# HG changeset patch
# User smarthey
# Date 1552911353 14400
# Node ID 5e48082308a84b197379d8b868a318e347645534
Uploaded
diff -r 000000000000 -r 5e48082308a8 paqmir_create_mirna_references/.directory
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/paqmir_create_mirna_references/.directory Mon Mar 18 08:15:53 2019 -0400
@@ -0,0 +1,4 @@
+[Dolphin]
+Timestamp=2019,2,28,8,53,7
+Version=4
+ViewMode=1
diff -r 000000000000 -r 5e48082308a8 paqmir_create_mirna_references/create_miRNA_references.sh
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/paqmir_create_mirna_references/create_miRNA_references.sh Mon Mar 18 08:15:53 2019 -0400
@@ -0,0 +1,15 @@
+#!/bin/bash
+
+directory=`dirname $0`
+
+# Extraction of precursors corresponding to the selected species (by identification of 3 letter code at the begining of the identifier)
+perl $directory/extract_seq_which_id_contains.pl --fasta_in ${1} --word ${3} --inverse no --begining no --file_out ${4} #extract sequence with word in the identifier
+perl -pi -e 's/(>\S+)\s.+/\1/' ${4} #recuperate informations before the first space
+
+# Extraction of matures corresponding to the selected species (by identification of 3 letter code at the begining of the identifier)
+perl $directory/extract_seq_which_id_contains.pl --fasta_in ${2} --word ${3} --inverse no --begining no --file_out ${5} #extract sequence with word in the identifier
+perl -pi -e 's/(>\S+)\s.+/\1/' ${5} #recuperate informations before the first space
+
+# Extraction of matures which are not corresponding to the selected species (by identification of 3 letter code at the begining of the identifier)
+perl $directory/extract_seq_which_id_contains.pl --fasta_in ${2} --word ${3} --inverse yes --begining no --file_out ${6} #extract sequence without word in the identifier
+perl -pi -e 's/(>\S+)\s.+/\1/' ${6} #recuperate informations before the first space
diff -r 000000000000 -r 5e48082308a8 paqmir_create_mirna_references/create_miRNA_references.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/paqmir_create_mirna_references/create_miRNA_references.xml Mon Mar 18 08:15:53 2019 -0400
@@ -0,0 +1,84 @@
+
+ creates the microRNA reference files used by the miRDeep2 software
+
+ perl
+ perl-bioperl
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 10.1371/journal.pone.0091938
+ 10.1186/s12864-015-1471-y
+ 10.1093/nar/gkr688
+ 10.1002/0471250953.bi1210s36
+
+
diff -r 000000000000 -r 5e48082308a8 paqmir_create_mirna_references/extract_seq_which_id_contains.pl
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/paqmir_create_mirna_references/extract_seq_which_id_contains.pl Mon Mar 18 08:15:53 2019 -0400
@@ -0,0 +1,123 @@
+#! /usr/bin/perl
+#
+# extract_seq_which_id_contains.pl
+#
+# Copyright 2019 Sylvain Marthey
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program; if not, see .
+
+use strict;
+use Getopt::Long;
+use Pod::Usage;
+use Bio::Seq;
+use Bio::SeqIO;
+
+my ($help,$fasta_in,$word,$file_out,$inverse,$begining,$expr);
+
+GetOptions("help|?" => \$help,
+ "fasta_in:s" => \$fasta_in,
+ "word:s" => \$word,
+ "file_out:s" => \$file_out,
+ "inverse:s" => \$inverse,
+ "begining:s" => \$begining)
+or
+pod2usage(-message=>"Try `$0' for more information.", -exitval => 2,-verbose=> 0);
+
+pod2usage(-exitval =>1, -verbose => 2) if ($help);
+
+if((!$fasta_in && !-f($fasta_in)) ){
+ print "--fasta_in parameter missing : try extract_seq_which_id_contains.pl --help\n";
+ exit;
+}
+if((!$file_out && !-f($file_out)) ){
+ print "--file_out parameter missing : try extract_seq_which_id_contains.pl --help\n";
+ exit;
+}
+if((!$word) ){
+ print "--file_out_path parameter missing : try extract_seq_which_id_contains.pl --help\n";
+ exit;
+}
+if(uc($inverse) eq 'YES' || uc($inverse) eq 'Y'){
+ $inverse = 1;
+}else{
+ $inverse = 0;
+}
+if(uc($begining) eq 'YES' || uc($begining) eq 'Y'){
+ $expr = qr/^$word/;
+}else{
+ $expr = qr/$word/;
+}
+
+my $first = Bio::SeqIO->new(-file => $fasta_in, -format => "fasta");
+my $out_fasta = Bio::SeqIO->new(-file => ">".$file_out , '-format' => 'Fasta');
+
+# read the input fasta file
+while (my $seq = $first->next_seq) {
+ # seach the word in the identifier
+ if($seq->id() =~ /$expr/){
+ if(!$inverse){
+ $out_fasta->write_seq($seq);
+ }
+ }elsif($inverse){
+ $out_fasta->write_seq($seq);
+ }
+}
+
+
+=head1 NAME
+
+ extract_seq_which_id_contains.pl
+
+=head1 SYNOPSIS
+
+ extract_seq_which_id_contains.pl --fasta_in --word --file_out [--begining --inverse ]
+
+=head1 OPTIONS
+
+ --fasta_in fasta file containing sequences we want to extract
+
+ --word word that will be searched in the id of the sequences we want to extract
+
+ --file_out out fasta file
+
+ --begining search the word only in the begining of the sequence identifier
+
+ --inverse inverse the sequence selection (like grep -v)
+
+
+=head1 DESCRIPTION
+
+ This tool will read the fasta file and extract sequences where identifiers contain the searched word.
+
+=head1 AUTHORS
+
+Sylvain Marthey