diff options
| author | Peter Amstutz | 2020-04-20 14:57:25 -0400 |
|---|---|---|
| committer | Peter Amstutz | 2020-04-20 14:57:25 -0400 |
| commit | 9ddcfeacb3191638f42b08af999889d867f0f81c (patch) | |
| tree | 4cfe4c2b1df38bf6e5c79f5f8c0700407f76a472 /workflows/pangenome-generate/relabel-seqs.py | |
| parent | d29dfd593233541b85c1cefb239650279d57d59f (diff) | |
| download | bh20-seq-resource-9ddcfeacb3191638f42b08af999889d867f0f81c.tar.gz bh20-seq-resource-9ddcfeacb3191638f42b08af999889d867f0f81c.tar.lz bh20-seq-resource-9ddcfeacb3191638f42b08af999889d867f0f81c.zip | |
Better handling of duplicate sequences
Also save original fasta label in metadata
Diffstat (limited to 'workflows/pangenome-generate/relabel-seqs.py')
| -rw-r--r-- | workflows/pangenome-generate/relabel-seqs.py | 12 |
1 files changed, 7 insertions, 5 deletions
diff --git a/workflows/pangenome-generate/relabel-seqs.py b/workflows/pangenome-generate/relabel-seqs.py index 32f2386..b558fe2 100644 --- a/workflows/pangenome-generate/relabel-seqs.py +++ b/workflows/pangenome-generate/relabel-seqs.py @@ -1,13 +1,15 @@ -import sys - reads = $(inputs.readsFA) subjects = $(inputs.subjects) +relabeled_fasta = open("relabeledSeqs.fasta", "wt") +original_labels = open("originalLabels.ttl", "wt") + for i, r in enumerate(reads): with open(r["path"], "rt") as fa: - fa.readline() - print(">"+subjects[i]) + label = fa.readline() + original_labels.write("<%s> <http://biohackathon.org/bh20-seq-schema/original_fasta_label> \\"%s\\" .\\n" % (subjects[i], label[1:].strip().replace('"', '\\\\"'))) + relabeled_fasta.write(">"+subjects[i]+"\\n") data = fa.read(8096) while data: - sys.stdout.write(data) + relabeled_fasta.write(data) data = fa.read(8096) |