1 package Maasha::Biopieces;
4 # Copyright (C) 2007-2008 Martin A. Hansen.
6 # This program is free software; you can redistribute it and/or
7 # modify it under the terms of the GNU General Public License
8 # as published by the Free Software Foundation; either version 2
9 # of the License, or (at your option) any later version.
11 # This program is distributed in the hope that it will be useful,
12 # but WITHOUT ANY WARRANTY; without even the implied warranty of
13 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
14 # GNU General Public License for more details.
16 # You should have received a copy of the GNU General Public License
17 # along with this program; if not, write to the Free Software
18 # Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
20 # http://www.gnu.org/copyleft/gpl.html
23 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> DESCRIPTION <<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
26 # Routines for manipulation, parsing and emitting of human/machine readable biopieces records.
29 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
34 use Getopt::Long qw( :config bundling );
35 use Time::HiRes qw( gettimeofday );
36 use Storable qw( dclone );
45 use Maasha::Stockholm;
51 use Maasha::UCSC::BED;
52 use Maasha::UCSC::Wiggle;
61 use vars qw( @ISA @EXPORT_OK );
65 @ISA = qw( Exporter );
80 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> SIGNAL HANDLER <<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
83 $SIG{ '__DIE__' } = \&sig_handler;
84 $SIG{ 'INT' } = \&sig_handler;
85 $SIG{ 'TERM' } = \&sig_handler;
88 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> GLOBALS <<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
91 my ( $script, $BP_TMP );
93 $script = Maasha::Common::get_scriptname();
94 $BP_TMP = Maasha::Common::get_tmpdir();
97 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> LOG <<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
100 my $log_global = Maasha::Common::append_open( "$ENV{ 'BP_LOG' }/biopieces.log" );
101 my $log_local = Maasha::Common::append_open( "$ENV{ 'HOME' }/.biopieces.log" );
103 $log_global->autoflush( 1 );
104 $log_local->autoflush( 1 );
106 &log( $log_global, $script, \@ARGV );
107 &log( $log_local, $script, \@ARGV );
113 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> RUN SCRIPT <<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
116 run_script( $script );
119 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> SUBROUTINES <<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
124 # Martin A. Hansen, January 2008.
126 # Log messages to logfile.
128 my ( $fh, # filehandle to logfile
129 $script, # script name
130 $argv, # reference to @ARGV
135 my ( $time_stamp, $user );
137 $time_stamp = Maasha::Common::time_stamp();
139 $user = $ENV{ 'USER' };
141 $script = "biopieces" if $script eq "-e";
143 print $fh "$time_stamp\t$user\t$script ", join( " ", @{ $argv } ), "\n";
149 # Martin A. Hansen, August 2007.
151 # Run a specific script.
153 my ( $script, # script name
158 my ( $t0, $t1, $options, $in, $out );
160 $t0 = gettimeofday();
162 $options = get_options( $script );
164 $options->{ "SCRIPT" } = $script;
166 if ( $script ne "list_biopieces" and $script ne "list_genomes" ) {
167 $script = "print_usage" if ( -t STDIN and keys %{ $options } <= 1 or $options->{ 'help' } );
170 $in = read_stream( $options->{ "stream_in" } );
171 $out = write_stream( $options->{ "stream_out" } );
173 if ( $script eq "print_usage" ) { script_print_usage( $in, $out, $options ) }
174 elsif ( $script eq "list_biopieces" ) { script_list_biopieces( $in, $out, $options ) }
175 elsif ( $script eq "list_genomes" ) { script_list_genomes( $in, $out, $options ) }
176 elsif ( $script eq "read_fasta" ) { script_read_fasta( $in, $out, $options ) }
177 elsif ( $script eq "read_tab" ) { script_read_tab( $in, $out, $options ) }
178 elsif ( $script eq "read_psl" ) { script_read_psl( $in, $out, $options ) }
179 elsif ( $script eq "read_bed" ) { script_read_bed( $in, $out, $options ) }
180 elsif ( $script eq "read_fixedstep" ) { script_read_fixedstep( $in, $out, $options ) }
181 elsif ( $script eq "read_blast_tab" ) { script_read_blast_tab( $in, $out, $options ) }
182 elsif ( $script eq "read_embl" ) { script_read_embl( $in, $out, $options ) }
183 elsif ( $script eq "read_stockholm" ) { script_read_stockholm( $in, $out, $options ) }
184 elsif ( $script eq "read_phastcons" ) { script_read_phastcons( $in, $out, $options ) }
185 elsif ( $script eq "read_soft" ) { script_read_soft( $in, $out, $options ) }
186 elsif ( $script eq "read_gff" ) { script_read_gff( $in, $out, $options ) }
187 elsif ( $script eq "read_2bit" ) { script_read_2bit( $in, $out, $options ) }
188 elsif ( $script eq "read_solexa" ) { script_read_solexa( $in, $out, $options ) }
189 elsif ( $script eq "read_solid" ) { script_read_solid( $in, $out, $options ) }
190 elsif ( $script eq "read_mysql" ) { script_read_mysql( $in, $out, $options ) }
191 elsif ( $script eq "read_ucsc_config" ) { script_read_ucsc_config( $in, $out, $options ) }
192 elsif ( $script eq "assemble_tag_contigs" ) { script_assemble_tag_contigs( $in, $out, $options ) }
193 elsif ( $script eq "format_genome" ) { script_format_genome( $in, $out, $options ) }
194 elsif ( $script eq "length_seq" ) { script_length_seq( $in, $out, $options ) }
195 elsif ( $script eq "uppercase_seq" ) { script_uppercase_seq( $in, $out, $options ) }
196 elsif ( $script eq "shuffle_seq" ) { script_shuffle_seq( $in, $out, $options ) }
197 elsif ( $script eq "analyze_seq" ) { script_analyze_seq( $in, $out, $options ) }
198 elsif ( $script eq "analyze_tags" ) { script_analyze_tags( $in, $out, $options ) }
199 elsif ( $script eq "complexity_seq" ) { script_complexity_seq( $in, $out, $options ) }
200 elsif ( $script eq "oligo_freq" ) { script_oligo_freq( $in, $out, $options ) }
201 elsif ( $script eq "create_weight_matrix" ) { script_create_weight_matrix( $in, $out, $options ) }
202 elsif ( $script eq "calc_bit_scores" ) { script_calc_bit_scores( $in, $out, $options ) }
203 elsif ( $script eq "calc_fixedstep" ) { script_calc_fixedstep( $in, $out, $options ) }
204 elsif ( $script eq "reverse_seq" ) { script_reverse_seq( $in, $out, $options ) }
205 elsif ( $script eq "complement_seq" ) { script_complement_seq( $in, $out, $options ) }
206 elsif ( $script eq "remove_indels" ) { script_remove_indels( $in, $out, $options ) }
207 elsif ( $script eq "transliterate_seq" ) { script_transliterate_seq( $in, $out, $options ) }
208 elsif ( $script eq "transliterate_vals" ) { script_transliterate_vals( $in, $out, $options ) }
209 elsif ( $script eq "translate_seq" ) { script_translate_seq( $in, $out, $options ) }
210 elsif ( $script eq "extract_seq" ) { script_extract_seq( $in, $out, $options ) }
211 elsif ( $script eq "get_genome_seq" ) { script_get_genome_seq( $in, $out, $options ) }
212 elsif ( $script eq "get_genome_align" ) { script_get_genome_align( $in, $out, $options ) }
213 elsif ( $script eq "get_genome_phastcons" ) { script_get_genome_phastcons( $in, $out, $options ) }
214 elsif ( $script eq "fold_seq" ) { script_fold_seq( $in, $out, $options ) }
215 elsif ( $script eq "split_seq" ) { script_split_seq( $in, $out, $options ) }
216 elsif ( $script eq "split_bed" ) { script_split_bed( $in, $out, $options ) }
217 elsif ( $script eq "align_seq" ) { script_align_seq( $in, $out, $options ) }
218 elsif ( $script eq "tile_seq" ) { script_tile_seq( $in, $out, $options ) }
219 elsif ( $script eq "invert_align" ) { script_invert_align( $in, $out, $options ) }
220 elsif ( $script eq "patscan_seq" ) { script_patscan_seq( $in, $out, $options ) }
221 elsif ( $script eq "create_blast_db" ) { script_create_blast_db( $in, $out, $options ) }
222 elsif ( $script eq "blast_seq" ) { script_blast_seq( $in, $out, $options ) }
223 elsif ( $script eq "blat_seq" ) { script_blat_seq( $in, $out, $options ) }
224 elsif ( $script eq "soap_seq" ) { script_soap_seq( $in, $out, $options ) }
225 elsif ( $script eq "match_seq" ) { script_match_seq( $in, $out, $options ) }
226 elsif ( $script eq "create_vmatch_index" ) { script_create_vmatch_index( $in, $out, $options ) }
227 elsif ( $script eq "vmatch_seq" ) { script_vmatch_seq( $in, $out, $options ) }
228 elsif ( $script eq "write_fasta" ) { script_write_fasta( $in, $out, $options ) }
229 elsif ( $script eq "write_align" ) { script_write_align( $in, $out, $options ) }
230 elsif ( $script eq "write_blast" ) { script_write_blast( $in, $out, $options ) }
231 elsif ( $script eq "write_tab" ) { script_write_tab( $in, $out, $options ) }
232 elsif ( $script eq "write_bed" ) { script_write_bed( $in, $out, $options ) }
233 elsif ( $script eq "write_psl" ) { script_write_psl( $in, $out, $options ) }
234 elsif ( $script eq "write_fixedstep" ) { script_write_fixedstep( $in, $out, $options ) }
235 elsif ( $script eq "write_2bit" ) { script_write_2bit( $in, $out, $options ) }
236 elsif ( $script eq "write_solid" ) { script_write_solid( $in, $out, $options ) }
237 elsif ( $script eq "write_ucsc_config" ) { script_write_ucsc_config( $in, $out, $options ) }
238 elsif ( $script eq "head_records" ) { script_head_records( $in, $out, $options ) }
239 elsif ( $script eq "remove_keys" ) { script_remove_keys( $in, $out, $options ) }
240 elsif ( $script eq "remove_adaptor" ) { script_remove_adaptor( $in, $out, $options ) }
241 elsif ( $script eq "remove_mysql_tables" ) { script_remove_mysql_tables( $in, $out, $options ) }
242 elsif ( $script eq "remove_ucsc_tracks" ) { script_remove_ucsc_tracks( $in, $out, $options ) }
243 elsif ( $script eq "rename_keys" ) { script_rename_keys( $in, $out, $options ) }
244 elsif ( $script eq "uniq_vals" ) { script_uniq_vals( $in, $out, $options ) }
245 elsif ( $script eq "merge_vals" ) { script_merge_vals( $in, $out, $options ) }
246 elsif ( $script eq "merge_records" ) { script_merge_records( $in, $out, $options ) }
247 elsif ( $script eq "grab" ) { script_grab( $in, $out, $options ) }
248 elsif ( $script eq "compute" ) { script_compute( $in, $out, $options ) }
249 elsif ( $script eq "flip_tab" ) { script_flip_tab( $in, $out, $options ) }
250 elsif ( $script eq "add_ident" ) { script_add_ident( $in, $out, $options ) }
251 elsif ( $script eq "count_records" ) { script_count_records( $in, $out, $options ) }
252 elsif ( $script eq "random_records" ) { script_random_records( $in, $out, $options ) }
253 elsif ( $script eq "sort_records" ) { script_sort_records( $in, $out, $options ) }
254 elsif ( $script eq "count_vals" ) { script_count_vals( $in, $out, $options ) }
255 elsif ( $script eq "plot_histogram" ) { script_plot_histogram( $in, $out, $options ) }
256 elsif ( $script eq "plot_lendist" ) { script_plot_lendist( $in, $out, $options ) }
257 elsif ( $script eq "plot_chrdist" ) { script_plot_chrdist( $in, $out, $options ) }
258 elsif ( $script eq "plot_karyogram" ) { script_plot_karyogram( $in, $out, $options ) }
259 elsif ( $script eq "plot_matches" ) { script_plot_matches( $in, $out, $options ) }
260 elsif ( $script eq "plot_seqlogo" ) { script_plot_seqlogo( $in, $out, $options ) }
261 elsif ( $script eq "plot_phastcons_profiles" ) { script_plot_phastcons_profiles( $in, $out, $options ) }
262 elsif ( $script eq "analyze_bed" ) { script_analyze_bed( $in, $out, $options ) }
263 elsif ( $script eq "analyze_vals" ) { script_analyze_vals( $in, $out, $options ) }
264 elsif ( $script eq "length_vals" ) { script_length_vals( $in, $out, $options ) }
265 elsif ( $script eq "sum_vals" ) { script_sum_vals( $in, $out, $options ) }
266 elsif ( $script eq "mean_vals" ) { script_mean_vals( $in, $out, $options ) }
267 elsif ( $script eq "median_vals" ) { script_median_vals( $in, $out, $options ) }
268 elsif ( $script eq "max_vals" ) { script_max_vals( $in, $out, $options ) }
269 elsif ( $script eq "min_vals" ) { script_min_vals( $in, $out, $options ) }
270 elsif ( $script eq "upload_to_ucsc" ) { script_upload_to_ucsc( $in, $out, $options ) }
272 close $in if defined $in;
275 $t1 = gettimeofday();
277 print STDERR "Program: $script" . ( " " x ( 25 - length( $script ) ) ) . sprintf( "Run time: %.4f\n", ( $t1 - $t0 ) ) if $options->{ 'verbose' };
283 # Martin A. Hansen, February 2008.
285 # Gets options from commandline and checks these vigerously.
287 my ( $script, # name of script
292 my ( %options, @options, $opt, @genomes, $real );
294 if ( $script eq "print_usage" )
300 elsif ( $script eq "read_fasta" )
307 elsif ( $script eq "read_tab" )
318 elsif ( $script eq "read_psl" )
325 elsif ( $script eq "read_bed" )
333 elsif ( $script eq "read_fixedstep" )
340 elsif ( $script eq "read_blast_tab" )
347 elsif ( $script eq "read_embl" )
357 elsif ( $script eq "read_stockholm" )
364 elsif ( $script eq "read_phastcons" )
375 elsif ( $script eq "read_soft" )
383 elsif ( $script eq "read_gff" )
390 elsif ( $script eq "read_2bit" )
398 elsif ( $script eq "read_solexa" )
407 elsif ( $script eq "read_solid" )
415 elsif ( $script eq "read_mysql" )
424 elsif ( $script eq "read_ucsc_config" )
431 elsif ( $script eq "format_genome" )
440 elsif ( $script eq "length_seq" )
447 elsif ( $script eq "oligo_freq" )
454 elsif ( $script eq "create_weight_matrix" )
460 elsif ( $script eq "transliterate_seq" )
468 elsif ( $script eq "transliterate_vals" )
477 elsif ( $script eq "translate_seq" )
483 elsif ( $script eq "extract_seq" )
491 elsif ( $script eq "get_genome_seq" )
503 elsif ( $script eq "get_genome_align" )
514 elsif ( $script eq "get_genome_phastcons" )
525 elsif ( $script eq "split_seq" )
532 elsif ( $script eq "split_bed" )
539 elsif ( $script eq "tile_seq" )
546 elsif ( $script eq "invert_align" )
552 elsif ( $script eq "patscan_seq" )
563 elsif ( $script eq "create_blast_db" )
570 elsif ( $script eq "blast_seq" )
582 elsif ( $script eq "blat_seq" )
594 elsif ( $script eq "soap_seq" )
605 elsif ( $script eq "match_seq" )
612 elsif ( $script eq "create_vmatch_index" )
620 elsif ( $script eq "vmatch_seq" )
631 elsif ( $script eq "write_fasta" )
640 elsif ( $script eq "write_align" )
650 elsif ( $script eq "write_blast" )
659 elsif ( $script eq "write_tab" )
671 elsif ( $script eq "write_bed" )
680 elsif ( $script eq "write_psl" )
688 elsif ( $script eq "write_fixedstep" )
696 elsif ( $script eq "write_2bit" )
704 elsif ( $script eq "write_solid" )
713 elsif ( $script eq "write_ucsc_config" )
720 elsif ( $script eq "plot_seqlogo" )
727 elsif ( $script eq "plot_phastcons_profiles" )
742 elsif ( $script eq "analyze_vals" )
749 elsif ( $script eq "head_records" )
755 elsif ( $script eq "remove_keys" )
762 elsif ( $script eq "remove_adaptor" )
771 elsif ( $script eq "remove_mysql_tables" )
782 elsif ( $script eq "remove_ucsc_tracks" )
794 elsif ( $script eq "rename_keys" )
800 elsif ( $script eq "uniq_vals" )
807 elsif ( $script eq "merge_vals" )
814 elsif ( $script eq "merge_records" )
821 elsif ( $script eq "grab" )
836 elsif ( $script eq "compute" )
842 elsif ( $script eq "add_ident" )
849 elsif ( $script eq "count_records" )
856 elsif ( $script eq "random_records" )
862 elsif ( $script eq "sort_records" )
869 elsif ( $script eq "count_vals" )
875 elsif ( $script eq "plot_histogram" )
888 elsif ( $script eq "plot_lendist" )
900 elsif ( $script eq "plot_chrdist" )
911 elsif ( $script eq "plot_karyogram" )
920 elsif ( $script eq "plot_matches" )
932 elsif ( $script eq "length_vals" )
938 elsif ( $script eq "sum_vals" )
946 elsif ( $script eq "mean_vals" )
954 elsif ( $script eq "median_vals" )
962 elsif ( $script eq "max_vals" )
970 elsif ( $script eq "min_vals" )
978 elsif ( $script eq "upload_to_ucsc" )
1002 # print STDERR Dumper( \@options );
1009 # print STDERR Dumper( \%options );
1011 if ( -t STDIN && scalar( keys %options ) == 0 or $options{ "help" } ) {
1012 return wantarray ? %options : \%options;
1015 $options{ "cols" } = [ split ",", $options{ "cols" } ] if defined $options{ "cols" };
1016 $options{ "keys" } = [ split ",", $options{ "keys" } ] if defined $options{ "keys" };
1017 $options{ "no_keys" } = [ split ",", $options{ "no_keys" } ] if defined $options{ "no_keys" };
1018 $options{ "save_keys" } = [ split ",", $options{ "save_keys" } ] if defined $options{ "save_keys" };
1019 $options{ "quals" } = [ split ",", $options{ "quals" } ] if defined $options{ "quals" };
1020 $options{ "feats" } = [ split ",", $options{ "feats" } ] if defined $options{ "feats" };
1021 $options{ "frames" } = [ split ",", $options{ "frames" } ] if defined $options{ "frames" };
1022 $options{ "formats" } = [ split ",", $options{ "formats" } ] if defined $options{ "formats" };
1023 $options{ "samples" } = [ split ",", $options{ "samples" } ] if defined $options{ "samples" };
1024 $options{ "tables" } = [ split ",", $options{ "tables" } ] if defined $options{ "tables" };
1025 $options{ "tracks" } = [ split ",", $options{ "tracks" } ] if defined $options{ "tracks" };
1027 # ---- check arguments ----
1029 if ( $options{ 'data_in' } )
1031 $options{ "files" } = getopt_files( $options{ 'data_in' } );
1033 Maasha::Common::error( qq(Argument to --data_in must be a valid file or fileglob expression) ) if scalar @{ $options{ "files" } } == 0;
1036 map { Maasha::Common::error( qq(Argument to --cols must be a whole numbers - not "$_") ) if $_ !~ /^\d+$/ } @{ $options{ "cols" } } if $options{ "cols" };
1038 # print STDERR Dumper( \%options );
1040 $real = "beg|end|word_size|wrap|chunk_size|tile_size|len|prefix_length|mismatches|offset|num|skip|cpus|window_size|step_size";
1042 foreach $opt ( keys %options )
1044 if ( $opt =~ /stream_in|pattern_in|exact_in/ and not -f $options{ $opt } )
1046 Maasha::Common::error( qq(Argument to --$opt must be a valid file or fileglob expression - not "$options{ $opt }") );
1048 elsif ( $opt =~ /$real/ and $options{ $opt } !~ /^\d+$/ )
1050 Maasha::Common::error( qq(Argument to --$opt must be a whole number - not "$options{ $opt }") );
1052 elsif ( $opt =~ /max_hits|max_hits|max_misses|dist|edit_dist|flank|gap|hamming_dist|priority/ and $options{ $opt } !~ /^-?\d+$/ )
1054 Maasha::Common::error( qq(Argument to --$opt must be an integer - not "$options{ $opt }") );
1056 elsif ( $opt =~ /identity|threshold/ and $options{ $opt } !~ /^-?(?:\d+(?:\.\d*)?|\.\d+)$/ )
1058 Maasha::Common::error( qq(Argument to --$opt must be a decimal number - not "$options{ $opt }") );
1060 elsif ( $opt =~ /e_val/ and $options{ $opt } !~ /^([+-]?)(?=\d|\.\d)\d*(\.\d*)?([Ee]([+-]?\d+))?$/ )
1062 Maasha::Common::error( qq(Argument to --$opt must be a float - not "$options{ $opt }") );
1064 elsif ( $opt =~ /strand/ and $options{ $opt } !~ /^(\+|-)$/ )
1066 Maasha::Common::error( qq(Argument to --$opt must be "+" or "-" - not "$options{ $opt }") );
1068 elsif ( $opt eq "genome" and $script ne "format_genome" )
1070 @genomes = Maasha::Common::ls_dirs( "$ENV{ 'BP_DATA' }/genomes" );
1071 map { $_ =~ s/.*\/(.+)$/$1/ } @genomes;
1073 if ( not grep { $_ =~ /^$options{ $opt }$/ } @genomes ) {
1074 Maasha::Common::error( qq(Genome $options{ $opt } not found in "$ENV{ 'BP_DATA' }/genomes/") );
1077 elsif ( $opt eq "terminal" and not $options{ $opt } =~ /^(svg|post|dumb|x11)/ )
1079 Maasha::Common::error( qq(Bad --$opt argument "$options{ $opt }") );
1081 elsif ( $opt eq "table" and $options{ $opt } =~ /(-|\.)/ )
1083 Maasha::Common::error( qq(Character '$1' is not allowed in table name: $options{ $opt }) );
1085 elsif ( $opt eq "merge" and $options{ $opt } !~ /^(AandB|AorB|BorA|AnotB|BnotA)$/ )
1087 Maasha::Common::error( qq(Argument to --$opt must be AandB, AorB, BorA, AnotB, or BnotA - not "$options{ $opt }") );
1089 elsif ( $opt eq "format" and $script eq "read_solexa" and $options{ $opt } !~ /octal|decimal/ )
1091 Maasha::Common::error( qq(Argument to --$opt must be octal or decimal - not "$options{ $opt }") );
1093 elsif ( $opt eq "remove" and $script eq "remove_adaptor" and $options{ $opt } !~ /before|after|skip/ )
1095 Maasha::Common::error( qq(Argument to --$opt must be before, after, or skip - not "$options{ $opt }") );
1099 Maasha::Common::error( qq(no --database specified) ) if $script eq "create_blast_db" and not $options{ "database" };
1100 Maasha::Common::error( qq(no --index_name specified) ) if $script =~ /create_vmatch_index/ and not $options{ "index_name" };
1101 Maasha::Common::error( qq(no --database or --genome specified) ) if $script eq "blast_seq" and not $options{ "genome" } and not $options{ "database" };
1102 Maasha::Common::error( qq(both --database and --genome specified) ) if $script eq "blast_seq" and $options{ "genome" } and $options{ "database" };
1103 Maasha::Common::error( qq(no --index_name or --genome specified) ) if $script eq "vmatch_seq" and not $options{ "genome" } and not $options{ "index_name" };
1104 Maasha::Common::error( qq(both --index and --genome specified) ) if $script eq "vmatch_seq" and $options{ "genome" } and $options{ "index_name" };
1105 Maasha::Common::error( qq(no --in_file or --genome specified) ) if $script eq "soap_seq" and not $options{ "genome" } and not $options{ "in_file" };
1106 Maasha::Common::error( qq(both --in_file and --genome specified) ) if $script eq "soap_seq" and $options{ "genome" } and $options{ "in_file" };
1107 Maasha::Common::error( qq(no --genome specified) ) if $script =~ /format_genome|get_genome_seq|get_genome_align|get_genome_phastcons|blat_seq|plot_phastcons_profiles|plot_karyogram/ and not $options{ "genome" };
1108 Maasha::Common::error( qq(no --key specified) ) if $script =~ /plot_lendist|plot_histogram/ and not $options{ "key" };
1109 Maasha::Common::error( qq(no --keys speficied) ) if $script =~ /sort_records|count_vals|sum_vals|mean_vals|median_vals|length_vals/ and not $options{ "keys" };
1111 if ( $script eq "upload_to_ucsc" )
1113 Maasha::Common::error( qq(no --database specified) ) if not $options{ "database" };
1114 Maasha::Common::error( qq(no --table specified) ) if not $options{ "table" };
1117 return wantarray ? %options : \%options;
1121 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> SCRIPTS <<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
1124 sub script_print_usage
1126 # Martin A. Hansen, January 2008.
