Created
December 10, 2025 19:01
-
-
Save sdhutchins/60d719928884376f67eae51196edb3c9 to your computer and use it in GitHub Desktop.
Fetch the ProtVar API & Return JSON
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| """ | |
| Fetch ProtVar API JSON response for a variant. | |
| Edit HGVS or RS_ID below and set USE_HGVS or USE_RSID to True. | |
| ProtVar API docs: | |
| - https://www.ebi.ac.uk/ProtVar/api/swagger-ui/index.html | |
| - https://www.ebi.ac.uk/ProtVar/api/docs | |
| """ | |
| import json | |
| import re | |
| import urllib.request | |
| import urllib.parse | |
| from pathlib import Path | |
| # Configuration | |
| HGVS = "NM_001204.7:c.354T>G p.(Cys118Trp)" # BMPR2 Pathogenic Variant | |
| RS_ID = "rs137852743" | |
| # Try HGVS or RSID | |
| # Protvar only will return missense variants | |
| USE_HGVS = True | |
| USE_RSID = False | |
| OUTPUT_FILE = "protvar_response.json" | |
| def fetch_protvar_by_hgvs(hgvs: str) -> dict: | |
| """Query ProtVar mappings endpoint using HGVS notation.""" | |
| cdna_match = re.search(r'(N[MP]_\d+(?:\.\d+)?:c\.\d+[A-Z][>][A-Z])', hgvs) | |
| cdna_variant = cdna_match.group(1) if cdna_match else hgvs | |
| url = "https://www.ebi.ac.uk/ProtVar/api/mappings" | |
| params = urllib.parse.urlencode({ | |
| "function": "true", | |
| "structure": "true", | |
| "population": "true", | |
| "assembly": "AUTO" | |
| }) | |
| data = json.dumps([cdna_variant]).encode('utf-8') | |
| req = urllib.request.Request( | |
| f"{url}?{params}", | |
| data=data, | |
| headers={'Content-Type': 'application/json'}, | |
| method='POST' | |
| ) | |
| try: | |
| with urllib.request.urlopen(req, timeout=20) as response: | |
| return json.load(response) | |
| except urllib.error.HTTPError as e: | |
| print(f"Error: HTTP {e.code}") | |
| return {} | |
| except Exception as e: | |
| print(f"Error: {e}") | |
| return {} | |
| def fetch_protvar_by_rsid(rsid: str) -> dict: | |
| """Query ProtVar variant endpoint using RS ID.""" | |
| url = f"https://www.ebi.ac.uk/ProtVar/api/variant/{rsid}" | |
| try: | |
| with urllib.request.urlopen(url, timeout=15) as response: | |
| return json.load(response) | |
| except urllib.error.HTTPError as e: | |
| print(f"Error: HTTP {e.code}") | |
| return {} | |
| except Exception as e: | |
| print(f"Error: {e}") | |
| return {} | |
| if __name__ == "__main__": | |
| if USE_HGVS: | |
| print(f"Fetching ProtVar data for HGVS: {HGVS}") | |
| data = fetch_protvar_by_hgvs(HGVS) | |
| elif USE_RSID: | |
| print(f"Fetching ProtVar data for RS ID: {RS_ID}") | |
| data = fetch_protvar_by_rsid(RS_ID) | |
| else: | |
| print("Set USE_HGVS or USE_RSID to True") | |
| data = {} | |
| output_path = Path(OUTPUT_FILE) | |
| with open(output_path, 'w') as f: | |
| json.dump(data, f, indent=2, default=str) | |
| print(f"Saved to: {output_path}") | |
| print(f"Size: {output_path.stat().st_size / 1024:.2f} KB") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment