/usr/bin/mipe2dbSTS is in mipe 1.1-3.
This file is owned by root:root, with mode 0o755.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 | #!/usr/bin/perl
# This library is free software; you can redistribute it and/or
# modify it under the terms of the GNU Lesser General Public
# License as published by the Free Software Foundation; either
# version 2.1 of the License, or (at your option) any later version.
#
# This library 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
# Lesser General Public License for more details.
#
# You should have received a copy of the GNU Lesser General Public
# License along with this library ('COPYING'); if not, write to the Free Software
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
use strict;
use warnings;
use XML::Twig;
=head1 NAME
mipe2dbSTS.pl - Generates input file for submission to dbSTS
included in output: STS section of dbSTS submission
based on MIPE version v1.1
arguments: * mipe_file
* config file
* (optional) list of PCR IDs
The config file consists of lines containing a key and a value, separated by an equal sign ('=').
The key consists of the lowercase name of the NCBI submission file (see website dbSTS), followed by
an underscore and the lowercase name of the field in that file.
The following fields should be defined in the config file:
pub_title=
pub_authors=
source_name=
source_organism=
cont_name=
cont_fax=
cont_tel=
cont_email=
cont_lab=
cont_inst=
cont_addr=
protocol_name=
protocol_protocol=
buffer_name=
buffer_buffer=
sts_pcr_profile=
For protocol_protocol, buffer_buffer and sts_pcr_profile, more lines are necessary (see example).
An example of a config file look like this:
pub_title=Genetic mapping of chicken SNPs
pub_authors=Aerts,J.A.; Veenendaal,T.; Crooijmans,R.P.M.A; Groenen,M.A.M
source_name=Chicken genomic DNA
source_organism=Gallus gallus
cont_name=Jan Aerts
cont_fax=+31 317 483929
cont_tel=+31 317 483397
cont_email=jan.aerts@wur.nl
cont_lab=Animal Breeding and Genomics Group
cont_inst=Wageningen University
cont_addr=PO Box 338, 6700 AH Wageningen, The Netherlands
protocol_name=Protocol_Aerts
protocol_protocol=Template: 30-60 ng
protocol_protocol=Primer: each 4 uM
protocol_protocol=dNTPs: each 200 uM
protocol_protocol=Taq: 0.3 units
protocol_protocol=Volume: 12 ul
buffer_name=Buffer_Aerts
buffer_buffer=MgCl2: 1.5 mM
buffer_buffer=(NH4)2SO4: 20 mM
buffer_buffer=Tris-HCl: 75 mM
buffer_buffer=Tween 20: 0.01% (w/v)
buffer_buffer=pH: 8.8
=head1 BUGS
Unknown. If you encounter one, please let me know (jan.aerts@wur.nl).
=head1 SYNOPSIS
mipe2dbSTS.pl your_file.mipe dbSTS.config <pcr_id1> <pcr_id2>
=head1 ADDITIONAL INFO
See http://mipe.sourceforge.net
=head1 AUTHOR
Jan Aerts (jan.aerts@bbsrc.ac.uk)
=cut
my %amb_codes = ( M => ['A', 'C']
, R => ['A', 'G']
, W => ['A', 'T']
, S => ['C', 'G']
, Y => ['C', 'T']
, K => ['G', 'T']
, V => ['A', 'C', 'G']
, H => ['A', 'C', 'T']
, D => ['A', 'G', 'T']
, B => ['C', 'G', 'T']
, N => ['A', 'C', 'G', 'T']
);
my ( $mipe_file, $config_file ) = @ARGV;
if ( not defined $mipe_file or not defined $config_file ) { die "Please provide filenames\n" };
chomp (my @pcr_ids = grep { /[a-zA-Z0-9]/ } (<STDIN>));
my %config;
open CONFIG, $config_file || die "Cannot open config file $config_file\n";
chomp ( my @config = ( <CONFIG> ) );
close CONFIG;
foreach ( @config ) {
my ( $key, $value ) = split /=/, $_;
if ( $key ne 'protocol_protocol' and $key ne 'buffer_buffer' and $key ne 'sts_pcr_profile' ) {
$config{$key} = $value;
} elsif ( $key eq 'protocol_protocol' ) {
push @{$config{'protocol_protocol'}}, $value;
} elsif ( $key eq 'buffer_buffer' ) {
push @{$config{'buffer_buffer'}}, $value;
}
}
print pub();
print source();
print contact();
print protocol();
print buffer();
print sts();
sub pub {
my $to_print;
$to_print .= "TYPE: PUB\n";
$to_print .= "TITLE:\n";
$to_print .= $config{'pub_title'} . "\n";
$to_print .= "AUTHORS:\n";
$to_print .= $config{'pub_authors'} . "\n";
$to_print .= "STATUS: 1\n";
$to_print .= "||\n";
return $to_print;
}
sub source {
my $to_print;
$to_print .= "TYPE: SOURCE\n";
$to_print .= "NAME: " . $config{'source_name'} . "\n";
