From f7666a7766c8138aa690340fc68cb67f709327f3 Mon Sep 17 00:00:00 2001 From: AndreaGuarracino Date: Tue, 5 Jan 2021 17:35:46 +0100 Subject: cleaning genbank-fetch-ids.py --- workflows/pull-data/genbank/genbank-fetch-ids.py | 40 +++++++++++------------- 1 file changed, 19 insertions(+), 21 deletions(-) (limited to 'workflows/pull-data/genbank/genbank-fetch-ids.py') diff --git a/workflows/pull-data/genbank/genbank-fetch-ids.py b/workflows/pull-data/genbank/genbank-fetch-ids.py index 1962daa..cb48cd8 100755 --- a/workflows/pull-data/genbank/genbank-fetch-ids.py +++ b/workflows/pull-data/genbank/genbank-fetch-ids.py @@ -6,28 +6,20 @@ # # See also directory .guix-run and README.md -BATCH_SIZE=5000 - import argparse -import json -import os -import requests import sys -import xml.etree.ElementTree as ET -from datetime import date, datetime -from dateutil.parser import parse +from datetime import date + +from Bio import Entrez parser = argparse.ArgumentParser() parser.add_argument('--max', type=int, help='Max queries', required=False) parser.add_argument('--skip', type=str, help='File with ids to skip, 1 id per line', required=False) args = parser.parse_args() -from Bio import Entrez -Entrez.email = 'another_email@gmail.com' # FIXME - -# min_acceptable_collection_date = datetime(2019, 12, 1) +BATCH_SIZE = 5000 -today_date = date.today().strftime("%Y.%m.%d") +Entrez.email = 'another_email@gmail.com' # FIXME skip = set() if args.skip: @@ -36,10 +28,11 @@ if args.skip: for line in content: skip.add(line.strip()) -print(f"Skip size is {len(skip)}",file=sys.stderr) +print(f"Skip size is {len(skip)}", file=sys.stderr) # Try to search several strings TERMS = ['SARS-CoV-2', 'SARS-CoV2', 'SARS CoV2', 'SARSCoV2', 'txid2697049[Organism]'] + # Remove mRNAs, ncRNAs, Proteins, and predicted models (more information here: https://en.wikipedia.org/wiki/RefSeq) starting with PREFIX = ['NM', 'NR', 'NP', 'XM', 'XR', 'XP', 'WP'] @@ -47,22 +40,27 @@ ids = set() for term in TERMS: num_read = BATCH_SIZE retstart = 0 + while num_read == BATCH_SIZE: record = Entrez.read( - Entrez.esearch(db='nuccore', term=term, idtype='acc', - retstart=retstart, retmax=BATCH_SIZE) + Entrez.esearch(db='nuccore', term=term, idtype='acc', retstart=retstart, retmax=BATCH_SIZE) ) + idlist = record['IdList'] new_ids = set(idlist) num_read = len(new_ids) - print(num_read,":",idlist[0],file=sys.stderr) retstart += num_read - new_ids.difference_update(skip) # remove skip ids + + print(num_read, ":", idlist[0], file=sys.stderr) + + new_ids.difference_update(skip) # remove skip ids new_ids = set([id for id in new_ids if id[:2] not in PREFIX]) - ids.update(new_ids) # add to total set - print(f"Term: {term} --> #{len(new_ids)} new IDs ---> Total unique IDs #{len(ids)})",file=sys.stderr) + ids.update(new_ids) # add to total set + + print(f"Term: {term} --> #{len(new_ids)} new IDs ---> Total unique IDs #{len(ids)}", file=sys.stderr) + if args.max and len(ids) > args.max: - print(f"Stopping past #{args.max} items",file=sys.stderr) + print(f"Stopping past #{args.max} items", file=sys.stderr) break for id in ids: -- cgit v1.2.3 From 911ba372cfc4b35c5b52d18a573a636ea78d16d7 Mon Sep 17 00:00:00 2001 From: AndreaGuarracino Date: Tue, 5 Jan 2021 17:56:19 +0100 Subject: cleaning update-from-genbank.py; removed unused import from genbank-fetch-ids.py --- workflows/pull-data/genbank/genbank-fetch-ids.py | 1 - workflows/pull-data/genbank/update-from-genbank.py | 25 +++++++++++----------- 2 files changed, 13 insertions(+), 13 deletions(-) (limited to 'workflows/pull-data/genbank/genbank-fetch-ids.py') diff --git a/workflows/pull-data/genbank/genbank-fetch-ids.py b/workflows/pull-data/genbank/genbank-fetch-ids.py index cb48cd8..e9e7315 100755 --- a/workflows/pull-data/genbank/genbank-fetch-ids.py +++ b/workflows/pull-data/genbank/genbank-fetch-ids.py @@ -8,7 +8,6 @@ import argparse import sys -from datetime import date from Bio import Entrez diff --git a/workflows/pull-data/genbank/update-from-genbank.py b/workflows/pull-data/genbank/update-from-genbank.py index dca5563..95f5a93 100755 --- a/workflows/pull-data/genbank/update-from-genbank.py +++ b/workflows/pull-data/genbank/update-from-genbank.py @@ -14,22 +14,21 @@ import sys from utils import chunks from Bio import Entrez -Entrez.email = 'another_email@gmail.com' # FIXME -BATCH=100 +Entrez.email = 'another_email@gmail.com' # FIXME + +BATCH = 100 parser = argparse.ArgumentParser() -parser.add_argument('--max', type=int, help='Max queries', required=False) parser.add_argument('--ids', type=str, help='File with ids to fetch, 1 id per line', required=True) parser.add_argument('--out', type=str, help='Directory to write to', required=True) +parser.add_argument('--max', type=int, help='Max queries', required=False) args = parser.parse_args() ids = set() with open(args.ids) as f: - content = f.readlines() - for line in content: - ids.add(line.strip()) + ids.update([line.strip() for line in f]) dir = args.out if not os.path.exists(dir): @@ -37,12 +36,14 @@ if not os.path.exists(dir): request_num = BATCH if args.max: - request_num = min(BATCH,args.max) + request_num = min(BATCH, args.max) + +for num_chunk, ids_chunk in enumerate(chunks(list(ids), request_num)): + xmlfn = os.path.join(dir, f"metadata_{num_chunk}.xml.gz") + print(f"Fetching {xmlfn} ({num_chunk * request_num})", file=sys.stderr) -for i, idsx in enumerate(chunks(list(ids), request_num)): - xmlfn = os.path.join(dir, f"metadata_{i}.xml.gz") - print(f"Fetching {xmlfn} ({i*request_num})",file=sys.stderr) with gzip.open(xmlfn, 'w') as f: - f.write((Entrez.efetch(db='nuccore', id=idsx, retmode='xml').read()).encode()) - if args.max and i*request_num >= args.max: + f.write(Entrez.efetch(db='nuccore', id=ids_chunk, retmode='xml').read().encode()) + + if args.max and num_chunk * request_num >= args.max: break -- cgit v1.2.3