1128 # Retrieves usage information from file and
1129 # prints this nicely formatted.
1131 my ( $in, # handle to in stream
1132 $out, # handle to out stream
1133 $options, # options hash
1138 my ( $file, $wiki, $lines );
1140 if ( $options->{ 'data_in' } ) {
1141 $file = $options->{ 'data_in' };
1143 $file = join "", $ENV{ 'BP_DIR' }, "/bp_usage/", $options->{ 'SCRIPT' }, ".wiki";
1146 $wiki = Maasha::Gwiki::gwiki_read( $file );
1148 if ( not $options->{ "help" } ) {
1149 @{ $wiki } = grep { $_->[ 0 ]->{ 'SECTION' } =~ /Biopiece|Synopsis|Usage|Options|Help/ } @{ $wiki };
1152 $lines = Maasha::Gwiki::gwiki2ascii( $wiki );
1154 print STDERR "$_\n" foreach @{ $lines };
1160 sub script_list_biopieces
1162 # Martin A. Hansen, January 2008.
1164 # Prints the synopsis from the usage for each of the biopieces.
1166 my ( $in, # handle to in stream
1167 $out, # handle to out stream
1168 $options, # options hash
1173 my ( @files, $file, $wiki, $program, $synopsis );
1175 @files = Maasha::Common::ls_files( "$ENV{ 'BP_DIR' }/bp_usage" );
1177 foreach $file ( sort @files )
1179 if ( $file =~ /\/([a-z0-9_]+)\.wiki$/ )
1183 $wiki = Maasha::Gwiki::gwiki_read( $file );
1185 @{ $wiki } = grep { $_->[ 0 ]->{ 'SECTION' } =~ /Synopsis/ } @{ $wiki };
1186 @{ $wiki } = grep { $_->[ 0 ]->{ 'FORMAT' } =~ /paragraph/ } @{ $wiki };
1188 $synopsis = $wiki->[ 0 ]->[ 0 ]->{ 'TEXT' };
1189 $synopsis =~ s/!(\w)/$1/g;
1191 printf( "%-30s%s\n", $program, $synopsis );
1199 sub script_list_genomes
1201 # Martin A. Hansen, January 2008.
1203 # Prints the synopsis from the usage for each of the biopieces.
1205 my ( $in, # handle to in stream
1206 $out, # handle to out stream
1207 $options, # options hash
1212 my ( @genomes, $genome, @formats, $format, %hash, %found, @row );
1214 @genomes = Maasha::Common::ls_dirs( "$ENV{ 'BP_DATA' }/genomes" );
1216 foreach $genome ( @genomes )
1218 next if $genome =~ /\.$/;
1220 @formats = Maasha::Common::ls_dirs( $genome );
1222 foreach $format ( @formats )
1224 if ( $format =~ /\/([^\/]+)\/(\w+)$/ )
1226 $hash{ $1 }{ $2 } = 1;
1235 map { push @row, $_ } sort keys %found;
1237 print join( "\t", @row ), "\n";
1239 foreach $genome ( sort keys %hash )
1243 foreach $format ( sort keys %found )
1245 if ( exists $hash{ $genome }{ $format } ) {
1252 print join( "\t", @row ), "\n";
1257 sub script_read_fasta
1259 # Martin A. Hansen, August 2007.
1261 # Read sequences from FASTA file.
1263 my ( $in, # handle to in stream
1264 $out, # handle to out stream
1265 $options, # options hash
1270 my ( $record, $file, $data_in, $entry, $num );
1272 while ( $record = get_record( $in ) ) {
1273 put_record( $record, $out );
1278 foreach $file ( @{ $options->{ "files" } } )
1280 $data_in = Maasha::Common::read_open( $file );
1282 while ( $entry = Maasha::Fasta::get_entry( $data_in ) )
1284 if ( defined $entry->[ SEQ_NAME ] and $entry->[ SEQ ] )
1287 SEQ_NAME => $entry->[ SEQ_NAME ],
1288 SEQ => $entry->[ SEQ ],
1289 SEQ_LEN => length $entry->[ SEQ ],
1292 put_record( $record, $out );
1295 goto NUM if $options->{ "num" } and $num == $options->{ "num" };
1305 close $data_in if $data_in;
1311 # Martin A. Hansen, August 2007.
1313 # Read table or table columns from stream or file.
1315 my ( $in, # handle to in stream
1316 $out, # handle to out stream
1317 $options, # options hash
1322 my ( $file, $line, @fields, @fields2, $i, $record, $data_in, $skip, $num );
1324 $options->{ 'delimit' } ||= '\s+';
1326 while ( $record = get_record( $in ) ) {
1327 put_record( $record, $out );
1330 $skip = $options->{ 'skip' } ||= 0;
1333 foreach $file ( @{ $options->{ "files" } } )
1335 $data_in = Maasha::Common::read_open( $file );
1337 while ( $line = <$data_in> )
1345 next if $line =~ /^#|^$/;
1352 @fields = split /$options->{'delimit'}/, $line;
1354 if ( $options->{ "cols" } ) {
1355 map { push @fields2, $fields[ $_ ] } @{ $options->{ "cols" } };
1360 for ( $i = 0; $i < @fields2; $i++ )
1362 if ( $options->{ "keys" }->[ $i ] ) {
1363 $record->{ $options->{ "keys" }->[ $i ] } = $fields2[ $i ];
1365 $record->{ "V" . $i } = $fields2[ $i ];
1369 put_record( $record, $out );
1371 goto NUM if $options->{ "num" } and $num == $options->{ "num" };
1381 close $data_in if $data_in;
1387 # Martin A. Hansen, August 2007.
1389 # Read psl table from stream or file.
1391 my ( $in, # handle to in stream
1392 $out, # handle to out stream
1393 $options, # options hash
1398 my ( $record, $file, $data_in, $num );
1400 while ( $record = get_record( $in ) ) {
1401 put_record( $record, $out );
1406 foreach $file ( @{ $options->{ "files" } } )
1408 $data_in = Maasha::Common::read_open( $file );
1410 while ( $record = Maasha::UCSC::psl_get_entry( $data_in ) )
1412 put_record( $record, $out );
1414 goto NUM if $options->{ "num" } and $num == $options->{ "num" };
1426 # Martin A. Hansen, August 2007.
1428 # Read bed table from stream or file.
1430 my ( $in, # handle to in stream
1431 $out, # handle to out stream
1432 $options, # options hash
1437 my ( $cols, $file, $record, $bed_entry, $data_in, $num );
1439 $cols = $options->{ 'cols' }->[ 0 ];
1441 while ( $record = get_record( $in ) ) {
1442 put_record( $record, $out );
1447 foreach $file ( @{ $options->{ "files" } } )
1449 $data_in = Maasha::Common::read_open( $file );
1451 while ( $bed_entry = Maasha::UCSC::BED::bed_entry_get( $data_in, $cols, 1 ) )
1453 $record = Maasha::UCSC::BED::bed2biopiece( $bed_entry );
1455 put_record( $record, $out );
1457 goto NUM if $options->{ "num" } and $num == $options->{ "num" };
1467 close $data_in if $data_in;
1471 sub script_read_fixedstep
1473 # Martin A. Hansen, Juli 2008.
1475 # Read fixedstep wiggle format from stream or file.
1477 my ( $in, # handle to in stream
1478 $out, # handle to out stream
1479 $options, # options hash
1484 my ( $file, $record, $entry, $data_in, $num );
1486 while ( $record = get_record( $in ) ) {
1487 put_record( $record, $out );
1492 foreach $file ( @{ $options->{ "files" } } )
1494 $data_in = Maasha::Common::read_open( $file );
1496 while ( $entry = Maasha::UCSC::Wiggle::fixedstep_entry_get( $data_in ) )
1498 $record = Maasha::UCSC::Wiggle::fixedstep2biopiece( $entry );
1500 put_record( $record, $out );
1502 goto NUM if $options->{ "num" } and $num == $options->{ "num" };
1512 close $data_in if $data_in;
1516 sub script_read_blast_tab
1518 # Martin A. Hansen, September 2007.
1520 # Read tabular BLAST output from NCBI blast run with -m8 or -m9.
1522 my ( $in, # handle to in stream
1523 $out, # handle to out stream
1524 $options, # options hash
1529 my ( $file, $line, @fields, $strand, $record, $data_in, $num );
1531 while ( $record = get_record( $in ) ) {
1532 put_record( $record, $out );
1537 foreach $file ( @{ $options->{ "files" } } )
1539 $data_in = Maasha::Common::read_open( $file );
1541 while ( $line = <$data_in> )
1545 next if $line =~ /^#/;
1547 @fields = split /\t/, $line;
1549 $record->{ "REC_TYPE" } = "BLAST";
1550 $record->{ "Q_ID" } = $fields[ 0 ];
1551 $record->{ "S_ID" } = $fields[ 1 ];
1552 $record->{ "IDENT" } = $fields[ 2 ];
1553 $record->{ "ALIGN_LEN" } = $fields[ 3 ];
1554 $record->{ "MISMATCHES" } = $fields[ 4 ];
1555 $record->{ "GAPS" } = $fields[ 5 ];
1556 $record->{ "Q_BEG" } = $fields[ 6 ] - 1; # BLAST is 1-based
1557 $record->{ "Q_END" } = $fields[ 7 ] - 1; # BLAST is 1-based
1558 $record->{ "S_BEG" } = $fields[ 8 ] - 1; # BLAST is 1-based
1559 $record->{ "S_END" } = $fields[ 9 ] - 1; # BLAST is 1-based
1560 $record->{ "E_VAL" } = $fields[ 10 ];
1561 $record->{ "BIT_SCORE" } = $fields[ 11 ];
1563 if ( $record->{ "S_BEG" } > $record->{ "S_END" } )
1565 $record->{ "STRAND" } = '-';
1567 ( $record->{ "S_BEG" }, $record->{ "S_END" } ) = ( $record->{ "S_END" }, $record->{ "S_BEG" } );
1571 $record->{ "STRAND" } = '+';
1574 put_record( $record, $out );
1576 goto NUM if $options->{ "num" } and $num == $options->{ "num" };
1586 close $data_in if $data_in;
1590 sub script_read_embl
1592 # Martin A. Hansen, August 2007.
1596 my ( $in, # handle to in stream
1597 $out, # handle to out stream
1598 $options, # options hash
1603 my ( %options2, $file, $data_in, $num, $entry, $record );
1605 map { $options2{ "keys" }{ $_ } = 1 } @{ $options->{ "keys" } };
1606 map { $options2{ "feats" }{ $_ } = 1 } @{ $options->{ "feats" } };
1607 map { $options2{ "quals" }{ $_ } = 1 } @{ $options->{ "quals" } };
1609 while ( $record = get_record( $in ) ) {
1610 put_record( $record, $out );
1615 foreach $file ( @{ $options->{ "files" } } )
1617 $data_in = Maasha::Common::read_open( $file );
1619 while ( $entry = Maasha::EMBL::get_embl_entry( $data_in ) )
1621 $record = Maasha::EMBL::parse_embl_entry( $entry, \%options2 );
1623 my ( $feat, $feat2, $qual, $qual_val, $record_copy );
1625 $record_copy = dclone $record;
1627 delete $record_copy->{ "FT" };
1629 put_record( $record_copy, $out );
1631 delete $record_copy->{ "SEQ" };
1633 foreach $feat ( keys %{ $record->{ "FT" } } )
1635 $record_copy->{ "FEAT_TYPE" } = $feat;
1637 foreach $feat2 ( @{ $record->{ "FT" }->{ $feat } } )
1639 foreach $qual ( keys %{ $feat2 } )
1641 $qual_val = join "; ", @{ $feat2->{ $qual } };
1646 $record_copy->{ $qual } = $qual_val;
1649 put_record( $record_copy, $out );
1653 goto NUM if $options->{ "num" } and $num == $options->{ "num" };
1663 close $data_in if $data_in;
1667 sub script_read_stockholm
1669 # Martin A. Hansen, August 2007.
1671 # Read Stockholm format.
1673 my ( $in, # handle to in stream
1674 $out, # handle to out stream
1675 $options, # options hash
1680 my ( $data_in, $file, $num, $entry, $record, $record_anno, $record_align, $key, $seq );
1682 while ( $record = get_record( $in ) ) {
1683 put_record( $record, $out );
1688 foreach $file ( @{ $options->{ "files" } } )
1690 $data_in = Maasha::Common::read_open( $file );
1692 while ( $entry = Maasha::Stockholm::get_stockholm_entry( $data_in ) )
1694 $record = Maasha::Stockholm::parse_stockholm_entry( $entry );
1698 foreach $key ( keys %{ $record->{ "GF" } } ) {
1699 $record_anno->{ $key } = $record->{ "GF" }->{ $key };
1702 $record_anno->{ "ALIGN" } = $num;
1704 put_record( $record_anno, $out );
1706 foreach $seq ( @{ $record->{ "ALIGN" } } )
1708 undef $record_align;
1711 SEQ_NAME => $seq->[ 0 ],
1715 put_record( $record_align, $out );
1718 goto NUM if $options->{ "num" } and $num == $options->{ "num" };
1728 close $data_in if $data_in;
1732 sub script_read_phastcons
1734 # Martin A. Hansen, December 2007.
1736 # Read PhastCons format.
1738 my ( $in, # handle to in stream
1739 $out, # handle to out stream
1740 $options, # options hash
1745 my ( $data_in, $file, $num, $entry, @records, $record );
1747 $options->{ "min" } ||= 10;
1748 $options->{ "dist" } ||= 25;
1749 $options->{ "threshold" } ||= 0.8;
1750 $options->{ "gap" } ||= 5;
1752 while ( $record = get_record( $in ) ) {
1753 put_record( $record, $out );
1758 foreach $file ( @{ $options->{ "files" } } )
1760 $data_in = Maasha::Common::read_open( $file );
1762 while ( $entry = Maasha::UCSC::fixedstep_get_entry( $data_in ) )
1764 @records = Maasha::UCSC::phastcons_parse_entry( $entry, $options );
1766 foreach $record ( @records )
1768 $record->{ "REC_TYPE" } = "BED";
1769 $record->{ "BED_LEN" } = $record->{ "CHR_END" } - $record->{ "CHR_BEG" } + 1;
1771 put_record( $record, $out );
1773 goto NUM if $options->{ "num" } and $num == $options->{ "num" };
1784 close $data_in if $data_in;
1788 sub script_read_soft
1790 # Martin A. Hansen, December 2007.
1793 # http://www.ncbi.nlm.nih.gov/geo/info/soft2.html
1795 my ( $in, # handle to in stream
1796 $out, # handle to out stream
1797 $options, # options hash
1802 my ( $data_in, $file, $num, $records, $record, $soft_index, $fh, @platforms, $plat_table, @samples, $sample, $old_end, $skip );
1804 while ( $record = get_record( $in ) ) {
1805 put_record( $record, $out );
1810 foreach $file ( @{ $options->{ "files" } } )
1812 print STDERR "Creating index for file: $file\n" if $options->{ "verbose" };
1814 $soft_index = Maasha::NCBI::soft_index_file( $file );
1816 $fh = Maasha::Common::read_open( $file );
1818 @platforms = grep { $_->{ "SECTION" } =~ /PLATFORM/ } @{ $soft_index };
1820 print STDERR "Getting platform tables for file: $file\n" if $options->{ "verbose" };
1822 $plat_table = Maasha::NCBI::soft_get_platform( $fh, $platforms[ 0 ]->{ "LINE_BEG" }, $platforms[ -1 ]->{ "LINE_END" } );
1824 @samples = grep { $_->{ "SECTION" } =~ /SAMPLE/ } @{ $soft_index };
1826 $old_end = $platforms[ -1 ]->{ "LINE_END" };
1828 foreach $sample ( @samples )
1831 $skip = 1 if ( $options->{ "samples" } and grep { $sample->{ "SECTION" } !~ /$_/ } @{ $options->{ "samples" } } );
1833 print STDERR "Getting samples for dataset: $sample->{ 'SECTION' }\n" if $options->{ "verbose" } and not $skip;
1835 $records = Maasha::NCBI::soft_get_sample( $fh, $plat_table, $sample->{ "LINE_BEG" } - $old_end - 1, $sample->{ "LINE_END" } - $old_end - 1, $skip );
1837 foreach $record ( @{ $records } )
1839 put_record( $record, $out );
1841 goto NUM if $options->{ "num" } and $num == $options->{ "num" };
1846 $old_end = $sample->{ "LINE_END" };
1854 close $data_in if $data_in;
1861 # Martin A. Hansen, February 2008.