$to_print .= "ORGANISM: " . $config{'source_organism'} . "\n";
$to_print .= "||\n";
return $to_print;
}
sub contact {
my $to_print;
$to_print .= "TYPE: CONT\n";
$to_print .= "NAME: " . $config{'cont_name'} . "\n";
$to_print .= "FAX: " . $config{'cont_fax'} . "\n";
$to_print .= "TEL: " . $config{'cont_tel'} . "\n";
$to_print .= "EMAIL: " . $config{'cont_email'} . "\n";
$to_print .= "LAB: " . $config{'cont_lab'} . "\n";
$to_print .= "INST: " . $config{'cont_inst'} . "\n";
$to_print .= "ADDR: " . $config{'cont_addr'} . "\n";
$to_print .= "||\n";
return $to_print;
}
sub protocol {
my $to_print;
$to_print .= "TYPE: PROTOCOL\n";
$to_print .= "NAME: " . $config{'protocol_name'} . "\n";
$to_print .= "PROTOCOL:\n";
foreach ( @{$config{'protocol_protocol'}} ) {
$to_print .= " " . $_ . "\n";
}
$to_print .= "||\n";
return $to_print;
}
sub buffer {
my $to_print;
$to_print .= "TYPE: BUFFER\n";
$to_print .= "NAME: " . $config{'buffer_name'} . "\n";
$to_print .= "BUFFER:\n";
foreach ( @{$config{'buffer_buffer'}} ) {
$to_print .= " " . $_ . "\n";
}
$to_print .= "||\n";
return $to_print;
}
sub sts {
my $twig = XML::Twig->new( TwigHandlers => { pcr => \&pcr }
, pretty_print => 'indented' );
$twig->parsefile($mipe_file);
exit;
}
sub pcr {
my ( $twig, $pcr ) = @_;
my $to_include = 0;
my $pcr_id = $pcr->{att}->{id};
if ( scalar @pcr_ids > 0 ) {
$to_include = 0;
foreach ( @pcr_ids ) {
if ( $pcr_id =~ /$_/i ) {
$to_include = 1;
}
}
} else {
$to_include = 1;
}
if ( $to_include ) {
my $design = $pcr->first_child('design');
my %snps;
print "TYPE: STS\n";
print "STATUS: New\n";
print "CONT_NAME: ", $config{'cont_name'}, "\n";
print "PROTOCOL: ", $config{'protocol_name'}, "\n";
print "BUFFER: ", $config{'buffer_name'}, "\n";
print "SOURCE: ", $config{'source_name'}, "\n";
print "CITATION:\nGenetic mapping of chicken SNPs\n";
print "STS#: ", $pcr_id, "\n";
print "SIZE: ", length $design->first_child('seq')->text, "\n";
print "F_PRIMER: ", $design->first_child('primer1')->first_child('seq')->text, "\n";
print "R_PRIMER: ", $design->first_child('primer2')->first_child('seq')->text, "\n";
print "DNA_TYPE: Genomic\n";
print "PCR_PROFILE:\n";
if ( defined $design->first_child('profile') ) {
my $profile = $design->first_child('profile');
if ( defined $profile->first_child('predenaturation') ) {
print " Presoak: ", $profile->first_child('predenaturation')->first_child('temp')->text, " for ", $profile->first_child('predenaturation')->first_child('time')->text, "\n";
}
if ( defined $profile->first_child('cycle') ) {
my @cycles = $profile->children('cycle');
foreach ( @cycles ) {
print " Denaturation: ", $_->first_child('denaturation')->first_child('temp')->text, " for ", $_->first_child('denaturation')->first_child('time')->text, "\n";
print " Annealing: ", $_->first_child('annealing')->first_child('temp')->text, " for ", $_->first_child('annealing')->first_child('time')->text, "\n";
print " Elongation: ", $_->first_child('elongation')->first_child('temp')->text, " for ", $_->first_child('elongation')->first_child('time')->text, "\n";
print " PCR cycles: ", $_->first_child('number')->text, "\n";
}
}
if ( defined $profile->first_child('postelongation') ) {
print " Presoak: ", $profile->first_child('postelongation')->first_child('temp')->text, " for ", $profile->first_child('postelongation')->first_child('time')->text, "\n";
}
} else {
print " UNKNOWN\n";
}
print "PUBLIC:\n";
if ( defined $pcr->first_child('use') ) {
my $use = $pcr->first_child('use');
my @snps = $use->children('snp');
if ( scalar @snps > 0 ) {
print "COMMENT:\n";
print " Polymorphism(s) (positions as in sequence):\n";
}
foreach my $snp ( @snps ) {
if ( defined $snp->first_child('pos_design') ) {
my $snp_amb = $snp->first_child('amb')->text;
if ( $use->first_child('revcomp')->text == 1 ) {
$snp_amb =~ tr/ACGTMRWSYKVHDBN
/TGCAKYWSRMBDHVN
/s;
}
print " ID=", $snp->{att}->{id}, "\n";
print " Position=", $snp->first_child('pos_design')->text, "\n";
print " Ambiguity=", $snp_amb, "\n";
}
}
}
print "SEQUENCE:\n";
my $seq = $design->first_child('seq')->text;
$seq =~ s/(.{50})/$1\n/g;
print $seq, "\n";
print "||\n";
}
}
|