Mercurial > repos > abims-sbr > orthogroups_tool
annotate scripts/format_transdecoder_headers.sh @ 0:d33ad52f59bc draft default tip
planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit 3c7982d775b6f3b472f6514d791edcb43cd258a1-dirty
| author | abims-sbr | 
|---|---|
| date | Fri, 01 Feb 2019 10:25:10 -0500 | 
| parents | |
| children | 
| rev | line source | 
|---|---|
| 0 
d33ad52f59bc
planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit 3c7982d775b6f3b472f6514d791edcb43cd258a1-dirty
 abims-sbr parents: diff
changeset | 1 #/bin/bash | 
| 
d33ad52f59bc
planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit 3c7982d775b6f3b472f6514d791edcb43cd258a1-dirty
 abims-sbr parents: diff
changeset | 2 | 
| 
d33ad52f59bc
planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit 3c7982d775b6f3b472f6514d791edcb43cd258a1-dirty
 abims-sbr parents: 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 | 
| 
d33ad52f59bc
planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit 3c7982d775b6f3b472f6514d791edcb43cd258a1-dirty
 abims-sbr parents: diff
changeset | 4 #Example : | 
| 
d33ad52f59bc
planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit 3c7982d775b6f3b472f6514d791edcb43cd258a1-dirty
 abims-sbr parents: 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 | 
| 
d33ad52f59bc
planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit 3c7982d775b6f3b472f6514d791edcb43cd258a1-dirty
 abims-sbr parents: diff
changeset | 6 #Becomes : | 
| 
d33ad52f59bc
planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit 3c7982d775b6f3b472f6514d791edcb43cd258a1-dirty
 abims-sbr parents: diff
changeset | 7 #As119_1/1_1.000_543 As170_1/1_1.000_1203 | 
| 
d33ad52f59bc
planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit 3c7982d775b6f3b472f6514d791edcb43cd258a1-dirty
 abims-sbr parents: diff
changeset | 8 | 
| 
d33ad52f59bc
planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit 3c7982d775b6f3b472f6514d791edcb43cd258a1-dirty
 abims-sbr parents: diff
changeset | 9 # removes 'OGxxxxxxx: ' | 
| 
d33ad52f59bc
planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit 3c7982d775b6f3b472f6514d791edcb43cd258a1-dirty
 abims-sbr parents: diff
changeset | 10 sed -E 's/OG[0-9]{7,}:\s//' $1 > $2 | 
| 
d33ad52f59bc
planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit 3c7982d775b6f3b472f6514d791edcb43cd258a1-dirty
 abims-sbr parents: diff
changeset | 11 # removes things like Gene.119__ | 
| 
d33ad52f59bc
planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit 3c7982d775b6f3b472f6514d791edcb43cd258a1-dirty
 abims-sbr parents: diff
changeset | 12 sed -i -E 's/Gene\.[0-9]{1,}\_\_/>/g' $2 | 
| 
d33ad52f59bc
planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit 3c7982d775b6f3b472f6514d791edcb43cd258a1-dirty
 abims-sbr parents: diff
changeset | 13 # removes things like __g.117__m.117 | 
| 
d33ad52f59bc
planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit 3c7982d775b6f3b472f6514d791edcb43cd258a1-dirty
 abims-sbr parents: diff
changeset | 14 sed -i -E 's/\_\_g\.[0-9]{1,}\_\_m\.[0-9]{1,}//g' $2 | 
| 
d33ad52f59bc
planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit 3c7982d775b6f3b472f6514d791edcb43cd258a1-dirty
 abims-sbr parents: diff
changeset | 15 | 
| 
d33ad52f59bc
planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit 3c7982d775b6f3b472f6514d791edcb43cd258a1-dirty
 abims-sbr parents: diff
changeset | 16 # Old version | 
| 
d33ad52f59bc
planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit 3c7982d775b6f3b472f6514d791edcb43cd258a1-dirty
 abims-sbr parents: diff
changeset | 17 | 
| 
d33ad52f59bc
planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit 3c7982d775b6f3b472f6514d791edcb43cd258a1-dirty
 abims-sbr parents: diff
changeset | 18 # removes 'OGxxxxxxx ' | 
| 
d33ad52f59bc
planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit 3c7982d775b6f3b472f6514d791edcb43cd258a1-dirty
 abims-sbr parents: diff
changeset | 19 #sed -E 's/OG[0-9]{7}:\s//' $1 > $2 | 
| 
d33ad52f59bc
planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit 3c7982d775b6f3b472f6514d791edcb43cd258a1-dirty
 abims-sbr parents: diff
changeset | 20 # replace _+_ by (+) because '_' causes bugs | 
| 
d33ad52f59bc
planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit 3c7982d775b6f3b472f6514d791edcb43cd258a1-dirty
 abims-sbr parents: diff
changeset | 21 #sed -i 's/_+_/(+)/g' $2 | 
| 
d33ad52f59bc
planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit 3c7982d775b6f3b472f6514d791edcb43cd258a1-dirty
 abims-sbr parents: diff
changeset | 22 # Replaces everything by '>' | 
| 
d33ad52f59bc
planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit 3c7982d775b6f3b472f6514d791edcb43cd258a1-dirty
 abims-sbr parents: diff
changeset | 23 #sed -i -E 's/m\.[0-9]{1,}[^()]+\(\+\)\s*/>/g' $2 | 
| 
d33ad52f59bc
planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit 3c7982d775b6f3b472f6514d791edcb43cd258a1-dirty
 abims-sbr parents: diff
changeset | 24 # Removes terminal '(+)' | 
| 
d33ad52f59bc
planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit 3c7982d775b6f3b472f6514d791edcb43cd258a1-dirty
 abims-sbr parents: diff
changeset | 25 #sed -i 's/(+)//g' $2 | 
| 
d33ad52f59bc
planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit 3c7982d775b6f3b472f6514d791edcb43cd258a1-dirty
 abims-sbr parents: diff
changeset | 26 # Removes last suite of unwanted numbers, underscore and dash | 
| 
d33ad52f59bc
planemo upload for repository htpps://github.com/abims-sbr/adaptearch commit 3c7982d775b6f3b472f6514d791edcb43cd258a1-dirty
 abims-sbr parents: diff
changeset | 27 #sed -i -E 's/\_[0-9]{1,}-[0-9]{1,}//g' $2 | 
