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" )
334 elsif ( $script eq "read_fixedstep" )
341 elsif ( $script eq "read_blast_tab" )
348 elsif ( $script eq "read_embl" )
358 elsif ( $script eq "read_stockholm" )
365 elsif ( $script eq "read_phastcons" )
376 elsif ( $script eq "read_soft" )
384 elsif ( $script eq "read_gff" )
391 elsif ( $script eq "read_2bit" )
399 elsif ( $script eq "read_solexa" )
408 elsif ( $script eq "read_solid" )
416 elsif ( $script eq "read_mysql" )
425 elsif ( $script eq "read_ucsc_config" )
432 elsif ( $script eq "assemble_tag_contigs" )
438 elsif ( $script eq "calc_fixedstep" )
444 elsif ( $script eq "format_genome" )
453 elsif ( $script eq "length_seq" )
460 elsif ( $script eq "oligo_freq" )
467 elsif ( $script eq "create_weight_matrix" )
473 elsif ( $script eq "transliterate_seq" )
481 elsif ( $script eq "transliterate_vals" )
490 elsif ( $script eq "translate_seq" )
496 elsif ( $script eq "extract_seq" )
504 elsif ( $script eq "get_genome_seq" )
516 elsif ( $script eq "get_genome_align" )
527 elsif ( $script eq "get_genome_phastcons" )
538 elsif ( $script eq "split_seq" )
545 elsif ( $script eq "split_bed" )
552 elsif ( $script eq "tile_seq" )
559 elsif ( $script eq "invert_align" )
565 elsif ( $script eq "patscan_seq" )
576 elsif ( $script eq "create_blast_db" )
583 elsif ( $script eq "blast_seq" )
595 elsif ( $script eq "blat_seq" )
607 elsif ( $script eq "soap_seq" )
618 elsif ( $script eq "match_seq" )
625 elsif ( $script eq "create_vmatch_index" )
633 elsif ( $script eq "vmatch_seq" )
644 elsif ( $script eq "write_fasta" )
653 elsif ( $script eq "write_align" )
663 elsif ( $script eq "write_blast" )
672 elsif ( $script eq "write_tab" )
684 elsif ( $script eq "write_bed" )
694 elsif ( $script eq "write_psl" )
702 elsif ( $script eq "write_fixedstep" )
710 elsif ( $script eq "write_2bit" )
718 elsif ( $script eq "write_solid" )
727 elsif ( $script eq "write_ucsc_config" )
734 elsif ( $script eq "plot_seqlogo" )
741 elsif ( $script eq "plot_phastcons_profiles" )
756 elsif ( $script eq "analyze_vals" )
763 elsif ( $script eq "head_records" )
769 elsif ( $script eq "remove_keys" )
776 elsif ( $script eq "remove_adaptor" )
785 elsif ( $script eq "remove_mysql_tables" )
796 elsif ( $script eq "remove_ucsc_tracks" )
808 elsif ( $script eq "rename_keys" )
814 elsif ( $script eq "uniq_vals" )
821 elsif ( $script eq "merge_vals" )
828 elsif ( $script eq "merge_records" )
835 elsif ( $script eq "grab" )
850 elsif ( $script eq "compute" )
856 elsif ( $script eq "add_ident" )
863 elsif ( $script eq "count_records" )
870 elsif ( $script eq "random_records" )
876 elsif ( $script eq "sort_records" )
883 elsif ( $script eq "count_vals" )
889 elsif ( $script eq "plot_histogram" )
902 elsif ( $script eq "plot_lendist" )
914 elsif ( $script eq "plot_chrdist" )
925 elsif ( $script eq "plot_karyogram" )
934 elsif ( $script eq "plot_matches" )
946 elsif ( $script eq "length_vals" )
952 elsif ( $script eq "sum_vals" )
960 elsif ( $script eq "mean_vals" )
968 elsif ( $script eq "median_vals" )
976 elsif ( $script eq "max_vals" )
984 elsif ( $script eq "min_vals" )
992 elsif ( $script eq "upload_to_ucsc" )
1016 # print STDERR Dumper( \@options );
1023 # print STDERR Dumper( \%options );
1025 if ( -t STDIN && scalar( keys %options ) == 0 or $options{ "help" } ) {
1026 return wantarray ? %options : \%options;
1029 $options{ "cols" } = [ split ",", $options{ "cols" } ] if defined $options{ "cols" };
1030 $options{ "keys" } = [ split ",", $options{ "keys" } ] if defined $options{ "keys" };
1031 $options{ "no_keys" } = [ split ",", $options{ "no_keys" } ] if defined $options{ "no_keys" };
1032 $options{ "save_keys" } = [ split ",", $options{ "save_keys" } ] if defined $options{ "save_keys" };
1033 $options{ "quals" } = [ split ",", $options{ "quals" } ] if defined $options{ "quals" };
1034 $options{ "feats" } = [ split ",", $options{ "feats" } ] if defined $options{ "feats" };
1035 $options{ "frames" } = [ split ",", $options{ "frames" } ] if defined $options{ "frames" };
1036 $options{ "formats" } = [ split ",", $options{ "formats" } ] if defined $options{ "formats" };
1037 $options{ "samples" } = [ split ",", $options{ "samples" } ] if defined $options{ "samples" };
1038 $options{ "tables" } = [ split ",", $options{ "tables" } ] if defined $options{ "tables" };
1039 $options{ "tracks" } = [ split ",", $options{ "tracks" } ] if defined $options{ "tracks" };
1041 # ---- check arguments ----
1043 if ( $options{ 'data_in' } )
1045 $options{ "files" } = getopt_files( $options{ 'data_in' } );
1047 Maasha::Common::error( qq(Argument to --data_in must be a valid file or fileglob expression) ) if scalar @{ $options{ "files" } } == 0;
1050 map { Maasha::Common::error( qq(Argument to --cols must be a whole numbers - not "$_") ) if $_ !~ /^\d+$/ } @{ $options{ "cols" } } if $options{ "cols" };
1052 # print STDERR Dumper( \%options );
1054 $real = "beg|end|word_size|wrap|tile_size|len|prefix_length|mismatches|offset|num|skip|cpus|window_size|step_size";
1056 foreach $opt ( keys %options )
1058 if ( $opt =~ /stream_in|pattern_in|exact_in/ and not -f $options{ $opt } )
1060 Maasha::Common::error( qq(Argument to --$opt must be a valid file or fileglob expression - not "$options{ $opt }") );
1062 elsif ( $opt =~ /$real/ and $options{ $opt } !~ /^\d+$/ )
1064 Maasha::Common::error( qq(Argument to --$opt must be a whole number - not "$options{ $opt }") );
1066 elsif ( $opt =~ /max_hits|max_hits|max_misses|dist|edit_dist|flank|gap|hamming_dist|priority/ and $options{ $opt } !~ /^-?\d+$/ )
1068 Maasha::Common::error( qq(Argument to --$opt must be an integer - not "$options{ $opt }") );
1070 elsif ( $opt =~ /identity|threshold/ and $options{ $opt } !~ /^-?(?:\d+(?:\.\d*)?|\.\d+)$/ )
1072 Maasha::Common::error( qq(Argument to --$opt must be a decimal number - not "$options{ $opt }") );
1074 elsif ( $opt =~ /e_val/ and $options{ $opt } !~ /^([+-]?)(?=\d|\.\d)\d*(\.\d*)?([Ee]([+-]?\d+))?$/ )
1076 Maasha::Common::error( qq(Argument to --$opt must be a float - not "$options{ $opt }") );
1078 elsif ( $opt =~ /strand/ and $options{ $opt } !~ /^(\+|-)$/ )
1080 Maasha::Common::error( qq(Argument to --$opt must be "+" or "-" - not "$options{ $opt }") );
1082 elsif ( $opt eq "genome" and $script ne "format_genome" )
1084 @genomes = Maasha::Common::ls_dirs( "$ENV{ 'BP_DATA' }/genomes" );
1085 map { $_ =~ s/.*\/(.+)$/$1/ } @genomes;
1087 if ( not grep { $_ =~ /^$options{ $opt }$/ } @genomes ) {
1088 Maasha::Common::error( qq(Genome $options{ $opt } not found in "$ENV{ 'BP_DATA' }/genomes/") );
1091 elsif ( $opt eq "terminal" and not $options{ $opt } =~ /^(svg|post|dumb|x11)/ )
1093 Maasha::Common::error( qq(Bad --$opt argument "$options{ $opt }") );
1095 elsif ( $opt eq "table" and $options{ $opt } =~ /(-|\.)/ )
1097 Maasha::Common::error( qq(Character '$1' is not allowed in table name: $options{ $opt }) );
1099 elsif ( $opt eq "merge" and $options{ $opt } !~ /^(AandB|AorB|BorA|AnotB|BnotA)$/ )
1101 Maasha::Common::error( qq(Argument to --$opt must be AandB, AorB, BorA, AnotB, or BnotA - not "$options{ $opt }") );
1103 elsif ( $opt eq "format" and $script eq "read_solexa" and $options{ $opt } !~ /octal|decimal/ )
1105 Maasha::Common::error( qq(Argument to --$opt must be octal or decimal - not "$options{ $opt }") );
1107 elsif ( $opt eq "remove" and $script eq "remove_adaptor" and $options{ $opt } !~ /before|after|skip/ )
1109 Maasha::Common::error( qq(Argument to --$opt must be before, after, or skip - not "$options{ $opt }") );
1113 Maasha::Common::error( qq(no --database specified) ) if $script eq "create_blast_db" and not $options{ "database" };
1114 Maasha::Common::error( qq(no --index_name specified) ) if $script =~ /create_vmatch_index/ and not $options{ "index_name" };
1115 Maasha::Common::error( qq(no --database or --genome specified) ) if $script eq "blast_seq" and not $options{ "genome" } and not $options{ "database" };
1116 Maasha::Common::error( qq(both --database and --genome specified) ) if $script eq "blast_seq" and $options{ "genome" } and $options{ "database" };
1117 Maasha::Common::error( qq(no --index_name or --genome specified) ) if $script eq "vmatch_seq" and not $options{ "genome" } and not $options{ "index_name" };
1118 Maasha::Common::error( qq(both --index and --genome specified) ) if $script eq "vmatch_seq" and $options{ "genome" } and $options{ "index_name" };
1119 Maasha::Common::error( qq(no --in_file or --genome specified) ) if $script eq "soap_seq" and not $options{ "genome" } and not $options{ "in_file" };
1120 Maasha::Common::error( qq(both --in_file and --genome specified) ) if $script eq "soap_seq" and $options{ "genome" } and $options{ "in_file" };
1121 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" };
1122 Maasha::Common::error( qq(no --key specified) ) if $script =~ /plot_lendist|plot_histogram/ and not $options{ "key" };
1123 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" };
1125 if ( $script eq "upload_to_ucsc" )
1127 Maasha::Common::error( qq(no --database specified) ) if not $options{ "database" };
1128 Maasha::Common::error( qq(no --table specified) ) if not $options{ "table" };
1131 return wantarray ? %options : \%options;
1135 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> SCRIPTS <<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
1138 sub script_print_usage
1140 # Martin A. Hansen, January 2008.
