annotate scripts/format_transdecoder_headers.sh @ 2:d557212b575b draft

planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit 76e603ecd0118c8060d972b675a13db858956eb6
author abims-sbr
date Wed, 17 Jan 2018 11:32:14 -0500
parents 3f862f346967
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
f3600c96e961 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit f30d34a6decb05f6b7803f6d677dad4c50f9cebe
abims-sbr
parents:
diff changeset
1 #/bin/bash
f3600c96e961 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit f30d34a6decb05f6b7803f6d677dad4c50f9cebe
abims-sbr
parents:
diff changeset
2
1
3f862f346967 planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit cf1b9c905931ca2ca25faa4844d45c908756472f-dirty
abims-sbr
parents: 0
diff changeset
3 # v2 - this script modifies the 'Orthogroups.txt' file in order to make it easily readable by the following script, filter_orthofinder.py
3f862f346967 planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit cf1b9c905931ca2ca25faa4844d45c908756472f-dirty
abims-sbr
parents: 0
diff changeset
4 #Example :
3f862f346967 planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit cf1b9c905931ca2ca25faa4844d45c908756472f-dirty
abims-sbr
parents: 0
diff changeset
5 #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
3f862f346967 planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit cf1b9c905931ca2ca25faa4844d45c908756472f-dirty
abims-sbr
parents: 0
diff changeset
6 #Becomes :
3f862f346967 planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit cf1b9c905931ca2ca25faa4844d45c908756472f-dirty
abims-sbr
parents: 0
diff changeset
7 #As119_1/1_1.000_543 As170_1/1_1.000_1203
3f862f346967 planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit cf1b9c905931ca2ca25faa4844d45c908756472f-dirty
abims-sbr
parents: 0
diff changeset
8
3f862f346967 planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit cf1b9c905931ca2ca25faa4844d45c908756472f-dirty
abims-sbr
parents: 0
diff changeset
9 # removes 'OGxxxxxxx: '
3f862f346967 planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit cf1b9c905931ca2ca25faa4844d45c908756472f-dirty
abims-sbr
parents: 0
diff changeset
10 sed -E 's/OG[0-9]{7,}:\s//' $1 > $2
3f862f346967 planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit cf1b9c905931ca2ca25faa4844d45c908756472f-dirty
abims-sbr
parents: 0
diff changeset
11 # removes things like Gene.119__
3f862f346967 planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit cf1b9c905931ca2ca25faa4844d45c908756472f-dirty
abims-sbr
parents: 0
diff changeset
12 sed -i -E 's/Gene\.[0-9]{1,}\_\_/>/g' $2
3f862f346967 planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit cf1b9c905931ca2ca25faa4844d45c908756472f-dirty
abims-sbr
parents: 0
diff changeset
13 # removes things like __g.117__m.117
3f862f346967 planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit cf1b9c905931ca2ca25faa4844d45c908756472f-dirty
abims-sbr
parents: 0
diff changeset
14 sed -i -E 's/\_\_g\.[0-9]{1,}\_\_m\.[0-9]{1,}//g' $2
0
f3600c96e961 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit f30d34a6decb05f6b7803f6d677dad4c50f9cebe
abims-sbr
parents:
diff changeset
15
1
3f862f346967 planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit cf1b9c905931ca2ca25faa4844d45c908756472f-dirty
abims-sbr
parents: 0
diff changeset
16 # Old version
0
f3600c96e961 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit f30d34a6decb05f6b7803f6d677dad4c50f9cebe
abims-sbr
parents:
diff changeset
17
f3600c96e961 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit f30d34a6decb05f6b7803f6d677dad4c50f9cebe
abims-sbr
parents:
diff changeset
18 # removes 'OGxxxxxxx '
1
3f862f346967 planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit cf1b9c905931ca2ca25faa4844d45c908756472f-dirty
abims-sbr
parents: 0
diff changeset
19 #sed -E 's/OG[0-9]{7}:\s//' $1 > $2
0
f3600c96e961 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit f30d34a6decb05f6b7803f6d677dad4c50f9cebe
abims-sbr
parents:
diff changeset
20 # replace _+_ by (+) because '_' causes bugs
1
3f862f346967 planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit cf1b9c905931ca2ca25faa4844d45c908756472f-dirty
abims-sbr
parents: 0
diff changeset
21 #sed -i 's/_+_/(+)/g' $2
0
f3600c96e961 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit f30d34a6decb05f6b7803f6d677dad4c50f9cebe
abims-sbr
parents:
diff changeset
22 # Replaces everything by '>'
1
3f862f346967 planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit cf1b9c905931ca2ca25faa4844d45c908756472f-dirty
abims-sbr
parents: 0
diff changeset
23 #sed -i -E 's/m\.[0-9]{1,}[^()]+\(\+\)\s*/>/g' $2
0
f3600c96e961 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit f30d34a6decb05f6b7803f6d677dad4c50f9cebe
abims-sbr
parents:
diff changeset
24 # Removes terminal '(+)'
1
3f862f346967 planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit cf1b9c905931ca2ca25faa4844d45c908756472f-dirty
abims-sbr
parents: 0
diff changeset
25 #sed -i 's/(+)//g' $2
0
f3600c96e961 planemo upload for repository https://github.com/abims-sbr/adaptsearch commit f30d34a6decb05f6b7803f6d677dad4c50f9cebe
abims-sbr
parents:
diff changeset
26 # Removes last suite of unwanted numbers, underscore and dash
1
3f862f346967 planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit cf1b9c905931ca2ca25faa4844d45c908756472f-dirty
abims-sbr
parents: 0
diff changeset
27 #sed -i -E 's/\_[0-9]{1,}-[0-9]{1,}//g' $2