/data/shared/glygen/downloads/glytoucan/gtc_02_04_2022/README.txt

# clone forked repository
$ git clone https://github.com/kmartinez834/PyGly.git

# move export folder to downloads, delete unused PyGly directory
$ mv PyGly/smw/glycandata/export/ /data/shared/glygen/downloads/glytoucan/gtc_02_04_2022/ && rm -rf PyGly/

-----------

# run unzip.sh program in new export folder
$ cd /data/shared/glygen/downloads/glytoucan/gtc_02_04_2022/export/ && bash /software/glygen/unzip.sh 

-----------

# run glycan_images.sh program in new export folder
$ cd /data/shared/glygen/downloads/glytoucan/gtc_02_04_2022/export/ && bash /software/glygen/glycan_images.sh

-----------

# convert byonic_glygen_human_nlinked.txt to byonic_glygen_human_nlinked.tsv where first column is GlyTouCanAccession and second column is Byonic

# print GlyTouCan Accession in first column and convert to .tsv
$ awk '{print $4"\t"$1,$2,$3}' byonic_glygen_human_nlinked.txt > byonic_glygen_human_nlinked.tsv

# remove comma at end of each row, save in place
$sed -i 's/,//' byonic_glygen_human_nlinked.tsv

#insert headers, save in place
$ sed -i '1i\GlyTouCanAccession\tByonic' byonic_glygen_human_nlinked.tsv

-----------

# rename species_expanded.tsv to species_expanded_original.tsv and create copy with name species_expanded.tsv
$ mv species_expanded.tsv species_expanded_original.tsv && cat species_expanded_original.tsv > species_expanded.tsv

# move rows with "GLYDS" accession in column 4 to column 5, add "GlyGen" to source column
$ awk 'OFS="\t"{ if($4~"GLYDS") print $1,$2,$3,"GlyGen",$4,$5; else print $0}' species_expanded.tsv > tmp.tsv && mv tmp.tsv species_expanded.tsv 

# replace "GLYDS" with "GLY_", save in place
sed -i 's/GLYDS/GLY_/' species_expanded.tsv