From f9f27a787fef0ad58c1ae465d8ba1ee4634083ae Mon Sep 17 00:00:00 2001
From: Pjotr Prins
Date: Mon, 4 Jan 2021 10:25:36 +0000
Subject: mapping: no longer requires specimen file for genbank output

---
 workflows/pull-data/genbank/README.md | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

(limited to 'workflows/pull-data/genbank')

diff --git a/workflows/pull-data/genbank/README.md b/workflows/pull-data/genbank/README.md
index d7cc15f..5464d1d 100644
--- a/workflows/pull-data/genbank/README.md
+++ b/workflows/pull-data/genbank/README.md
@@ -13,13 +13,17 @@ The following workflow sends GenBank data into PubSeq
 # --- get list of IDs already in PubSeq
 ../../tools/sparql-fetch-ids > pubseq_ids.txt
 # --- get list of missing genbank IDs
-./genbank-fetch-ids.py --skip pubseq_ids.txt > genbank_ids.txt
+python3 genbank-fetch-ids.py --skip pubseq_ids.txt > genbank_ids.txt
+
 # --- fetch XML
 python3 update-from-genbank.py --ids genbank_ids.txt --out ~/tmp/genbank
+
 # --- Transform to YAML/JSON and FASTA
 python3 transform-genbank-xml2yamlfa.py --out ~/tmp/pubseq file(s)
-# --- Normalize data
-../../tools/normalize-yamlfa.py --in ~/tmp/pubseq/state.json file(s)
+
+# --- Normalize data (validation mode)
+python3 ../../workflows/tools/normalize-yamlfa.py -s ~/tmp/yamlfa/state.json --species ncbi_host_species.csv --specimen specimen.csv --validate
+
 ```
 
 # TODO
-- 
cgit v1.2.3