Mercurial > repos > cpt > cpt_gff_extract_seq
annotate all_fasta.loc.sample @ 10:3d9f283ff09d draft default tip
planemo upload commit e14699677f337fd1324aa6898c1388796c5446c1-dirty
author | cpt |
---|---|
date | Fri, 01 Dec 2023 05:01:01 +0000 |
parents | ab40380424c9 |
children |
rev | line source |
---|---|
5
ab40380424c9
planemo upload commit 852ac96ca53a2ffa0947e6df5e24671866b642f5
cpt
parents:
diff
changeset
|
1 #This file lists the locations and dbkeys of all the fasta files |
ab40380424c9
planemo upload commit 852ac96ca53a2ffa0947e6df5e24671866b642f5
cpt
parents:
diff
changeset
|
2 #under the "genome" directory (a directory that contains a directory |
ab40380424c9
planemo upload commit 852ac96ca53a2ffa0947e6df5e24671866b642f5
cpt
parents:
diff
changeset
|
3 #for each build). The script extract_fasta.py will generate the file |
ab40380424c9
planemo upload commit 852ac96ca53a2ffa0947e6df5e24671866b642f5
cpt
parents:
diff
changeset
|
4 #all_fasta.loc. This file has the format (white space characters are |
ab40380424c9
planemo upload commit 852ac96ca53a2ffa0947e6df5e24671866b642f5
cpt
parents:
diff
changeset
|
5 #TAB characters): |
ab40380424c9
planemo upload commit 852ac96ca53a2ffa0947e6df5e24671866b642f5
cpt
parents:
diff
changeset
|
6 # |
ab40380424c9
planemo upload commit 852ac96ca53a2ffa0947e6df5e24671866b642f5
cpt
parents:
diff
changeset
|
7 #<unique_build_id> <dbkey> <display_name> <file_path> |
ab40380424c9
planemo upload commit 852ac96ca53a2ffa0947e6df5e24671866b642f5
cpt
parents:
diff
changeset
|
8 # |
ab40380424c9
planemo upload commit 852ac96ca53a2ffa0947e6df5e24671866b642f5
cpt
parents:
diff
changeset
|
9 #So, all_fasta.loc could look something like this: |
ab40380424c9
planemo upload commit 852ac96ca53a2ffa0947e6df5e24671866b642f5
cpt
parents:
diff
changeset
|
10 # |
ab40380424c9
planemo upload commit 852ac96ca53a2ffa0947e6df5e24671866b642f5
cpt
parents:
diff
changeset
|
11 #apiMel3 apiMel3 Honeybee (Apis mellifera): apiMel3 /path/to/genome/apiMel3/apiMel3.fa |
ab40380424c9
planemo upload commit 852ac96ca53a2ffa0947e6df5e24671866b642f5
cpt
parents:
diff
changeset
|
12 #hg19canon hg19 Human (Homo sapiens): hg19 Canonical /path/to/genome/hg19/hg19canon.fa |
ab40380424c9
planemo upload commit 852ac96ca53a2ffa0947e6df5e24671866b642f5
cpt
parents:
diff
changeset
|
13 #hg19full hg19 Human (Homo sapiens): hg19 Full /path/to/genome/hg19/hg19full.fa |
ab40380424c9
planemo upload commit 852ac96ca53a2ffa0947e6df5e24671866b642f5
cpt
parents:
diff
changeset
|
14 # |
ab40380424c9
planemo upload commit 852ac96ca53a2ffa0947e6df5e24671866b642f5
cpt
parents:
diff
changeset
|
15 #Your all_fasta.loc file should contain an entry for each individual |
ab40380424c9
planemo upload commit 852ac96ca53a2ffa0947e6df5e24671866b642f5
cpt
parents:
diff
changeset
|
16 #fasta file. So there will be multiple fasta files for each build, |
ab40380424c9
planemo upload commit 852ac96ca53a2ffa0947e6df5e24671866b642f5
cpt
parents:
diff
changeset
|
17 #such as with hg19 above. |
ab40380424c9
planemo upload commit 852ac96ca53a2ffa0947e6df5e24671866b642f5
cpt
parents:
diff
changeset
|
18 # |