-
Notifications
You must be signed in to change notification settings - Fork 1
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
git subrepo pull (merge) ingest/vendored
subrepo: subdir: "ingest/vendored" merged: "d141c04" upstream: origin: "https://github.com/nextstrain/ingest" branch: "main" commit: "d141c04" git-subrepo: version: "0.4.6" origin: "https://github.com/ingydotnet/git-subrepo" commit: "110b9eb"
- Loading branch information
Showing
5 changed files
with
83 additions
and
8 deletions.
There are no files selected for viewing
This file contains 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
This file contains 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
This file contains 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
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,70 @@ | ||
#!/usr/bin/env python3 | ||
""" | ||
Fetch metadata and nucleotide sequences from NCBI Entrez and output to a GenBank file. | ||
""" | ||
import json | ||
import argparse | ||
from Bio import SeqIO, Entrez | ||
|
||
# To use the efetch API, the docs indicate only around 10,000 records should be fetched per request | ||
# https://www.ncbi.nlm.nih.gov/books/NBK25499/#chapter4.EFetch | ||
# However, in my testing with HepB, the max records returned was 9,999 | ||
# - Jover, 16 August 2023 | ||
BATCH_SIZE = 9999 | ||
|
||
Entrez.email = "hello@nextstrain.org" | ||
|
||
def parse_args(): | ||
parser = argparse.ArgumentParser(description=__doc__) | ||
parser.add_argument('--term', required=True, type=str, | ||
help='Genbank search term. Replace spaces with "+", e.g. "Hepatitis+B+virus[All+Fields]complete+genome[All+Fields]"') | ||
parser.add_argument('--output', required=True, type=str, help='Output file (Genbank)') | ||
return parser.parse_args() | ||
|
||
|
||
def get_esearch_history(term): | ||
""" | ||
Search for the provided *term* via ESearch and store the results using the | ||
Entrez history server.¹ | ||
Returns the total count of returned records, query key, and web env needed | ||
to access the records from the server. | ||
¹ https://www.ncbi.nlm.nih.gov/books/NBK25497/#chapter2.Using_the_Entrez_History_Server | ||
""" | ||
handle = Entrez.esearch(db="nucleotide", term=term, retmode="json", usehistory="y", retmax=0) | ||
esearch_result = json.loads(handle.read())['esearchresult'] | ||
print(f"Search term {term!r} returned {esearch_result['count']} IDs.") | ||
return { | ||
"count": int(esearch_result["count"]), | ||
"query_key": esearch_result["querykey"], | ||
"web_env": esearch_result["webenv"] | ||
} | ||
|
||
|
||
def fetch_from_esearch_history(count, query_key, web_env): | ||
""" | ||
Fetch records in batches from Entrez history server using the provided | ||
*query_key* and *web_env* and yields them as a BioPython SeqRecord iterator. | ||
""" | ||
print(f"Fetching GenBank records in batches of n={BATCH_SIZE}") | ||
|
||
for start in range(0, count, BATCH_SIZE): | ||
handle = Entrez.efetch( | ||
db="nucleotide", | ||
query_key=query_key, | ||
webenv=web_env, | ||
retstart=start, | ||
retmax=BATCH_SIZE, | ||
rettype="gb", | ||
retmode="text") | ||
|
||
yield SeqIO.parse(handle, "genbank") | ||
|
||
|
||
if __name__=="__main__": | ||
args = parse_args() | ||
|
||
with open(args.output, "w") as output_handle: | ||
for batch_results in fetch_from_esearch_history(**get_esearch_history(args.term)): | ||
SeqIO.write(batch_results, output_handle, "genbank") |
This file contains 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
This file contains 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