aboutsummaryrefslogtreecommitdiff
path: root/workflows/tools
diff options
context:
space:
mode:
authorAndreaGuarracino2021-01-07 23:50:01 +0100
committerAndreaGuarracino2021-01-07 23:50:01 +0100
commit4d841d279b2bf73da2ba815d53863c7f2861c956 (patch)
tree83b9ad136dabacbf7ed54e19b2db6df348bef904 /workflows/tools
parent141e619929cee17018417d71111063015e73c366 (diff)
parentc080c3cffedcc0cc99496b5e70fcfdf998978f16 (diff)
downloadbh20-seq-resource-4d841d279b2bf73da2ba815d53863c7f2861c956.tar.gz
bh20-seq-resource-4d841d279b2bf73da2ba815d53863c7f2861c956.tar.lz
bh20-seq-resource-4d841d279b2bf73da2ba815d53863c7f2861c956.zip
Merge branch 'master' into yamlfa2ttl
Diffstat (limited to 'workflows/tools')
-rwxr-xr-xworkflows/tools/pubseq-fetch-data.py55
-rwxr-xr-xworkflows/tools/pubseq-fetch-ids (renamed from workflows/tools/sparql-fetch-ids)2
2 files changed, 56 insertions, 1 deletions
diff --git a/workflows/tools/pubseq-fetch-data.py b/workflows/tools/pubseq-fetch-data.py
new file mode 100755
index 0000000..ef4edde
--- /dev/null
+++ b/workflows/tools/pubseq-fetch-data.py
@@ -0,0 +1,55 @@
+#!/usr/bin/env python3
+
+import argparse
+import json
+import os
+import requests
+import sys
+import time
+
+parser = argparse.ArgumentParser(description="""
+
+Fetch metadata (JSON) from PubSeq and optionally the FASTA files. IDs
+can be passed in on the command line or in a file.
+
+""")
+parser.add_argument('--fasta', action='store_true', help='Also fetch FASTA records')
+parser.add_argument('--out', type=str, help='Directory to write to',
+required=True)
+parser.add_argument('--ids', type=str, help='File with ids', required=False)
+parser.add_argument('id', nargs='*', help='id(s)')
+args = parser.parse_args()
+
+dir = args.out
+if not os.path.exists(dir):
+ raise Exception(f"Directory {dir} does not exist")
+
+ids = args.id
+if (len(ids)==0):
+ print(f"Reading {args.ids}")
+ with open(args.ids) as f:
+ ids = [ l.strip() for l in f.readlines() ]
+
+for id in ids:
+ print(id)
+ jsonfn = dir+"/"+id+".json"
+ if not os.path.exists(jsonfn):
+ count = 0
+ r = requests.get(f"http://covid19.genenetwork.org/api/sample/{id}.json")
+ while not r:
+ count += 1
+ if count>10: raise Exception(f"Can not find record for {id}")
+ time.sleep(15)
+ r = requests.get(f"http://covid19.genenetwork.org/api/sample/{id}.json")
+ m_url = r.json()[0]['metadata']
+ mr = requests.get(m_url)
+ with open(dir+"/"+id+".json","w") as outf:
+ outf.write(mr.text)
+ if args.fasta:
+ fastafn = dir+"/"+id+".fa"
+ if os.path.exists(fastafn): continue
+ fa_url = r.json()[0]['fasta']
+ fr = requests.get(fa_url)
+ with open(fastafn,"w") as outf:
+ outf.write(fr.text)
+
diff --git a/workflows/tools/sparql-fetch-ids b/workflows/tools/pubseq-fetch-ids
index 19b2d82..f5920ec 100755
--- a/workflows/tools/sparql-fetch-ids
+++ b/workflows/tools/pubseq-fetch-ids
@@ -2,7 +2,7 @@
#
# Use a SPARQL query to fetch all IDs in the PubSeq database
#
-# sparql-fetch-ids > pubseq_ids.txt
+# pubseq-fetch-ids > pubseq_ids.txt
#
# Note: requires Ruby 3.x. Older Ruby gives a syntax error