1864 # http://www.ncbi.nlm.nih.gov/geo/info/soft2.html
1866 my ( $in, # handle to in stream
1867 $out, # handle to out stream
1868 $options, # options hash
1873 my ( $data_in, $file, $fh, $num, $record, $entry );
1875 while ( $record = get_record( $in ) ) {
1876 put_record( $record, $out );
1881 foreach $file ( @{ $options->{ "files" } } )
1883 $fh = Maasha::Common::read_open( $file );
1885 while ( $entry = Maasha::GFF::get_entry( $fh ) )
1887 put_record( $entry, $out );
1889 goto NUM if $options->{ "num" } and $num == $options->{ "num" };
1899 close $data_in if $data_in;
1903 sub script_read_2bit
1905 # Martin A. Hansen, March 2008.
1907 # Read sequences from 2bit file.
1909 my ( $in, # handle to in stream
1910 $out, # handle to out stream
1911 $options, # options hash
1916 my ( $record, $file, $data_in, $mask, $toc, $line, $num );
1918 $mask = 1 if not $options->{ "no_mask" };
1920 while ( $record = get_record( $in ) ) {
1921 put_record( $record, $out );
1926 foreach $file ( @{ $options->{ "files" } } )
1928 $data_in = Maasha::Common::read_open( $file );
1930 $toc = Maasha::TwoBit::twobit_get_TOC( $data_in );
1932 foreach $line ( @{ $toc } )
1934 $record->{ "SEQ_NAME" } = $line->[ 0 ];
1935 $record->{ "SEQ" } = Maasha::TwoBit::twobit_get_seq( $data_in, $line->[ 1 ], undef, undef, $mask );
1936 $record->{ "SEQ_LEN" } = length $record->{ "SEQ" };
1938 put_record( $record, $out );
1940 goto NUM if $options->{ "num" } and $num == $options->{ "num" };
1950 close $data_in if $data_in;
1954 sub script_read_solexa
1956 # Martin A. Hansen, March 2008.
1958 # Read Solexa sequence reads from file.
1960 my ( $in, # handle to in stream
1961 $out, # handle to out stream
1962 $options, # options hash
1967 my ( $record, $file, $data_in, $entry, $num, @seqs, @scores, $i );
1969 $options->{ "format" } ||= "octal";
1970 $options->{ "quality" } ||= 20;
1972 while ( $record = get_record( $in ) ) {
1973 put_record( $record, $out );
1978 foreach $file ( @{ $options->{ "files" } } )
1980 $data_in = Maasha::Common::read_open( $file );
1982 if ( $options->{ "format" } eq "octal" )
1984 while ( $entry = Maasha::Solexa::solexa_get_entry_octal( $data_in ) )
1986 $record = Maasha::Solexa::solexa2biopiece( $entry, $options->{ "quality" } );
1988 put_record( $record, $out );
1990 goto NUM if $options->{ "num" } and $num == $options->{ "num" };
1997 while ( $entry = Maasha::Solexa::solexa_get_entry_decimal( $data_in ) )
1999 $record = Maasha::Solexa::solexa2biopiece( $entry, $options->{ "quality" } );
2001 put_record( $record, $out );
2003 goto NUM if $options->{ "num" } and $num == $options->{ "num" };
2014 close $data_in if $data_in;
2018 sub script_read_solid
2020 # Martin A. Hansen, April 2008.
2022 # Read Solid sequence from file.
2024 my ( $in, # handle to in stream
2025 $out, # handle to out stream
2026 $options, # options hash
2031 my ( $record, $file, $data_in, $line, $num, $seq_name, $seq_cs, $seq_qual, @scores, @seqs, $i );
2033 $options->{ "quality" } ||= 15;
2035 while ( $record = get_record( $in ) ) {
2036 put_record( $record, $out );
2041 foreach $file ( @{ $options->{ "files" } } )
2043 $data_in = Maasha::Common::read_open( $file );
2045 while ( $line = <$data_in> )
2049 ( $seq_name, $seq_cs, $seq_qual ) = split /\t/, $line;
2051 @scores = split /,/, $seq_qual;
2052 @seqs = split //, Maasha::Solid::color_space2seq( $seq_cs );
2054 for ( $i = 0; $i < @seqs; $i++ ) {
2055 $seqs[ $i ] = lc $seqs[ $i ] if $scores[ $i ] < $options->{ "quality" };
2059 REC_TYPE => 'SOLID',
2060 SEQ_NAME => $seq_name,
2062 SEQ_QUAL => join( ";", @scores ),
2063 SEQ_LEN => length $seq_cs,
2064 SEQ => join( "", @seqs ),
2065 SCORE_MEAN => sprintf( "%.2f", Maasha::Calc::mean( \@scores ) ),
2068 put_record( $record, $out );
2070 goto NUM if $options->{ "num" } and $num == $options->{ "num" };
2080 close $data_in if $data_in;
2084 sub script_read_mysql
2086 # Martin A. Hansen, May 2008.
2088 # Read a MySQL query into stream.
2090 my ( $in, # handle to in stream
2091 $out, # handle to out stream
2092 $options, # options hash
2097 my ( $record, $dbh, $results );
2099 $options->{ "user" } ||= Maasha::UCSC::ucsc_get_user();
2100 $options->{ "password" } ||= Maasha::UCSC::ucsc_get_password();
2102 while ( $record = get_record( $in ) ) {
2103 put_record( $record, $out );
2106 $dbh = Maasha::SQL::connect( $options->{ "database" }, $options->{ "user" }, $options->{ "password" } );
2108 $results = Maasha::SQL::query_hashref_list( $dbh, $options->{ "query" } );
2110 Maasha::SQL::disconnect( $dbh );
2112 map { put_record( $_ ) } @{ $results };
2116 sub script_read_ucsc_config
2118 # Martin A. Hansen, November 2008.
2120 # Read track entries from UCSC Genome Browser '.ra' files.
2122 my ( $in, # handle to in stream
2123 $out, # handle to out stream
2124 $options, # options hash
2129 my ( $record, $file, $data_in, $entry, $num );
2131 while ( $record = get_record( $in ) ) {
2132 put_record( $record, $out );
2137 foreach $file ( @{ $options->{ "files" } } )
2139 $data_in = Maasha::Common::read_open( $file );
2141 while ( $record = Maasha::UCSC::ucsc_config_entry_get( $data_in ) )
2143 $record->{ 'REC_TYPE' } = "UCSC Config";
2145 put_record( $record, $out );
2147 goto NUM if $options->{ "num" } and $num == $options->{ "num" };
2157 close $data_in if $data_in;
2161 sub script_assemble_tag_contigs
2163 # Martin A. Hansen, November 2008.
2165 # Assemble tags from the stream into
2168 # The current implementation is quite
2169 # slow because of heavy use of temporary
2172 my ( $in, # handle to in stream
2173 $out, # handle to out stream
2174 $options, # options hash
2179 my ( $bed_file, $tag_file, $fh_in, $fh_out, $cols, $record, $bed_entry, $file_hash, $chr, $strand );
2181 $bed_file = "$BP_TMP/assemble_tag_contigs.bed";
2182 $fh_out = Maasha::Filesys::file_write_open( $bed_file );
2183 $cols = 6; # we only need the first 6 BED columns
2185 while ( $record = get_record( $in ) )
2187 if ( $bed_entry = Maasha::UCSC::BED::biopiece2bed( $record, $cols ) )
2189 $strand = $record->{ 'STRAND' } || '+';
2191 Maasha::UCSC::BED::bed_entry_put( $bed_entry, $fh_out, $cols, 1 );
2197 $file_hash = Maasha::UCSC::BED::bed_file_split_on_chr( $bed_file, $BP_TMP, $cols );
2201 foreach $chr ( sort keys %{ $file_hash } )
2203 $bed_file = $file_hash->{ $chr };
2204 $tag_file = "$bed_file.tc";
2206 Maasha::Common::run( "bed2tag_contigs", "< $bed_file > $tag_file" );
2208 $fh_in = Maasha::Filesys::file_read_open( $tag_file );
2210 while ( $bed_entry = Maasha::UCSC::BED::bed_entry_get( $fh_in, $cols ) )
2212 if ( $record = Maasha::UCSC::BED::bed2biopiece( $bed_entry ) ) {
2213 put_record( $record, $out );
2225 sub script_format_genome
2227 # Martin A. Hansen, Juli 2008.
2229 # Format a genome to speficed formats.
2231 my ( $in, # handle to in stream
2232 $out, # handle to out stream
2233 $options, # options hash
2238 my ( $dir, $genome, $fasta_dir, $phastcons_dir, $vals, $fh_out, $record, $format, $index, $entry );
2240 $dir = $options->{ 'dir' } || $ENV{ 'BP_DATA' };
2241 $genome = $options->{ 'genome' };
2243 Maasha::Common::error( "Directory: $dir does not exist" ) if not -d $dir;
2244 Maasha::Common::dir_create_if_not_exists( "$dir/genomes" );
2245 Maasha::Common::dir_create_if_not_exists( "$dir/genomes/$genome" );
2247 if ( grep { $_ =~ /fasta|blast|vmatch/i } @{ $options->{ "formats" } } )
2249 if ( -f "$dir/genomes/$genome/fasta/$genome.fna" )
2251 $fasta_dir = "$dir/genomes/$genome/fasta";
2255 Maasha::Common::dir_create_if_not_exists( "$dir/genomes/$genome/fasta" );
2257 $fasta_dir = "$dir/genomes/$genome/fasta";
2259 $fh_out = Maasha::Common::write_open( "$fasta_dir/$genome.fna" );
2262 elsif ( grep { $_ =~ /phastcons/i } @{ $options->{ "formats" } } )
2264 Maasha::Common::dir_create_if_not_exists( "$dir/genomes/$genome/phastcons" );
2266 $phastcons_dir = "$dir/genomes/$genome/phastcons";
2268 $fh_out = Maasha::Common::write_open( "$phastcons_dir/$genome.pp" );
2271 while ( $record = get_record( $in ) )
2273 if ( $fh_out and $entry = Maasha::Fasta::biopiece2fasta( $record ) )
2275 Maasha::Fasta::put_entry( $entry, $fh_out, $options->{ "wrap" } );
2277 elsif ( $fh_out and $record->{ "CHR" } and $record->{ "CHR_BEG" } and $record->{ "STEP" } and $record->{ "VALS" } )
2279 print $fh_out "fixedStep chrom=$record->{ 'CHR' } start=$record->{ 'CHR_BEG' } step=$record->{ 'STEP' }\n";
2281 $vals = $record->{ 'VALS' };
2285 print $fh_out "$vals\n";
2288 put_record( $record, $out ) if not $options->{ "no_stream" };
2291 foreach $format ( @{ $options->{ 'formats' } } )
2293 if ( $format =~ /^fasta$/i ) { Maasha::Fasta::fasta_index( "$fasta_dir/$genome.fna", "$dir/genomes/$genome/fasta/$genome.index" ) }
2294 elsif ( $format =~ /^blast$/i ) { Maasha::NCBI::blast_index( "$genome.fna", $fasta_dir, "$dir/genomes/$genome/blast", "dna", $genome ) }
2295 elsif ( $format =~ /^blat$/i ) { print STDERR "BLAT FORMAT NOT IMPLEMENTED" }
2296 elsif ( $format =~ /^vmatch$/i ) { Maasha::Match::vmatch_index( "$genome.fna", $fasta_dir, "$dir/genomes/$genome/vmatch", $BP_TMP ) }
2297 elsif ( $format =~ /^phastcons$/i ) { Maasha::UCSC::phastcons_index( "$genome.pp", $phastcons_dir ) }
2300 close $fh_out if $fh_out;
2304 sub script_length_seq
2306 # Martin A. Hansen, August 2007.
2308 # Determine the length of sequences in stream.
2310 my ( $in, # handle to in stream
2311 $out, # handle to out stream
2312 $options, # options hash
2317 my ( $record, $total );
2319 while ( $record = get_record( $in ) )
2321 if ( $record->{ "SEQ" } )
2323 $record->{ "SEQ_LEN" } = length $record->{ "SEQ" };
2324 $total += $record->{ "SEQ_LEN" };
2327 put_record( $record, $out ) if not $options->{ "no_stream" };
2330 put_record( { TOTAL_SEQ_LEN => $total }, $out );
2334 sub script_uppercase_seq
2336 # Martin A. Hansen, August 2007.
2338 # Uppercases sequences in stream.
2340 my ( $in, # handle to in stream
2341 $out, # handle to out stream
2348 while ( $record = get_record( $in ) )
2350 $record->{ "SEQ" } = uc $record->{ "SEQ" } if $record->{ "SEQ" };
2352 put_record( $record, $out );
2357 sub script_shuffle_seq
2359 # Martin A. Hansen, December 2007.
2361 # Shuffle sequences in stream.
2363 my ( $in, # handle to in stream
2364 $out, # handle to out stream
2371 while ( $record = get_record( $in ) )
2373 $record->{ "SEQ" } = Maasha::Seq::seq_shuffle( $record->{ "SEQ" } ) if $record->{ "SEQ" };
2375 put_record( $record, $out );
2380 sub script_analyze_seq
2382 # Martin A. Hansen, August 2007.
2384 # Analyze sequence composition of sequences in stream.
2386 my ( $in, # handle to in stream
2387 $out, # handle to out stream
2392 my ( $record, $analysis );
2394 while ( $record = get_record( $in ) )
2396 if ( $record->{ "SEQ" } )
2398 $analysis = Maasha::Seq::seq_analyze( $record->{ "SEQ" } );
2400 map { $record->{ $_ } = $analysis->{ $_ } } keys %{ $analysis };
2403 put_record( $record, $out );
2408 sub script_analyze_tags
2410 # Martin A. Hansen, August 2008.
2412 # Analyze sequence tags in stream.
2414 my ( $in, # handle to in stream
2415 $out, # handle to out stream
2420 my ( $record, $analysis, %len_hash, %clone_hash, $clones, $key, $tag_record );
2422 while ( $record = get_record( $in ) )
2424 if ( $record->{ "SEQ_NAME" } and $record->{ "SEQ" } )
2426 if ( $record->{ "SEQ_NAME" } =~ /_(\d+)$/ )
2430 $len_hash{ length( $record->{ "SEQ" } ) }++;
2431 $clone_hash{ length( $record->{ "SEQ" } ) } += $clones;
2434 elsif ( $record->{ "Q_ID" } and $record->{ "BED_LEN" } )
2436 if ( $record->{ "Q_ID" } =~ /_(\d+)$/ )
2440 $len_hash{ $record->{ "BED_LEN" } }++;
2441 $clone_hash{ $record->{ "BED_LEN" } } += $clones;
2446 foreach $key ( sort { $a <=> $b } keys %len_hash )
2448 $tag_record->{ "TAG_LEN" } = $key;
2449 $tag_record->{ "TAG_COUNT" } = $len_hash{ $key };
2450 $tag_record->{ "TAG_CLONES" } = $clone_hash{ $key };
2452 put_record( $tag_record, $out );
2457 sub script_complexity_seq
2459 # Martin A. Hansen, May 2008.
2461 # Generates an index calculated as the most common di-residue over
2462 # the sequence length for all sequences in stream.
2464 my ( $in, # handle to in stream
2465 $out, # handle to out stream
2470 my ( $record, $index );
2472 while ( $record = get_record( $in ) )
2474 $record->{ "SEQ_COMPLEXITY" } = sprintf( "%.2f", Maasha::Seq::seq_complexity( $record->{ "SEQ" } ) ) if $record->{ "SEQ" };
2476 put_record( $record, $out );
2481 sub script_oligo_freq
2483 # Martin A. Hansen, August 2007.
2485 # Determine the length of sequences in stream.
2487 my ( $in, # handle to in stream
2488 $out, # handle to out stream
2489 $options, # options hash
2494 my ( $record, %oligos, @freq_table );
2496 $options->{ "word_size" } ||= 7;
2498 while ( $record = get_record( $in ) )
2500 if ( $record->{ "SEQ" } )
2502 map { $oligos{ $_ }++ } Maasha::Seq::seq2oligos( \$record->{ "SEQ" }, $options->{ "word_size" } );
2504 if ( not $options->{ "all" } )
2506 @freq_table = Maasha::Seq::oligo_freq( \%oligos );
2508 map { put_record( $_, $out ) } @freq_table;
2514 put_record( $record, $out );
2517 if ( $options->{ "all" } )
2519 @freq_table = Maasha::Seq::oligo_freq( \%oligos );
2521 map { put_record( $_, $out ) } @freq_table;
2526 sub script_create_weight_matrix
2528 # Martin A. Hansen, August 2007.
2530 # Creates a weight matrix from an alignmnet.
2532 my ( $in, # handle to in stream
2533 $out, # handle to out stream
2534 $options, # options hash
2539 my ( $record, $count, $i, $res, %freq_hash, %res_hash, $freq );
2543 while ( $record = get_record( $in ) )
2545 if ( $record->{ "SEQ" } )
2547 for ( $i = 0; $i < length $record->{ "SEQ" }; $i++ )
2549 $res = substr $record->{ "SEQ" }, $i, 1;
2551 $freq_hash{ $i }{ $res }++;
2552 $res_hash{ $res } = 1;
2559 put_record( $record, $out );
2563 foreach $res ( sort keys %res_hash )
2567 $record->{ "V0" } = $res;
2569 for ( $i = 0; $i < keys %freq_hash; $i++ )
2571 $freq = $freq_hash{ $i }{ $res } || 0;
2573 if ( $options->{ "percent" } ) {
2574 $freq = sprintf( "%.0f", 100 * $freq / $count ) if $freq > 0;
2577 $record->{ "V" . ( $i + 1 ) } = $freq;
2580 put_record( $record, $out );
2585 sub script_calc_bit_scores
2587 # Martin A. Hansen, March 2007.
2589 # Calculates the bit scores for each position from an alignmnet in the stream.
2591 my ( $in, # handle to in stream
2592 $out, # handle to out stream
2597 my ( $record, $type, $count, $i, $res, %freq_hash, $bit_max, $bit_height, $bit_diff );
2601 while ( $record = get_record( $in ) )
2603 if ( $record->{ "SEQ" } )
2605 $type = Maasha::Seq::seq_guess_type( $record->{ "SEQ" } ) if not $type;
2607 for ( $i = 0; $i < length $record->{ "SEQ" }; $i++ )
2609 $res = substr $record->{ "SEQ" }, $i, 1;
2611 next if $res =~ /-|_|~|\./;
2613 $freq_hash{ $i }{ $res }++;
2620 put_record( $record, $out );
2626 if ( $type eq "protein" ) {
2632 for ( $i = 0; $i < keys %freq_hash; $i++ )
2634 $bit_height = Maasha::Seq::seqlogo_calc_bit_height( $freq_hash{ $i }, $count );
2636 $bit_diff = $bit_max - $bit_height;
2638 $record->{ "V" . ( $i ) } = sprintf( "%.2f", $bit_diff );
2641 put_record( $record, $out );
2645 sub script_calc_fixedstep
2647 # Martin A. Hansen, September 2008.
2649 # Calculates fixedstep entries from data in the stream.
2651 my ( $in, # handle to in stream
2652 $out, # handle to out stream
2653 $options, # options hash
2658 my ( $bed_file, $fh_in, $fh_out, $cols, $record, $file_hash, $chr, $bed_entry, $fixedstep_file, $fixedstep_entry );
2660 $bed_file = "$BP_TMP/calc_fixedstep.bed";
2661 $fh_out = Maasha::Filesys::file_write_open( $bed_file );
2662 $cols = 5; # we only need the first 5 BED columns
2664 while ( $record = get_record( $in ) )
2666 if ( $bed_entry = Maasha::UCSC::BED::biopiece2bed( $record, $cols ) ) {
2667 Maasha::UCSC::BED::bed_entry_put( $bed_entry, $fh_out, $cols, 1 );
2673 $file_hash = Maasha::UCSC::BED::bed_file_split_on_chr( $bed_file, $BP_TMP, $cols );
2677 foreach $chr ( sort keys %{ $file_hash } )
2679 $bed_file = $file_hash->{ $chr };
2680 $fixedstep_file = "$bed_file.fixedstep";
2682 Maasha::Common::run( "bed2fixedstep", "< $bed_file > $fixedstep_file" );
2684 $fh_in = Maasha::Filesys::file_read_open( $fixedstep_file );
2686 while ( $fixedstep_entry = Maasha::UCSC::Wiggle::fixedstep_entry_get( $fh_in ) )
2688 if ( $record = Maasha::UCSC::Wiggle::fixedstep2biopiece( $fixedstep_entry ) ) {
2689 put_record( $record, $out );
2696 unlink $fixedstep_file;
2701 sub script_reverse_seq
2703 # Martin A. Hansen, August 2007.
2705 # Reverse sequence in record.
2707 my ( $in, # handle to in stream
2708 $out, # handle to out stream
2715 while ( $record = get_record( $in ) )
2717 if ( $record->{ "SEQ" } ) {
2718 $record->{ "SEQ" } = reverse $record->{ "SEQ" };
2721 put_record( $record, $out );
2726 sub script_complement_seq
2728 # Martin A. Hansen, August 2007.
