Mercurial > repos > fgiacomoni > hmdb_ms_search

comparison wsdl_hmdb.pl @ 1:6d0a0f8f672a draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit f67323ae4fa7fdbd9f4518ede105a7d7cd44b471
author fgiacomoni
date Wed, 23 Nov 2016 09:31:50 -0500
parents
children 6091a80df951
comparison
equal deleted inserted replaced
0:9583f9772198 1:6d0a0f8f672a
1 #!perl
2
3 ## script : wsdl_hmdb.pl
4 #=============================================================================
5 # Included modules and versions
6 #=============================================================================
7 ## Perl modules
8 use strict ;
9 use warnings ;
10 use Carp qw (cluck croak carp) ;
11
12 use Data::Dumper ;
13 use Getopt::Long ;
14 use POSIX ;
15 use FindBin ; ## Permet de localisez le repertoire du script perl d'origine
16
17 ## Specific Modules (Home made...)
18 use lib $FindBin::Bin ;
19 my $binPath = $FindBin::Bin ;
20 use lib::hmdb qw( :ALL ) ;
21 ## PFEM Perl Modules
22 use lib::conf qw( :ALL ) ;
23 use lib::csv qw( :ALL ) ;
24
25 ## Initialized values
26 my ( $help ) = undef ;
27 my ( $mass ) = undef ;
28 my ( $masses_file, $col_id, $col_mass, $header_choice, $nbline_header ) = ( undef, undef, undef, undef, undef ) ;
29 my $max_query = undef ;
30 my ( $delta, $molecular_species, $out_tab, $out_html, $out_xls ) = ( undef, undef, undef, undef, undef ) ;
31
32
33 #=============================================================================
34 # Manage EXCEPTIONS
35 #=============================================================================
36
37 &GetOptions ( "h" => \$help, # HELP
38 "mass:s" => \$mass, ## option : one masse
39 "masses:s" => \$masses_file, ## option : path to the input
40 "header_choice:s" => \$header_choice, ## Presence or not of header in tabular file
41 "nblineheader:i" => \$nbline_header, ## numbre of header line present in file
42 "colfactor:i" => \$col_mass, ## Column id for retrieve formula list in tabular file
43 "delta:f" => \$delta,
44 "mode:s" => \$molecular_species, ## Molecular species (positive/negative/neutral)
45 "maxquery:i" => \$max_query, ## Maximum query return (default is 20 entries by query // min 1 & max 50 )
46 "output_tabular:s" => \$out_tab, ## option : path to the ouput (tabular : input+results )
47 "output_html|v:s" => \$out_html, ## option : path to the results view (output2)
48 "output_xlsx:s" => \$out_xls, ## option : path to the xls-like format output
49 ) ;
50
51 #=============================================================================
52 # EXCEPTIONS
53 #=============================================================================
54 $help and &help ;
55
56 #=============================================================================
57 # MAIN SCRIPT
58 #=============================================================================
59
60
61 ## -------------- Conf file ------------------------ :
62 my ( $CONF ) = ( undef ) ;
63 foreach my $conf ( <$binPath/*.cfg> ) {
64 my $oConf = lib::conf::new() ;
65 $CONF = $oConf->as_conf($conf) ;
66 }
67
68 ## -------------- HTML template file ------------------------ :
69 foreach my $html_template ( <$binPath/*.tmpl> ) { $CONF->{'HTML_TEMPLATE'} = $html_template ; }
70
71 if (!defined $max_query) {
72 $max_query = $CONF->{'HMDB_MAX_QUERY'} ;
73 }
74
75
76 ## --------------- Global parameters ---------------- :
77 my ( $ids, $masses, $results ) = ( undef, undef, undef ) ;
78 my ( $complete_rows, $nb_pages_for_html_out ) = ( undef, 1 ) ;
79 my $metabocard_features = undef ;
80 my $search_condition = "Search params : Molecular specie = $molecular_species / delta (mass-to-charge ratio) = $delta" ;
81
82 ## --------------- retrieve input data -------------- :
83
84 ## manage only one mass
85 if ( ( defined $mass ) and ( $mass ne '' ) ) {
86 my @masses = split(" ", $mass);
87 $masses = \@masses ;
88 for (my $i=1 ; $i<=$#masses+1 ; $i++){ push (@$ids,"mz_0".sprintf("%04s", $i ) ); }
89 } ## END IF
90 ## manage csv file containing list of masses
