aboutsummaryrefslogtreecommitdiff
path: root/workflows/pull-data/genbank/README.md
diff options
context:
space:
mode:
authorPjotr Prins2021-01-01 12:09:10 +0000
committerPjotr Prins2021-01-01 12:09:10 +0000
commitdd9c8df418040093f2116de6592fc6add0c6a2ce (patch)
tree723c6976953159b0a17ea2c2c3b78480832b64be /workflows/pull-data/genbank/README.md
parentacdd66f36e1596f8337195f22fdd7dd8a85c2b70 (diff)
downloadbh20-seq-resource-dd9c8df418040093f2116de6592fc6add0c6a2ce.tar.gz
bh20-seq-resource-dd9c8df418040093f2116de6592fc6add0c6a2ce.tar.lz
bh20-seq-resource-dd9c8df418040093f2116de6592fc6add0c6a2ce.zip
genbank: cleaning up
Diffstat (limited to 'workflows/pull-data/genbank/README.md')
-rw-r--r--workflows/pull-data/genbank/README.md9
1 files changed, 3 insertions, 6 deletions
diff --git a/workflows/pull-data/genbank/README.md b/workflows/pull-data/genbank/README.md
index 22dd920..c235be7 100644
--- a/workflows/pull-data/genbank/README.md
+++ b/workflows/pull-data/genbank/README.md
@@ -4,12 +4,9 @@
# --- get list of IDs already in PubSeq
sparql-fetch-ids > pubseq_ids.txt
# --- fetch XML
-update-from-genbank --skip pubseq_ids.txt --max 100 --outdir ~/tmp/genbank
-# --- get new IDs
-genbank-fetch-ids > genbank_ids.txt
-# --- loop through IDs (pseudo code)
-for id in genbank_ids.txt:
- transform-genbank-xml2yamlfa --dir ~/tmp/genbank id --outdir ~/tmp/pubseq
+update-from-genbank.py --skip pubseq_ids.txt --outdir ~/tmp/genbank
+# --- Transform to YAML and FASTA
+transform-genbank-xml2yamlfa --dir ~/tmp/genbank id --outdir ~/tmp/pubseq
```
# TODO