From 1c4e055b8a9dc53b7fdbdf12d4b0a7e877fbc2ef Mon Sep 17 00:00:00 2001
From: Pjotr Prins
Date: Mon, 4 Jan 2021 08:58:38 +0000
Subject: Started on normalization

---
 workflows/pull-data/genbank/README.md | 19 +++++++++++++++----
 1 file changed, 15 insertions(+), 4 deletions(-)

(limited to 'workflows/pull-data/genbank/README.md')

diff --git a/workflows/pull-data/genbank/README.md b/workflows/pull-data/genbank/README.md
index b5bac84..d7cc15f 100644
--- a/workflows/pull-data/genbank/README.md
+++ b/workflows/pull-data/genbank/README.md
@@ -1,14 +1,25 @@
-# pipeline
+# GenBank
+
+This directory contains the tools to pull and transform
+GenBank data.
+
+# Workflows
+
+## Prepare new GenBank data for upload
+
+The following workflow sends GenBank data into PubSeq
 
 ```sh
 # --- get list of IDs already in PubSeq
-./sparql-fetch-ids > pubseq_ids.txt
+../../tools/sparql-fetch-ids > pubseq_ids.txt
 # --- get list of missing genbank IDs
 ./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 and FASTA
-python3 transform-genbank-xml2yamlfa --out ~/tmp/pubseq file(s)
+# --- 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)
 ```
 
 # TODO
-- 
cgit v1.2.3