SkillAgentSearch skills...

alphafold-database-access

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.

Install / Use

npx skills add jaechang-hits/SciAgent-Skills --skill alphafold-database-access

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

91/100

Supported Platforms

Universal

Our assessment of alphafold-database-access

alphafold-database-access scores 91/100 on our quality scale, 223rd of 599 Data & Analytics skills we index (top 38%).

Its SKILL.md is 16 KB long, well organised into 55 sections with 16 code examples: a thorough specification that gives an agent plenty to work with.

It has 367 GitHub stars, a meaningful sign that others use it.

Substance
30/30
Structure
20/20
Description
15/15
Adoption
11/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 3 months ago, so alphafold-database-access is actively maintained.
  • Our last check on 2026-11-20 found the source still online.
  • No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
  • Its trust signals score 88/100, with 1 caution from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-10-07. Automated pattern scan on 2026-10-07. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

alphafold-database-access compared with similar skills

All 4 of these similar skills score higher than alphafold-database-access; compare them before choosing.

SkillScoreStarsUpdatedFormat
alphafold-database-access (this skill)by jaechang-hits913673mo agoSKILL.md
Agent-Reachby Panniantong100113.3k12d agoCLAUDE.md
headroomby headroomlabs-ai10080.2ktodayCLAUDE.md
Scraplingby D4Vinci100104.4k2d agoMCP Server
crawl4aiby unclecode10087.6ktodayMCP Server

Frequently asked questions

How do I install alphafold-database-access?
Run npx skills add jaechang-hits/SciAgent-Skills --skill alphafold-database-access. The install tabs above show the steps for each supported agent.
Which AI agents does alphafold-database-access work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is alphafold-database-access safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It declares no license and scores 88/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is alphafold-database-access still maintained?
The repository was last updated about 3 months ago, so alphafold-database-access is actively maintained.

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

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(f"https://alphafold.ebi.ac.uk/files/{af_id}-confidence_v4.json").json()
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 = "v4"
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_v4.json"
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_v4.json"
pae = requests.get(pae_url).json()
pae_matrix = np.array(pae['distance'])

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://public-datasets-deepmind-alphafold-v4/

# Download entire proteome by taxonomy ID
gsutil -m cp gs://public-datasets-deepmind-alphafold-v4/proteomes/proteome-tax_id-9606-*_v4.tar .

# Download accession index
gsutil cp gs://public-datasets-deepmind-alphafold-v4/accession_ids.csv .

BigQuery metadata queries:

from google.cloud import bigquery

client = bigquery.Client()
query = """
SELECT entryId, uniprotAccession, gene, organismScientificName,
       globalMetricValue, fractionPlddtVeryHigh
FROM `bigquery-public-data.deepmind_alphafold.metadata`
WHERE organismScientificName = 'Homo sapiens'
  AND fractionPlddtVeryHigh > 0.8
  AND isReviewed = TRUE
LIMIT 100
"""
df = client.query(query).to_dataframe()
print(f"Found {len(df)} high-confidence human proteins")

5. Structure Parsing & Analysis

from Bio.PDB import MMCIFParser
import numpy as np
from scipy.spatial.distance import pdist, squareform

parser = MMCIFParser(QUIET=True)
structure = parser.get_structure("protein", f"{af_id}-model_v4.cif")

# Extract alpha-carbon coordinates
coords, plddt_scores = [], []
for model in structure:
    for chain in model:
        for residue in chain:
            if 'CA' in residue:
                coords.append(residue['CA'].get_coord())
                plddt_scores.append(residue['CA'].get_bfactor())  # pLDDT stored as B-factor

coords = np.array(coords)
print(f"Residues: {len(coords)}, Mean pLDDT: {np.mean(plddt_scores):.1f}")

# Contact map (Cα-Cα < 8 Å)
dist_matrix = squareform(pdist(coords))
contacts = np.where((dist_matrix > 0) & (dist_matrix < 8))
print(f"Contacts: {len(contacts[0]) // 2}")

Key Concepts

Confidence Interpretation

| Metric | Range | Interpretation | Suitable For | |--------|-------|---------------|--------------| | pLDDT >90 | Very high | Backbone + side-chain reliable | Detailed analysis, docking | | pLDDT 70–90 | High | Backbone generally reliable | Fold analysis, domain ID | | pLDDT 50–70 | Low | Use with caution | May be flexible/disordered | | pLDDT <50 | Very low | Likely disordered | Exclude from analysis | | PAE <5 Å | Confident | Reliable relative domain positions | Multi-domain assembly | | PAE 5–10 Å | Moderate | Uncertain arrangement | Treat domains independently | | PAE >15 Å | Uncertain | Domains may be mobile | Do not trust orientation |

AlphaFold ID Format

Format: AF-{UniProt_accession}-F{fragment_number} (e.g., AF-P00520-F1). Large proteins may be split into fragments (F1, F2, ...). Current database version: v4 — include version suffix in all file URLs.