2730 # Complement sequence in record.
2732 my ( $in, # handle to in stream
2733 $out, # handle to out stream
2738 my ( $record, $type );
2740 while ( $record = get_record( $in ) )
2742 if ( $record->{ "SEQ" } )
2745 $type = Maasha::Seq::seq_guess_type( $record->{ "SEQ" } );
2748 if ( $type eq "rna" ) {
2749 Maasha::Seq::rna_comp( \$record->{ "SEQ" } );
2750 } elsif ( $type eq "dna" ) {
2751 Maasha::Seq::dna_comp( \$record->{ "SEQ" } );
2755 put_record( $record, $out );
2760 sub script_remove_indels
2762 # Martin A. Hansen, August 2007.
2764 # Remove indels from sequences in stream.
2766 my ( $in, # handle to in stream
2767 $out, # handle to out stream
2774 while ( $record = get_record( $in ) )
2776 $record->{ 'SEQ' } =~ tr/-~.//d if $record->{ "SEQ" };
2778 put_record( $record, $out );
2783 sub script_transliterate_seq
2785 # Martin A. Hansen, August 2007.
2787 # Transliterate chars from sequence in record.
2789 my ( $in, # handle to in stream
2790 $out, # handle to out stream
2791 $options, # options hash
2796 my ( $record, $search, $replace, $delete );
2798 $search = $options->{ "search" } || "";
2799 $replace = $options->{ "replace" } || "";
2800 $delete = $options->{ "delete" } || "";
2802 while ( $record = get_record( $in ) )
2804 if ( $record->{ "SEQ" } )
2806 if ( $search and $replace ) {
2807 eval "\$record->{ 'SEQ' } =~ tr/$search/$replace/";
2808 } elsif ( $delete ) {
2809 eval "\$record->{ 'SEQ' } =~ tr/$delete//d";
2813 put_record( $record, $out );
2818 sub script_transliterate_vals
2820 # Martin A. Hansen, April 2008.
2822 # Transliterate chars from values in record.
2824 my ( $in, # handle to in stream
2825 $out, # handle to out stream
2826 $options, # options hash
2831 my ( $record, $search, $replace, $delete, $key );
2833 $search = $options->{ "search" } || "";
2834 $replace = $options->{ "replace" } || "";
2835 $delete = $options->{ "delete" } || "";
2837 while ( $record = get_record( $in ) )
2839 foreach $key ( @{ $options->{ "keys" } } )
2841 if ( exists $record->{ $key } )
2843 if ( $search and $replace ) {
2844 eval "\$record->{ $key } =~ tr/$search/$replace/";
2845 } elsif ( $delete ) {
2846 eval "\$record->{ $key } =~ tr/$delete//d";
2851 put_record( $record, $out );
2856 sub script_translate_seq
2858 # Martin A. Hansen, February 2008.
2860 # Translate DNA sequence into protein sequence.
2862 my ( $in, # handle to in stream
2863 $out, # handle to out stream
2864 $options, # options hash
2869 my ( $record, $frame, %new_record );
2871 $options->{ "frames" } ||= [ 1, 2, 3, -1, -2, -3 ];
2873 while ( $record = get_record( $in ) )
2875 if ( $record->{ "SEQ" } )
2877 if ( Maasha::Seq::seq_guess_type( $record->{ "SEQ" } ) eq "dna" )
2879 foreach $frame ( @{ $options->{ "frames" } } )
2881 %new_record = %{ $record };
2883 $new_record{ "SEQ" } = Maasha::Seq::translate( $record->{ "SEQ" }, $frame );
2884 $new_record{ "SEQ_LEN" } = length $new_record{ "SEQ" };
2885 $new_record{ "FRAME" } = $frame;
2887 put_record( \%new_record, $out );
2893 put_record( $record, $out );
2899 sub script_extract_seq
2901 # Martin A. Hansen, August 2007.
2903 # Extract subsequences from sequences in record.
2905 my ( $in, # handle to in stream
2906 $out, # handle to out stream
2907 $options, # options hash
2912 my ( $beg, $end, $len, $record );
2914 if ( not defined $options->{ "beg" } or $options->{ "beg" } < 0 ) {
2917 $beg = $options->{ "beg" } - 1; # correcting for start offset
2920 if ( defined $options->{ "end" } and $options->{ "end" } - 1 < $beg ) {
2922 } elsif ( defined $options->{ "end" } ) {
2923 $end = $options->{ "end" } - 1; # correcting for start offset
2926 $len = $options->{ "len" };
2928 # print "beg->$beg, end->$end, len->$len\n";
2930 while ( $record = get_record( $in ) )
2932 if ( $record->{ "SEQ" } )
2934 if ( defined $beg and defined $end )
2936 if ( $end - $beg + 1 > length $record->{ "SEQ" } ) {
2937 $record->{ "SEQ" } = substr $record->{ "SEQ" }, $beg;
2939 $record->{ "SEQ" } = substr $record->{ "SEQ" }, $beg, $end - $beg + 1;
2942 elsif ( defined $beg and defined $len )
2944 if ( $len > length $record->{ "SEQ" } ) {
2945 $record->{ "SEQ" } = substr $record->{ "SEQ" }, $beg;
2947 $record->{ "SEQ" } = substr $record->{ "SEQ" }, $beg, $len;
2950 elsif ( defined $beg )
2952 $record->{ "SEQ" } = substr $record->{ "SEQ" }, $beg;
2956 $record->{ "SEQ_LEN" } = length $record->{ "SEQ" };
2958 put_record( $record, $out );
2963 sub script_get_genome_seq
2965 # Martin A. Hansen, December 2007.
2967 # Gets a subsequence from a genome.
2969 my ( $in, # handle to in stream
2970 $out, # handle to out stream
2971 $options, # options hash
2976 my ( $record, $genome, $genome_file, $index_file, $index, $fh, $index_head, $index_beg, $index_len, $beg, $len, %lookup_hash, @begs, @lens, $i );
2978 $options->{ "flank" } ||= 0;
2980 if ( $options->{ "genome" } )
2982 $genome = $options->{ "genome" };
2984 $genome_file = "$ENV{ 'BP_DATA' }/genomes/$genome/fasta/$genome.fna";
2985 $index_file = "$ENV{ 'BP_DATA' }/genomes/$genome/fasta/$genome.index";
2987 $fh = Maasha::Common::read_open( $genome_file );
2988 $index = Maasha::Fasta::index_retrieve( $index_file );
2990 shift @{ $index }; # Get rid of the file size info
2992 map { $lookup_hash{ $_->[ 0 ] } = [ $_->[ 1 ], $_->[ 2 ] ] } @{ $index };
2994 if ( exists $lookup_hash{ $options->{ "chr" } } and defined $options->{ "beg" } and ( defined $options->{ "end" } or defined $options->{ "len" } ) )
2996 ( $index_beg, $index_len ) = @{ $lookup_hash{ $options->{ "chr" } } };
2998 $beg = $index_beg + $options->{ "beg" } - 1;
3000 if ( $options->{ "len" } ) {
3001 $len = $options->{ "len" };
3002 } elsif ( $options->{ "end" } ) {
3003 $len = ( $options->{ "end" } - $options->{ "beg" } + 1 );
3006 $beg -= $options->{ "flank" };
3007 $len += 2 * $options->{ "flank" };
3009 if ( $beg <= $index_beg )
3011 $len -= $index_beg - $beg;
3015 $len = $index_beg + $index_len - $beg if $beg + $len > $index_beg + $index_len;
3017 next if $beg > $index_beg + $index_len;
3019 $record->{ "CHR" } = $options->{ "chr" };
3020 $record->{ "CHR_BEG" } = $beg - $index_beg;
3021 $record->{ "CHR_END" } = $record->{ "CHR_BEG" } + $len - 1;
3023 $record->{ "SEQ" } = Maasha::Common::file_read( $fh, $beg, $len );
3024 $record->{ "SEQ_LEN" } = $len;
3026 put_record( $record, $out );
3030 while ( $record = get_record( $in ) )
3032 if ( $options->{ "genome" } and not $record->{ "SEQ" } )
3034 if ( $record->{ "REC_TYPE" } eq "BED" and exists $lookup_hash{ $record->{ "CHR" } } )
3036 ( $index_beg, $index_len ) = @{ $lookup_hash{ $record->{ "CHR" } } };
3038 $beg = $record->{ "CHR_BEG" } + $index_beg;
3039 $len = $record->{ "CHR_END" } - $record->{ "CHR_BEG" } + 1;
3041 elsif ( $record->{ "REC_TYPE" } eq "PSL" and exists $lookup_hash{ $record->{ "S_ID" } } )
3043 ( $index_beg, $index_len ) = @{ $lookup_hash{ $record->{ "S_ID" } } };
3045 $beg = $record->{ "S_BEG" } + $index_beg;
3046 $len = $record->{ "S_END" } - $record->{ "S_BEG" } + 1;
3048 elsif ( $record->{ "REC_TYPE" } eq "BLAST" and exists $lookup_hash{ $record->{ "S_ID" } } )
3050 ( $index_beg, $index_len ) = @{ $lookup_hash{ $record->{ "S_ID" } } };
3052 $beg = $record->{ "S_BEG" } + $index_beg;
3053 $len = $record->{ "S_END" } - $record->{ "S_BEG" } + 1;
3056 $beg -= $options->{ "flank" };
3057 $len += 2 * $options->{ "flank" };
3059 if ( $beg <= $index_beg )
3061 $len -= $index_beg - $beg;
3065 $len = $index_beg + $index_len - $beg if $beg + $len > $index_beg + $index_len;
3067 next if $beg > $index_beg + $index_len;
3069 $record->{ "CHR_BEG" } = $beg - $index_beg;
3070 $record->{ "CHR_END" } = $record->{ "CHR_BEG" } + $len - 1;
3072 $record->{ "SEQ" } = Maasha::Common::file_read( $fh, $beg, $len );
3074 if ( $record->{ "STRAND" } and $record->{ "STRAND" } eq "-" )
3076 Maasha::Seq::dna_comp( \$record->{ "SEQ" } );
3077 $record->{ "SEQ" } = reverse $record->{ "SEQ" };
3080 if ( $options->{ "mask" } )
3082 if ( $record->{ "BLOCKCOUNT" } > 1 ) # uppercase hit block segments and lowercase the rest.
3084 $record->{ "SEQ" } = lc $record->{ "SEQ" };
3086 @begs = split ",", $record->{ "Q_BEGS" };
3087 @lens = split ",", $record->{ "BLOCKSIZES" };
3089 for ( $i = 0; $i < @begs; $i++ ) {
3090 substr $record->{ "SEQ" }, $begs[ $i ], $lens[ $i ], uc substr $record->{ "SEQ" }, $begs[ $i ], $lens[ $i ];
3096 put_record( $record, $out );
3103 sub script_get_genome_align
3105 # Martin A. Hansen, April 2008.
3107 # Gets a subalignment from a multiple genome alignment.
3109 my ( $in, # handle to in stream
3110 $out, # handle to out stream
3111 $options, # options hash
3116 my ( $record, $maf_track, $align, $align_num, $beg, $end, $len, $entry );
3118 $options->{ "strand" } ||= "+";
3122 $maf_track = Maasha::Config::maf_track( $options->{ "genome" } );
3124 if ( $options->{ "chr" } and $options->{ "beg" } and ( $options->{ "end" } or $options->{ "len" } ) )
3126 $beg = $options->{ "beg" } - 1;
3128 if ( $options->{ "end" } ) {
3129 $end = $options->{ "end" };
3130 } elsif ( $options->{ "len" } ) {
3131 $end = $beg + $options->{ "len" };
3134 $align = Maasha::UCSC::maf_extract( $BP_TMP, $options->{ "genome" }, $maf_track, $options->{ "chr" }, $beg, $end, $options->{ "strand" } );
3136 foreach $entry ( @{ $align } )
3138 $entry->{ "CHR" } = $record->{ "CHR" };
3139 $entry->{ "CHR_BEG" } = $record->{ "CHR_BEG" };
3140 $entry->{ "CHR_END" } = $record->{ "CHR_END" };
3141 $entry->{ "STRAND" } = $record->{ "STRAND" } || '+';
3142 $entry->{ "Q_ID" } = $record->{ "Q_ID" };
3143 $entry->{ "SCORE" } = $record->{ "SCORE" };
3145 put_record( $entry, $out );
3149 while ( $record = get_record( $in ) )
3151 if ( $record->{ "REC_TYPE" } eq "BED" )
3153 $align = Maasha::UCSC::maf_extract( $BP_TMP, $options->{ "genome" }, $maf_track, $record->{ "CHR" }, $record->{ "CHR_BEG" }, $record->{ "CHR_END" }, $record->{ "STRAND" } );
3155 elsif ( $record->{ "REC_TYPE" } eq "VMATCH" )
3157 $align = Maasha::UCSC::maf_extract( $BP_TMP, $options->{ "genome" }, $maf_track, $record->{ "S_ID" }, $record->{ "S_BEG" }, $record->{ "S_END" } + 1, $record->{ "STRAND" } );
3159 elsif ( $record->{ "REC_TYPE" } eq "PSL" )
3161 $align = Maasha::UCSC::maf_extract( $BP_TMP, $options->{ "genome" }, $maf_track, $record->{ "S_ID" }, $record->{ "S_BEG" }, $record->{ "S_END" }, $record->{ "STRAND" } );
3163 elsif ( $record->{ "REC_TYPE" } eq "BLAST" )
3165 $align = Maasha::UCSC::maf_extract( $BP_TMP, $options->{ "genome" }, $maf_track, $record->{ "S_ID" }, $record->{ "S_BEG" }, $record->{ "S_END" }, $record->{ "STRAND" } );
3168 foreach $entry ( @{ $align } )
3170 $entry->{ "CHR" } = $record->{ "CHR" };
3171 $entry->{ "CHR_BEG" } = $record->{ "CHR_BEG" };
3172 $entry->{ "CHR_END" } = $record->{ "CHR_END" };
3173 $entry->{ "STRAND" } = $record->{ "STRAND" };
3174 $entry->{ "Q_ID" } = $record->{ "Q_ID" };
3175 $entry->{ "SCORE" } = $record->{ "SCORE" };
3177 put_record( $entry, $out );
3185 sub script_get_genome_phastcons
3187 # Martin A. Hansen, February 2008.
3189 # Get phastcons scores from genome intervals.
3191 my ( $in, # handle to in stream
3192 $out, # handle to out stream
3193 $options, # options hash
3198 my ( $phastcons_file, $phastcons_index, $index, $fh_phastcons, $scores, $record );
3200 $options->{ "flank" } ||= 0;
3202 $phastcons_file = Maasha::Config::genome_phastcons( $options->{ "genome" } );
3203 $phastcons_index = Maasha::Config::genome_phastcons_index( $options->{ "genome" } );
3205 $index = Maasha::UCSC::fixedstep_index_retrieve( $phastcons_index );
3206 $fh_phastcons = Maasha::Common::read_open( $phastcons_file );
3208 if ( defined $options->{ "chr" } and defined $options->{ "beg" } and ( defined $options->{ "end" } or defined $options->{ "len" } ) )
3210 $options->{ "beg" } -= 1; # request is 1-based
3211 $options->{ "end" } -= 1; # request is 1-based
3213 if ( $options->{ "len" } ) {
3214 $options->{ "end" } = $options->{ "beg" } + $options->{ "len" } - 1;
3217 $scores = Maasha::UCSC::fixedstep_index_lookup( $index, $fh_phastcons, $options->{ "chr" }, $options->{ "beg" }, $options->{ "end" }, $options->{ "flank" } );
3219 $record->{ "CHR" } = $options->{ "chr" };
3220 $record->{ "CHR_BEG" } = $options->{ "beg" } - $options->{ "flank" };
3221 $record->{ "CHR_END" } = $options->{ "end" } + $options->{ "flank" };
3223 $record->{ "PHASTCONS" } = join ",", @{ $scores };
3224 $record->{ "PHAST_COUNT" } = scalar @{ $scores }; # DEBUG
3226 put_record( $record, $out );
3229 while ( $record = get_record( $in ) )
3231 if ( $record->{ "REC_TYPE" } eq "BED" )
3233 $scores = Maasha::UCSC::fixedstep_index_lookup( $index, $fh_phastcons, $record->{ "CHR" }, $record->{ "CHR_BEG" }, $record->{ "CHR_END" }, $options->{ "flank" } );
3235 elsif ( $record->{ "REC_TYPE" } eq "PSL" )
3237 $scores = Maasha::UCSC::fixedstep_index_lookup( $index, $fh_phastcons, $record->{ "S_ID" }, $record->{ "S_BEG" }, $record->{ "S_END" }, $options->{ "flank" } );
3239 elsif ( $record->{ "REC_TYPE" } eq "BLAST" )
3241 $scores = Maasha::UCSC::fixedstep_index_lookup( $index, $fh_phastcons, $record->{ "S_ID" }, $record->{ "S_BEG" }, $record->{ "S_END" }, $options->{ "flank" } );
3244 $record->{ "PHASTCONS" } = join ",", @{ $scores } if @{ $scores };
3245 # $record->{ "PHAST_COUNT" } = @{ $scores } if @{ $scores }; # DEBUG
3247 put_record( $record, $out );
3250 close $fh_phastcons if $fh_phastcons;
3256 # Martin A. Hansen, December 2007.
3258 # Folds sequences in stream into secondary structures.
3260 my ( $in, # handle to in stream
3261 $out, # handle to out stream
3266 my ( $record, $type, $struct, $index );
3268 while ( $record = get_record( $in ) )
3270 if ( $record->{ "SEQ" } )
3273 $type = Maasha::Seq::seq_guess_type( $record->{ "SEQ" } );
3276 if ( $type ne "protein" )
3278 ( $struct, $index ) = Maasha::Seq::fold_struct_rnafold( $record->{ "SEQ" } );
3279 $record->{ "SEC_STRUCT" } = $struct;
3280 $record->{ "FREE_ENERGY" } = $index;
3281 $record->{ "SCORE" } = abs int $index;
3282 $record->{ "SIZE" } = length $struct;
3283 $record->{ "CONF" } = "1," x $record->{ "SIZE" };
3287 put_record( $record, $out );
3292 sub script_split_seq
3294 # Martin A. Hansen, August 2007.
3296 # Split a sequence in stream into words.
3298 my ( $in, # handle to in stream
3299 $out, # handle to out stream
3300 $options, # options hash
3305 my ( $record, $new_record, $i, $subseq, %lookup );
3307 $options->{ "word_size" } ||= 7;
3309 while ( $record = get_record( $in ) )
3311 if ( $record->{ "SEQ_NAME" } and $record->{ "SEQ" } )
3313 for ( $i = 0; $i < length( $record->{ "SEQ" } ) - $options->{ "word_size" } + 1; $i++ )
3315 $subseq = substr $record->{ "SEQ" }, $i, $options->{ "word_size" };
3317 if ( $options->{ "uniq" } and not $lookup{ $subseq } )
3319 $new_record->{ "SEQ_NAME" } = $record->{ "SEQ_NAME" } . "[" . ( $i + 1 ) . "-" . ( $i + $options->{ "word_size" } ) . "]";
3320 $new_record->{ "SEQ" } = $subseq;
3322 put_record( $new_record, $out );
3324 $lookup{ $subseq } = 1;
3328 $new_record->{ "SEQ_NAME" } = $record->{ "SEQ_NAME" } . "[" . ( $i + 1 ) . "-" . ( $i + $options->{ "word_size" } ) . "]";
3329 $new_record->{ "SEQ" } = $subseq;
3331 put_record( $new_record, $out );
3337 put_record( $record, $out );
3343 sub script_split_bed
3345 # Martin A. Hansen, June 2008.
3347 # Split a BED record into overlapping windows.
3349 my ( $in, # handle to in stream
3350 $out, # handle to out stream
3351 $options, # options hash
3356 my ( $record, $new_record, $i );
3358 $options->{ "window_size" } ||= 20;
3359 $options->{ "step_size" } ||= 1;
3361 while ( $record = get_record( $in ) )
3363 if ( $record->{ "CHR" } and $record->{ "CHR_BEG" } and $record->{ "CHR_END" } )
3365 $record->{ "BED_LEN" } = $record->{ "CHR_END" } - $record->{ "CHR_BEG" } + 1;
3367 for ( $i = 0; $i < $record->{ "BED_LEN" } - $options->{ "window_size" }; $i += $options->{ "step_size" } )
3369 $new_record->{ "REC_TYPE" } = "BED";
3370 $new_record->{ "CHR" } = $record->{ "CHR" };
3371 $new_record->{ "CHR_BEG" } = $record->{ "CHR_BEG" } + $i;
3372 $new_record->{ "CHR_END" } = $record->{ "CHR_BEG" } + $i + $options->{ "window_size" };
3373 $new_record->{ "BED_LEN" } = $options->{ "window_size" };
3374 $new_record->{ "Q_ID" } = $record->{ "Q_ID" } . "_$i";
3375 $new_record->{ "SCORE" } = $record->{ "SCORE" };
3376 $new_record->{ "STRAND" } = $record->{ "STRAND" };
3378 put_record( $new_record, $out );
3383 put_record( $record, $out );
3389 sub script_align_seq
3391 # Martin A. Hansen, August 2007.
