update hgnc

MaastrichtU-IDS · Jan 26, 2021 · e954a19 · e954a19
1 parent a81a543
commit e954a19
Show file tree

Hide file tree

Showing 3 changed files with 3 additions and 135 deletions.
diff --git a/datasets/hgnc/config.yml b/datasets/hgnc/config.yml
@@ -1,5 +1,6 @@
 
 dataset_to_process: "hgnc"
+# THIS FILE IS NOT USED BY GITHUB ACTIONS
 
 ## For XML workflows
 # dir_to_process:

diff --git a/datasets/hgnc/download/download.sh b/datasets/hgnc/download/download.sh
@@ -3,12 +3,12 @@
 ## Download sample TSV files from GitHub (OMOP CDM mappings, about 15M)
 wget -N ftp://ftp.ebi.ac.uk/pub/databases/genenames/hgnc/tsv/hgnc_complete_set.txt
 
-# Convert TSV to CSV for RMLStreamer
+# Convert TSV to CSV for RML Mapper
 sed -e 's/"//g' -e 's/\t/","/g' -e 's/^/"/' -e 's/$/"/' -e 's/\r//' hgnc_complete_set.txt > hgnc.csv
 
+##Example to run quick python scripts:
 
 # pip install pandas
-
 # python3 <<HEREDOC
 # import pandas as pd
 # csv_table=pd.read_table('hgnc_complete_set.tsv',sep='\t')

diff --git a/datasets/hgnc/process-hgnc.ipynb b/datasets/hgnc/process-hgnc.ipynb