1142 # Retrieves usage information from file and
1143 # prints this nicely formatted.
1145 my ( $in, # handle to in stream
1146 $out, # handle to out stream
1147 $options, # options hash
1152 my ( $file, $wiki, $lines );
1154 if ( $options->{ 'data_in' } ) {
1155 $file = $options->{ 'data_in' };
1157 $file = join "", $ENV{ 'BP_DIR' }, "/bp_usage/", $options->{ 'SCRIPT' }, ".wiki";
1160 $wiki = Maasha::Gwiki::gwiki_read( $file );
1162 if ( not $options->{ "help" } ) {
1163 @{ $wiki } = grep { $_->[ 0 ]->{ 'SECTION' } =~ /Biopiece|Synopsis|Usage|Options|Help/ } @{ $wiki };
1166 $lines = Maasha::Gwiki::gwiki2ascii( $wiki );
1168 print STDERR "$_\n" foreach @{ $lines };
1174 sub script_list_biopieces
1176 # Martin A. Hansen, January 2008.
1178 # Prints the synopsis from the usage for each of the biopieces.
1180 my ( $in, # handle to in stream
1181 $out, # handle to out stream
1182 $options, # options hash
1187 my ( @files, $file, $wiki, $program, $synopsis );
1189 @files = Maasha::Common::ls_files( "$ENV{ 'BP_DIR' }/bp_usage" );
1191 foreach $file ( sort @files )
1193 if ( $file =~ /\/([a-z0-9_]+)\.wiki$/ )
1197 $wiki = Maasha::Gwiki::gwiki_read( $file );
1199 @{ $wiki } = grep { $_->[ 0 ]->{ 'SECTION' } =~ /Synopsis/ } @{ $wiki };
1200 @{ $wiki } = grep { $_->[ 0 ]->{ 'FORMAT' } =~ /paragraph/ } @{ $wiki };
1202 $synopsis = $wiki->[ 0 ]->[ 0 ]->{ 'TEXT' };
1203 $synopsis =~ s/!(\w)/$1/g;
1205 printf( "%-30s%s\n", $program, $synopsis );
1213 sub script_list_genomes
1215 # Martin A. Hansen, January 2008.
1217 # Prints the synopsis from the usage for each of the biopieces.
1219 my ( $in, # handle to in stream
1220 $out, # handle to out stream
1221 $options, # options hash
1226 my ( @genomes, $genome, @formats, $format, %hash, %found, @row );
1228 @genomes = Maasha::Common::ls_dirs( "$ENV{ 'BP_DATA' }/genomes" );
1230 foreach $genome ( @genomes )
1232 next if $genome =~ /\.$/;
1234 @formats = Maasha::Common::ls_dirs( $genome );
1236 foreach $format ( @formats )
1238 if ( $format =~ /\/([^\/]+)\/(\w+)$/ )
1240 $hash{ $1 }{ $2 } = 1;
1249 map { push @row, $_ } sort keys %found;
1251 print join( "\t", @row ), "\n";
1253 foreach $genome ( sort keys %hash )
1257 foreach $format ( sort keys %found )
1259 if ( exists $hash{ $genome }{ $format } ) {
1266 print join( "\t", @row ), "\n";
1271 sub script_read_fasta
1273 # Martin A. Hansen, August 2007.
1275 # Read sequences from FASTA file.
1277 my ( $in, # handle to in stream
1278 $out, # handle to out stream
1279 $options, # options hash
1284 my ( $record, $file, $data_in, $entry, $num );
1286 while ( $record = get_record( $in ) ) {
1287 put_record( $record, $out );
1292 foreach $file ( @{ $options->{ "files" } } )
1294 $data_in = Maasha::Common::read_open( $file );
1296 while ( $entry = Maasha::Fasta::get_entry( $data_in ) )
1298 if ( defined $entry->[ SEQ_NAME ] and $entry->[ SEQ ] )
1301 SEQ_NAME => $entry->[ SEQ_NAME ],
1302 SEQ => $entry->[ SEQ ],
1303 SEQ_LEN => length $entry->[ SEQ ],
1306 put_record( $record, $out );
1309 goto NUM if $options->{ "num" } and $num == $options->{ "num" };
1319 close $data_in if $data_in;
1325 # Martin A. Hansen, August 2007.
1327 # Read table or table columns from stream or file.
1329 my ( $in, # handle to in stream
1330 $out, # handle to out stream
1331 $options, # options hash
1336 my ( $file, $line, @fields, @fields2, $i, $record, $data_in, $skip, $num );
1338 $options->{ 'delimit' } ||= '\s+';
1340 while ( $record = get_record( $in ) ) {
1341 put_record( $record, $out );
1344 $skip = $options->{ 'skip' } ||= 0;
1347 foreach $file ( @{ $options->{ "files" } } )
1349 $data_in = Maasha::Common::read_open( $file );
1351 while ( $line = <$data_in> )
1359 next if $line =~ /^#|^$/;
1366 @fields = split /$options->{'delimit'}/, $line;
1368 if ( $options->{ "cols" } ) {
1369 map { push @fields2, $fields[ $_ ] } @{ $options->{ "cols" } };
1374 for ( $i = 0; $i < @fields2; $i++ )
1376 if ( $options->{ "keys" }->[ $i ] ) {
1377 $record->{ $options->{ "keys" }->[ $i ] } = $fields2[ $i ];
1379 $record->{ "V" . $i } = $fields2[ $i ];
1383 put_record( $record, $out );
1385 goto NUM if $options->{ "num" } and $num == $options->{ "num" };
1395 close $data_in if $data_in;
1401 # Martin A. Hansen, August 2007.
1403 # Read psl table from stream or file.
1405 my ( $in, # handle to in stream
1406 $out, # handle to out stream
1407 $options, # options hash
1412 my ( $record, $file, $data_in, $num );
1414 while ( $record = get_record( $in ) ) {
1415 put_record( $record, $out );
1420 foreach $file ( @{ $options->{ "files" } } )
1422 $data_in = Maasha::Common::read_open( $file );
1424 while ( $record = Maasha::UCSC::psl_get_entry( $data_in ) )
1426 put_record( $record, $out );
1428 goto NUM if $options->{ "num" } and $num == $options->{ "num" };
1440 # Martin A. Hansen, August 2007.
1442 # Read bed table from stream or file.
1444 my ( $in, # handle to in stream
1445 $out, # handle to out stream
1446 $options, # options hash
1451 my ( $cols, $file, $record, $bed_entry, $data_in, $num );
1453 $cols = $options->{ 'cols' }->[ 0 ];
1455 while ( $record = get_record( $in ) ) {
1456 put_record( $record, $out );
1461 foreach $file ( @{ $options->{ "files" } } )
1463 $data_in = Maasha::Common::read_open( $file );
1465 while ( $bed_entry = Maasha::UCSC::BED::bed_entry_get( $data_in, $cols, $options->{ 'check' } ) )
1467 $record = Maasha::UCSC::BED::bed2biopiece( $bed_entry );
1469 put_record( $record, $out );
1471 goto NUM if $options->{ "num" } and $num == $options->{ "num" };
1481 close $data_in if $data_in;
1485 sub script_read_fixedstep
1487 # Martin A. Hansen, Juli 2008.
1489 # Read fixedstep wiggle format from stream or file.
1491 my ( $in, # handle to in stream
1492 $out, # handle to out stream
1493 $options, # options hash
1498 my ( $file, $record, $entry, $data_in, $num );
1500 while ( $record = get_record( $in ) ) {
1501 put_record( $record, $out );
1506 foreach $file ( @{ $options->{ "files" } } )
1508 $data_in = Maasha::Common::read_open( $file );
1510 while ( $entry = Maasha::UCSC::Wiggle::fixedstep_entry_get( $data_in ) )
1512 $record = Maasha::UCSC::Wiggle::fixedstep2biopiece( $entry );
1514 put_record( $record, $out );
1516 goto NUM if $options->{ "num" } and $num == $options->{ "num" };
1526 close $data_in if $data_in;
1530 sub script_read_blast_tab
1532 # Martin A. Hansen, September 2007.
1534 # Read tabular BLAST output from NCBI blast run with -m8 or -m9.
