From ee01616a8c5ab5449325599dfaea32341f049784 Mon Sep 17 00:00:00 2001
From: Pjotr Prins
Date: Fri, 1 Jan 2021 15:43:47 +0000
Subject: update-from-genbank.py

---
 workflows/pull-data/genbank/update-from-genbank.py | 43 ++++++++++++++++++++++
 1 file changed, 43 insertions(+)
 create mode 100755 workflows/pull-data/genbank/update-from-genbank.py

(limited to 'workflows/pull-data/genbank/update-from-genbank.py')

diff --git a/workflows/pull-data/genbank/update-from-genbank.py b/workflows/pull-data/genbank/update-from-genbank.py
new file mode 100755
index 0000000..6d6d90c
--- /dev/null
+++ b/workflows/pull-data/genbank/update-from-genbank.py
@@ -0,0 +1,43 @@
+#!/usr/bin/env python3
+#
+# bulk download genbank data and matadata, preparing the FASTA and the
+# YAML files
+#
+#   update-from-genbank.py --max 10 --ids ids.txt --out ~/tmp/genbank-xml
+#
+# See also directory .guix-run and README.md
+
+import argparse
+import os
+import sys
+from utils import chunks
+
+from Bio import Entrez
+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)
+args = parser.parse_args()
+
+ids = set()
+with open(args.ids) as f:
+    content = f.readlines()
+    for line in content:
+        ids.add(line.strip())
+
+dir = args.out
+if not os.path.exists(dir):
+    raise Exception(f"Directory {dir} does not exist")
+
+request_num = min(BATCH,args.max)
+for i, idsx in enumerate(chunks(list(ids), request_num)):
+    xmlfn = os.path.join(dir, f"metadata_{i}.xml")
+    print(f"Fetching {xmlfn} ({i*request_num})",file=sys.stderr)
+    with open(xmlfn, 'w') as f:
+        f.write(Entrez.efetch(db='nuccore', id=idsx, retmode='xml').read())
+    if i*request_num >= args.max:
+        break
-- 
cgit v1.2.3