3rd Option for Featrures

[RPSeaman]

Description of feature

SYMBOL::SYSTEMATICID

rename feature file and aux gene list

[RPSeaman]

#!/bin/bash

mkdir OrigFiles
mkdir UpdatedFiles

mv features.tsv.gz OrigFiles/
mv zfAuxiliaryGeneList.csv OrigFiles/

gzcat OrigFiles/features.tsv.gz | perl -ane 'if ($F[0] ne $F[1]) { print "$F[0]\t$F[1]::$F[0]\tExpression\n"; } else { print "$F[0]\t$F[1]\tExpression\n"; }' | gzip > features.tsv.gz

echo "MTgenes" > UpdatedFiles/MT.csv
cut -f1 -d ","  OrigFiles/zfAuxiliaryGeneList.csv | grep -v "^$" | tail -n +2 | perl -pe "s/^/\\t/;s/$/::/"> UpdatedFiles/origMT.csv
gzcat features.tsv.gz | grep -f UpdatedFiles/origMT.csv | cut -f2 >> UpdatedFiles/MT.csv
rm UpdatedFiles/origMT.csv

echo "G2Mgenes" > UpdatedFiles/G2M.csv
cut -f2 -d ","  OrigFiles/zfAuxiliaryGeneList.csv | grep -v "^$" | tail -n +2 | perl -pe "s/^/\\t/;s/$/::/"> UpdatedFiles/origG2M.csv
gzcat features.tsv.gz | grep -f UpdatedFiles/origG2M.csv | cut -f2 >> UpdatedFiles/G2M.csv
rm UpdatedFiles/origG2M.csv

echo "Sgenes" > UpdatedFiles/S.csv
cut -f3 -d ","  OrigFiles/zfAuxiliaryGeneList.csv | grep -v "^$" | tail -n +2 | perl -pe "s/^/\\t/;s/$/::/"> UpdatedFiles/origS.csv
gzcat features.tsv.gz | grep -f UpdatedFiles/origS.csv | cut -f2 >> UpdatedFiles/S.csv
rm UpdatedFiles/origS.csv

echo "RMgenes" > UpdatedFiles/RM.csv
cut -f4 -d ","  OrigFiles/zfAuxiliaryGeneList.csv | grep -v "^$" | tail -n +2 | perl -pe "s/^/\\t/;s/$/::/"> UpdatedFiles/origRM.csv
gzcat features.tsv.gz | grep -f UpdatedFiles/origRM.csv | cut -f2 >> UpdatedFiles/RM.csv
rm UpdatedFiles/origRM.csv

paste -d ',' UpdatedFiles/MT.csv UpdatedFiles/G2M.csv UpdatedFiles/S.csv UpdatedFiles/RM.csv > AuxGeneList.csv

rm -r UpdatedFiles

[RPSeaman]

^^^ Is an option, depending if it is in R or outside

[Riley-Grindle]

1st Column - Systematic ID
2nd - Gene name if applicable - otherwise ID

force SO features to use combined Sys::Name format
REGEX check for ENS to determine loupe search term