annotate format_fasta_hairpins.sh @ 5:9ea96a02c416 draft

planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mircounts commit 04980585c257ab5f8eb5d10de007316c47c5d1ce
author artbio
date Tue, 05 Sep 2017 06:33:16 -0400
parents da29af78a960
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
da29af78a960 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mircounts commit d4d8106d66b65679a1a685ab94bfcf99cdb7b959
artbio
parents:
diff changeset
1 GENOME_KEY=$1
da29af78a960 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mircounts commit d4d8106d66b65679a1a685ab94bfcf99cdb7b959
artbio
parents:
diff changeset
2
da29af78a960 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mircounts commit d4d8106d66b65679a1a685ab94bfcf99cdb7b959
artbio
parents:
diff changeset
3 gunzip hairpin.fa.gz
da29af78a960 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mircounts commit d4d8106d66b65679a1a685ab94bfcf99cdb7b959
artbio
parents:
diff changeset
4 sed -i.bak '/^[^>]/ y/uU/tT/' hairpin.fa ## replace U by tT
da29af78a960 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mircounts commit d4d8106d66b65679a1a685ab94bfcf99cdb7b959
artbio
parents:
diff changeset
5 sed -i.bak2 -E 's/ .+//' hairpin.fa ## just leaves mir name as one word header
da29af78a960 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mircounts commit d4d8106d66b65679a1a685ab94bfcf99cdb7b959
artbio
parents:
diff changeset
6 awk '/^>/ {printf("\n%s\n",$0);next; } { printf("%s",$0);} END {printf("\n");}' < hairpin.fa > hairpin.fa.bak3
da29af78a960 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mircounts commit d4d8106d66b65679a1a685ab94bfcf99cdb7b959
artbio
parents:
diff changeset
7 tail -n +2 hairpin.fa.bak3 > hairpin.fa ## generate single line sequences
da29af78a960 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mircounts commit d4d8106d66b65679a1a685ab94bfcf99cdb7b959
artbio
parents:
diff changeset
8 awk 'BEGIN{RS=">"}{gsub("\n","\t",$0); print ">"$0}' < hairpin.fa > hairpin.fa.tmp
da29af78a960 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mircounts commit d4d8106d66b65679a1a685ab94bfcf99cdb7b959
artbio
parents:
diff changeset
9 mv hairpin.fa hairpin.bak4 && tail -n +2 hairpin.fa.tmp > hairpin.fa
da29af78a960 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mircounts commit d4d8106d66b65679a1a685ab94bfcf99cdb7b959
artbio
parents:
diff changeset
10 rm hairpin.fa.tmp ## tabular sequences
da29af78a960 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mircounts commit d4d8106d66b65679a1a685ab94bfcf99cdb7b959
artbio
parents:
diff changeset
11 sed -i.bak5 -E $'s/\t$//g' hairpin.fa ## remove tab before end line leaved by previous awk
da29af78a960 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mircounts commit d4d8106d66b65679a1a685ab94bfcf99cdb7b959
artbio
parents:
diff changeset
12 grep ">${GENOME_KEY}-" hairpin.fa > hairpin.fa.tmp
da29af78a960 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mircounts commit d4d8106d66b65679a1a685ab94bfcf99cdb7b959
artbio
parents:
diff changeset
13 mv hairpin.fa hairpin.fa.bak6
da29af78a960 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mircounts commit d4d8106d66b65679a1a685ab94bfcf99cdb7b959
artbio
parents:
diff changeset
14 mv hairpin.fa.tmp hairpin.fa ## filter tabular hairpins with proper genomeKey
da29af78a960 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mircounts commit d4d8106d66b65679a1a685ab94bfcf99cdb7b959
artbio
parents:
diff changeset
15 tr '\t' '\n' < hairpin.fa > hairpin.fa.tmp
da29af78a960 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mircounts commit d4d8106d66b65679a1a685ab94bfcf99cdb7b959
artbio
parents:
diff changeset
16 mv hairpin.fa hairpin.fa.bak7
da29af78a960 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mircounts commit d4d8106d66b65679a1a685ab94bfcf99cdb7b959
artbio
parents:
diff changeset
17 mv hairpin.fa.tmp hairpin.fa ## terminate parsing by regenerating fasta format, bowtie-build ready
da29af78a960 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mircounts commit d4d8106d66b65679a1a685ab94bfcf99cdb7b959
artbio
parents:
diff changeset
18 rm ./*.bak* ## cleaning job directory
da29af78a960 planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/mircounts commit d4d8106d66b65679a1a685ab94bfcf99cdb7b959
artbio
parents:
diff changeset
19