1536 my ( $in, # handle to in stream
1537 $out, # handle to out stream
1538 $options, # options hash
1543 my ( $file, $line, @fields, $strand, $record, $data_in, $num );
1545 while ( $record = get_record( $in ) ) {
1546 put_record( $record, $out );
1551 foreach $file ( @{ $options->{ "files" } } )
1553 $data_in = Maasha::Common::read_open( $file );
1555 while ( $line = <$data_in> )
1559 next if $line =~ /^#/;
1561 @fields = split /\t/, $line;
1563 $record->{ "REC_TYPE" } = "BLAST";
1564 $record->{ "Q_ID" } = $fields[ 0 ];
1565 $record->{ "S_ID" } = $fields[ 1 ];
1566 $record->{ "IDENT" } = $fields[ 2 ];
1567 $record->{ "ALIGN_LEN" } = $fields[ 3 ];
1568 $record->{ "MISMATCHES" } = $fields[ 4 ];
1569 $record->{ "GAPS" } = $fields[ 5 ];
1570 $record->{ "Q_BEG" } = $fields[ 6 ] - 1; # BLAST is 1-based
1571 $record->{ "Q_END" } = $fields[ 7 ] - 1; # BLAST is 1-based
1572 $record->{ "S_BEG" } = $fields[ 8 ] - 1; # BLAST is 1-based
1573 $record->{ "S_END" } = $fields[ 9 ] - 1; # BLAST is 1-based
1574 $record->{ "E_VAL" } = $fields[ 10 ];
1575 $record->{ "BIT_SCORE" } = $fields[ 11 ];
1577 if ( $record->{ "S_BEG" } > $record->{ "S_END" } )
1579 $record->{ "STRAND" } = '-';
1581 ( $record->{ "S_BEG" }, $record->{ "S_END" } ) = ( $record->{ "S_END" }, $record->{ "S_BEG" } );
1585 $record->{ "STRAND" } = '+';
1588 put_record( $record, $out );
1590 goto NUM if $options->{ "num" } and $num == $options->{ "num" };
1600 close $data_in if $data_in;
1604 sub script_read_embl
1606 # Martin A. Hansen, August 2007.
1610 my ( $in, # handle to in stream
1611 $out, # handle to out stream
1612 $options, # options hash
1617 my ( %options2, $file, $data_in, $num, $entry, $record );
1619 map { $options2{ "keys" }{ $_ } = 1 } @{ $options->{ "keys" } };
1620 map { $options2{ "feats" }{ $_ } = 1 } @{ $options->{ "feats" } };
1621 map { $options2{ "quals" }{ $_ } = 1 } @{ $options->{ "quals" } };
1623 while ( $record = get_record( $in ) ) {
1624 put_record( $record, $out );
1629 foreach $file ( @{ $options->{ "files" } } )
1631 $data_in = Maasha::Common::read_open( $file );
1633 while ( $entry = Maasha::EMBL::get_embl_entry( $data_in ) )
1635 $record = Maasha::EMBL::parse_embl_entry( $entry, \%options2 );
1637 my ( $feat, $feat2, $qual, $qual_val, $record_copy );
1639 $record_copy = dclone $record;
1641 delete $record_copy->{ "FT" };
1643 put_record( $record_copy, $out );
1645 delete $record_copy->{ "SEQ" };
1647 foreach $feat ( keys %{ $record->{ "FT" } } )
1649 $record_copy->{ "FEAT_TYPE" } = $feat;
1651 foreach $feat2 ( @{ $record->{ "FT" }->{ $feat } } )
1653 foreach $qual ( keys %{ $feat2 } )
1655 $qual_val = join "; ", @{ $feat2->{ $qual } };
1660 $record_copy->{ $qual } = $qual_val;
1663 put_record( $record_copy, $out );
1667 goto NUM if $options->{ "num" } and $num == $options->{ "num" };
1677 close $data_in if $data_in;
1681 sub script_read_stockholm
1683 # Martin A. Hansen, August 2007.
1685 # Read Stockholm format.
1687 my ( $in, # handle to in stream
1688 $out, # handle to out stream
1689 $options, # options hash
1694 my ( $data_in, $file, $num, $entry, $record, $record_anno, $record_align, $key, $seq );
1696 while ( $record = get_record( $in ) ) {
1697 put_record( $record, $out );
1702 foreach $file ( @{ $options->{ "files" } } )
1704 $data_in = Maasha::Common::read_open( $file );
1706 while ( $entry = Maasha::Stockholm::get_stockholm_entry( $data_in ) )
1708 $record = Maasha::Stockholm::parse_stockholm_entry( $entry );
1712 foreach $key ( keys %{ $record->{ "GF" } } ) {
1713 $record_anno->{ $key } = $record->{ "GF" }->{ $key };
1716 $record_anno->{ "ALIGN" } = $num;
1718 put_record( $record_anno, $out );
1720 foreach $seq ( @{ $record->{ "ALIGN" } } )
1722 undef $record_align;
1725 SEQ_NAME => $seq->[ 0 ],
1729 put_record( $record_align, $out );
1732 goto NUM if $options->{ "num" } and $num == $options->{ "num" };
1742 close $data_in if $data_in;
1746 sub script_read_phastcons
1748 # Martin A. Hansen, December 2007.
1750 # Read PhastCons format.
1752 my ( $in, # handle to in stream
1753 $out, # handle to out stream
1754 $options, # options hash
1759 my ( $data_in, $file, $num, $entry, @records, $record );
1761 $options->{ "min" } ||= 10;
1762 $options->{ "dist" } ||= 25;
1763 $options->{ "threshold" } ||= 0.8;
1764 $options->{ "gap" } ||= 5;
1766 while ( $record = get_record( $in ) ) {
1767 put_record( $record, $out );
1772 foreach $file ( @{ $options->{ "files" } } )
1774 $data_in = Maasha::Common::read_open( $file );
1776 while ( $entry = Maasha::UCSC::fixedstep_get_entry( $data_in ) )
1778 @records = Maasha::UCSC::phastcons_parse_entry( $entry, $options );
1780 foreach $record ( @records )
1782 $record->{ "REC_TYPE" } = "BED";
1783 $record->{ "BED_LEN" } = $record->{ "CHR_END" } - $record->{ "CHR_BEG" } + 1;
1785 put_record( $record, $out );
1787 goto NUM if $options->{ "num" } and $num == $options->{ "num" };
1798 close $data_in if $data_in;
1802 sub script_read_soft
1804 # Martin A. Hansen, December 2007.
1807 # http://www.ncbi.nlm.nih.gov/geo/info/soft2.html
1809 my ( $in, # handle to in stream
1810 $out, # handle to out stream
1811 $options, # options hash
1816 my ( $data_in, $file, $num, $records, $record, $soft_index, $fh, @platforms, $plat_table, @samples, $sample, $old_end, $skip );
1818 while ( $record = get_record( $in ) ) {
1819 put_record( $record, $out );
1824 foreach $file ( @{ $options->{ "files" } } )
1826 print STDERR "Creating index for file: $file\n" if $options->{ "verbose" };
1828 $soft_index = Maasha::NCBI::soft_index_file( $file );
1830 $fh = Maasha::Common::read_open( $file );
1832 @platforms = grep { $_->{ "SECTION" } =~ /PLATFORM/ } @{ $soft_index };
1834 print STDERR "Getting platform tables for file: $file\n" if $options->{ "verbose" };
1836 $plat_table = Maasha::NCBI::soft_get_platform( $fh, $platforms[ 0 ]->{ "LINE_BEG" }, $platforms[ -1 ]->{ "LINE_END" } );
1838 @samples = grep { $_->{ "SECTION" } =~ /SAMPLE/ } @{ $soft_index };
1840 $old_end = $platforms[ -1 ]->{ "LINE_END" };
1842 foreach $sample ( @samples )
1845 $skip = 1 if ( $options->{ "samples" } and grep { $sample->{ "SECTION" } !~ /$_/ } @{ $options->{ "samples" } } );
1847 print STDERR "Getting samples for dataset: $sample->{ 'SECTION' }\n" if $options->{ "verbose" } and not $skip;
1849 $records = Maasha::NCBI::soft_get_sample( $fh, $plat_table, $sample->{ "LINE_BEG" } - $old_end - 1, $sample->{ "LINE_END" } - $old_end - 1, $skip );
1851 foreach $record ( @{ $records } )
1853 put_record( $record, $out );
1855 goto NUM if $options->{ "num" } and $num == $options->{ "num" };
1860 $old_end = $sample->{ "LINE_END" };
1868 close $data_in if $data_in;
1875 # Martin A. Hansen, February 2008.
1878 # http://www.ncbi.nlm.nih.gov/geo/info/soft2.html
1880 my ( $in, # handle to in stream
1881 $out, # handle to out stream
1882 $options, # options hash
1887 my ( $data_in, $file, $fh, $num, $record, $entry );
1889 while ( $record = get_record( $in ) ) {
1890 put_record( $record, $out );
1895 foreach $file ( @{ $options->{ "files" } } )
1897 $fh = Maasha::Common::read_open( $file );
1899 while ( $entry = Maasha::GFF::get_entry( $fh ) )
1901 put_record( $entry, $out );
1903 goto NUM if $options->{ "num" } and $num == $options->{ "num" };
1913 close $data_in if $data_in;
1917 sub script_read_2bit
1919 # Martin A. Hansen, March 2008.
1921 # Read sequences from 2bit file.