3393 # Align sequences in stream.
3395 my ( $in, # handle to in stream
3396 $out, # handle to out stream
3401 my ( $record, @entries, $entry );
3403 while ( $record = get_record( $in ) )
3405 if ( $record->{ "SEQ_NAME" } and $record->{ "SEQ" } ) {
3406 push @entries, [ $record->{ "SEQ_NAME" }, $record->{ "SEQ" } ];
3407 } elsif ( $record->{ "Q_ID" } and $record->{ "SEQ" } ) {
3408 push @entries, [ $record->{ "Q_ID" }, $record->{ "SEQ" } ];
3410 put_record( $record, $out );
3414 @entries = Maasha::Align::align( \@entries );
3416 foreach $entry ( @entries )
3418 if ( $entry->[ SEQ_NAME ] and $entry->[ SEQ ] )
3421 SEQ_NAME => $entry->[ SEQ_NAME ],
3422 SEQ => $entry->[ SEQ ],
3425 put_record( $record, $out );
3433 # Martin A. Hansen, February 2008.
3435 # Using the first sequence in stream as reference, tile
3436 # all subsequent sequences based on pairwise alignments.
3438 my ( $in, # handle to in stream
3439 $out, # handle to out stream
3440 $options, # options hash
3445 my ( $record, $first, $ref_entry, @entries );
3449 while ( $record = get_record( $in ) )
3451 if ( $record->{ "SEQ_NAME" } and $record->{ "SEQ" } )
3455 $ref_entry = [ $record->{ "SEQ_NAME" }, $record->{ "SEQ" } ];
3461 push @entries, [ $record->{ "SEQ_NAME" }, $record->{ "SEQ" } ];
3466 put_record( $record, $out );
3470 @entries = Maasha::Align::align_tile( $ref_entry, \@entries, $options );
3472 map { put_record( { SEQ_NAME => $_->[ SEQ_NAME ], SEQ => $_->[ SEQ ] }, $out ) } @entries;
3476 sub script_invert_align
3478 # Martin A. Hansen, February 2008.
3480 # Inverts an alignment showing only non-mathing residues
3481 # using the first sequence as reference.
3483 my ( $in, # handle to in stream
3484 $out, # handle to out stream
3485 $options, # options hash
3490 my ( $record, @entries );
3492 while ( $record = get_record( $in ) )
3494 if ( $record->{ "SEQ_NAME" } and $record->{ "SEQ" } )
3496 push @entries, [ $record->{ "SEQ_NAME" }, $record->{ "SEQ" } ];
3500 put_record( $record, $out );
3504 Maasha::Align::align_invert( \@entries, $options->{ "soft" } );
3506 map { put_record( { SEQ_NAME => $_->[ SEQ_NAME ], SEQ => $_->[ SEQ ] }, $out ) } @entries;
3510 sub script_patscan_seq
3512 # Martin A. Hansen, August 2007.
3514 # Locates patterns in sequences using scan_for_matches.
3516 my ( $in, # handle to in stream
3517 $out, # handle to out stream
3518 $options, # options hash
3523 my ( $genome_file, @args, $arg, $type, $seq_file, $pat_file, $out_file, $fh_in, $fh_out, $record, $patterns, $pattern, $entry, $result, %head_hash, $i );
3525 if ( $options->{ "patterns" } ) {
3526 $patterns = Maasha::Patscan::parse_patterns( $options->{ "patterns" } );
3527 } elsif ( -f $options->{ "patterns_in" } ) {
3528 $patterns = Maasha::Patscan::read_patterns( $options->{ "patterns_in" } );
3531 $genome_file = "$ENV{ 'BP_DATA' }/genomes/$options->{ 'genome' }/fasta/$options->{ 'genome' }.fna" if $options->{ 'genome' };
3533 push @args, "-c" if $options->{ "comp" };
3534 push @args, "-m $options->{ 'max_hits' }" if $options->{ 'max_hits' };
3535 push @args, "-n $options->{ 'max_misses' }" if $options->{ 'max_hits' };
3537 $seq_file = "$BP_TMP/patscan.seq";
3538 $pat_file = "$BP_TMP/patscan.pat";
3539 $out_file = "$BP_TMP/patscan.out";
3541 $fh_out = Maasha::Common::write_open( $seq_file );
3545 while ( $record = get_record( $in ) )
3547 if ( $record->{ "SEQ" } and $record->{ "SEQ_NAME" } )
3549 $type = Maasha::Seq::seq_guess_type( $record->{ "SEQ" } ) if not $type;
3551 Maasha::Fasta::put_entry( [ $i, $record->{ "SEQ" } ], $fh_out );
3553 $head_hash{ $i } = $record->{ "SEQ_NAME" };
3561 $arg = join " ", @args;
3562 $arg .= " -p" if $type eq "protein";
3564 foreach $pattern ( @{ $patterns } )
3566 $fh_out = Maasha::Common::write_open( $pat_file );
3568 print $fh_out "$pattern\n";
3572 if ( $options->{ 'genome' } ) {
3573 `scan_for_matches $arg $pat_file < $genome_file > $out_file`;
3574 # Maasha::Common::run( "scan_for_matches", "$arg $pat_file < $genome_file > $out_file" );
3576 `scan_for_matches $arg $pat_file < $seq_file > $out_file`;
3577 # Maasha::Common::run( "scan_for_matches", "$arg $pat_file < $seq_file > $out_file" );
3580 $fh_in = Maasha::Common::read_open( $out_file );
3582 while ( $entry = Maasha::Fasta::get_entry( $fh_in ) )
3584 $result = Maasha::Patscan::parse_scan_result( $entry, $pattern );
3586 if ( $options->{ 'genome' } )
3588 $result->{ "CHR" } = $result->{ "S_ID" };
3589 $result->{ "CHR_BEG" } = $result->{ "S_BEG" };
3590 $result->{ "CHR_END" } = $result->{ "S_END" };
3592 delete $result->{ "S_ID" };
3593 delete $result->{ "S_BEG" };
3594 delete $result->{ "S_END" };
3598 $result->{ "S_ID" } = $head_hash{ $result->{ "S_ID" } };
3601 put_record( $result, $out );
3613 sub script_create_blast_db
3615 # Martin A. Hansen, September 2007.
3617 # Creates a NCBI BLAST database with formatdb
3619 my ( $in, # handle to in stream
3620 $out, # handle to out stream
3621 $options, # options hash
3626 my ( $fh, $seq_type, $path, $record, $entry );
3628 $path = $options->{ "database" };
3630 $fh = Maasha::Common::write_open( $path );
3632 while ( $record = get_record( $in ) )
3634 put_record( $record, $out ) if not $options->{ "no_stream" };
3636 if ( $entry = Maasha::Fasta::biopiece2fasta( $record ) )
3638 $seq_type = Maasha::Seq::seq_guess_type( $entry->[ SEQ ] ) if not $seq_type;
3640 Maasha::Fasta::put_entry( $entry, $fh );
3646 if ( $seq_type eq "protein" ) {
3647 Maasha::Common::run( "formatdb", "-p T -i $path -t $options->{ 'database' }" );
3649 Maasha::Common::run( "formatdb", "-p F -i $path -t $options->{ 'database' }" );
3656 sub script_blast_seq
3658 # Martin A. Hansen, September 2007.
3660 # BLASTs sequences in stream against a given database.
3662 my ( $in, # handle to in stream
3663 $out, # handle to out stream
3664 $options, # options hash
3669 my ( $genome, $q_type, $s_type, $tmp_in, $tmp_out, $fh_in, $fh_out, $record, $line, @fields, $entry );
3671 $options->{ "e_val" } = 10 if not defined $options->{ "e_val" };
3672 $options->{ "filter" } = "F";
3673 $options->{ "filter" } = "T" if $options->{ "filter" };
3674 $options->{ "cpus" } ||= 1;
3676 $options->{ "database" } = "$ENV{ 'BP_DATA' }/genomes/$options->{ 'genome' }/blast/$options->{ 'genome' }.fna" if $options->{ 'genome' };
3678 $tmp_in = "$BP_TMP/blast_query.seq";
3679 $tmp_out = "$BP_TMP/blast.result";
3681 $fh_out = Maasha::Filesys::file_write_open( $tmp_in );
3683 while ( $record = get_record( $in ) )
3685 if ( $entry = Maasha::Fasta::biopiece2fasta( $record ) )
3687 $q_type = Maasha::Seq::seq_guess_type( $entry->[ SEQ ] ) if not $q_type;
3689 Maasha::Fasta::put_entry( $entry, $fh_out );
3692 put_record( $record, $out );
3697 if ( -f $options->{ 'database' } . ".phr" ) {
3698 $s_type = "protein";
3700 $s_type = "nucleotide";
3703 if ( not $options->{ 'program' } )
3705 if ( $q_type ne "protein" and $s_type ne "protein" ) {
3706 $options->{ 'program' } = "blastn";
3707 } elsif ( $q_type eq "protein" and $s_type eq "protein" ) {
3708 $options->{ 'program' } = "blastp";
3709 } elsif ( $q_type ne "protein" and $s_type eq "protein" ) {
3710 $options->{ 'program' } = "blastx";
3711 } elsif ( $q_type eq "protein" and $s_type ne "protein" ) {
3712 $options->{ 'program' } = "tblastn";
3716 if ( $options->{ 'verbose' } )
3718 Maasha::Common::run(
3721 "-p $options->{ 'program' }",
3722 "-e $options->{ 'e_val' }",
3723 "-a $options->{ 'cpus' }",
3726 "-d $options->{ 'database' }",
3727 "-F $options->{ 'filter' }",
3735 Maasha::Common::run(
3738 "-p $options->{ 'program' }",
3739 "-e $options->{ 'e_val' }",
3740 "-a $options->{ 'cpus' }",
3743 "-d $options->{ 'database' }",
3744 "-F $options->{ 'filter' }",
3754 $fh_out = Maasha::Filesys::file_read_open( $tmp_out );
3758 while ( $line = <$fh_out> )
3762 next if $line =~ /^#/;
3764 @fields = split /\s+/, $line;
3766 $record->{ "REC_TYPE" } = "BLAST";
3767 $record->{ "Q_ID" } = $fields[ 0 ];
3768 $record->{ "S_ID" } = $fields[ 1 ];
3769 $record->{ "IDENT" } = $fields[ 2 ];
3770 $record->{ "ALIGN_LEN" } = $fields[ 3 ];
3771 $record->{ "MISMATCHES" } = $fields[ 4 ];
3772 $record->{ "GAPS" } = $fields[ 5 ];
3773 $record->{ "Q_BEG" } = $fields[ 6 ] - 1; # BLAST is 1-based
3774 $record->{ "Q_END" } = $fields[ 7 ] - 1; # BLAST is 1-based
3775 $record->{ "S_BEG" } = $fields[ 8 ] - 1; # BLAST is 1-based
3776 $record->{ "S_END" } = $fields[ 9 ] - 1; # BLAST is 1-based
3777 $record->{ "E_VAL" } = $fields[ 10 ];
3778 $record->{ "BIT_SCORE" } = $fields[ 11 ];
3780 if ( $record->{ "S_BEG" } > $record->{ "S_END" } )
3782 $record->{ "STRAND" } = '-';
3784 ( $record->{ "S_BEG" }, $record->{ "S_END" } ) = ( $record->{ "S_END" }, $record->{ "S_BEG" } );
3788 $record->{ "STRAND" } = '+';
3791 put_record( $record, $out );
3802 # Martin A. Hansen, August 2007.
3804 # BLATs sequences in stream against a given genome.
3806 my ( $in, # handle to in stream
3807 $out, # handle to out stream
3808 $options, # options hash
3813 my ( $blat_args, $genome_file, $query_file, $fh_in, $fh_out, $type, $record, $result_file, $entries, $entry );
3815 $genome_file = "$ENV{ 'BP_DATA' }/genomes/$options->{ 'genome' }/fasta/$options->{ 'genome' }.fna";
3817 $options->{ 'tile_size' } ||= 11;
3818 $options->{ 'one_off' } ||= 0;
3819 $options->{ 'min_identity' } ||= 90;
3820 $options->{ 'min_score' } ||= 0;
3821 $options->{ 'step_size' } ||= $options->{ 'tile_size' };
3823 $blat_args .= " -tileSize=$options->{ 'tile_size' }";
3824 $blat_args .= " -oneOff=$options->{ 'one_off' }";
3825 $blat_args .= " -minIdentity=$options->{ 'min_identity' }";
3826 $blat_args .= " -minScore=$options->{ 'min_score' }";
3827 $blat_args .= " -stepSize=$options->{ 'step_size' }";
3828 # $blat_args .= " -ooc=" . Maasha::Config::genome_blat_ooc( $options->{ "genome" }, 11 ) if $options->{ 'ooc' };
3830 $query_file = "$BP_TMP/blat.seq";
3832 $fh_out = Maasha::Common::write_open( $query_file );
3834 while ( $record = get_record( $in ) )
3836 if ( $entry = Maasha::Fasta::biopiece2fasta( $record ) )
3838 $type = Maasha::Seq::seq_guess_type( $entry->[ SEQ ] ) if not $type;
3839 Maasha::Fasta::put_entry( $entry, $fh_out, 80 );
3842 put_record( $record, $out );
3847 $blat_args .= " -t=dnax" if $type eq "protein";
3848 $blat_args .= " -q=$type";
3850 $result_file = "$BP_TMP/blat.psl";
3852 Maasha::Common::run( "blat", "$genome_file $query_file $blat_args $result_file > /dev/null 2>&1" );
3856 $entries = Maasha::UCSC::psl_get_entries( $result_file );
3858 map { put_record( $_, $out ) } @{ $entries };
3860 unlink $result_file;
3866 # Martin A. Hansen, July 2008.
3868 # soap sequences in stream against a given file or genome.
3870 my ( $in, # handle to in stream
3871 $out, # handle to out stream
3872 $options, # options hash
3877 my ( $genome, $tmp_in, $tmp_out, $fh_in, $fh_out, $record, $line, @fields, $entry, $count, $args );
3879 $options->{ "seed_size" } ||= 10;
3880 $options->{ "mismatches" } ||= 2;
3881 $options->{ "gap_size" } ||= 0;
3882 $options->{ "cpus" } ||= 1;
3884 if ( $options->{ "genome" } ) {
3885 $options->{ "in_file" } = "$ENV{ 'BP_DATA' }/genomes/$options->{ 'genome' }/fasta/$options->{ 'genome' }.fna";
3888 $tmp_in = "$BP_TMP/soap_query.seq";
3889 $tmp_out = "$BP_TMP/soap.result";
3891 $fh_out = Maasha::Common::write_open( $tmp_in );
3895 while ( $record = get_record( $in ) )
3897 if ( $entry = Maasha::Fasta::biopiece2fasta( $record ) )
3899 Maasha::Fasta::put_entry( $entry, $fh_out );
3904 put_record( $record, $out );
3912 "-s $options->{ 'seed_size' }",
3915 "-v $options->{ 'mismatches' }",
3916 "-g $options->{ 'gap_size' }",
3917 "-p $options->{ 'cpus' }",
3918 "-d $options->{ 'in_file' }",
3922 $args .= " > /dev/null 2>&1" if not $options->{ 'verbose' };
3924 Maasha::Common::run( "soap", $args, 1 );
3928 $fh_out = Maasha::Common::read_open( $tmp_out );
3932 while ( $line = <$fh_out> )
3936 @fields = split /\t/, $line;
3938 $record->{ "REC_TYPE" } = "SOAP";
3939 $record->{ "Q_ID" } = $fields[ 0 ];
3940 $record->{ "SCORE" } = $fields[ 3 ];
3941 $record->{ "STRAND" } = $fields[ 6 ];
3942 $record->{ "S_ID" } = $fields[ 7 ];
3943 $record->{ "S_BEG" } = $fields[ 8 ] - 1; # soap is 1-based
3944 $record->{ "S_END" } = $fields[ 8 ] + $fields[ 5 ] - 2;
3946 put_record( $record, $out );
3956 sub script_match_seq
3958 # Martin A. Hansen, August 2007.
3960 # BLATs sequences in stream against a given genome.
3962 my ( $in, # handle to in stream
3963 $out, # handle to out stream
3964 $options, # options hash
3969 my ( $record, @entries, $results );
3971 $options->{ "word_size" } ||= 20;
3972 $options->{ "direction" } ||= "both";
3974 while ( $record = get_record( $in ) )
3976 if ( $record->{ "SEQ_NAME" } and $record->{ "SEQ" } ) {
3977 push @entries, [ $record->{ "SEQ_NAME" }, $record->{ "SEQ" } ];
3980 put_record( $record, $out );
3983 if ( @entries == 1 )
3985 $results = Maasha::Match::match_mummer( [ $entries[ 0 ] ], [ $entries[ 0 ] ], $options, $BP_TMP );
3987 map { put_record( $_, $out ) } @{ $results };
3989 elsif ( @entries == 2 )
3991 $results = Maasha::Match::match_mummer( [ $entries[ 0 ] ], [ $entries[ 1 ] ], $options, $BP_TMP );
3993 map { put_record( $_, $out ) } @{ $results };
3998 sub script_create_vmatch_index
4000 # Martin A. Hansen, January 2008.
4002 # Create a vmatch index from sequences in the stream.
4004 my ( $in, # handle to in stream
4005 $out, # handle to out stream
4006 $options, # options hash
4011 my ( $record, $file_tmp, $fh_tmp, $type, $entry );
4013 if ( $options->{ "index_name" } )
4015 $file_tmp = $options->{ 'index_name' };
4016 $fh_tmp = Maasha::Common::write_open( $file_tmp );
4019 while ( $record = get_record( $in ) )
4021 if ( $options->{ "index_name" } and $entry = Maasha::Fasta::biopiece2fasta( $record ) )
4023 Maasha::Fasta::put_entry( $entry, $fh_tmp );
4025 $type = Maasha::Seq::seq_guess_type( $entry->[ SEQ ] ) if not defined $type;
4028 put_record( $record, $out ) if not $options->{ "no_stream" };
4031 if ( $options->{ "index_name" } )
4035 if ( $type eq "protein" ) {
4036 Maasha::Common::run( "mkvtree", "-db $file_tmp -protein -pl $options->{ 'prefix_length' } -allout -indexname $file_tmp > /dev/null 2>&1" );
4038 Maasha::Common::run( "mkvtree", "-db $file_tmp -dna -pl $options->{ 'prefix_length' } -allout -indexname $file_tmp > /dev/null 2>&1" );
4046 sub script_vmatch_seq
4048 # Martin A. Hansen, August 2007.
4050 # Vmatches sequences in stream against a given genome.
4052 my ( $in, # handle to in stream
4053 $out, # handle to out stream
4054 $options, # options hash
4059 my ( @index_files, @records, $result_file, $fh_in, $record, %hash );
4061 $options->{ 'count' } = 1 if $options->{ 'max_hits' };
4063 if ( $options->{ "index_name" } )
4065 @index_files = $options->{ "index_name" };
4069 @index_files = Maasha::Common::ls_files( "$ENV{ 'BP_DATA' }/genomes/$options->{ 'genome' }/vmatch" );
4071 map { $_ =~ /^(.+)\.[a-z1]{3,4}$/; $hash{ $1 } = 1 } @index_files;
4073 @index_files = sort keys %hash;
4076 while ( $record = get_record( $in ) )
4078 push @records, $record;
4080 put_record( $record, $out );
4083 $result_file = Maasha::Match::match_vmatch( $BP_TMP, \@records, \@index_files, $options );
4087 $fh_in = Maasha::Common::read_open( $result_file );
4089 while ( $record = Maasha::Match::vmatch_get_entry( $fh_in ) ) {
4090 put_record( $record, $out );
4095 unlink $result_file;
4099 sub script_write_fasta
4101 # Martin A. Hansen, August 2007.
4103 # Write FASTA entries from sequences in stream.
4105 my ( $in, # handle to in stream
4106 $out, # handle to out stream
4107 $options, # options hash
4112 my ( $record, $fh, $entry );
4114 $fh = write_stream( $options->{ "data_out" }, $options->{ "compress" } );
4116 while ( $record = get_record( $in ) )
4118 if ( $entry = Maasha::Fasta::biopiece2fasta( $record ) ) {
4119 Maasha::Fasta::put_entry( $entry, $fh, $options->{ "wrap" } );
4122 put_record( $record, $out ) if not $options->{ "no_stream" };
4129 sub script_write_align
4131 # Martin A. Hansen, August 2007.
4133 # Write pretty alignments aligned sequences in stream.
