diff options
author | Peter Amstutz | 2020-11-09 17:32:05 -0500 |
---|---|---|
committer | GitHub | 2020-11-09 17:32:05 -0500 |
commit | 74d46196ae69c0c557f64593910ada48d84b3654 (patch) | |
tree | 57c7df946e1aa1f2054eb49379439ebee4d4c0e6 /workflows/pangenome-generate/collect-seqs.py | |
parent | b311e2ec0f1d02cf16152855dd8bdd760ed4578b (diff) | |
parent | 98a80bd64d8a495b8fddffdef6e07e5a3fbea1e3 (diff) | |
download | bh20-seq-resource-74d46196ae69c0c557f64593910ada48d84b3654.tar.gz bh20-seq-resource-74d46196ae69c0c557f64593910ada48d84b3654.tar.lz bh20-seq-resource-74d46196ae69c0c557f64593910ada48d84b3654.zip |
Merge pull request #105 from arvados/fasta-subset-from-query
Extract subset of the all-sequences fasta by running a sparql query.
Also includes some tweaks to the permalinks.
Diffstat (limited to 'workflows/pangenome-generate/collect-seqs.py')
-rw-r--r-- | workflows/pangenome-generate/collect-seqs.py | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/workflows/pangenome-generate/collect-seqs.py b/workflows/pangenome-generate/collect-seqs.py index af4a0dc..1a0807c 100644 --- a/workflows/pangenome-generate/collect-seqs.py +++ b/workflows/pangenome-generate/collect-seqs.py @@ -38,7 +38,7 @@ for item in validated: pdh = item["portable_data_hash"] with arvados.collection.CollectionReader(pdh, api_client=api, keep_client=keepclient) as col: with col.open("sequence.fasta", "rt") as fa: - subject = "http://collections.lugli.arvadosapi.com/c=%s/sequence.fasta" % pdh + subject = "http://covid19.genenetwork.org/resource/%s" % pdh label = fa.readline().strip() merged_metadata.write("<%s> <http://biohackathon.org/bh20-seq-schema/original_fasta_label> \"%s\" .\n" % (subject, label[1:].replace('"', '\\"'))) skip = (subject in blacklist or label[1:] in blacklist) |