1923 my ( $in, # handle to in stream
1924 $out, # handle to out stream
1925 $options, # options hash
1930 my ( $record, $file, $data_in, $mask, $toc, $line, $num );
1932 $mask = 1 if not $options->{ "no_mask" };
1934 while ( $record = get_record( $in ) ) {
1935 put_record( $record, $out );
1940 foreach $file ( @{ $options->{ "files" } } )
1942 $data_in = Maasha::Common::read_open( $file );
1944 $toc = Maasha::TwoBit::twobit_get_TOC( $data_in );
1946 foreach $line ( @{ $toc } )
1948 $record->{ "SEQ_NAME" } = $line->[ 0 ];
1949 $record->{ "SEQ" } = Maasha::TwoBit::twobit_get_seq( $data_in, $line->[ 1 ], undef, undef, $mask );
1950 $record->{ "SEQ_LEN" } = length $record->{ "SEQ" };
1952 put_record( $record, $out );
1954 goto NUM if $options->{ "num" } and $num == $options->{ "num" };
1964 close $data_in if $data_in;
1968 sub script_read_solexa
1970 # Martin A. Hansen, March 2008.
1972 # Read Solexa sequence reads from file.
1974 my ( $in, # handle to in stream
1975 $out, # handle to out stream
1976 $options, # options hash
1981 my ( $record, $file, $data_in, $entry, $num, @seqs, @scores, $i );
1983 $options->{ "format" } ||= "octal";
1984 $options->{ "quality" } ||= 20;
1986 while ( $record = get_record( $in ) ) {
1987 put_record( $record, $out );
1992 foreach $file ( @{ $options->{ "files" } } )
1994 $data_in = Maasha::Common::read_open( $file );
1996 if ( $options->{ "format" } eq "octal" )
1998 while ( $entry = Maasha::Solexa::solexa_get_entry_octal( $data_in ) )
2000 $record = Maasha::Solexa::solexa2biopiece( $entry, $options->{ "quality" } );
2002 put_record( $record, $out );
2004 goto NUM if $options->{ "num" } and $num == $options->{ "num" };
2011 while ( $entry = Maasha::Solexa::solexa_get_entry_decimal( $data_in ) )
2013 $record = Maasha::Solexa::solexa2biopiece( $entry, $options->{ "quality" } );
2015 put_record( $record, $out );
2017 goto NUM if $options->{ "num" } and $num == $options->{ "num" };
2028 close $data_in if $data_in;
2032 sub script_read_solid
2034 # Martin A. Hansen, April 2008.
2036 # Read Solid sequence from file.
2038 my ( $in, # handle to in stream
2039 $out, # handle to out stream
2040 $options, # options hash
2045 my ( $record, $file, $data_in, $line, $num, $seq_name, $seq_cs, $seq_qual, @scores, @seqs, $i );
2047 $options->{ "quality" } ||= 15;
2049 while ( $record = get_record( $in ) ) {
2050 put_record( $record, $out );
2055 foreach $file ( @{ $options->{ "files" } } )
2057 $data_in = Maasha::Common::read_open( $file );
2059 while ( $line = <$data_in> )
2063 ( $seq_name, $seq_cs, $seq_qual ) = split /\t/, $line;
2065 @scores = split /,/, $seq_qual;
2066 @seqs = split //, Maasha::Solid::color_space2seq( $seq_cs );
2068 for ( $i = 0; $i < @seqs; $i++ ) {
2069 $seqs[ $i ] = lc $seqs[ $i ] if $scores[ $i ] < $options->{ "quality" };
2073 REC_TYPE => 'SOLID',
2074 SEQ_NAME => $seq_name,
2076 SEQ_QUAL => join( ";", @scores ),
2077 SEQ_LEN => length $seq_cs,
2078 SEQ => join( "", @seqs ),
2079 SCORE_MEAN => sprintf( "%.2f", Maasha::Calc::mean( \@scores ) ),
2082 put_record( $record, $out );
2084 goto NUM if $options->{ "num" } and $num == $options->{ "num" };
2094 close $data_in if $data_in;
2098 sub script_read_mysql
2100 # Martin A. Hansen, May 2008.
2102 # Read a MySQL query into stream.
2104 my ( $in, # handle to in stream
2105 $out, # handle to out stream
2106 $options, # options hash
2111 my ( $record, $dbh, $results );
2113 $options->{ "user" } ||= Maasha::UCSC::ucsc_get_user();
2114 $options->{ "password" } ||= Maasha::UCSC::ucsc_get_password();
2116 while ( $record = get_record( $in ) ) {
2117 put_record( $record, $out );
2120 $dbh = Maasha::SQL::connect( $options->{ "database" }, $options->{ "user" }, $options->{ "password" } );
2122 $results = Maasha::SQL::query_hashref_list( $dbh, $options->{ "query" } );
2124 Maasha::SQL::disconnect( $dbh );
2126 map { put_record( $_ ) } @{ $results };
2130 sub script_read_ucsc_config
2132 # Martin A. Hansen, November 2008.
2134 # Read track entries from UCSC Genome Browser '.ra' files.
2136 my ( $in, # handle to in stream
2137 $out, # handle to out stream
2138 $options, # options hash
2143 my ( $record, $file, $data_in, $entry, $num );
2145 while ( $record = get_record( $in ) ) {
2146 put_record( $record, $out );
2151 foreach $file ( @{ $options->{ "files" } } )
2153 $data_in = Maasha::Common::read_open( $file );
2155 while ( $record = Maasha::UCSC::ucsc_config_entry_get( $data_in ) )
2157 $record->{ 'REC_TYPE' } = "UCSC Config";
2159 put_record( $record, $out );
2161 goto NUM if $options->{ "num" } and $num == $options->{ "num" };
2171 close $data_in if $data_in;
2175 sub script_assemble_tag_contigs
2177 # Martin A. Hansen, November 2008.
2179 # Assemble tags from the stream into
2182 # The current implementation is quite
2183 # slow because of heavy use of temporary
2186 my ( $in, # handle to in stream
2187 $out, # handle to out stream
2188 $options, # options hash
2193 my ( $bed_file, $tag_file, $fh_in, $fh_out, $cols, $record, $bed_entry, $file_hash, $chr, $strand );
2195 $bed_file = "$BP_TMP/assemble_tag_contigs.bed";
2196 $fh_out = Maasha::Filesys::file_write_open( $bed_file );
2197 $cols = 6; # we only need the first 6 BED columns
2199 while ( $record = get_record( $in ) )
2201 if ( $bed_entry = Maasha::UCSC::BED::biopiece2bed( $record, $cols ) )
2203 $strand = $record->{ 'STRAND' } || '+';
2205 Maasha::UCSC::BED::bed_entry_put( $bed_entry, $fh_out, $cols, $options->{ 'check' } );
2211 $file_hash = Maasha::UCSC::BED::bed_file_split_on_chr( $bed_file, $BP_TMP, $cols );
2215 foreach $chr ( sort keys %{ $file_hash } )
2217 $bed_file = $file_hash->{ $chr };
2218 $tag_file = "$bed_file.tc";
2220 Maasha::Common::run( "bed2tag_contigs", "< $bed_file > $tag_file" );
2222 $fh_in = Maasha::Filesys::file_read_open( $tag_file );
2224 while ( $bed_entry = Maasha::UCSC::BED::bed_entry_get( $fh_in, $cols, $options->{ 'check' } ) )
2226 if ( $record = Maasha::UCSC::BED::bed2biopiece( $bed_entry ) ) {
2227 put_record( $record, $out );
2239 sub script_format_genome
2241 # Martin A. Hansen, Juli 2008.
2243 # Format a genome to speficed formats.
2245 my ( $in, # handle to in stream
2246 $out, # handle to out stream
2247 $options, # options hash
2252 my ( $dir, $genome, $fasta_dir, $phastcons_dir, $vals, $fh_out, $record, $format, $index, $entry );
2254 $dir = $options->{ 'dir' } || $ENV{ 'BP_DATA' };
2255 $genome = $options->{ 'genome' };
2257 Maasha::Common::error( "Directory: $dir does not exist" ) if not -d $dir;
2258 Maasha::Common::dir_create_if_not_exists( "$dir/genomes" );
2259 Maasha::Common::dir_create_if_not_exists( "$dir/genomes/$genome" );
2261 if ( grep { $_ =~ /fasta|blast|vmatch/i } @{ $options->{ "formats" } } )
2263 if ( -f "$dir/genomes/$genome/fasta/$genome.fna" )
2265 $fasta_dir = "$dir/genomes/$genome/fasta";
2269 Maasha::Common::dir_create_if_not_exists( "$dir/genomes/$genome/fasta" );
2271 $fasta_dir = "$dir/genomes/$genome/fasta";
2273 $fh_out = Maasha::Common::write_open( "$fasta_dir/$genome.fna" );
2276 elsif ( grep { $_ =~ /phastcons/i } @{ $options->{ "formats" } } )
2278 Maasha::Common::dir_create_if_not_exists( "$dir/genomes/$genome/phastcons" );
2280 $phastcons_dir = "$dir/genomes/$genome/phastcons";
2282 $fh_out = Maasha::Common::write_open( "$phastcons_dir/$genome.pp" );
2285 while ( $record = get_record( $in ) )
2287 if ( $fh_out and $entry = Maasha::Fasta::biopiece2fasta( $record ) )
2289 Maasha::Fasta::put_entry( $entry, $fh_out, $options->{ "wrap" } );
2291 elsif ( $fh_out and $record->{ "CHR" } and $record->{ "CHR_BEG" } and $record->{ "STEP" } and $record->{ "VALS" } )
2293 print $fh_out "fixedStep chrom=$record->{ 'CHR' } start=$record->{ 'CHR_BEG' } step=$record->{ 'STEP' }\n";
2295 $vals = $record->{ 'VALS' };
2299 print $fh_out "$vals\n";
2302 put_record( $record, $out ) if not $options->{ "no_stream" };
2305 foreach $format ( @{ $options->{ 'formats' } } )
2307 if ( $format =~ /^fasta$/i ) { Maasha::Fasta::fasta_index( "$fasta_dir/$genome.fna", "$dir/genomes/$genome/fasta/$genome.index" ) }
2308 elsif ( $format =~ /^blast$/i ) { Maasha::NCBI::blast_index( "$genome.fna", $fasta_dir, "$dir/genomes/$genome/blast", "dna", $genome ) }
2309 elsif ( $format =~ /^blat$/i ) { print STDERR "BLAT FORMAT NOT IMPLEMENTED" }
2310 elsif ( $format =~ /^vmatch$/i ) { Maasha::Match::vmatch_index( "$genome.fna", $fasta_dir, "$dir/genomes/$genome/vmatch", $BP_TMP ) }
2311 elsif ( $format =~ /^phastcons$/i ) { Maasha::UCSC::phastcons_index( "$genome.pp", $phastcons_dir ) }
2314 close $fh_out if $fh_out;
2318 sub script_length_seq
2320 # Martin A. Hansen, August 2007.