4135 my ( $in, # handle to in stream
4136 $out, # handle to out stream
4137 $options, # options hash
4142 my ( $fh, $record, @entries );
4144 $fh = write_stream( $options->{ "data_out" } ) ;
4146 while ( $record = get_record( $in ) )
4148 if ( $record->{ "SEQ_NAME" } and $record->{ "SEQ" } ) {
4149 push @entries, [ $record->{ "SEQ_NAME" }, $record->{ "SEQ" } ];
4152 put_record( $record, $out ) if not $options->{ "no_stream" };
4155 if ( scalar( @entries ) == 2 ) {
4156 Maasha::Align::align_print_pairwise( $entries[ 0 ], $entries[ 1 ], $fh, $options->{ "wrap" } );
4157 } elsif ( scalar ( @entries ) > 2 ) {
4158 Maasha::Align::align_print_multi( \@entries, $fh, $options->{ "wrap" }, $options->{ "no_ruler" }, $options->{ "no_consensus" } );
4165 sub script_write_blast
4167 # Martin A. Hansen, November 2007.
4169 # Write data in blast table format (-m8 and 9).
4171 my ( $in, # handle to in stream
4172 $out, # handle to out stream
4173 $options, # options hash
4178 my ( $fh, $record, $first );
4180 $fh = write_stream( $options->{ "data_out" }, $options->{ "compress" } ) ;
4184 while ( $record = get_record( $in ) )
4186 if ( $record->{ "REC_TYPE" } eq "BLAST" )
4188 if ( $options->{ "comment" } and $first )
4190 print "# Fields: Query id, Subject id, % identity, alignment length, mismatches, gap openings, q. start, q. end, s. start, s. end, e-value, bit score\n";
4195 if ( $record->{ "STRAND" } eq "-" ) {
4196 ( $record->{ "S_BEG" }, $record->{ "S_END" } ) = ( $record->{ "S_END" }, $record->{ "S_BEG" } );
4199 print $fh join( "\t",
4200 $record->{ "Q_ID" },
4201 $record->{ "S_ID" },
4202 $record->{ "IDENT" },
4203 $record->{ "ALIGN_LEN" },
4204 $record->{ "MISMATCHES" },
4205 $record->{ "GAPS" },
4206 $record->{ "Q_BEG" } + 1,
4207 $record->{ "Q_END" } + 1,
4208 $record->{ "S_BEG" } + 1,
4209 $record->{ "S_END" } + 1,
4210 $record->{ "E_VAL" },
4211 $record->{ "BIT_SCORE" }
4215 put_record( $record, $out ) if not $options->{ "no_stream" };
4222 sub script_write_tab
4224 # Martin A. Hansen, August 2007.
4226 # Write data as table.
4228 my ( $in, # handle to in stream
4229 $out, # handle to out stream
4230 $options, # options hash
4235 my ( $fh, $record, $key, @keys, @vals, $ok, %no_keys, $A, $B );
4237 $options->{ "delimit" } ||= "\t";
4239 map { $no_keys{ $_ } = 1 } @{ $options->{ "no_keys" } };
4241 $fh = write_stream( $options->{ "data_out" }, $options->{ "compress" } );
4243 while ( $record = get_record( $in ) )
4248 if ( $options->{ "keys" } )
4250 map { $ok = 0 if not exists $record->{ $_ } } @{ $options->{ "keys" } };
4254 foreach $key ( @{ $options->{ "keys" } } )
4256 if ( exists $record->{ $key } )
4258 push @keys, $key if $options->{ "comment" };
4259 push @vals, $record->{ $key };
4266 foreach $key ( sort { $A = $a; $B = $b; $A =~ s/^V(\d+)$/$1/; $B =~ s/^V(\d+)$/$1/; $A <=> $B } keys %{ $record } )
4268 next if exists $no_keys{ $key };
4270 push @keys, $key if $options->{ "comment" };
4271 push @vals, $record->{ $key };
4275 if ( @keys and $options->{ "comment" } )
4277 print $fh "#", join( $options->{ "delimit" }, @keys ), "\n";
4279 delete $options->{ "comment" };
4282 print $fh join( $options->{ "delimit" }, @vals ), "\n" if @vals;
4284 put_record( $record, $out ) if not $options->{ "no_stream" };
4291 sub script_write_bed
4293 # Martin A. Hansen, August 2007.
4295 # Write BED format for the UCSC genome browser using records in stream.
4297 my ( $in, # handle to in stream
4298 $out, # handle to out stream
4299 $options, # options hash
4304 my ( $cols, $fh, $record, $bed_entry, $new_record );
4306 $cols = $options->{ 'cols' }->[ 0 ];
4308 $fh = write_stream( $options->{ 'data_out' }, $options->{ 'compress' } );
4310 while ( $record = get_record( $in ) )
4312 $record = Maasha::UCSC::psl2record( $record ) if $record->{ 'tBaseInsert' }; # Dirty addition to allow Affy data from MySQL to be dumped
4314 if ( $bed_entry = Maasha::UCSC::BED::biopiece2bed( $record, $cols ) ) {
4315 Maasha::UCSC::BED::bed_entry_put( $bed_entry, $fh, $cols, 1 );
4318 put_record( $record, $out ) if not $options->{ 'no_stream' };
4325 sub script_write_psl
4327 # Martin A. Hansen, August 2007.
4329 # Write PSL output from stream.
4331 my ( $in, # handle to in stream
4332 $out, # handle to out stream
4333 $options, # options hash
4338 my ( $fh, $record, @output, $first );
4342 $fh = write_stream( $options->{ "data_out" }, $options->{ "compress" } );
4344 while ( $record = get_record( $in ) )
4346 put_record( $record, $out ) if not $options->{ "no_stream" };
4348 if ( $record->{ "REC_TYPE" } and $record->{ "REC_TYPE" } eq "PSL" )
4350 Maasha::UCSC::psl_put_header( $fh ) if $first;
4351 Maasha::UCSC::psl_put_entry( $record, $fh );
4360 sub script_write_fixedstep
4362 # Martin A. Hansen, Juli 2008.
4364 # Write fixedStep entries from recrods in the stream.
4366 my ( $in, # handle to in stream
4367 $out, # handle to out stream
4368 $options, # options hash
4373 my ( $fh, $record, $entry );
4375 $fh = write_stream( $options->{ "data_out" }, $options->{ "compress" } );
4377 while ( $record = get_record( $in ) )
4379 if ( $entry = Maasha::UCSC::Wiggle::biopiece2fixedstep( $record ) ) {
4380 Maasha::UCSC::Wiggle::fixedstep_entry_put( $entry, $fh );
4383 put_record( $record, $out ) if not $options->{ "no_stream" };
4390 sub script_write_2bit
4392 # Martin A. Hansen, March 2008.
4394 # Write sequence entries from stream in 2bit format.
4396 my ( $in, # handle to in stream
4397 $out, # handle to out stream
4398 $options, # options hash
4403 my ( $record, $mask, $tmp_file, $fh_tmp, $fh_in, $fh_out, $entry );
4405 $mask = 1 if not $options->{ "no_mask" };
4407 $tmp_file = "$BP_TMP/write_2bit.fna";
4408 $fh_tmp = Maasha::Common::write_open( $tmp_file );
4410 $fh_out = write_stream( $options->{ "data_out" } );
4412 while ( $record = get_record( $in ) )
4414 if ( $entry = Maasha::Fasta::biopiece2fasta( $record ) ) {
4415 Maasha::Fasta::put_entry( $entry, $fh_tmp );
4418 put_record( $record, $out ) if not $options->{ "no_stream" };
4423 $fh_in = Maasha::Common::read_open( $tmp_file );
4425 Maasha::TwoBit::fasta2twobit( $fh_in, $fh_out, $mask );
4434 sub script_write_solid
4436 # Martin A. Hansen, April 2008.
4438 # Write di-base encoded Solid sequence from entries in stream.
4440 my ( $in, # handle to in stream
4441 $out, # handle to out stream
4442 $options, # options hash
4447 my ( $record, $fh, $entry );
4449 $fh = write_stream( $options->{ "data_out" }, $options->{ "compress" } );
4451 while ( $record = get_record( $in ) )
4453 if ( $entry = Maasha::Fasta::biopiece2fasta( $record ) )
4455 $entry->[ SEQ ] = Maasha::Solid::seq2color_space( uc $entry->[ SEQ ] );
4457 Maasha::Fasta::put_entry( $entry, $fh, $options->{ "wrap" } );
4460 put_record( $record, $out ) if not $options->{ "no_stream" };
4467 sub script_write_ucsc_config
4469 # Martin A. Hansen, November 2008.
4471 # Write UCSC Genome Broser configuration (.ra file type) from
4472 # records in the stream.
4474 my ( $in, # handle to in stream
4475 $out, # handle to out stream
4476 $options, # options hash
4481 my ( $record, $fh );
4483 $fh = write_stream( $options->{ "data_out" } );
4485 while ( $record = get_record( $in ) )
4487 Maasha::UCSC::ucsc_config_entry_put( $record, $fh ) if $record->{ "REC_TYPE" } eq "UCSC Config";
4489 put_record( $record, $out ) if not $options->{ "no_stream" };
4496 sub script_plot_seqlogo
4498 # Martin A. Hansen, August 2007.
4500 # Calculates and writes a sequence logo for alignments.
4502 my ( $in, # handle to in stream
4503 $out, # handle to out stream
4504 $options, # options hash
4509 my ( $record, @entries, $logo, $fh );
4511 while ( $record = get_record( $in ) )
4513 if ( $record->{ "SEQ_NAME" } and $record->{ "SEQ" } ) {
4514 push @entries, [ $record->{ "SEQ_NAME" }, $record->{ "SEQ" } ];
4517 put_record( $record, $out ) if not $options->{ "no_stream" };
4520 $logo = Maasha::Plot::seq_logo( \@entries );
4522 $fh = write_stream( $options->{ "data_out" } );
4530 sub script_plot_phastcons_profiles
4532 # Martin A. Hansen, January 2008.
4534 # Plots PhastCons profiles.
4536 my ( $in, # handle to in stream
4537 $out, # handle to out stream
4538 $options, # options hash
4543 my ( $phastcons_file, $phastcons_index, $index, $fh_phastcons, $record, $scores, $AoA, $plot, $fh );
4545 $options->{ "title" } ||= "PhastCons Profiles";
4547 $phastcons_file = Maasha::Config::genome_phastcons( $options->{ "genome" } );
4548 $phastcons_index = Maasha::Config::genome_phastcons_index( $options->{ "genome" } );
4550 $index = Maasha::UCSC::fixedstep_index_retrieve( $phastcons_index );
4551 $fh_phastcons = Maasha::Common::read_open( $phastcons_file );
4553 while ( $record = get_record( $in ) )
4555 if ( $record->{ "CHR" } and $record->{ "CHR_BEG" } and $record->{ "CHR_END" } )
4557 $scores = Maasha::UCSC::fixedstep_index_lookup( $index, $fh_phastcons, $record->{ "CHR" },
4558 $record->{ "CHR_BEG" },
4559 $record->{ "CHR_END" },
4560 $options->{ "flank" } );
4562 push @{ $AoA }, [ @{ $scores } ];
4565 put_record( $record, $out ) if not $options->{ "no_stream" };
4568 Maasha::UCSC::phastcons_normalize( $AoA );
4570 $AoA = [ [ Maasha::UCSC::phastcons_mean( $AoA ) ] ] if $options->{ "mean" };
4571 $AoA = [ [ Maasha::UCSC::phastcons_median( $AoA ) ] ] if $options->{ "median" };
4573 $AoA = Maasha::Matrix::matrix_flip( $AoA );
4575 $plot = Maasha::Plot::lineplot_simple( $AoA, $options, $BP_TMP );
4577 $fh = write_stream( $options->{ "data_out" } );
4579 print $fh "$_\n" foreach @{ $plot };
4585 sub script_analyze_bed
4587 # Martin A. Hansen, March 2008.
4589 # Analyze BED entries in stream.
4591 my ( $in, # handle to in stream
4592 $out, # handle to out stream
4593 $options, # options hash
4600 while ( $record = get_record( $in ) )
4602 $record = Maasha::UCSC::bed_analyze( $record ) if $record->{ "REC_TYPE" } eq "BED";
4604 put_record( $record, $out );
4609 sub script_analyze_vals
4611 # Martin A. Hansen, August 2007.
4613 # Analyze values for given keys in stream.
4615 my ( $in, # handle to in stream
4616 $out, # handle to out stream
4617 $options, # options hash
4622 my ( $record, $key, @keys, %key_hash, $analysis, $len );
4624 map { $key_hash{ $_ } = 1 } @{ $options->{ "keys" } };
4626 while ( $record = get_record( $in ) )
4628 foreach $key ( keys %{ $record } )
4630 next if $options->{ "keys" } and not exists $key_hash{ $key };
4632 $analysis->{ $key }->{ "COUNT" }++;
4634 if ( Maasha::Calc::is_a_number( $record->{ $key } ) )
4636 $analysis->{ $key }->{ "TYPE" } = "num";
4637 $analysis->{ $key }->{ "SUM" } += $record->{ $key };
4638 $analysis->{ $key }->{ "MAX" } = $record->{ $key } if $record->{ $key } > $analysis->{ $key }->{ "MAX" } or not $analysis->{ $key }->{ "MAX" };
4639 $analysis->{ $key }->{ "MIN" } = $record->{ $key } if $record->{ $key } < $analysis->{ $key }->{ "MIN" } or not $analysis->{ $key }->{ "MIN" };
4643 $len = length $record->{ $key };
4645 $analysis->{ $key }->{ "TYPE" } = "alph";
4646 $analysis->{ $key }->{ "SUM" } += $len;
4647 $analysis->{ $key }->{ "MAX" } = $len if $len > $analysis->{ $key }->{ "MAX" } or not $analysis->{ $key }->{ "MAX" };
4648 $analysis->{ $key }->{ "MIN" } = $len if $len < $analysis->{ $key }->{ "MIM" } or not $analysis->{ $key }->{ "MIN" };
4652 put_record( $record, $out ) if not $options->{ "no_stream" };
4655 foreach $key ( keys %{ $analysis } )
4657 $analysis->{ $key }->{ "MEAN" } = sprintf "%.2f", $analysis->{ $key }->{ "SUM" } / $analysis->{ $key }->{ "COUNT" };
4658 $analysis->{ $key }->{ "SUM" } = sprintf "%.2f", $analysis->{ $key }->{ "SUM" };
4661 my ( $keys, $types, $counts, $mins, $maxs, $sums, $means );
4671 if ( $options->{ "keys" } ) {
4672 @keys = @{ $options->{ "keys" } };
4674 @keys = keys %{ $analysis };
4677 foreach $key ( @keys )
4679 $keys .= sprintf "% 15s", $key;
4680 $types .= sprintf "% 15s", $analysis->{ $key }->{ "TYPE" };
4681 $counts .= sprintf "% 15s", $analysis->{ $key }->{ "COUNT" };
4682 $mins .= sprintf "% 15s", $analysis->{ $key }->{ "MIN" };
4683 $maxs .= sprintf "% 15s", $analysis->{ $key }->{ "MAX" };
4684 $sums .= sprintf "% 15s", $analysis->{ $key }->{ "SUM" };
4685 $means .= sprintf "% 15s", $analysis->{ $key }->{ "MEAN" };
4688 print $out "$keys\n";
4689 print $out "$types\n";
4690 print $out "$counts\n";
4691 print $out "$mins\n";
4692 print $out "$maxs\n";
4693 print $out "$sums\n";
4694 print $out "$means\n";
4698 sub script_head_records
4700 # Martin A. Hansen, August 2007.
4702 # Display the first sequences in stream.
4704 my ( $in, # handle to in stream
4705 $out, # handle to out stream
4706 $options, # options hash
4711 my ( $record, $count );
4713 $options->{ "num" } ||= 10;
4717 while ( $record = get_record( $in ) )
4721 put_record( $record, $out );
4723 last if $count == $options->{ "num" };
4728 sub script_remove_keys
4730 # Martin A. Hansen, August 2007.
4732 # Remove keys from stream.
4734 my ( $in, # handle to in stream
4735 $out, # handle to out stream
4736 $options, # options hash
4741 my ( $record, $new_record );
4743 while ( $record = get_record( $in ) )
4745 if ( $options->{ "keys" } )
4747 map { delete $record->{ $_ } } @{ $options->{ "keys" } };
4749 elsif ( $options->{ "save_keys" } )
4751 map { $new_record->{ $_ } = $record->{ $_ } if exists $record->{ $_ } } @{ $options->{ "save_keys" } };
4753 $record = $new_record;
4756 put_record( $record, $out ) if keys %{ $record };
4761 sub script_remove_adaptor
4763 # Martin A. Hansen, August 2008.
4765 # Find and remove adaptor from sequences in the stream.
4767 my ( $in, # handle to in stream
4768 $out, # handle to out stream
4769 $options, # options hash
4774 my ( $record, $adaptor, $seq, $adaptor_len, $seq_len, $offset, $max_match, $max_mismatch, $pos );
4776 $options->{ "remove" } ||= "after";
4778 $max_mismatch = $options->{ "mismatches" } || 0;
4779 $offset = $options->{ "offset" };
4781 if ( not defined $offset ) {
4787 $adaptor = uc $options->{ "adaptor" };
4788 $adaptor_len = length $adaptor;
4790 while ( $record = get_record( $in ) )
4792 if ( $record->{ "SEQ" } )
4794 $seq = uc $record->{ "SEQ" };
4795 $seq_len = length $seq;
4797 $pos = Maasha::Common::index_m( $seq, $adaptor, $seq_len, $adaptor_len, $offset, $max_mismatch );
4799 $record->{ "ADAPTOR_POS" } = $pos;
4801 if ( $pos >= 0 and $options->{ "remove" } ne "skip" )
4803 if ( $options->{ "remove" } eq "after" )
4805 $record->{ "SEQ" } = substr $record->{ "SEQ" }, 0, $pos;
4806 $record->{ "SEQ_LEN" } = $pos;
4810 $record->{ "SEQ" } = substr $record->{ "SEQ" }, $pos + $adaptor_len;
4811 $record->{ "SEQ_LEN" } = length $record->{ "SEQ" };
4815 put_record( $record, $out );
4819 put_record( $record, $out );
4825 sub script_remove_mysql_tables
4827 # Martin A. Hansen, November 2008.
4829 # Remove MySQL tables from values in stream.
4831 my ( $in, # handle to in stream
4832 $out, # handle to out stream
4833 $options, # options hash
4838 my ( $record, %table_hash, $dbh, $table );
4840 $options->{ "user" } ||= Maasha::UCSC::ucsc_get_user();
4841 $options->{ "password" } ||= Maasha::UCSC::ucsc_get_password();
4843 map { $table_hash{ $_ } = 1 } @{ $options->{ 'tables' } };
4845 while ( $record = get_record( $in ) )
4847 map { $table_hash{ $record->{ $_ } } = 1 } @{ $options->{ 'keys' } };
4849 put_record( $record, $out ) if not $options->{ 'no_stream' };
4852 $dbh = Maasha::SQL::connect( $options->{ "database" }, $options->{ "user" }, $options->{ "password" } );
4854 foreach $table ( sort keys %table_hash )
4856 if ( Maasha::SQL::table_exists( $dbh, $table ) )
4858 print STDERR qq(Removing table "$table" from database "$options->{ 'database' }" ... ) if $options->{ 'verbose' };
4859 Maasha::SQL::delete_table( $dbh, $table );
4860 print STDERR "done.\n" if $options->{ 'verbose' };
4864 print STDERR qq(WARNING: table "$table" not found in database "$options->{ 'database' }\n");
4868 Maasha::SQL::disconnect( $dbh );
4872 sub script_remove_ucsc_tracks
4874 # Martin A. Hansen, November 2008.
4876 # Remove track from MySQL tables and config file.
