Spiral gives your agent every tool with one account. Browse the tools →

goose · Health

How to Use AlphaFold protein structure prediction in goose

Retrieve an existing AlphaFold protein model’s metadata, confidence measures, and structure file links. Use it to check which regions support structural analysis before choosing an experimental construct or examining a mutation site.

Prompts to try with AlphaFold protein structure prediction in goose

Copy an example into goose, or ask in your own words.

Use AlphaFold protein structure prediction for P04637 and add its model metadata, confidence summary, and structure file links to a JSON file in this project.

AlphaFold protein structure predictiongoose
Try asking
  • Use AlphaFold protein structure prediction for P00533 and build a residue-confidence chart from the available confidence data.

  • Use AlphaFold protein structure prediction for P69905 and P68871 and create a comparison table of sequence lengths and confidence summaries.

  • Use AlphaFold protein structure prediction for Q13542 and add a report showing which residue stretches have pLDDT above 90 or below 50.

  • Use AlphaFold protein structure prediction for P04637 and compare the returned metadata with the saved model record in this repository.

How to set up AlphaFold protein structure prediction in goose

Pick the way that suits you. Each takes about two minutes.

Use Spiral's MCP server

  1. Add the extension

    In goose Desktop, open the sidebar, click Extensions, then Add custom extension. Enter:

  2. Sign in

    When goose first connects to Spiral, your browser opens. Sign in to Spiral, pick the organization and click Authorize. No API key. If the browser does not open, goose prints the link to open yourself.

Use the Spiral skill

  1. Send goose this message

    Your agent reads Spiral's skill and sets itself up.

    set up https://spiral.ai/SKILL.md
  2. Sign in or paste a key

    Approve Spiral in the browser, or give the agent a key from the console.

Use the Spiral CLI

  1. Install and sign in

    Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

    npx -y spiral-cli@latest init

Call the Spiral API

  1. Create an API key

    In the console, under API keys.

  2. Run AlphaFold protein structure prediction

    One request; the result comes back by polling or a webhook.

    curl https://api.spiral.ai/v1/runs \
      -H "Authorization: Bearer $SPIRAL_API_KEY" \
      -H "Content-Type: application/json" \
      -H "Idempotency-Key: $(uuidgen)" \
      -d '{
        "provider": "alexandria",
        "model": "alphafold-ebi-ac-uk/structures/prediction",
        "input": {
          "id": "<id>"
        }
      }'

Then paste one of the prompts above: goose finds AlphaFold protein structure prediction on Spiral, shows the price and runs it.

AlphaFold protein structure prediction providers and prices

Spiral runs AlphaFold protein structure prediction through Alexandria. Open a card for today's price, with every fee included.

AlexandriaHealth
AlphaFold Protein Structure Database · Prediction
alphafold-ebi-ac-uk/structures/prediction

What can you do with AlphaFold protein structure prediction in goose?

Build a protein review table that pairs AlphaFold model metadata with confidence measures and structure file links. A coding agent can add the results to project files and highlight regions that need closer inspection.

Choose candidate construct boundaries

Inspect residue confidence before proposing protein fragments for expression experiments. Use confidence changes to identify candidate boundaries for experimental review.

Review a mutation site’s structural context

Locate a residue in the predicted structure and examine its local confidence. Use the result to decide how much structural detail can support a research discussion.

Screen models before downstream analysis

Compare confidence distributions across candidate proteins and identify regions that deserve closer inspection before structural calculations.

Identify possible disordered regions

Find low-confidence stretches for follow-up. Separate possible intrinsic disorder from regions where AlphaFold may lack enough information to predict a structure.

Review domain placement

Inspect PAE alongside local confidence before interpreting the spatial relationship between two protein regions.

Prepare a protein model for visualization

Retrieve structure file links and confidence information for a protein visualization or research presentation.

Check models after database updates

Compare retrieved model metadata with an earlier snapshot and flag entries for review. Account for version labels that change while coordinates remain the same.

Questions about AlphaFold protein structure prediction in goose

Can goose use AlphaFold protein structure prediction?

Yes. Add Spiral to goose as an MCP server, and goose can find and run AlphaFold protein structure prediction like any built-in tool.

How much does AlphaFold protein structure prediction cost in goose?

$0.00873 per call. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your goose plan is separate.

Do I need an Alexandria account to use AlphaFold protein structure prediction in goose?

No. Spiral runs AlphaFold protein structure prediction on its own Alexandria account. You sign in to Spiral once and never paste a key.

How long does it take to set up AlphaFold protein structure prediction in goose?

About two minutes: add the extension, then sign in.

Does goose wait while AlphaFold protein structure prediction runs?

AlphaFold protein structure prediction runs in the background. goose starts the run, checks on it and gives you the json when it's ready.

Does AlphaFold cover proteins outside humans?

Yes. The core UniProt dataset includes predicted protein structures from more than 1 million organisms, including model organisms and pathogens.

Does a newer model version mean the structure was recalculated?

No. AlphaFold DB v6 aligned the core database with UniProt 2025_03, but entries with unchanged sequences retained their v4 coordinates while receiving updated metadata and v6 labels.

How should I interpret the confidence scores?

pLDDT measures local confidence for each residue from 0 to 100. Scores above 90 indicate the highest accuracy category; scores below 50 can reflect disorder or insufficient information to predict the region confidently.

Can I retrieve a complete structure for a very long protein?

Do not assume a complete model is available. For human proteins longer than 2,700 amino acids, AlphaFold supplies overlapping 1,400-residue fragments in proteome archives, outside the website’s individual structure pages.

Does high local confidence establish how protein domains fit together?

Check predicted aligned error, or PAE, when assessing domain placement. Low PAE between residues in different domains indicates lower predicted positional error, while high PAE indicates uncertain relative placement.

Get started

Start using AlphaFold protein structure prediction in goose

One Spiral account for every tool your agent needs. No subscription; you pay per run.

Paste this into goose:

Set up goose

set up https://spiral.ai/SKILL.md
Are you an AI agent? See setup options