2322 # Determine the length of sequences in stream.
2324 my ( $in, # handle to in stream
2325 $out, # handle to out stream
2326 $options, # options hash
2331 my ( $record, $total );
2333 while ( $record = get_record( $in ) )
2335 if ( $record->{ "SEQ" } )
2337 $record->{ "SEQ_LEN" } = length $record->{ "SEQ" };
2338 $total += $record->{ "SEQ_LEN" };
2341 put_record( $record, $out ) if not $options->{ "no_stream" };
2344 put_record( { TOTAL_SEQ_LEN => $total }, $out );
2348 sub script_uppercase_seq
2350 # Martin A. Hansen, August 2007.
2352 # Uppercases sequences in stream.
2354 my ( $in, # handle to in stream
2355 $out, # handle to out stream
2362 while ( $record = get_record( $in ) )
2364 $record->{ "SEQ" } = uc $record->{ "SEQ" } if $record->{ "SEQ" };
2366 put_record( $record, $out );
2371 sub script_shuffle_seq
2373 # Martin A. Hansen, December 2007.
2375 # Shuffle sequences in stream.
2377 my ( $in, # handle to in stream
2378 $out, # handle to out stream
2385 while ( $record = get_record( $in ) )
2387 $record->{ "SEQ" } = Maasha::Seq::seq_shuffle( $record->{ "SEQ" } ) if $record->{ "SEQ" };
2389 put_record( $record, $out );
2394 sub script_analyze_seq
2396 # Martin A. Hansen, August 2007.
2398 # Analyze sequence composition of sequences in stream.
2400 my ( $in, # handle to in stream
2401 $out, # handle to out stream
2406 my ( $record, $analysis );
2408 while ( $record = get_record( $in ) )
2410 if ( $record->{ "SEQ" } )
2412 $analysis = Maasha::Seq::seq_analyze( $record->{ "SEQ" } );
2414 map { $record->{ $_ } = $analysis->{ $_ } } keys %{ $analysis };
2417 put_record( $record, $out );
2422 sub script_analyze_tags
2424 # Martin A. Hansen, August 2008.
2426 # Analyze sequence tags in stream.
2428 my ( $in, # handle to in stream
2429 $out, # handle to out stream
2434 my ( $record, $analysis, %len_hash, %clone_hash, $clones, $key, $tag_record );
2436 while ( $record = get_record( $in ) )
2438 if ( $record->{ "SEQ_NAME" } and $record->{ "SEQ" } )
2440 if ( $record->{ "SEQ_NAME" } =~ /_(\d+)$/ )
2444 $len_hash{ length( $record->{ "SEQ" } ) }++;
2445 $clone_hash{ length( $record->{ "SEQ" } ) } += $clones;
2448 elsif ( $record->{ "Q_ID" } and $record->{ "BED_LEN" } )
2450 if ( $record->{ "Q_ID" } =~ /_(\d+)$/ )
2454 $len_hash{ $record->{ "BED_LEN" } }++;
2455 $clone_hash{ $record->{ "BED_LEN" } } += $clones;
2460 foreach $key ( sort { $a <=> $b } keys %len_hash )
2462 $tag_record->{ "TAG_LEN" } = $key;
2463 $tag_record->{ "TAG_COUNT" } = $len_hash{ $key };
2464 $tag_record->{ "TAG_CLONES" } = $clone_hash{ $key };
2466 put_record( $tag_record, $out );
2471 sub script_complexity_seq
2473 # Martin A. Hansen, May 2008.
2475 # Generates an index calculated as the most common di-residue over
2476 # the sequence length for all sequences in stream.
2478 my ( $in, # handle to in stream
2479 $out, # handle to out stream
2484 my ( $record, $index );
2486 while ( $record = get_record( $in ) )
2488 $record->{ "SEQ_COMPLEXITY" } = sprintf( "%.2f", Maasha::Seq::seq_complexity( $record->{ "SEQ" } ) ) if $record->{ "SEQ" };
2490 put_record( $record, $out );
2495 sub script_oligo_freq
2497 # Martin A. Hansen, August 2007.
2499 # Determine the length of sequences in stream.
2501 my ( $in, # handle to in stream
2502 $out, # handle to out stream
2503 $options, # options hash
2508 my ( $record, %oligos, @freq_table );
2510 $options->{ "word_size" } ||= 7;
2512 while ( $record = get_record( $in ) )
2514 if ( $record->{ "SEQ" } )
2516 map { $oligos{ $_ }++ } Maasha::Seq::seq2oligos( \$record->{ "SEQ" }, $options->{ "word_size" } );
2518 if ( not $options->{ "all" } )
2520 @freq_table = Maasha::Seq::oligo_freq( \%oligos );
2522 map { put_record( $_, $out ) } @freq_table;
2528 put_record( $record, $out );
2531 if ( $options->{ "all" } )
2533 @freq_table = Maasha::Seq::oligo_freq( \%oligos );
2535 map { put_record( $_, $out ) } @freq_table;
2540 sub script_create_weight_matrix
2542 # Martin A. Hansen, August 2007.
2544 # Creates a weight matrix from an alignmnet.
2546 my ( $in, # handle to in stream
2547 $out, # handle to out stream
2548 $options, # options hash
2553 my ( $record, $count, $i, $res, %freq_hash, %res_hash, $freq );
2557 while ( $record = get_record( $in ) )
2559 if ( $record->{ "SEQ" } )
2561 for ( $i = 0; $i < length $record->{ "SEQ" }; $i++ )
2563 $res = substr $record->{ "SEQ" }, $i, 1;
2565 $freq_hash{ $i }{ $res }++;
2566 $res_hash{ $res } = 1;
2573 put_record( $record, $out );
2577 foreach $res ( sort keys %res_hash )
2581 $record->{ "V0" } = $res;
2583 for ( $i = 0; $i < keys %freq_hash; $i++ )
2585 $freq = $freq_hash{ $i }{ $res } || 0;
2587 if ( $options->{ "percent" } ) {
2588 $freq = sprintf( "%.0f", 100 * $freq / $count ) if $freq > 0;
2591 $record->{ "V" . ( $i + 1 ) } = $freq;
2594 put_record( $record, $out );
2599 sub script_calc_bit_scores
2601 # Martin A. Hansen, March 2007.
2603 # Calculates the bit scores for each position from an alignmnet in the stream.
2605 my ( $in, # handle to in stream
2606 $out, # handle to out stream
2611 my ( $record, $type, $count, $i, $res, %freq_hash, $bit_max, $bit_height, $bit_diff );
2615 while ( $record = get_record( $in ) )
2617 if ( $record->{ "SEQ" } )
2619 $type = Maasha::Seq::seq_guess_type( $record->{ "SEQ" } ) if not $type;
2621 for ( $i = 0; $i < length $record->{ "SEQ" }; $i++ )
2623 $res = substr $record->{ "SEQ" }, $i, 1;
2625 next if $res =~ /-|_|~|\./;
2627 $freq_hash{ $i }{ $res }++;
2634 put_record( $record, $out );
2640 if ( $type eq "protein" ) {
2646 for ( $i = 0; $i < keys %freq_hash; $i++ )
2648 $bit_height = Maasha::Seq::seqlogo_calc_bit_height( $freq_hash{ $i }, $count );
2650 $bit_diff = $bit_max - $bit_height;
2652 $record->{ "V" . ( $i ) } = sprintf( "%.2f", $bit_diff );
2655 put_record( $record, $out );
2659 sub script_calc_fixedstep
2661 # Martin A. Hansen, September 2008.
2663 # Calculates fixedstep entries from data in the stream.
2665 my ( $in, # handle to in stream
2666 $out, # handle to out stream
2667 $options, # options hash
2672 my ( $bed_file, $fh_in, $fh_out, $cols, $record, $file_hash, $chr, $bed_entry, $fixedstep_file, $fixedstep_entry );
2674 $bed_file = "$BP_TMP/calc_fixedstep.bed";
2675 $fh_out = Maasha::Filesys::file_write_open( $bed_file );
2676 $cols = 5; # we only need the first 5 BED columns
2678 while ( $record = get_record( $in ) )
2680 if ( $bed_entry = Maasha::UCSC::BED::biopiece2bed( $record, $cols ) ) {
2681 Maasha::UCSC::BED::bed_entry_put( $bed_entry, $fh_out, $cols, $options->{ 'check' } );
2687 $file_hash = Maasha::UCSC::BED::bed_file_split_on_chr( $bed_file, $BP_TMP, $cols );
2691 foreach $chr ( sort keys %{ $file_hash } )
2693 $bed_file = $file_hash->{ $chr };
2694 $fixedstep_file = "$bed_file.fixedstep";
2696 Maasha::Common::run( "bed2fixedstep", "< $bed_file > $fixedstep_file" );
2698 $fh_in = Maasha::Filesys::file_read_open( $fixedstep_file );
2700 while ( $fixedstep_entry = Maasha::UCSC::Wiggle::fixedstep_entry_get( $fh_in ) )
2702 if ( $record = Maasha::UCSC::Wiggle::fixedstep2biopiece( $fixedstep_entry ) ) {
2703 put_record( $record, $out );
2710 unlink $fixedstep_file;
2715 sub script_reverse_seq
2717 # Martin A. Hansen, August 2007.
