annotate shuffle_sequences.sh @ 0:b45de206654d draft default tip

"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
author erinija
date Fri, 01 May 2020 12:08:23 +0000
parents
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
1 #!/bin/sh
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
2
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
3 if test "$#" -ne 3; then
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
4
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
5 echo ""
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
6 echo ""
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
7 echo " CALL "
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
8 echo " sh shuffle_sequences.sh input.fasta k output.fasta"
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
9 echo ""
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
10 echo " INPUT"
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
11 echo " input.fasta - input fasta file "
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
12 echo " k - 'preserve frequency of k letters (dinucleotide k=2)'"
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
13 echo ""
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
14 echo " OUTPUT"
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
15 echo " output.fasta - shuffle fasta file "
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
16 echo ""
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
17 echo " DESCRIPTION"
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
18 echo " Wrapper for ushuffle program Created by M Jiang. Reference PMID: 18405375 ."
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
19 echo " The ushuffle shuffles nucleotides in fasta sequence preserving frequency"
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
20 echo " of k-mers, a positional order is changed. By default k=2."
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
21 echo " A sequence in fasta file is shuffled only once. The output fasta"
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
22 echo " in the identifier >line contains the original sequence; a shuffled sequence "
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
23 echo " is output on the second line."
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
24 echo ""
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
25 echo " REQUIREMENT"
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
26 echo " ushuffle installed"
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
27 echo " conda install -c bioconda ushuffle"
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
28 echo ""
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
29
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
30 exit 1
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
31 fi
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
32
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
33 name=$1
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
34 diset=$2
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
35 out=$3
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
36
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
37 # comment for a galaxy tool
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
38 call=ushuffle
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
39
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
40 # prepare fasta into tabular
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
41 cat ${name} | awk 'BEGIN{RS=">";OFS="\t"}NR>1{print ">"$1,$2}' > temp.tab.fa
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
42
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
43 # read the tab file and create shuffled fasta
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
44 while read -r line;
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
45 do
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
46 seq=`echo $line | tr " " "\t" | cut -f2`
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
47 useq=`${call} -s ${seq} -k ${diset} -n 1`;
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
48 echo $line
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
49 echo $useq
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
50 done < temp.tab.fa > ${out}
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
51 rm temp.tab.fa
b45de206654d "planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
erinija
parents:
diff changeset
52