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/from_sparql.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/from_sparql.py')
| -rw-r--r-- | workflows/pangenome-generate/from_sparql.py | 8 |
1 files changed, 8 insertions, 0 deletions
diff --git a/workflows/pangenome-generate/from_sparql.py b/workflows/pangenome-generate/from_sparql.py new file mode 100644 index 0000000..4610cad --- /dev/null +++ b/workflows/pangenome-generate/from_sparql.py @@ -0,0 +1,8 @@ +from rdflib import Graph +import sys +import subprocess +g = Graph() +g.parse(sys.argv[1], format="nt") +res = g.query(sys.argv[3]) +for r in res: + subprocess.run(["samtools", "faidx", sys.argv[2], r[0]]) |