2719 # Reverse sequence in record.
2721 my ( $in, # handle to in stream
2722 $out, # handle to out stream
2729 while ( $record = get_record( $in ) )
2731 if ( $record->{ "SEQ" } ) {
2732 $record->{ "SEQ" } = reverse $record->{ "SEQ" };
2735 put_record( $record, $out );
2740 sub script_complement_seq
2742 # Martin A. Hansen, August 2007.
2744 # Complement sequence in record.
2746 my ( $in, # handle to in stream
2747 $out, # handle to out stream
2752 my ( $record, $type );
2754 while ( $record = get_record( $in ) )
2756 if ( $record->{ "SEQ" } )
2759 $type = Maasha::Seq::seq_guess_type( $record->{ "SEQ" } );
2762 if ( $type eq "rna" ) {
2763 Maasha::Seq::rna_comp( \$record->{ "SEQ" } );
2764 } elsif ( $type eq "dna" ) {
2765 Maasha::Seq::dna_comp( \$record->{ "SEQ" } );
2769 put_record( $record, $out );
2774 sub script_remove_indels
2776 # Martin A. Hansen, August 2007.
2778 # Remove indels from sequences in stream.
2780 my ( $in, # handle to in stream
2781 $out, # handle to out stream
2788 while ( $record = get_record( $in ) )
2790 $record->{ 'SEQ' } =~ tr/-~.//d if $record->{ "SEQ" };
2792 put_record( $record, $out );
2797 sub script_transliterate_seq
2799 # Martin A. Hansen, August 2007.
2801 # Transliterate chars from sequence in record.
2803 my ( $in, # handle to in stream
2804 $out, # handle to out stream
2805 $options, # options hash
2810 my ( $record, $search, $replace, $delete );
2812 $search = $options->{ "search" } || "";
2813 $replace = $options->{ "replace" } || "";
2814 $delete = $options->{ "delete" } || "";
2816 while ( $record = get_record( $in ) )
2818 if ( $record->{ "SEQ" } )
2820 if ( $search and $replace ) {
2821 eval "\$record->{ 'SEQ' } =~ tr/$search/$replace/";
2822 } elsif ( $delete ) {
2823 eval "\$record->{ 'SEQ' } =~ tr/$delete//d";
2827 put_record( $record, $out );
2832 sub script_transliterate_vals
2834 # Martin A. Hansen, April 2008.
2836 # Transliterate chars from values in record.
2838 my ( $in, # handle to in stream
2839 $out, # handle to out stream
2840 $options, # options hash
2845 my ( $record, $search, $replace, $delete, $key );
2847 $search = $options->{ "search" } || "";
2848 $replace = $options->{ "replace" } || "";
2849 $delete = $options->{ "delete" } || "";
2851 while ( $record = get_record( $in ) )
2853 foreach $key ( @{ $options->{ "keys" } } )
2855 if ( exists $record->{ $key } )
2857 if ( $search and $replace ) {
2858 eval "\$record->{ $key } =~ tr/$search/$replace/";
2859 } elsif ( $delete ) {
2860 eval "\$record->{ $key } =~ tr/$delete//d";
2865 put_record( $record, $out );
2870 sub script_translate_seq
2872 # Martin A. Hansen, February 2008.
2874 # Translate DNA sequence into protein sequence.
2876 my ( $in, # handle to in stream
2877 $out, # handle to out stream
2878 $options, # options hash
2883 my ( $record, $frame, %new_record );
2885 $options->{ "frames" } ||= [ 1, 2, 3, -1, -2, -3 ];
2887 while ( $record = get_record( $in ) )
2889 if ( $record->{ "SEQ" } )
2891 if ( Maasha::Seq::seq_guess_type( $record->{ "SEQ" } ) eq "dna" )
2893 foreach $frame ( @{ $options->{ "frames" } } )
2895 %new_record = %{ $record };
2897 $new_record{ "SEQ" } = Maasha::Seq::translate( $record->{ "SEQ" }, $frame );
2898 $new_record{ "SEQ_LEN" } = length $new_record{ "SEQ" };
2899 $new_record{ "FRAME" } = $frame;
2901 put_record( \%new_record, $out );
2907 put_record( $record, $out );
2913 sub script_extract_seq
2915 # Martin A. Hansen, August 2007.
2917 # Extract subsequences from sequences in record.
2919 my ( $in, # handle to in stream
2920 $out, # handle to out stream
2921 $options, # options hash
2926 my ( $beg, $end, $len, $record );
2928 if ( not defined $options->{ "beg" } or $options->{ "beg" } < 0 ) {
2931 $beg = $options->{ "beg" } - 1; # correcting for start offset
2934 if ( defined $options->{ "end" } and $options->{ "end" } - 1 < $beg ) {
2936 } elsif ( defined $options->{ "end" } ) {
2937 $end = $options->{ "end" } - 1; # correcting for start offset
2940 $len = $options->{ "len" };
2942 # print "beg->$beg, end->$end, len->$len\n";
2944 while ( $record = get_record( $in ) )
2946 if ( $record->{ "SEQ" } )
2948 if ( defined $beg and defined $end )
2950 if ( $end - $beg + 1 > length $record->{ "SEQ" } ) {
2951 $record->{ "SEQ" } = substr $record->{ "SEQ" }, $beg;
2953 $record->{ "SEQ" } = substr $record->{ "SEQ" }, $beg, $end - $beg + 1;
2956 elsif ( defined $beg and defined $len )
2958 if ( $len > length $record->{ "SEQ" } ) {
2959 $record->{ "SEQ" } = substr $record->{ "SEQ" }, $beg;
2961 $record->{ "SEQ" } = substr $record->{ "SEQ" }, $beg, $len;
2964 elsif ( defined $beg )
2966 $record->{ "SEQ" } = substr $record->{ "SEQ" }, $beg;
2970 $record->{ "SEQ_LEN" } = length $record->{ "SEQ" };
2972 put_record( $record, $out );
2977 sub script_get_genome_seq
2979 # Martin A. Hansen, December 2007.
2981 # Gets a subsequence from a genome.
2983 my ( $in, # handle to in stream
2984 $out, # handle to out stream
2985 $options, # options hash
2990 my ( $record, $genome, $genome_file, $index_file, $index, $fh, $index_head, $index_beg, $index_len, $beg, $len, %lookup_hash, @begs, @lens, $i );
2992 $options->{ "flank" } ||= 0;
2994 if ( $options->{ "genome" } )
2996 $genome = $options->{ "genome" };
2998 $genome_file = "$ENV{ 'BP_DATA' }/genomes/$genome/fasta/$genome.fna";
2999 $index_file = "$ENV{ 'BP_DATA' }/genomes/$genome/fasta/$genome.index";
3001 $fh = Maasha::Common::read_open( $genome_file );
3002 $index = Maasha::Fasta::index_retrieve( $index_file );
3004 shift @{ $index }; # Get rid of the file size info
3006 map { $lookup_hash{ $_->[ 0 ] } = [ $_->[ 1 ], $_->[ 2 ] ] } @{ $index };
3008 if ( exists $lookup_hash{ $options->{ "chr" } } and defined $options->{ "beg" } and ( defined $options->{ "end" } or defined $options->{ "len" } ) )
3010 ( $index_beg, $index_len ) = @{ $lookup_hash{ $options->{ "chr" } } };
3012 $beg = $index_beg + $options->{ "beg" } - 1;
3014 if ( $options->{ "len" } ) {
3015 $len = $options->{ "len" };
3016 } elsif ( $options->{ "end" } ) {
3017 $len = ( $options->{ "end" } - $options->{ "beg" } + 1 );
3020 $beg -= $options->{ "flank" };
3021 $len += 2 * $options->{ "flank" };
3023 if ( $beg <= $index_beg )
3025 $len -= $index_beg - $beg;
3029 $len = $index_beg + $index_len - $beg if $beg + $len > $index_beg + $index_len;
3031 next if $beg > $index_beg + $index_len;
3033 $record->{ "CHR" } = $options->{ "chr" };
3034 $record->{ "CHR_BEG" } = $beg - $index_beg;
3035 $record->{ "CHR_END" } = $record->{ "CHR_BEG" } + $len - 1;
3037 $record->{ "SEQ" } = Maasha::Common::file_read( $fh, $beg, $len );
3038 $record->{ "SEQ_LEN" } = $len;
3040 put_record( $record, $out );
3044 while ( $record = get_record( $in ) )
3046 if ( $options->{ "genome" } and not $record->{ "SEQ" } )
3048 if ( $record->{ "REC_TYPE" } eq "BED" and exists $lookup_hash{ $record->{ "CHR" } } )
3050 ( $index_beg, $index_len ) = @{ $lookup_hash{ $record->{ "CHR" } } };
3052 $beg = $record->{ "CHR_BEG" } + $index_beg;
3053 $len = $record->{ "CHR_END" } - $record->{ "CHR_BEG" } + 1;
3055 elsif ( $record->{ "REC_TYPE" } eq "PSL" and exists $lookup_hash{ $record->{ "S_ID" } } )
3057 ( $index_beg, $index_len ) = @{ $lookup_hash{ $record->{ "S_ID" } } };
3059 $beg = $record->{ "S_BEG" } + $index_beg;
3060 $len = $record->{ "S_END" } - $record->{ "S_BEG" } + 1;
3062 elsif ( $record->{ "REC_TYPE" } eq "BLAST" and exists $lookup_hash{ $record->{ "S_ID" } } )
3064 ( $index_beg, $index_len ) = @{ $lookup_hash{ $record->{ "S_ID" } } };
3066 $beg = $record->{ "S_BEG" } + $index_beg;
3067 $len = $record->{ "S_END" } - $record->{ "S_BEG" } + 1;
3070 $beg -= $options->{ "flank" };
3071 $len += 2 * $options->{ "flank" };
3073 if ( $beg <= $index_beg )
3075 $len -= $index_beg - $beg;
3079 $len = $index_beg + $index_len - $beg if $beg + $len > $index_beg + $index_len;
3081 next if $beg > $index_beg + $index_len;
3083 $record->{ "CHR_BEG" } = $beg - $index_beg;
3084 $record->{ "CHR_END" } = $record->{ "CHR_BEG" } + $len - 1;
3086 $record->{ "SEQ" } = Maasha::Common::file_read( $fh, $beg, $len );
3088 if ( $record->{ "STRAND" } and $record->{ "STRAND" } eq "-" )
3090 Maasha::Seq::dna_comp( \$record->{ "SEQ" } );
3091 $record->{ "SEQ" } = reverse $record->{ "SEQ" };
3094 if ( $options->{ "mask" } )
3096 if ( $record->{ "BLOCKCOUNT" } > 1 ) # uppercase hit block segments and lowercase the rest.