File Types

| File | URL Suffix | Format | Use | |------|-----------|--------|-----| | Model coordinates | -model_v4.cif | mmCIF | Structural analysis (recommended) | | Model coordinates | -model_v4.pdb | PDB | Legacy tools (<99,999 atoms) | | Model coordinates | -model_v4.bcif | Binary CIF | Compressed (~70% smaller) | | Confidence | -confidence_v4.json | JSON | Per-residue pLDDT array | | Aligned error | -predicted_aligned_error_v4.json | JSON | N×N PAE matrix | | PAE image | -predicted_aligned_error_v4.png | PNG | Quick visual assessment |

Common Workflows

Workflow 1: Single Protein Structure Analysis

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

uniprot_id = "P04637"  # p53 tumor suppressor

# Retrieve and download
predictions = list(alphafold_db.get_predictions(uniprot_id))
cif_file = alphafold_db.download_cif_for(predictions[0], directory="./structures")
af_id = predictions[0]['entryId']

# Parse structure
parser = MMCIFParser(QUIET=True)
structure = parser.get_structure("p53", cif_file)

# Extract pLDDT from B-factors
plddt = [r['CA'].get_bfactor() for m in structure for c in m for r in c if 'CA' in r]
print(f"Length: {len(plddt)}, Mean pLDDT: {np.mean(plddt):.1f}")

# Identify high-confidence regions for docking
high_conf_regions = [(i+1, s) for i, s in enumerate(plddt) if s > 90]
print(f"High-confidence residues: {len(high_conf_regions)}/{len(plddt)}")

Workflow 2: Batch Protein Processing

from Bio.PDB import alphafold_db
import requests, numpy as np, pandas as pd, time

uniprot_ids = ["P00520", "P12931", "P04637", "P38398"]
results = []

for uid in uniprot_ids:
    try:
        preds = list(alphafold_db.get_predictions(uid))
        if not preds:
            continue
        af_id = preds[0]['entryId']
        conf = requests.get(f"https://alphafold.ebi.ac.uk/files/{af_id}-confidence_v4.json").json()
        scores = conf['confidenceScore']
        results.append({
            'uniprot': uid, 'alphafold_id': af_id,
            'length': len(scores), 'mean_plddt': np.mean(scores),
            'frac_high_conf': sum(1 for s in scores if s > 90) / len(scores)
        })
        time.sleep(0.2)  # Rate limit: 100-200ms between requests
    except Exception as e:
        print(f"Error {uid}: {e}")

df = pd.DataFrame(results)
print(df.to_string(index=False))

Key Parameters

| Parameter | Module | Default | Range | Effect | |-----------|--------|---------|-------|--------| | uniprot_id | All | — | UniProt accession | Primary query identifier | | version | Download | v4 | v1–v4 | Database version (always use latest) | | directory | BioPython | "." | Path | Download destination | | QUIET | MMCIFParser | False | bool | Suppress parser warnings | | vmin/vmax | PAE plot | 0/30 | Å | PAE colormap range | | taxonomy_id | GCS bulk | — | NCBI tax ID | Species for proteome download | | fractionPlddtVeryHigh | BigQuery | — | 0.0–1.0 | Filter by high-confidence fraction | | Concurrent requests | API | — | ≤10 | Max parallel API requests | | Request delay | API | — | 100–200ms | Delay between sequential requests |

Best Practices

  1. Use BioPython for single proteins, Google Cloud for bulk — individual API downloads are slow for >100 proteins; GCS parallel download is orders of magnitude faster
  2. Always check pLDDT before downstream analysis — low-confidence regions (pLDDT <50) are likely disordered and should be excluded from docking, contact analysis, or binding site prediction
  3. Anti-pattern — trusting all regions equally: AlphaFold predictions lack ligands, PTMs, cofactors, and multi-chain context. High pLDDT does not guarantee functional accuracy
  4. Cache downloaded files locally — avoid re-downloading the same structures; AlphaFold files are static per version
  5. Use PAE for multi-domain proteins — pLDDT tells you per-residue confidence, but PAE reveals whether domain orientations are reliable. Low inter-domain PAE (<5 Å) = trust the arrangement; high PAE (>15 Å) = treat domains inde

Truncated for display — read the full file on GitHub.

Related Skills

View on GitHub
GitHub Stars367
CategoryData
Updated2mo ago
Forks36

Languages

Python

Trust signals

88/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

1 medium