Skip to content
cccskills
FreePublished on GitHub

query-alphafold

Query AlphaFold protein structure predictions. Use when user asks about protein structure, 3D structure, protein folding, or structure prediction. Triggers on "alphafold", "protein structure", "3D structure", "folding", "pLDDT", "structure prediction".

The English summary is being prepared. Showing the original description.

See how to install

Files included (1)

  • SKILL.md2.7 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

AlphaFold Structure Database Query

Query the AlphaFold EBI API for predicted protein structures.

When to Use

  • User asks about a protein's predicted 3D structure
  • User wants to download PDB/CIF structure files
  • User asks about structure confidence (pLDDT scores)
  • User wants to visualize protein structure

How to Execute

import requests
import json

BASE_URL = "https://alphafold.ebi.ac.uk/api"

# 1. Get prediction info
def get_alphafold_prediction(uniprot_id):
    url = f"{BASE_URL}/prediction/{uniprot_id}"
    r = requests.get(url)
    r.raise_for_status()
    return r.json()

# 2. Download structure file
def download_structure(uniprot_id, output_dir="/workspace/group", fmt="pdb", version="v4"):
    filename = f"AF-{uniprot_id}-F1-model_{version}.{fmt}"
    url = f"https://alphafold.ebi.ac.uk/files/{filename}"
    r = requests.get(url)
    r.raise_for_status()
    filepath = f"{output_dir}/{filename}"
    with open(filepath, 'wb') as f:
        f.write(r.content)
    return filepath

# 3. Get per-residue confidence (pLDDT)
def get_plddt(uniprot_id):
    url = f"{BASE_URL}/prediction/{uniprot_id}"
    r = requests.get(url)
    data = r.json()
    if isinstance(data, list) and data:
        cif_url = data[0].get("cifUrl", "")
        plddt_url = data[0].get("paeImageUrl", "")
        return {"cifUrl": cif_url, "paeImageUrl": plddt_url, "data": data[0]}
    return data

# Example
data = get_alphafold_prediction("P04637")  # TP53
if isinstance(data, list) and data:
    entry = data[0]
    print(f"UniProt: {entry.get('uniprotAccession')}")
    print(f"Gene: {entry.get('gene', 'N/A')}")
    print(f"Organism: {entry.get('organismScientificName', 'N/A')}")
    print(f"Model confidence: {entry.get('globalMetricValue', 'N/A')}")
    print(f"PDB URL: {entry.get('pdbUrl', 'N/A')}")
    print(f"CIF URL: {entry.get('cifUrl', 'N/A')}")

Endpoints

EndpointURLUse
Prediction/api/prediction/{uniprot_id}Get model info & download URLs
Summary/api/uniprot/summary/{uniprot_id}.jsonBrief summary
Annotations/api/annotations/{uniprot_id}Per-residue annotations

Download Formats

  • PDB: AF-{UNIPROT_ID}-F1-model_v4.pdb
  • CIF: AF-{UNIPROT_ID}-F1-model_v4.cif
  • PAE image: Available from prediction endpoint

Follow-up Suggestions

  • "Want me to analyze the structure confidence by region?"
  • "Should I compare this to the experimental PDB structure?"
  • "Want me to identify disordered regions?"

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Workflow for read alignment, sorting, indexing, mapping statistics, and downstream-ready alignment artifacts.

The English summary is being prepared. Showing the original description.

BioTender-max/awesome-bio-agent-skills204Updated Jul 2, 2026

Validate protein designs using AlphaFold2 structure prediction. Use this skill when: (1) Validating designed sequences fold correctly, (2) Predicting binder-target complex structures, (3) Calculating confidence metrics (pLDDT, pTM, ipTM), (4) Self-consistency validation of designs, (5) Multi-chain complex prediction with AlphaFold-Multimer. For faster single-chain prediction, use esm. For QC thresholds, use protein-qc.

The English summary is being prepared. Showing the original description.

BioTender-max/awesome-bio-agent-skills204Updated Jul 2, 2026

AlphaFold2 / AlphaFold-Multimer structure prediction for validation and confidence scoring. Use this skill when: (1) Validating designed sequences fold correctly, (2) Predicting binder-target complex structures, (3) Calculating confidence metrics (pLDDT, pTM, ipTM), (4) Self-consistency validation of designs, (5) Multi-chain complex prediction with AlphaFold-Multimer. For faster single-chain prediction, use esm2-sequence-scoring. For QC thresholds, use protein-design-qc.

The English summary is being prepared. Showing the original description.

BioTender-max/awesome-bio-agent-skills204Updated Jul 2, 2026

Workflow for event-level and isoform-level splicing analysis with sashimi-ready outputs and splice QC.

The English summary is being prepared. Showing the original description.

BioTender-max/awesome-bio-agent-skills204Updated Jul 2, 2026

ATAC-seq processing with assay QC, MACS3 peak calling, consensus peak matrices, differential accessibility, and motif or footprint follow-up.

The English summary is being prepared. Showing the original description.

BioTender-max/awesome-bio-agent-skills204Updated Jul 2, 2026

End-to-end binder design using BindCraft hallucination. Use this skill when: (1) Designing protein binders with built-in AF2 validation, (2) Running production-quality binder campaigns, (3) Using different design protocols (fast, default, slow), (4) Need joint backbone and sequence optimization, (5) Want high experimental success rate. For backbone-only generation, use rfdiffusion. For QC thresholds, use protein-qc. For tool selection guidance, use binder-design.

The English summary is being prepared. Showing the original description.

BioTender-max/awesome-bio-agent-skills204Updated Jul 2, 2026

See all skills by BioTender-max

Report a problem with this skill