3098 $record->{ "SEQ" } = lc $record->{ "SEQ" };
3100 @begs = split ",", $record->{ "Q_BEGS" };
3101 @lens = split ",", $record->{ "BLOCKSIZES" };
3103 for ( $i = 0; $i < @begs; $i++ ) {
3104 substr $record->{ "SEQ" }, $begs[ $i ], $lens[ $i ], uc substr $record->{ "SEQ" }, $begs[ $i ], $lens[ $i ];
3110 put_record( $record, $out );
3117 sub script_get_genome_align
3119 # Martin A. Hansen, April 2008.
3121 # Gets a subalignment from a multiple genome alignment.
3123 my ( $in, # handle to in stream
3124 $out, # handle to out stream
3125 $options, # options hash
3130 my ( $record, $maf_track, $align, $align_num, $beg, $end, $len, $entry );
3132 $options->{ "strand" } ||= "+";
3136 $maf_track = Maasha::Config::maf_track( $options->{ "genome" } );
3138 if ( $options->{ "chr" } and $options->{ "beg" } and ( $options->{ "end" } or $options->{ "len" } ) )
3140 $beg = $options->{ "beg" } - 1;
3142 if ( $options->{ "end" } ) {
3143 $end = $options->{ "end" };
3144 } elsif ( $options->{ "len" } ) {
3145 $end = $beg + $options->{ "len" };
3148 $align = Maasha::UCSC::maf_extract( $BP_TMP, $options->{ "genome" }, $maf_track, $options->{ "chr" }, $beg, $end, $options->{ "strand" } );
3150 foreach $entry ( @{ $align } )
3152 $entry->{ "CHR" } = $record->{ "CHR" };
3153 $entry->{ "CHR_BEG" } = $record->{ "CHR_BEG" };
3154 $entry->{ "CHR_END" } = $record->{ "CHR_END" };
3155 $entry->{ "STRAND" } = $record->{ "STRAND" } || '+';
3156 $entry->{ "Q_ID" } = $record->{ "Q_ID" };
3157 $entry->{ "SCORE" } = $record->{ "SCORE" };
3159 put_record( $entry, $out );
3163 while ( $record = get_record( $in ) )
3165 if ( $record->{ "REC_TYPE" } eq "BED" )
3167 $align = Maasha::UCSC::maf_extract( $BP_TMP, $options->{ "genome" }, $maf_track, $record->{ "CHR" }, $record->{ "CHR_BEG" }, $record->{ "CHR_END" }, $record->{ "STRAND" } );
3169 elsif ( $record->{ "REC_TYPE" } eq "VMATCH" )
3171 $align = Maasha::UCSC::maf_extract( $BP_TMP, $options->{ "genome" }, $maf_track, $record->{ "S_ID" }, $record->{ "S_BEG" }, $record->{ "S_END" } + 1, $record->{ "STRAND" } );
3173 elsif ( $record->{ "REC_TYPE" } eq "PSL" )
3175 $align = Maasha::UCSC::maf_extract( $BP_TMP, $options->{ "genome" }, $maf_track, $record->{ "S_ID" }, $record->{ "S_BEG" }, $record->{ "S_END" }, $record->{ "STRAND" } );
3177 elsif ( $record->{ "REC_TYPE" } eq "BLAST" )
3179 $align = Maasha::UCSC::maf_extract( $BP_TMP, $options->{ "genome" }, $maf_track, $record->{ "S_ID" }, $record->{ "S_BEG" }, $record->{ "S_END" }, $record->{ "STRAND" } );
3182 foreach $entry ( @{ $align } )
3184 $entry->{ "CHR" } = $record->{ "CHR" };
3185 $entry->{ "CHR_BEG" } = $record->{ "CHR_BEG" };
3186 $entry->{ "CHR_END" } = $record->{ "CHR_END" };
3187 $entry->{ "STRAND" } = $record->{ "STRAND" };
3188 $entry->{ "Q_ID" } = $record->{ "Q_ID" };
3189 $entry->{ "SCORE" } = $record->{ "SCORE" };
3191 put_record( $entry, $out );
3199 sub script_get_genome_phastcons
3201 # Martin A. Hansen, February 2008.
3203 # Get phastcons scores from genome intervals.
3205 my ( $in, # handle to in stream
3206 $out, # handle to out stream
3207 $options, # options hash
3212 my ( $phastcons_file, $phastcons_index, $index, $fh_phastcons, $scores, $record );
3214 $options->{ "flank" } ||= 0;
3216 $phastcons_file = Maasha::Config::genome_phastcons( $options->{ "genome" } );
3217 $phastcons_index = Maasha::Config::genome_phastcons_index( $options->{ "genome" } );
3219 $index = Maasha::UCSC::fixedstep_index_retrieve( $phastcons_index );
3220 $fh_phastcons = Maasha::Common::read_open( $phastcons_file );
3222 if ( defined $options->{ "chr" } and defined $options->{ "beg" } and ( defined $options->{ "end" } or defined $options->{ "len" } ) )
3224 $options->{ "beg" } -= 1; # request is 1-based
3225 $options->{ "end" } -= 1; # request is 1-based
3227 if ( $options->{ "len" } ) {
3228 $options->{ "end" } = $options->{ "beg" } + $options->{ "len" } - 1;
3231 $scores = Maasha::UCSC::fixedstep_index_lookup( $index, $fh_phastcons, $options->{ "chr" }, $options->{ "beg" }, $options->{ "end" }, $options->{ "flank" } );
3233 $record->{ "CHR" } = $options->{ "chr" };
3234 $record->{ "CHR_BEG" } = $options->{ "beg" } - $options->{ "flank" };
3235 $record->{ "CHR_END" } = $options->{ "end" } + $options->{ "flank" };
3237 $record->{ "PHASTCONS" } = join ",", @{ $scores };
3238 $record->{ "PHAST_COUNT" } = scalar @{ $scores }; # DEBUG
3240 put_record( $record, $out );
3243 while ( $record = get_record( $in ) )
3245 if ( $record->{ "REC_TYPE" } eq "BED" )
3247 $scores = Maasha::UCSC::fixedstep_index_lookup( $index, $fh_phastcons, $record->{ "CHR" }, $record->{ "CHR_BEG" }, $record->{ "CHR_END" }, $options->{ "flank" } );
3249 elsif ( $record->{ "REC_TYPE" } eq "PSL" )
3251 $scores = Maasha::UCSC::fixedstep_index_lookup( $index, $fh_phastcons, $record->{ "S_ID" }, $record->{ "S_BEG" }, $record->{ "S_END" }, $options->{ "flank" } );
3253 elsif ( $record->{ "REC_TYPE" } eq "BLAST" )
3255 $scores = Maasha::UCSC::fixedstep_index_lookup( $index, $fh_phastcons, $record->{ "S_ID" }, $record->{ "S_BEG" }, $record->{ "S_END" }, $options->{ "flank" } );
3258 $record->{ "PHASTCONS" } = join ",", @{ $scores } if @{ $scores };
3259 # $record->{ "PHAST_COUNT" } = @{ $scores } if @{ $scores }; # DEBUG
3261 put_record( $record, $out );
3264 close $fh_phastcons if $fh_phastcons;
3270 # Martin A. Hansen, December 2007.
3272 # Folds sequences in stream into secondary structures.
3274 my ( $in, # handle to in stream
3275 $out, # handle to out stream
3280 my ( $record, $type, $struct, $index );
3282 while ( $record = get_record( $in ) )
3284 if ( $record->{ "SEQ" } )
3287 $type = Maasha::Seq::seq_guess_type( $record->{ "SEQ" } );
3290 if ( $type ne "protein" )
3292 ( $struct, $index ) = Maasha::Seq::fold_struct_rnafold( $record->{ "SEQ" } );
3293 $record->{ "SEC_STRUCT" } = $struct;
3294 $record->{ "FREE_ENERGY" } = $index;
3295 $record->{ "SCORE" } = abs int $index;
3296 $record->{ "SIZE" } = length $struct;
3297 $record->{ "CONF" } = "1," x $record->{ "SIZE" };
3301 put_record( $record, $out );
3306 sub script_split_seq
3308 # Martin A. Hansen, August 2007.
3310 # Split a sequence in stream into words.
