/alphafold-database-access

name: alphafold-database-access
description: >
  Access AlphaFold DB's 200M+ predicted structures by UniProt ID. Download PDB/mmCIF,
  analyze pLDDT/PAE, bulk-fetch proteomes via Google Cloud. For experimental structures
  use PDB; for prediction use ColabFold or ESMFold.
license: CC-BY-4.0
metadata:
  quick_use: 'one entry: GET https://alphafold.ebi.ac.uk/api/prediction/{UniProt ACC} -> a list (canonical, then isoforms such as {ACC}-2); take the item whose uniprotAccession equals the query: entryId, latestVersion, globalMetricValue (mean pLDDT), cifUrl, pdbUrl. Download from cifUrl/pdbUrl as given (model_v4 file names now 404) with requests; the file host returns 403 to curl''s default user agent. No model -> 404. Cite https://alphafold.ebi.ac.uk/entry/{ACC}'

AlphaFold Database Access

Overview

AlphaFold DB is a public repository of AI-predicted 3D protein structures for over 200 million proteins, maintained by DeepMind and EMBL-EBI. Access predictions via BioPython or REST API, download coordinate files in multiple formats, analyze confidence metrics, and retrieve bulk proteome datasets via Google Cloud.

When to Use

• Retrieving AI-predicted protein structures by UniProt accession
• Downloading PDB/mmCIF coordinate files for structural analysis or docking
• Analyzing prediction confidence (pLDDT per-residue, PAE domain-level)
• Bulk-downloading entire proteome predictions via Google Cloud
• Comparing predicted structures with experimental PDB structures
• Building structural models for proteins lacking experimental data
• Identifying high-confidence binding sites for drug discovery
• For experimental structures only → use PDB directly
• For running AlphaFold predictions → use ColabFold or local AlphaFold

Prerequisites

# Core (BioPython for structure access)
pip install biopython requests numpy matplotlib

# Optional: Google Cloud for bulk access
pip install google-cloud-bigquery google-cloud-storage

Quick Start

from Bio.PDB import alphafold_db, MMCIFParser
import requests, numpy as np

# 1. Get prediction for a protein
uniprot_id = "P00520"  # ABL1 kinase
predictions = list(alphafold_db.get_predictions(uniprot_id))
af_id = predictions[0]['entryId']  # AF-P00520-F1

# 2. Download structure
cif_file = alphafold_db.download_cif_for(predictions[0], directory="./structures")

# 3. Check confidence
conf = requests.get(predictions[0]["plddtDocUrl"]).json()  # file URLs come from the API; never hard-code _vN
scores = conf['confidenceScore']
print(f"Mean pLDDT: {np.mean(scores):.1f}, High-conf residues: {sum(1 for s in scores if s > 90)}/{len(scores)}")

Core API

1. Prediction Retrieval

**BioPython (recommended for single proteins):**

from Bio.PDB import alphafold_db

# Get prediction metadata
predictions = list(alphafold_db.get_predictions("P00520"))
pred = predictions[0]
print(f"AlphaFold ID: {pred['entryId']}")
print(f"Gene: {pred['gene']}, Species: {pred['organismScientificName']}")

# Get Structure objects directly
structures = list(alphafold_db.get_structural_models_for("P00520"))

**REST API (for metadata or integration):**

import requests

uniprot_id = "P00520"
url = f"https://alphafold.ebi.ac.uk/api/prediction/{uniprot_id}"
response = requests.get(url)
data = response.json()

# Response includes download URLs for all file types
pred = data[0]
print(f"CIF: {pred['cifUrl']}")
print(f"PDB: {pred['pdbUrl']}")
print(f"PAE: {pred['paeDocUrl']}")

**3D-Beacons federated API (query multiple structure providers):**

url = f"https://www.ebi.ac.uk/pdbe/pdbe-kb/3dbeacons/api/uniprot/summary/{uniprot_id}.json"
data = requests.get(url).json()
af_structures = [s for s in data['structures'] if s['provider'] == 'AlphaFold DB']

2. Structure File Download

import requests

af_id = "AF-P00520-F1"
version = "v6"  # = f"v{pred['latestVersion']}" from /api/prediction; v4 file names now 404
base = "https://alphafold.ebi.ac.uk/files"

# mmCIF (recommended — full metadata, supports large structures)
cif = requests.get(f"{base}/{af_id}-model_{version}.cif")
with open(f"{af_id}.cif", "w") as f:
    f.write(cif.text)

# PDB format (legacy — limited to 99,999 atoms)
pdb = requests.get(f"{base}/{af_id}-model_{version}.pdb")
with open(f"{af_id}.pdb", "wb") as f:
    f.write(pdb.content)

# Confidence JSON (per-residue pLDDT scores)
conf = requests.get(f"{base}/{af_id}-confidence_{version}.json").json()

# PAE matrix JSON (inter-residue confidence)
pae = requests.get(f"{base}/{af_id}-predicted_aligned_error_{version}.json").json()

3. Confidence Metrics Analysis

**pLDDT (per-residue confidence, 0–100):**

import numpy as np

conf_url = f"https://alphafold.ebi.ac.uk/files/{af_id}-confidence_{version}.json"  # or pred["plddtDocUrl"]
conf = requests.get(conf_url).json()
scores = conf['confidenceScore']

# Classify residues by confidence
very_high = sum(1 for s in scores if s > 90)
high = sum(1 for s in scores if 70 < s <= 90)
low = sum(1 for s in scores if 50 < s <= 70)
very_low = sum(1 for s in scores if s <= 50)
print(f"Very high (>90): {very_high}, High (70-90): {high}, Low (50-70): {low}, Very low (<50): {very_low}")

**PAE (Predicted Aligned Error) visualization:**

import matplotlib.pyplot as plt

pae_url = f"https://alphafold.ebi.ac.uk/files/{af_id}-predicted_aligned_error_{version}.json"  # or pred["paeDocUrl"]
pae = requests.get(pae_url).json()[0]  # a one-item list
pae_matrix = np.array(pae["predicted_aligned_error"])

plt.figure(figsize=(10, 8))
plt.imshow(pae_matrix, cmap='viridis_r', vmin=0, vmax=30)
plt.colorbar(label='PAE (Å)')
plt.title(f'Predicted Aligned Error: {af_id}')
plt.xlabel('Residue')
plt.ylabel('Residue')
plt.savefig(f'{af_id}_pae.png', dpi=300, bbox_inches='tight')
# Low PAE (<5 Å) = confident relative positioning; >15 Å = uncertain domain arrangement

4. Bulk Data Access (Google Cloud)

# List available data
gsutil ls gs:/