4878 my ( $in, # handle to in stream
4879 $out, # handle to out stream
4880 $options, # options hash
4885 my ( $record, %track_hash, $fh_in, $fh_out, $track, @tracks, @new_tracks, $dbh );
4887 $options->{ 'user' } ||= Maasha::UCSC::ucsc_get_user();
4888 $options->{ 'password' } ||= Maasha::UCSC::ucsc_get_password();
4889 $options->{ 'config_file' } ||= "$ENV{ 'HOME' }/ucsc/my_tracks.ra";
4891 map { $track_hash{ $_ } = 1 } @{ $options->{ 'tracks' } };
4893 while ( $record = get_record( $in ) )
4895 map { $track_hash{ $record->{ $_ } } = 1 } @{ $options->{ 'keys' } };
4897 put_record( $record, $out ) if not $options->{ 'no_stream' };
4900 # ---- locate track in config file ----
4902 $fh_in = Maasha::Common::read_open( $options->{ 'config_file' } );
4904 while ( $track = Maasha::UCSC::ucsc_config_entry_get( $fh_in ) ) {
4905 push @tracks, $track;
4910 map { push @new_tracks, $_ if not exists $track_hash{ $_->{ 'track' } } } @tracks;
4912 print STDERR qq(WARNING: track not found in config file: "$options->{ 'config_file' }"\n) if scalar @tracks == scalar @new_tracks;
4914 rename "$options->{ 'config_file' }", "$options->{ 'config_file' }~";
4916 $fh_out = Maasha::Common::write_open( $options->{ 'config_file' } );
4918 map { Maasha::UCSC::ucsc_config_entry_put( $_, $fh_out ) } @new_tracks;
4922 # ---- locate track in database ----
4924 $dbh = Maasha::SQL::connect( $options->{ "database" }, $options->{ "user" }, $options->{ "password" } );
4926 foreach $track ( sort keys %track_hash )
4928 if ( Maasha::SQL::table_exists( $dbh, $track ) )
4930 print STDERR qq(Removing table "$track" from database "$options->{ 'database' }" ... ) if $options->{ 'verbose' };
4931 Maasha::SQL::delete_table( $dbh, $track );
4932 print STDERR "done.\n" if $options->{ 'verbose' };
4936 print STDERR qq(WARNING: table "$track" not found in database "$options->{ 'database' }\n");
4940 Maasha::SQL::disconnect( $dbh );
4942 Maasha::Common::run( "ucscMakeTracks.pl", "-b > /dev/null 2>&1" );
4946 sub script_rename_keys
4948 # Martin A. Hansen, August 2007.
4950 # Rename keys in stream.
4952 my ( $in, # handle to in stream
4953 $out, # handle to out stream
4954 $options, # options hash
4961 while ( $record = get_record( $in ) )
4963 if ( exists $record->{ $options->{ "keys" }->[ 0 ] } )
4965 $record->{ $options->{ "keys" }->[ 1 ] } = $record->{ $options->{ "keys" }->[ 0 ] };
4967 delete $record->{ $options->{ "keys" }->[ 0 ] };
4970 put_record( $record, $out );
4975 sub script_uniq_vals
4977 # Martin A. Hansen, August 2007.
4979 # Find unique values in stream.
4981 my ( $in, # handle to in stream
4982 $out, # handle to out stream
4983 $options, # options hash
4988 my ( %hash, $record );
4990 while ( $record = get_record( $in ) )
4992 if ( $record->{ $options->{ "key" } } )
4994 if ( not $hash{ $record->{ $options->{ "key" } } } and not $options->{ "invert" } )
4996 put_record( $record, $out );
4998 $hash{ $record->{ $options->{ "key" } } } = 1;
5000 elsif ( $hash{ $record->{ $options->{ "key" } } } and $options->{ "invert" } )
5002 put_record( $record, $out );
5006 $hash{ $record->{ $options->{ "key" } } } = 1;
5011 put_record( $record, $out );
5017 sub script_merge_vals
5019 # Martin A. Hansen, August 2007.
5021 # Rename keys in stream.
5023 my ( $in, # handle to in stream
5024 $out, # handle to out stream
5025 $options, # options hash
5030 my ( $record, @join, $i );
5032 $options->{ "delimit" } ||= '_';
5034 while ( $record = get_record( $in ) )
5036 if ( exists $record->{ $options->{ "keys" }->[ 0 ] } )
5038 @join = $record->{ $options->{ "keys" }->[ 0 ] };
5040 for ( $i = 1; $i < @{ $options->{ "keys" } }; $i++ ) {
5041 push @join, $record->{ $options->{ "keys" }->[ $i ] } if exists $record->{ $options->{ "keys" }->[ $i ] };
5044 $record->{ $options->{ "keys" }->[ 0 ] } = join $options->{ "delimit" }, @join;
5047 put_record( $record, $out );
5052 sub script_merge_records
5054 # Martin A. Hansen, July 2008.
5056 # Merges records in the stream based on identical values of two given keys.
5058 my ( $in, # handle to in stream
5059 $out, # handle to out stream
5060 $options, # options hash
5065 my ( $merge, $record, $file1, $file2, $fh1, $fh2, $key1, $key2, @keys1, @keys2, @vals1, @vals2,
5066 $num1, $num2, $num, $cmp, $i );
5068 $merge = $options->{ "merge" } || "AandB";
5070 $file1 = "$BP_TMP/merge_records1.tmp";
5071 $file2 = "$BP_TMP/merge_records2.tmp";
5073 $fh1 = Maasha::Common::write_open( $file1 );
5074 $fh2 = Maasha::Common::write_open( $file2 );
5076 $key1 = $options->{ "keys" }->[ 0 ];
5077 $key2 = $options->{ "keys" }->[ 1 ];
5079 $num = $key2 =~ s/n$//;
5083 while ( $record = get_record( $in ) )
5085 if ( exists $record->{ $key1 } )
5088 @vals1 = $record->{ $key1 };
5090 delete $record->{ $key1 };
5092 map { push @keys1, $_; push @vals1, $record->{ $_ } } keys %{ $record };
5094 print $fh1 join( "\t", @vals1 ), "\n";
5098 elsif ( exists $record->{ $key2 } )
5101 @vals2 = $record->{ $key2 };
5103 delete $record->{ $key2 };
5105 map { push @keys2, $_; push @vals2, $record->{ $_ } } keys %{ $record };
5107 print $fh2 join( "\t", @vals2 ), "\n";
5118 Maasha::Common::run( "sort", "-k 1,1n $file1 > $file1.sort" ) and rename "$file1.sort", $file1;
5119 Maasha::Common::run( "sort", "-k 1,1n $file2 > $file2.sort" ) and rename "$file2.sort", $file2;
5123 Maasha::Common::run( "sort", "-k 1,1 $file1 > $file1.sort" ) and rename "$file1.sort", $file1;
5124 Maasha::Common::run( "sort", "-k 1,1 $file2 > $file2.sort" ) and rename "$file2.sort", $file2;
5127 $fh1 = Maasha::Common::read_open( $file1 );
5128 $fh2 = Maasha::Common::read_open( $file2 );
5130 @vals1 = Maasha::Common::get_fields( $fh1 );
5131 @vals2 = Maasha::Common::get_fields( $fh2 );
5133 while ( $num1 > 0 and $num2 > 0 )
5138 $cmp = $vals1[ 0 ] <=> $vals2[ 0 ];
5140 $cmp = $vals1[ 0 ] cmp $vals2[ 0 ];
5145 if ( $merge =~ /^(AorB|AnotB)$/ )
5147 for ( $i = 0; $i < @keys1; $i++ ) {
5148 $record->{ $keys1[ $i ] } = $vals1[ $i ];
5151 put_record( $record, $out );
5154 @vals1 = Maasha::Common::get_fields( $fh1 );
5159 if ( $merge =~ /^(BorA|BnotA)$/ )
5161 for ( $i = 0; $i < @keys2; $i++ ) {
5162 $record->{ $keys2[ $i ] } = $vals2[ $i ];
5165 put_record( $record, $out );
5168 @vals2 = Maasha::Common::get_fields( $fh2 );
5173 if ( $merge =~ /^(AandB|AorB|BorA)$/ )
5175 for ( $i = 0; $i < @keys1; $i++ ) {
5176 $record->{ $keys1[ $i ] } = $vals1[ $i ];
5179 for ( $i = 1; $i < @keys2; $i++ ) {
5180 $record->{ $keys2[ $i ] } = $vals2[ $i ];
5183 put_record( $record, $out );
5186 @vals1 = Maasha::Common::get_fields( $fh1 );
5187 @vals2 = Maasha::Common::get_fields( $fh2 );
5199 if ( $num1 > 0 and $merge =~ /^(AorB|AnotB)$/ )
5203 for ( $i = 0; $i < @keys1; $i++ ) {
5204 $record->{ $keys1[ $i ] } = $vals1[ $i ];
5207 put_record( $record, $out );
5210 if ( $num2 > 0 and $merge =~ /^(BorA|BnotA)$/ )
5214 for ( $i = 0; $i < @keys2; $i++ ) {
5215 $record->{ $keys2[ $i ] } = $vals2[ $i ];
5218 put_record( $record, $out );
5225 # Martin A. Hansen, August 2007.
5227 # Grab for records in stream.
5229 my ( $in, # handle to in stream
5230 $out, # handle to out stream
5231 $options, # options hash
5236 my ( $keys, $vals_only, $keys_only, $invert, $patterns, $pattern, $regex, $record, $key, $op, $val, %lookup_hash, $found );
5238 $keys = $options->{ 'keys' };
5239 $vals_only = $options->{ 'vals_only' };
5240 $keys_only = $options->{ 'keys_only' };
5241 $invert = $options->{ 'invert' };
5243 if ( $options->{ 'patterns' } )
5245 $patterns = [ split ",", $options->{ 'patterns' } ];
5247 elsif ( -f $options->{ 'patterns_in' } )
5249 $patterns = Maasha::Patscan::read_patterns( $options->{ 'patterns_in' } );
5251 elsif ( $options->{ 'regex' } )
5253 if ( $options->{ 'case_insensitive' } ) {
5254 $regex = qr/$options->{ 'regex' }/i;
5256 $regex = qr/$options->{ 'regex' }/;
5259 elsif ( -f $options->{ 'exact_in' } )
5261 $patterns = Maasha::Patscan::read_patterns( $options->{ 'exact_in' } );
5263 map { $lookup_hash{ $_ } = 1 } @{ $patterns };
5267 elsif ( $options->{ 'eval' } )
5269 if ( $options->{ 'eval' } =~ /^([^><=! ]+)\s*(>=|<=|>|<|=|!=|eq|ne)\s*(.+)$/ )
5277 while ( $record = get_record( $in ) )
5281 if ( %lookup_hash ) {
5282 $found = grab_lookup( \%lookup_hash, $record, $keys, $vals_only, $keys_only );
5283 } elsif ( $patterns ) {
5284 $found = grab_patterns( $patterns, $record, $keys, $vals_only, $keys_only );
5285 } elsif ( $regex ) {
5286 $found = grab_regex( $regex, $record, $keys, $vals_only, $keys_only );
5288 $found = grab_eval( $key, $op, $val, $record );
5291 if ( $found and not $invert ) {
5292 put_record( $record, $out );
5293 } elsif ( not $found and $invert ) {
5294 put_record( $record, $out );
5302 # Martin A. Hansen, August 2007.
5304 # Evaluate extression for records in stream.
5306 my ( $in, # handle to in stream
5307 $out, # handle to out stream
5308 $options, # options hash
5313 my ( $record, $eval_key, @keys, $eval_val );
5315 while ( $record = get_record( $in ) )
5317 if ( $options->{ "eval" } )
5319 if ( $options->{ "eval" } =~ /^(\S+)\s*=\s*(.+)$/ )
5326 @keys = split /\s+|\+|-|\*|\/|\*\*/, $eval_val;
5328 @keys = grep { exists $record->{ $_ } } @keys;
5331 map { $eval_val =~ s/\Q$_\E/$record->{ $_ }/g } @keys;
5333 $record->{ $eval_key } = eval "$eval_val";
5334 Maasha::Common::error( qq(eval "$eval_key = $eval_val" failed -> $@) ) if $@;
5338 Maasha::Common::error( qq(Bad compute expression: "$options->{ 'eval' }"\n) );
5342 put_record( $record, $out );
5349 # Martin A. Hansen, June 2008.
5353 my ( $in, # handle to in stream
5354 $out, # handle to out stream
5355 $options, # options hash
5360 my ( $record, $key, $A, $B, @rows, @matrix, $row, $i );
5362 while ( $record = get_record( $in ) )
5366 foreach $key ( sort { $A = $a; $B = $b; $A =~ s/^V(\d+)$/$1/; $B =~ s/^V(\d+)$/$1/; $A <=> $B } keys %{ $record } )
5368 push @rows, $record->{ $key };
5372 push @matrix, [ @rows ];
5377 @matrix = Maasha::Matrix::matrix_flip( \@matrix );
5379 foreach $row ( @matrix )
5381 for ( $i = 0; $i < @{ $row }; $i++ ) {
5382 $record->{ "V$i" } = $row->[ $i ];
5385 put_record( $record, $out );
5390 sub script_add_ident
5392 # Martin A. Hansen, May 2008.
5394 # Add a unique identifier to each record in stream.
5396 my ( $in, # handle to in stream
5397 $out, # handle to out stream
5398 $options, # options hash
5403 my ( $record, $key, $prefix, $i );
5405 $key = $options->{ "key" } || "ID";
5406 $prefix = $options->{ "prefix" } || "ID";
5410 while ( $record = get_record( $in ) )
5412 $record->{ $key } = sprintf( "$prefix%08d", $i );
5414 put_record( $record, $out );
5421 sub script_count_records
5423 # Martin A. Hansen, August 2007.
5425 # Count records in stream.
5427 my ( $in, # handle to in stream
5428 $out, # handle to out stream
5429 $options, # options hash
5434 my ( $record, $count, $result, $fh, $line );
5438 if ( $options->{ "no_stream" } )
5440 while ( $line = <$in> )
5444 $count++ if $line eq "---";
5449 while ( $record = get_record( $in ) )
5451 put_record( $record, $out );
5457 $result = { "RECORDS_COUNT" => $count };
5459 $fh = write_stream( $options->{ "data_out" } );
5461 put_record( $result, $fh );
5467 sub script_random_records
5469 # Martin A. Hansen, August 2007.
5471 # Pick a number or random records from stream.
5473 my ( $in, # handle to in stream
5474 $out, # handle to out stream
5475 $options, # options hash
5480 my ( $record, $tmp_file, $fh_out, $fh_in, $count, $i, %rand_hash, $rand, $max );
5482 $options->{ "num" } ||= 10;
5484 $tmp_file = "$BP_TMP/random_records.tmp";
5486 $fh_out = Maasha::Common::write_open( $tmp_file );
5490 while ( $record = get_record( $in ) )
5492 put_record( $record, $fh_out );
5502 Maasha::Common::error( qq(Requested random records > records in stream) ) if $options->{ "num" } > $count;
5504 while ( $i < $options->{ "num" } )
5506 $rand = int( rand( $count ) );
5508 if ( not exists $rand_hash{ $rand } )
5510 $rand_hash{ $rand } = 1;
5512 $max = $rand if $rand > $max;
5518 $fh_in = Maasha::Common::read_open( $tmp_file );
5522 while ( $record = get_record( $fh_in ) )
5524 put_record( $record, $out ) if exists $rand_hash{ $count };
5526 last if $count == $max;
5537 sub script_sort_records
5539 # Martin A. Hansen, August 2007.
5541 # Sort to sort records according to keys.
5543 my ( $in, # handle to in stream
5544 $out, # handle to out stream
5545 $options, # options hash
5550 my ( @keys, $key, @sort_cmd, $sort_str, $sort_sub, @records, $record, $i );
5552 foreach $key ( @{ $options->{ "keys" } } )
5554 if ( $key =~ s/n$// ) {
5555 push @sort_cmd, qq(\$a->{ "$key" } <=> \$b->{ "$key" });
5557 push @sort_cmd, qq(\$a->{ "$key" } cmp \$b->{ "$key" });
5561 $sort_str = join " or ", @sort_cmd;
5562 $sort_sub = eval "sub { $sort_str }"; # NB security issue!
5564 while ( $record = get_record( $in ) ) {
5565 push @records, $record;
5568 @records = sort $sort_sub @records;
5570 if ( $options->{ "reverse" } )
5572 for ( $i = scalar @records - 1; $i >= 0; $i-- ) {
5573 put_record( $records[ $i ], $out );
5578 for ( $i = 0; $i < scalar @records; $i++ ) {
5579 put_record( $records[ $i ], $out );
5585 sub script_count_vals
5587 # Martin A. Hansen, August 2007.
5589 # Count records in stream.
5591 my ( $in, # handle to in stream
5592 $out, # handle to out stream
5593 $options, # options hash
5598 my ( $num, $record, %count_hash, @records, $tmp_file, $fh_out, $fh_in, $cache );
5600 $tmp_file = "$BP_TMP/count_cache.tmp";
5602 $fh_out = Maasha::Common::write_open( $tmp_file );
5607 while ( $record = get_record( $in ) )
5609 map { $count_hash{ $_ }{ $record->{ $_ } }++ if exists $record->{ $_ } } @{ $options->{ "keys" } };
5611 push @records, $record;
5613 if ( scalar @records > 5_000_000 ) # too many records to hold in memory - use disk cache
5615 map { put_record( $_, $fh_out ) } @records;
5622 print STDERR "verbose: records read $num\n" if ( $options->{ 'verbose' } and ( $num % 1_000_000 ) == 0 );
5633 $fh_in = Maasha::Common::read_open( $tmp_file );
5635 while ( $record = get_record( $fh_in ) )
5637 map { $record->{ $_ . "_COUNT" } = $count_hash{ $_ }{ $record->{ $_ } } if exists $record->{ $_ } } @{ $options->{ "keys" } };
5639 put_record( $record, $out );
5641 print STDERR "verbose: cache read $num\n" if ( $options->{ 'verbose' } and ( $num % 1_000_000 ) == 0 );
5649 foreach $record ( @records )
5651 map { $record->{ $_ . "_COUNT" } = $count_hash{ $_ }{ $record->{ $_ } } if exists $record->{ $_ } } @{ $options->{ "keys" } };
5653 put_record( $record, $out );
5660 sub script_plot_histogram
5662 # Martin A. Hansen, September 2007.
5664 # Plot a simple histogram for a given key using GNU plot.
5666 my ( $in, # handle to in stream
5667 $out, # handle to out stream
5668 $options, # options hash
5673 my ( $record, %data_hash, $max, @data_list, $i, $result, $fh );
5675 $options->{ "title" } ||= "Histogram";
5676 $options->{ "sort" } ||= "num";
5678 while ( $record = get_record( $in ) )
5680 $data_hash{ $record->{ $options->{ "key" } } }++ if defined $record->{ $options->{ "key" } };
5682 put_record( $record, $out ) if not $options->{ "no_stream" };
5685 if ( $options->{ "sort" } eq "num" ) {
5686 map { push @data_list, [ $_, $data_hash{ $_ } ] } sort { $a <=> $b } keys %data_hash;
5688 map { push @data_list, [ $_, $data_hash{ $_ } ] } sort keys %data_hash;
5691 $result = Maasha::Plot::histogram_simple( \@data_list, $options );
5693 $fh = write_stream( $options->{ "data_out" } );
5695 print $fh "$_\n" foreach @{ $result };
5701 sub script_plot_lendist
5703 # Martin A. Hansen, August 2007.
5705 # Plot length distribution using GNU plot.
5707 my ( $in, # handle to in stream
5708 $out, # handle to out stream
5709 $options, # options hash
5714 my ( $record, %data_hash, $max, @data_list, $i, $result, $fh );
5716 $options->{ "title" } ||= "Length Distribution";
5718 while ( $record = get_record( $in ) )
5720 $data_hash{ $record->{ $options->{ "key" } } }++ if defined $record->{ $options->{ "key" } };
5722 put_record( $record, $out ) if not $options->{ "no_stream" };
5725 $max = Maasha::Calc::list_max( [ keys %data_hash ] );
5727 for ( $i = 0; $i < $max; $i++ ) {
5728 push @data_list, [ $i, $data_hash{ $i } || 0 ];
5731 $result = Maasha::Plot::histogram_lendist( \@data_list, $options );
5733 $fh = write_stream( $options->{ "data_out" } );
5735 print $fh "$_\n" foreach @{ $result };
5741 sub script_plot_chrdist
5743 # Martin A. Hansen, August 2007.
5745 # Plot chromosome distribution using GNU plot.
5747 my ( $in, # handle to in stream
5748 $out, # handle to out stream
5749 $options, # options hash
5754 my ( $record, %data_hash, @data_list, $elem, $sort_key, $count, $result, $fh );
5756 $options->{ "title" } ||= "Chromosome Distribution";
5758 while ( $record = get_record( $in ) )
5760 if ( $record->{ "CHR" } ) { # generic
5761 $data_hash{ $record->{ "CHR" } }++;
5762 } elsif ( $record->{ "REC_TYPE" } eq "PATSCAN" and $record->{ "S_ID" } =~ /^chr/i ) { # patscan
5763 $data_hash{ $record->{ "S_ID" } }++;
5764 } elsif ( $record->{ "REC_TYPE" } eq "PSL" and $record->{ "S_ID" } =~ /^chr/i ) { # BLAT / PSL
5765 $data_hash{ $record->{ "S_ID" } }++;
5766 } elsif ( $record->{ "REC_TYPE" } eq "BLAST" and $record->{ "S_ID" } =~ /^chr/i ) { # BLAST
5767 $data_hash{ $record->{ "S_ID" } }++;
5770 put_record( $record, $out ) if not $options->{ "no_stream" };
5773 foreach $elem ( keys %data_hash )
5777 $sort_key =~ s/chr//i;
5779 $sort_key =~ s/^X(.*)/99$1/;
5780 $sort_key =~ s/^Y(.*)/99$1/;
5781 $sort_key =~ s/^Z(.*)/999$1/;
5782 $sort_key =~ s/^M(.*)/9999$1/;
5783 $sort_key =~ s/^U(.*)/99999$1/;
5785 $count = $sort_key =~ tr/_//;
5787 $sort_key =~ s/_.*/"999999" x $count/ex;
5789 push @data_list, [ $elem, $data_hash{ $elem }, $sort_key ];
5792 @data_list = sort { $a->[ 2 ] <=> $b->[ 2 ] } @data_list;
5794 $result = Maasha::Plot::histogram_chrdist( \@data_list, $options );
5796 $fh = write_stream( $options->{ "data_out" } );
5798 print $fh "$_\n" foreach @{ $result };
5804 sub script_plot_karyogram
5806 # Martin A. Hansen, August 2007.
