comparison scripts/format_transdecoder_headers.sh @ 1:3f862f346967 draft

planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit cf1b9c905931ca2ca25faa4844d45c908756472f-dirty

0:f3600c96e961

#/bin/bash


#This script contains regex to re-write the outputs of transdecoder to the original AdaptSearch format 
#Example :
#OG0007971: m.35 g.35  ORF g.35 m.35 type_internal len_307 _+_ Th132_1/1_1.000_923_1-924_+_
#Becomes :
#Th132_1/1_1.000_923

# removes 'OGxxxxxxx '
sed -i -E 's/OG[0-9]{7}:\s//' $1 
# replace _+_ by (+) because '_' causes bugs
sed -i 's/_+_/(+)/g' $1
# Replaces everything by '>'
sed -i -E 's/m\.[0-9]{1,}[^()]+\(\+\)\s*/>/g' $1
# Removes terminal '(+)'
sed -i 's/(+)//g' $1
# Removes last suite of unwanted numbers, underscore and dash
sed -i -E 's/\_[0-9]{1,}-[0-9]{1,}//g' $1

1:3f862f346967

#/bin/bash

# v2 - this script modifies the 'Orthogroups.txt' file in order to make it easily readable by the following script, filter_orthofinder.py
  #Example :
    #OG0000001: Gene.117__As119_1/1_1.000_543__g.117__m.117 Gene.157__As170_1/1_1.000_1203__g.157__m.157
  #Becomes :
    #As119_1/1_1.000_543 As170_1/1_1.000_1203
    
# removes 'OGxxxxxxx: '
sed -E 's/OG[0-9]{7,}:\s//' $1 > $2
# removes things like Gene.119__
sed -i -E 's/Gene\.[0-9]{1,}\_\_/>/g' $2
# removes things like __g.117__m.117
sed -i -E 's/\_\_g\.[0-9]{1,}\_\_m\.[0-9]{1,}//g' $2

# Old version

# removes 'OGxxxxxxx '
#sed -E 's/OG[0-9]{7}:\s//' $1 > $2
# replace _+_ by (+) because '_' causes bugs
#sed -i 's/_+_/(+)/g' $2
# Replaces everything by '>'
#sed -i -E 's/m\.[0-9]{1,}[^()]+\(\+\)\s*/>/g' $2
# Removes terminal '(+)'
#sed -i 's/(+)//g' $2
# Removes last suite of unwanted numbers, underscore and dash
#sed -i -E 's/\_[0-9]{1,}-[0-9]{1,}//g' $2