/docs/guides/research-packages/).** Export the conversation branches, file versions, Notebook records, and verification evidence you want to share. Recipients can import the package into their own projects, open the read-only record, and trace a figure or table back to its inputs. Verification records describe the sender’s checks. In the desktop app, **Fork to continue** creates a writable copy.

**Present the same work as a [Research Film](https://aipoch.com/docs/guides/research-films/).** In the desktop app, choose **Generate research film** on a completed conversation branch. Your configured model prepares the presentation from the recorded session, and the local speech engine generates English narration. Review the film, then download the HTML player or export an MP4. A `.science` package can also carry the player for a film already generated on an included branch.

## 🚀 Quick Start

### 1. Download the app

Open the [official download page](https://aipoch.com/open-science/download) and choose the installer for your computer:

| Your computer                           | Choose                                     |
| --------------------------------------- | ------------------------------------------ |
| macOS 12+ — Apple Silicon (M1 or newer) | The macOS DMG for Apple Silicon / ARM64    |
| macOS 12+ — Intel                       | The macOS DMG for Intel / x64              |
| Windows 10/11 x64                       | The Windows x64 installer (code-signed)    |
| Linux x64                               | The Linux x64 AppImage or Debian package   |
| Linux ARM64                             | The Linux ARM64 AppImage or Debian package |

See [download verification](SECURITY.md#verifying-your-download) for checks before installation.

On macOS, you can also install with [Homebrew](https://brew.sh):

```bash
brew install --cask open-science
```

The [release assets](https://github.com/aipoch/open-science/releases/latest) include standalone CLI archives for macOS, Linux, and Windows. They bundle Node.js, so you can run the CLI without installing Node.js, npm, or Homebrew.

For the standalone CLI on macOS or Linux, use the separate [AIPOCH tap](https://github.com/aipoch/homebrew-tap):

```bash
brew install aipoch/tap/open-science
```

This Formula includes Node and runs without the desktop app; its release may differ from the desktop Cask. See the [standalone runtime guide](docs/standalone-runtime.md) for prerequisites and upgrades.

For the standalone CLI and Web UI, install the published [npm package](https://www.npmjs.com/package/@aipoch/open-science) with **Node.js 22.13.0 or later**:

```bash
npm install --global @aipoch/open-science
open-science start --no-open
open-science url
```

Open the printed URL to complete setup, or follow the [terminal setup guide](packages/open-science/CLI.md#first-run-setup-codex). npm supports macOS ARM64/x64, glibc Linux ARM64/x64 and Windows x64; the desktop app is not required. Keep npm optional dependencies enabled and review the [Linux prerequisites and upgrade instructions](docs/standalone-runtime.md#install-from-npm). The URL contains an authentication token; keep it private.

Windows reinstalls preserve research data. For a full cleanup, see the [data reset tool](scripts/windows-reset/README.md), which permanently deletes local data after confirmation.

### 2. Complete first-time setup

F
````