5808 # Plot hits on karyogram.
5810 my ( $in, # handle to in stream
5811 $out, # handle to out stream
5812 $options, # options hash
5817 my ( %options, $record, @data, $fh, $result, %data_hash );
5819 $options->{ "genome" } ||= "human";
5820 $options->{ "feat_color" } ||= "black";
5822 while ( $record = get_record( $in ) )
5824 if ( $record->{ "CHR" } and $record->{ "CHR_BEG" } and $record->{ "CHR_END" } )
5826 push @{ $data_hash{ $record->{ "CHR" } } }, [ $record->{ "CHR_BEG" }, $record->{ "CHR_END" }, $options->{ "feat_color" } ];
5829 put_record( $record, $out ) if not $options->{ "no_stream" };
5832 $result = Maasha::Plot::karyogram( \%data_hash, \%options );
5834 $fh = write_stream( $options->{ "data_out" } );
5842 sub script_plot_matches
5844 # Martin A. Hansen, August 2007.
5846 # Plot matches in 2D generating a dotplot.
5848 my ( $in, # handle to in stream
5849 $out, # handle to out stream
5850 $options, # options hash
5855 my ( $record, @data, $fh, $result, %data_hash );
5857 $options->{ "direction" } ||= "both";
5859 while ( $record = get_record( $in ) )
5861 if ( defined $record->{ "Q_BEG" } and defined $record->{ "S_BEG" } and $record->{ "Q_END" } and $record->{ "S_END" } ) {
5862 push @data, $record;
5865 put_record( $record, $out ) if not $options->{ "no_stream" };
5868 $options->{ "title" } ||= "plot_matches";
5869 $options->{ "xlabel" } ||= $data[ 0 ]->{ "Q_ID" };
5870 $options->{ "ylabel" } ||= $data[ 0 ]->{ "S_ID" };
5872 $result = Maasha::Plot::dotplot_matches( \@data, $options, $BP_TMP );
5874 $fh = write_stream( $options->{ "data_out" } );
5876 print $fh "$_\n" foreach @{ $result };
5882 sub script_length_vals
5884 # Martin A. Hansen, August 2007.
5886 # Determine the length of the value for given keys.
5888 my ( $in, # handle to in stream
5889 $out, # handle to out stream
5890 $options, # options hash
5895 my ( $record, $key );
5897 while ( $record = get_record( $in ) )
5899 foreach $key ( @{ $options->{ "keys" } } )
5901 if ( $record->{ $key } ) {
5902 $record->{ $key . "_LEN" } = length $record->{ $key };
5906 put_record( $record, $out );
5913 # Martin A. Hansen, August 2007.
5915 # Calculates the sums for values of given keys.
5917 my ( $in, # handle to in stream
5918 $out, # handle to out stream
5919 $options, # options hash
5924 my ( $record, $key, %sum_hash, $fh );
5926 while ( $record = get_record( $in ) )
5928 foreach $key ( @{ $options->{ "keys" } } )
5930 if ( $record->{ $key } ) {
5931 $sum_hash{ $key } += $record->{ $key };
5935 put_record( $record, $out ) if not $options->{ "no_stream" };
5938 $fh = write_stream( $options->{ "data_out" } );
5940 foreach $key ( @{ $options->{ "keys" } } ) {
5941 put_record( { $key . "_SUM" => $sum_hash{ $key } || 0 } , $fh );
5948 sub script_mean_vals
5950 # Martin A. Hansen, August 2007.
5952 # Calculate the mean of values of given keys.
5954 my ( $in, # handle to in stream
5955 $out, # handle to out stream
5956 $options, # options hash
5961 my ( $record, $key, %sum_hash, %count_hash, $mean, $fh );
5963 while ( $record = get_record( $in ) )
5965 foreach $key ( @{ $options->{ "keys" } } )
5967 if ( $record->{ $key } )
5969 $sum_hash{ $key } += $record->{ $key };
5970 $count_hash{ $key }++;
5974 put_record( $record, $out ) if not $options->{ "no_stream" };
5977 $fh = write_stream( $options->{ "data_out" } );
5979 foreach $key ( @{ $options->{ "keys" } } )
5981 if ( $count_hash{ $key } ) {
5982 $mean = sprintf( "%.2f", ( $sum_hash{ $key } / $count_hash{ $key } ) );
5987 put_record( { $key . "_MEAN" => $mean } , $fh );
5994 sub script_median_vals
5996 # Martin A. Hansen, March 2008.
5998 # Calculate the median values of given keys.
6000 my ( $in, # handle to in stream
6001 $out, # handle to out stream
6002 $options, # options hash
6007 my ( $record, $key, %median_hash, $median, $fh );
6009 while ( $record = get_record( $in ) )
6011 foreach $key ( @{ $options->{ "keys" } } ) {
6012 push @{ $median_hash{ $key } }, $record->{ $key } if defined $record->{ $key };
6015 put_record( $record, $out ) if not $options->{ "no_stream" };
6018 $fh = write_stream( $options->{ "data_out" } );
6020 foreach $key ( @{ $options->{ "keys" } } )
6022 if ( $median_hash{ $key } ) {
6023 $median = Maasha::Calc::median( $median_hash{ $key } );
6028 put_record( { $key . "_MEDIAN" => $median } , $fh );
6037 # Martin A. Hansen, February 2008.
6039 # Determine the maximum values of given keys.
6041 my ( $in, # handle to in stream
6042 $out, # handle to out stream
6043 $options, # options hash
6048 my ( $record, $key, $fh, %max_hash, $max_record );
6050 while ( $record = get_record( $in ) )
6052 foreach $key ( @{ $options->{ "keys" } } )
6054 if ( $record->{ $key } )
6056 $max_hash{ $key } = $record->{ $key } if $record->{ $key } > $max_hash{ $key };
6060 put_record( $record, $out ) if not $options->{ "no_stream" };
6063 $fh = write_stream( $options->{ "data_out" } );
6065 foreach $key ( @{ $options->{ "keys" } } )
6067 $max_record->{ $key . "_MAX" } = $max_hash{ $key };
6070 put_record( $max_record, $fh );
6078 # Martin A. Hansen, February 2008.
6080 # Determine the minimum values of given keys.
6082 my ( $in, # handle to in stream
6083 $out, # handle to out stream
6084 $options, # options hash
6089 my ( $record, $key, $fh, %min_hash, $min_record );
6091 while ( $record = get_record( $in ) )
6093 foreach $key ( @{ $options->{ "keys" } } )
6095 if ( defined $record->{ $key } )
6097 if ( exists $min_hash{ $key } ) {
6098 $min_hash{ $key } = $record->{ $key } if $record->{ $key } < $min_hash{ $key };
6100 $min_hash{ $key } = $record->{ $key };
6105 put_record( $record, $out ) if not $options->{ "no_stream" };
6108 $fh = write_stream( $options->{ "data_out" } );
6110 foreach $key ( @{ $options->{ "keys" } } )
6112 $min_record->{ $key . "_MIN" } = $min_hash{ $key };
6115 put_record( $min_record, $fh );
6121 sub script_upload_to_ucsc
6123 # Martin A. Hansen, August 2007.
6125 # Calculate the mean of values of given keys.
6127 # This routine has developed into the most ugly hack. Do something!
6129 my ( $in, # handle to in stream
6130 $out, # handle to out stream
6131 $options, # options hash
6136 my ( $record, $file, $wib_file, $wig_file, $wib_dir, $fh_out, $i, $first, $format, $type, $columns, $append, $entry );
6138 $options->{ "short_label" } ||= $options->{ 'table' };
6139 $options->{ "long_label" } ||= $options->{ 'table' };
6140 $options->{ "group" } ||= $ENV{ "LOGNAME" };
6141 $options->{ "priority" } ||= 1;
6142 $options->{ "visibility" } ||= "pack";
6143 $options->{ "color" } ||= join( ",", int( rand( 255 ) ), int( rand( 255 ) ), int( rand( 255 ) ) );
6144 $options->{ "chunk_size" } ||= 10_000_000_000; # Due to 32-bit UCSC compilation really large tables cannot be loaded in one go.
6146 $file = "$BP_TMP/ucsc_upload.tmp";
6151 $fh_out = Maasha::Common::write_open( $file );
6153 while ( $record = get_record( $in ) )
6155 put_record( $record, $out ) if not $options->{ "no_stream" };
6157 if ( $record->{ "REC_TYPE" } eq "fixed_step" )
6161 if ( $entry = Maasha::UCSC::Wiggle::biopiece2fixedstep( $record ) ) {
6162 Maasha::UCSC::Wiggle::fixedstep_entry_put( $entry, $fh_out );
6165 elsif ( $record->{ "REC_TYPE" } eq "PSL" )
6169 Maasha::UCSC::psl_put_header( $fh_out ) if $first;
6170 Maasha::UCSC::psl_put_entry( $record, $fh_out );
6174 elsif ( $record->{ "REC_TYPE" } eq "BED" and $record->{ "SEC_STRUCT" } )
6176 # chrom chromStart chromEnd name score strand size secStr conf
6180 print $fh_out join ( "\t",
6182 $record->{ "CHR_BEG" },
6183 $record->{ "CHR_END" } + 1,
6184 $record->{ "Q_ID" },
6185 $record->{ "SCORE" },
6186 $record->{ "STRAND" },
6187 $record->{ "SIZE" },
6188 $record->{ "SEC_STRUCT" },
6189 $record->{ "CONF" },
6192 elsif ( $record->{ "REC_TYPE" } eq "BED" )
6195 $columns = $record->{ "BED_COLS" };
6197 if ( $entry = Maasha::UCSC::BED::biopiece2bed( $record, $columns ) ) {
6198 Maasha::UCSC::BED::bed_entry_put( $entry, $fh_out, $columns, 1 );
6201 elsif ( $record->{ "REC_TYPE" } eq "PATSCAN" and $record->{ "CHR" } )
6206 if ( $entry = Maasha::UCSC::BED::biopiece2bed( $record, $columns ) ) {
6207 Maasha::UCSC::BED::bed_entry_put( $entry, $fh_out, $columns, 1 );
6210 elsif ( $record->{ "REC_TYPE" } eq "BLAST" and $record->{ "S_ID" } =~ /^chr/ )
6215 $record->{ "SCORE" } = $record->{ "BIT_SCORE" } * 1000;
6217 if ( $entry = Maasha::UCSC::BED::biopiece2bed( $record, $columns ) ) {
6218 Maasha::UCSC::BED::bed_entry_put( $entry, $fh_out, $columns, 1 );
6221 elsif ( $record->{ "REC_TYPE" } eq "VMATCH" and $record->{ "S_ID" } =~ /^chr/i )
6226 if ( $entry = Maasha::UCSC::BED::biopiece2bed( $record, $columns ) ) {
6227 Maasha::UCSC::BED::bed_entry_put( $entry, $fh_out, $columns, 1 );
6231 if ( $i == $options->{ "chunk_size" } )
6235 if ( $format eq "BED" ) {
6236 Maasha::UCSC::bed_upload_to_ucsc( $BP_TMP, $file, $options, $append );
6237 } elsif ( $format eq "PSL" ) {
6238 Maasha::UCSC::psl_upload_to_ucsc( $file, $options, $append );
6247 $fh_out = Maasha::Common::write_open( $file );
6255 if ( exists $options->{ "database" } and $options->{ "table" } )
6257 if ( $format eq "BED" )
6259 $type = "bed $columns";
6261 Maasha::UCSC::bed_upload_to_ucsc( $BP_TMP, $file, $options, $append );
6263 elsif ( $format eq "BED_SS" )
6265 $type = "type bed 6 +";
6267 Maasha::UCSC::bed_upload_to_ucsc( $BP_TMP, $file, $options, $append );
6269 elsif ( $format eq "PSL" )
6273 Maasha::UCSC::psl_upload_to_ucsc( $file, $options, $append );
6275 elsif ( $format eq "WIGGLE" )
6277 $options->{ "visibility" } = "full";
6279 $wig_file = "$options->{ 'table' }.wig";
6280 $wib_file = "$options->{ 'table' }.wib";
6282 $wib_dir = "$ENV{ 'HOME' }/ucsc/wib";
6284 Maasha::Common::dir_create_if_not_exists( $wib_dir );
6286 if ( $options->{ 'verbose' } ) {
6287 `cd $BP_TMP && wigEncode $file $wig_file $wib_file`;
6289 `cd $BP_TMP && wigEncode $file $wig_file $wib_file > /dev/null 2>&1`;
6292 Maasha::Common::run( "mv", "$BP_TMP/$wib_file $wib_dir" );
6300 Maasha::UCSC::wiggle_upload_to_ucsc( $BP_TMP, $wib_dir, $file, $options );
6305 Maasha::UCSC::ucsc_update_config( $options, $type );
6310 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
6315 # Martin A. Hansen, November 2009.
6317 # Uses keys from a lookup hash to search records. Optionally, a list of
6318 # keys can be given so the lookup is limited to these, also, flags
6319 # can be given to limit lookup to keys or vals only. Returns 1 if lookup
6320 # succeeded, else 0.
6322 my ( $lookup_hash, # hashref with patterns
6324 $keys, # list of keys - OPTIONAL
6325 $vals_only, # only vals flag - OPTIONAL
6326 $keys_only, # only keys flag - OPTIONAL
6333 map { return 1 if exists $lookup_hash->{ $record->{ $_ } } } @{ $keys };
6337 if ( not $vals_only ) {
6338 map { return 1 if exists $lookup_hash->{ $_ } } keys %{ $record };
6341 if ( not $keys_only ) {
6342 map { return 1 if exists $lookup_hash->{ $record->{ $_ } } } keys %{ $record };
6352 # Martin A. Hansen, November 2009.
6354 # Uses patterns to match records containing the pattern as a substring.
6355 # Returns 1 if the record is matched, else 0.
6357 my ( $patterns, # list of patterns
6359 $keys, # list of keys - OPTIONAL
6360 $vals_only, # only vals flag - OPTIONAL
6361 $keys_only, # only keys flag - OPTIONAL
6368 foreach $pattern ( @{ $patterns } )
6372 map { return 1 if index( $record->{ $_ }, $pattern ) >= 0 } @{ $keys };
6376 if ( not $vals_only ) {
6377 map { return 1 if index( $_, $pattern ) >= 0 } keys %{ $record };
6380 if ( not $keys_only ) {
6381 map { return 1 if index( $record->{ $_ }, $pattern ) >= 0 } keys %{ $record };
6392 # Martin A. Hansen, November 2009.
6394 # Uses regex to match records.
6395 # Returns 1 if the record is matched, else 0.
6397 my ( $regex, # regex to match
6399 $keys, # list of keys - OPTIONAL
6400 $vals_only, # only vals flag - OPTIONAL
6401 $keys_only, # only keys flag - OPTIONAL
6408 map { return 1 if $record->{ $_ } =~ /$regex/ } @{ $keys };
6412 if ( not $vals_only ) {
6413 map { return 1 if $_ =~ /$regex/ } keys %{ $record };
6416 if ( not $keys_only ) {
6417 map { return 1 if $record->{ $_ } =~ /$regex/ } keys %{ $record };
6427 # Martin A. Hansen, November 2009.
6429 # Test if the value of a given record key evaluates according
6430 # to a given operator. Returns 1 if eval is OK, else 0.
6432 my ( $key, # record key
6440 if ( defined $record->{ $key } )
6442 return 1 if ( $op eq "<" and $record->{ $key } < $val );
6443 return 1 if ( $op eq ">" and $record->{ $key } > $val );
6444 return 1 if ( $op eq ">=" and $record->{ $key } >= $val );
6445 return 1 if ( $op eq "<=" and $record->{ $key } <= $val );
6446 return 1 if ( $op eq "=" and $record->{ $key } == $val );
6447 return 1 if ( $op eq "!=" and $record->{ $key } != $val );
6448 return 1 if ( $op eq "eq" and $record->{ $key } eq $val );
6449 return 1 if ( $op eq "ne" and $record->{ $key } ne $val );
6458 # Martin A. Hansen, July 2007.
6460 # Opens a stream to STDIN or a file,
6462 my ( $path, # path - OPTIONAL
6465 # Returns filehandle.
6469 if ( not -t STDIN ) {
6470 $fh = Maasha::Common::read_stdin();
6471 } elsif ( not $path ) {
6472 # Maasha::Common::error( qq(no data stream) );
6474 $fh = Maasha::Common::read_open( $path );
6477 # $fh->autoflush(1) if $fh; # Disable file buffer for debugging.
6485 # Martin A. Hansen, August 2007.
6487 # Opens a stream to STDOUT or a file.
6489 my ( $path, # path - OPTIONAL
6490 $gzip, # compress data - OPTIONAL
6493 # Returns filehandle.
6498 $fh = Maasha::Common::write_open( $path, $gzip );
6500 $fh = Maasha::Common::write_stdout();
6509 # Martin A. Hansen, July 2007.
6511 # Reads one record at a time and converts that record
6512 # to a Perl data structure (a hash) which is returned.
6514 my ( $fh, # handle to stream
6519 my ( $block, @lines, $line, $key, $value, %record );
6521 local $/ = "\n---\n";
6527 return if not defined $block;
6529 @lines = split "\n", $block;
6531 foreach $line ( @lines )
6533 ( $key, $value ) = split ": ", $line, 2;
6535 $record{ $key } = $value;
6538 return wantarray ? %record : \%record;
6544 # Martin A. Hansen, July 2007.
6546 # Given a Perl datastructure (a hash ref) emits this to STDOUT or a filehandle.
6548 my ( $data, # data structure
6549 $fh, # file handle - OPTIONAL
6554 if ( scalar keys %{ $data } )
6558 map { print $fh "$_: $data->{ $_ }\n" } keys %{ $data };
6563 map { print "$_: $data->{ $_ }\n" } keys %{ $data };
6574 # Martin A. Hansen, November 2007.
6576 # Extracts files from an explicit GetOpt::Long argument
6577 # allowing for the use of glob. E.g.
6578 # --data_in=test.fna
6579 # --data_in=test.fna,test2.fna
6581 # --data_in=test.fna,/dir/*.fna
6583 my ( $option, # option from GetOpt::Long
6588 my ( $elem, @files );
6590 foreach $elem ( split ",", $option )
6594 } elsif ( $elem =~ /\*/ ) {
6595 push @files, glob( $elem );
6599 return wantarray ? @files : \@files;
6605 # Martin A. Hansen, April 2008.
6607 # Removes temporary directory and exits gracefully.
6608 # This subroutine is meant to be run always as the last
6609 # thing even if a script is dies or is interrupted
6612 my ( $sig, # signal from the %SIG
6615 # print STDERR "signal->$sig<-\n";
6623 if ( $sig =~ /MAASHA_ERROR/ ) {
6624 print STDERR "\nProgram '$script' had an error" . " - Please wait for temporary data to be removed\n";
6625 } elsif ( $sig eq "INT" ) {
6626 print STDERR "\nProgram '$script' interrupted (ctrl-c was pressed)" . " - Please wait for temporary data to be removed\n";
6627 } elsif ( $sig eq "TERM" ) {
6628 print STDERR "\nProgram '$script' terminated (someone used kill?)" . " - Please wait for temporary data to be removed\n";
6630 print STDERR "\nProgram '$script' died->$sig" . " - Please wait for temporary data to be removed\n";
6642 # Martin A. Hansen, July 2008.
6644 # Cleans out any unused temporary files and directories in BP_TMP.
6648 my ( $tmpdir, @dirs, $curr_pid, $dir, $user, $sid, $pid );
6650 $tmpdir = $ENV{ 'BP_TMP' } || Maasha::Common::error( 'No BP_TMP variable in environment.' );
6652 $curr_pid = Maasha::Common::get_processid();
6654 @dirs = Maasha::Common::ls_dirs( $tmpdir );
6656 foreach $dir ( @dirs )
6658 if ( $dir =~ /^$tmpdir\/(.+)_(\d+)_(\d+)_bp_tmp$/ )
6664 if ( $user eq Maasha::Common::get_user() )
6666 if ( not Maasha::Common::process_running( $pid ) )
6668 # print STDERR "Removing stale dir: $dir\n";
6669 Maasha::Common::dir_remove( $dir );
6671 elsif ( $pid == $curr_pid )
6673 # print STDERR "Removing current dir: $dir\n";
6674 # Maasha::Common::dir_remove( $dir );
6688 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<