91 elsif ( ( defined $masses_file ) and ( $masses_file ne "" ) and ( -e $masses_file ) ) {
92 ## parse all csv for later : output csv build
93 my $ocsv_input = lib::csv->new() ;
94 my $complete_csv = $ocsv_input->get_csv_object( "\t" ) ;
95 $complete_rows = $ocsv_input->parse_csv_object($complete_csv, \$masses_file) ;
96
97 ## parse masses and set ids
98 my $ocsv = lib::csv->new() ;
99 my $csv = $ocsv->get_csv_object( "\t" ) ;
100 if ( ( !defined $nbline_header ) or ( $nbline_header < 0 ) ) { $nbline_header = 0 ; }
101 $masses = $ocsv->get_value_from_csv_multi_header( $csv, $masses_file, $col_mass, $header_choice, $nbline_header ) ; ## retrieve mz values on csv
102 my $nbmz = @$masses ;
103 for (my $i=1 ; $i<=$nbmz+1 ; $i++){ push (@$ids,"mz_0".sprintf("%04s", $i ) ); }
104 }
105 else {
106 warn "[warning] Input data are missing : none mass or file of masses\n" ;
107 &help ;
108 }
109 #print Dumper $masses ;
110 ## ---------------- launch queries -------------------- :
111
112 if ( ( defined $delta ) and ( $delta > 0 ) and ( defined $molecular_species ) and ( $molecular_species ne '' ) ) {
113 ## prepare masses list and execute query
114 my $oHmdb = lib::hmdb::new() ;
115 my $hmdb_pages = undef ;
116 my $hmdb_ids = undef ;
117
118 $results = [] ; # prepare arrays ref
119 my $submasses = $oHmdb->extract_sub_mz_lists($masses, $CONF->{HMDB_LIMITS} ) ;
120
121 ## get the hmdb server status by a test query - continuous queries or kill script.
122 my $status = $oHmdb->test_matches_from_hmdb_ua() ;
123 $oHmdb->check_state_from_hmdb_ua($status) ; ## can kill the script execution
124
125 foreach my $mzs ( @{$submasses} ) {
126
127 my $result = undef ;
128 my ( $hmdb_masses, $nb_masses_to_submit ) = $oHmdb->prepare_multi_masses_query($mzs) ;
129 $hmdb_pages = $oHmdb->get_matches_from_hmdb_ua($hmdb_masses, $delta, $molecular_species) ;
130 ($result) = $oHmdb->parse_hmdb_csv_results($hmdb_pages, $mzs, $max_query) ; ## hash format result
131 ## This previous step return results with cutoff on the number of entries returned !
132 $results = [ @$results, @$result ] ;
133 }
134
135 ## foreach metabolite get its own metabocard
136 $hmdb_ids = $oHmdb->get_unik_ids_from_results($results) ;
137 # $hmdb_ids->{'HMDB03125'} = 1 ,
138 $metabocard_features = $oHmdb->get_hmdb_metabocard_from_id($hmdb_ids, $CONF->{'HMDB_METABOCARD_URL'}) ; ## Try to multithread the querying
139
140 ## Map metabocards with results (add supplementary data)
141
142 # print Dumper $results ;
143 # print Dumper $hmdb_ids ;
144 # print Dumper $metabocard_features ;
145
146 if ( ( defined $results ) and ( defined $metabocard_features ) ) {
147 $results = $oHmdb->map_suppl_data_on_hmdb_results($results, $metabocard_features) ;
148 }
149
150 ## Uses N mz and theirs entries per page (see config file).
151 # how many pages you need with your input mz list?
152 $nb_pages_for_html_out = ceil( scalar(@{$masses} ) / $CONF->{HTML_ENTRIES_PER_PAGE} ) ;
153
154 # print Dumper $results ;
155 }
156 else {
157 croak "Can't work with HMDB : missing paramaters (list of masses, delta or molecular species)\n" ;
158 } ## end ELSE
159
160 ## -------------- Produce HTML/CSV output ------------------ :
161
162 if ( ( defined $out_html ) and ( defined $results ) ) {
163 my $oHtml = lib::hmdb::new() ;
164 my ($tbody_object) = $oHtml->set_html_tbody_object( $nb_pages_for_html_out, $CONF->{HTML_ENTRIES_PER_PAGE} ) ;
165 ($tbody_object) = $oHtml->add_mz_to_tbody_object($tbody_object, $CONF->{HTML_ENTRIES_PER_PAGE}, $masses, $ids) ;
166 ($tbody_object) = $oHtml->add_entries_to_tbody_object($tbody_object, $CONF->{HTML_ENTRIES_PER_PAGE}, $masses, $results) ;
167 my $output_html = $oHtml->write_html_skel(\$out_html, $tbody_object, $nb_pages_for_html_out, $search_condition, $CONF->{'HTML_TEMPLATE'}, $CONF->{'JS_GALAXY_PATH'}, $CONF->{'CSS_GALAXY_PATH'}) ;
168
169 } ## END IF
170 else {
171 warn "Can't create a HTML output for HMDB : no result found or your output file is not defined\n" ;
172 }
173
174 if ( ( defined $out_tab ) and ( defined $results ) ) {
