Loading...
Loading...
Query and retrieve AI-predicted protein structures from DeepMind's AlphaFold database. Fetch structures via UniProt accession, interpret pLDDT/PAE confidence scores, and access bulk proteome data for structural biology workflows.
npx skill4agent add aminoanalytica/amina-skills alphafold-database# Fetch structure via Biopython
from Bio.PDB import alphafold_db
predictions = list(alphafold_db.get_predictions("P00520"))
alphafold_db.download_cif_for(predictions[0], directory="./output")
# Direct API call
import requests
resp = requests.get("https://alphafold.ebi.ac.uk/api/prediction/P00520")
entry_id = resp.json()[0]['entryId'] # AF-P00520-F1
# Download structure file
structure_url = f"https://alphafold.ebi.ac.uk/files/{entry_id}-model_v4.cif"| Term | Description |
|---|---|
| UniProt Accession | Protein identifier (e.g., |
| AlphaFold ID | Format: |
| pLDDT | Per-residue confidence (0-100); >90 = reliable, <50 = disordered |
| PAE | Predicted Aligned Error; <5A = high confidence domain positions |
references/confidence-scores.md| File | URL Pattern | Contents |
|---|---|---|
| Coordinates | | Atomic positions (mmCIF) |
| Confidence | | Per-residue pLDDT array |
| PAE Matrix | | Inter-residue error |
https://alphafold.ebi.ac.uk/files/import requests
resp = requests.get(f"https://alphafold.ebi.ac.uk/api/prediction/{uniprot_id}")
metadata = resp.json()[0]
af_id = metadata['entryId']scripts/alphafold_utils.pyfrom scripts.alphafold_utils import download_alphafold_files
paths = download_alphafold_files("AF-P04637-F1", output_dir="./data")from scripts.alphafold_utils import get_plddt_scores
stats = get_plddt_scores("AF-P04637-F1")
print(f"Average pLDDT: {stats['mean']:.1f}")# Google Cloud Storage
gsutil ls gs://public-datasets-deepmind-alphafold-v4/
gsutil -m cp "gs://public-datasets-deepmind-alphafold-v4/proteomes/proteome-tax_id-9606-*.tar" ./references/bulk-access.mdpip install biopython requests numpy matplotlib pandas scipy
# Optional: pip install google-cloud-bigquery gsutil