175 # produce a csv based on METLIN format
176 my $ocsv = lib::hmdb::new() ;
177 if (defined $masses_file) {
178 my $lm_matrix = undef ;
179 if ( ( defined $nbline_header ) and ( $header_choice eq 'yes' ) ) {
180 # $lm_matrix = $ocsv->set_lm_matrix_object('hmdb', $masses, $results ) ;
181 $lm_matrix = $ocsv->set_hmdb_matrix_object_with_ids('hmdb', $masses, $results ) ;
182 $lm_matrix = $ocsv->add_lm_matrix_to_input_matrix($complete_rows, $lm_matrix, $nbline_header-1) ;
183 }
184 elsif ( ( $header_choice eq 'no' ) ) {
185 # $lm_matrix = $ocsv->set_lm_matrix_object(undef, $masses, $results ) ;
186 $lm_matrix = $ocsv->set_hmdb_matrix_object_with_ids(undef, $masses, $results ) ;
187 $lm_matrix = $ocsv->add_lm_matrix_to_input_matrix($complete_rows, $lm_matrix, 0) ;
188 }
189 $ocsv->write_csv_skel(\$out_tab, $lm_matrix) ;
190 }
191 elsif (defined $mass) {
192 $ocsv->write_csv_one_mass($masses, $ids, $results, $out_tab) ;
193 }
194 } ## END IF
195 else {
196 warn "Can't create a tabular output for HMDB : no result found or your output file is not defined\n" ;
197 }
198
199 ## Write XLS like format
200 if ( ( defined $out_xls ) and ( defined $results ) ) {
201 my $ocsv = lib::hmdb::new() ;
202 $ocsv->write_csv_one_mass($masses, $ids, $results, $out_xls) ;
203 }
204
205
206 #====================================================================================
207 # Help subroutine called with -h option
208 # number of arguments : 0
209 # Argument(s) :
210 # Return : 1
211 #====================================================================================
212 sub help {
213 print STDERR "
214 help of wsdl_hmdb
215
216 # wsdl_hmdb is a script to query HMDB website using mz and return a list of candidates sent by HMDB based on the ms search tool.
217 # Input : formula or list of formula
218 # Author : Franck Giacomoni and Marion Landi
219 # Email : fgiacomoni\@clermont.inra.fr
220 # Version : 1.4
221 # Created : 08/07/2012
222 # Updated : 21/01/2016
223 USAGE :
224 wsdl_hmdb.pl -mass [one mass or a string list of exact masses] -delta [mz delta] -mode [molecular species: positive|negative|neutral] -output [output tabular file] -view [output html file]
225
226 or
227 wsdl_hmdb.pl -masses [an input file of mzs] -colfactor [col of mz] -header_choice [yes|no] -nblineheader [nb of lines containing file header : 0-n]
228 -delta [mz delta] -mode [molecular species: positive|negative|neutral] -output [output tabular file] -view [output html file]
229
230 or
231 wsdl_hmdb.pl -h for help
232
233 ";
234 exit(1);
235 }
236
237 ## END of script - F Giacomoni
238
239 __END__
240
241 =head1 NAME
242
243 wsdl_hmdb.pl -- script to query HMDB website using mz and return a list of candidates sent by HMDB based on the ms search tool.
244
245 =head1 USAGE
246
247 wsdl_hmdb.pl -mass [one mass or a string list of exact masses] -delta [mz delta] -mode [molecular species: positive|negative|neutral] -output [output tabular file] -view [output html file]
248
249 or
250 wsdl_hmdb.pl -masses [an input file of mzs] -colfactor [col of mz] -header_choice [yes|no] -nblineheader [nb of lines containing file header : 0-n]
251 -delta [mz delta] -mode [molecular species: positive|negative|neutral] -output [output tabular file] -view [output html file]
252
253 =head1 SYNOPSIS
254
255 This script manages batch queries on HMDB server.
256
257 =head1 DESCRIPTION
258
259 This main program is a script to query HMDB website using mz and return a list of candidates sent by HMDB based on the ms search tool.
260
261 =over 4
262
263 =item B<function01>
264
265 =item B<function02>
266
267 =back
268
269 =head1 AUTHOR
270
271 Franck Giacomoni E<lt>franck.giacomoni@clermont.inra.frE<gt>
272
273 =head1 LICENSE
274
275 This program is free software; you can redistribute it and/or modify it under the same terms as Perl itself.
276
277 =head1 VERSION
278
279 version 1.0 : 06 / 06 / 2013
280
281 version 1.2 : 27 / 01 / 2014
282
283 version 1.3 : 19 / 11 / 2014
284
285 version 1.4 : 21 / 01 / 2016 - a clean version for community
286
287 =cut