3312 my ( $in, # handle to in stream
3313 $out, # handle to out stream
3314 $options, # options hash
3319 my ( $record, $new_record, $i, $subseq, %lookup );
3321 $options->{ "word_size" } ||= 7;
3323 while ( $record = get_record( $in ) )
3325 if ( $record->{ "SEQ_NAME" } and $record->{ "SEQ" } )
3327 for ( $i = 0; $i < length( $record->{ "SEQ" } ) - $options->{ "word_size" } + 1; $i++ )
3329 $subseq = substr $record->{ "SEQ" }, $i, $options->{ "word_size" };
3331 if ( $options->{ "uniq" } and not $lookup{ $subseq } )
3333 $new_record->{ "SEQ_NAME" } = $record->{ "SEQ_NAME" } . "[" . ( $i + 1 ) . "-" . ( $i + $options->{ "word_size" } ) . "]";
3334 $new_record->{ "SEQ" } = $subseq;
3336 put_record( $new_record, $out );
3338 $lookup{ $subseq } = 1;
3342 $new_record->{ "SEQ_NAME" } = $record->{ "SEQ_NAME" } . "[" . ( $i + 1 ) . "-" . ( $i + $options->{ "word_size" } ) . "]";
3343 $new_record->{ "SEQ" } = $subseq;
3345 put_record( $new_record, $out );
3351 put_record( $record, $out );
3357 sub script_split_bed
3359 # Martin A. Hansen, June 2008.
3361 # Split a BED record into overlapping windows.
3363 my ( $in, # handle to in stream
3364 $out, # handle to out stream
3365 $options, # options hash
3370 my ( $record, $new_record, $i );
3372 $options->{ "window_size" } ||= 20;
3373 $options->{ "step_size" } ||= 1;
3375 while ( $record = get_record( $in ) )
3377 if ( $record->{ "CHR" } and $record->{ "CHR_BEG" } and $record->{ "CHR_END" } )
3379 $record->{ "BED_LEN" } = $record->{ "CHR_END" } - $record->{ "CHR_BEG" } + 1;
3381 for ( $i = 0; $i < $record->{ "BED_LEN" } - $options->{ "window_size" }; $i += $options->{ "step_size" } )
3383 $new_record->{ "REC_TYPE" } = "BED";
3384 $new_record->{ "CHR" } = $record->{ "CHR" };
3385 $new_record->{ "CHR_BEG" } = $record->{ "CHR_BEG" } + $i;
3386 $new_record->{ "CHR_END" } = $record->{ "CHR_BEG" } + $i + $options->{ "window_size" };
3387 $new_record->{ "BED_LEN" } = $options->{ "window_size" };
3388 $new_record->{ "Q_ID" } = $record->{ "Q_ID" } . "_$i";
3389 $new_record->{ "SCORE" } = $record->{ "SCORE" };
3390 $new_record->{ "STRAND" } = $record->{ "STRAND" };
3392 put_record( $new_record, $out );
3397 put_record( $record, $out );
3403 sub script_align_seq
3405 # Martin A. Hansen, August 2007.
3407 # Align sequences in stream.
3409 my ( $in, # handle to in stream
3410 $out, # handle to out stream
3415 my ( $record, @entries, $entry );
3417 while ( $record = get_record( $in ) )
3419 if ( $record->{ "SEQ_NAME" } and $record->{ "SEQ" } ) {
3420 push @entries, [ $record->{ "SEQ_NAME" }, $record->{ "SEQ" } ];
3421 } elsif ( $record->{ "Q_ID" } and $record->{ "SEQ" } ) {
3422 push @entries, [ $record->{ "Q_ID" }, $record->{ "SEQ" } ];
3424 put_record( $record, $out );
3428 @entries = Maasha::Align::align( \@entries );
3430 foreach $entry ( @entries )
3432 if ( $entry->[ SEQ_NAME ] and $entry->[ SEQ ] )
3435 SEQ_NAME => $entry->[ SEQ_NAME ],
3436 SEQ => $entry->[ SEQ ],
3439 put_record( $record, $out );
3447 # Martin A. Hansen, February 2008.
3449 # Using the first sequence in stream as reference, tile
3450 # all subsequent sequences based on pairwise alignments.
3452 my ( $in, # handle to in stream
3453 $out, # handle to out stream
3454 $options, # options hash
3459 my ( $record, $first, $ref_entry, @entries );
3463 while ( $record = get_record( $in ) )
3465 if ( $record->{ "SEQ_NAME" } and $record->{ "SEQ" } )
3469 $ref_entry = [ $record->{ "SEQ_NAME" }, $record->{ "SEQ" } ];
3475 push @entries, [ $record->{ "SEQ_NAME" }, $record->{ "SEQ" } ];
3480 put_record( $record, $out );
3484 @entries = Maasha::Align::align_tile( $ref_entry, \@entries, $options );
3486 map { put_record( { SEQ_NAME => $_->[ SEQ_NAME ], SEQ => $_->[ SEQ ] }, $out ) } @entries;
3490 sub script_invert_align
3492 # Martin A. Hansen, February 2008.
3494 # Inverts an alignment showing only non-mathing residues
3495 # using the first sequence as reference.
3497 my ( $in, # handle to in stream
3498 $out, # handle to out stream
3499 $options, # options hash
3504 my ( $record, @entries );
3506 while ( $record = get_record( $in ) )
3508 if ( $record->{ "SEQ_NAME" } and $record->{ "SEQ" } )
3510 push @entries, [ $record->{ "SEQ_NAME" }, $record->{ "SEQ" } ];
3514 put_record( $record, $out );
3518 Maasha::Align::align_invert( \@entries, $options->{ "soft" } );
3520 map { put_record( { SEQ_NAME => $_->[ SEQ_NAME ], SEQ => $_->[ SEQ ] }, $out ) } @entries;
3524 sub script_patscan_seq
3526 # Martin A. Hansen, August 2007.
3528 # Locates patterns in sequences using scan_for_matches.
3530 my ( $in, # handle to in stream
3531 $out, # handle to out stream
3532 $options, # options hash
3537 my ( $genome_file, @args, $arg, $type, $seq_file, $pat_file, $out_file, $fh_in, $fh_out, $record, $patterns, $pattern, $entry, $result, %head_hash, $i );
3539 if ( $options->{ "patterns" } ) {
3540 $patterns = Maasha::Patscan::parse_patterns( $options->{ "patterns" } );
3541 } elsif ( -f $options->{ "patterns_in" } ) {
3542 $patterns = Maasha::Patscan::read_patterns( $options->{ "patterns_in" } );
3545 $genome_file = "$ENV{ 'BP_DATA' }/genomes/$options->{ 'genome' }/fasta/$options->{ 'genome' }.fna" if $options->{ 'genome' };
3547 push @args, "-c" if $options->{ "comp" };
3548 push @args, "-m $options->{ 'max_hits' }" if $options->{ 'max_hits' };
3549 push @args, "-n $options->{ 'max_misses' }" if $options->{ 'max_hits' };
3551 $seq_file = "$BP_TMP/patscan.seq";
3552 $pat_file = "$BP_TMP/patscan.pat";
3553 $out_file = "$BP_TMP/patscan.out";
3555 $fh_out = Maasha::Common::write_open( $seq_file );
3559 while ( $record = get_record( $in ) )
3561 if ( $record->{ "SEQ" } and $record->{ "SEQ_NAME" } )
3563 $type = Maasha::Seq::seq_guess_type( $record->{ "SEQ" } ) if not $type;
3565 Maasha::Fasta::put_entry( [ $i, $record->{ "SEQ" } ], $fh_out );
3567 $head_hash{ $i } = $record->{ "SEQ_NAME" };
3575 $arg = join " ", @args;
3576 $arg .= " -p" if $type eq "protein";
3578 foreach $pattern ( @{ $patterns } )
3580 $fh_out = Maasha::Common::write_open( $pat_file );
3582 print $fh_out "$pattern\n";
3586 if ( $options->{ 'genome' } ) {
3587 `scan_for_matches $arg $pat_file < $genome_file > $out_file`;
3588 # Maasha::Common::run( "scan_for_matches", "$arg $pat_file < $genome_file > $out_file" );
3590 `scan_for_matches $arg $pat_file < $seq_file > $out_file`;
3591 # Maasha::Common::run( "scan_for_matches", "$arg $pat_file < $seq_file > $out_file" );
3594 $fh_in = Maasha::Common::read_open( $out_file );
3596 while ( $entry = Maasha::Fasta::get_entry( $fh_in ) )
3598 $result = Maasha::Patscan::parse_scan_result( $entry, $pattern );
3600 if ( $options->{ 'genome' } )
3602 $result->{ "CHR" } = $result->{ "S_ID" };
3603 $result->{ "CHR_BEG" } = $result->{ "S_BEG" };
3604 $result->{ "CHR_END" } = $result->{ "S_END" };
3606 delete $result->{ "S_ID" };
3607 delete $result->{ "S_BEG" };
3608 delete $result->{ "S_END" };
3612 $result->{ "S_ID" } = $head_hash{ $result->{ "S_ID" } };
3615 put_record( $result, $out );
3627 sub script_create_blast_db
3629 # Martin A. Hansen, September 2007.
3631 # Creates a NCBI BLAST database with formatdb
3633 my ( $in, # handle to in stream
3634 $out, # handle to out stream
3635 $options, # options hash
3640 my ( $fh, $seq_type, $path, $record, $entry );
3642 $path = $options->{ "database" };
3644 $fh = Maasha::Common::write_open( $path );
3646 while ( $record = get_record( $in ) )
3648 put_record( $record, $out ) if not $options->{ "no_stream" };
3650 if ( $entry = Maasha::Fasta::biopiece2fasta( $record ) )
3652 $seq_type = Maasha::Seq::seq_guess_type( $entry->[ SEQ ] ) if not $seq_type;
3654 Maasha::Fasta::put_entry( $entry, $fh );
3660 if ( $seq_type eq "protein" ) {
3661 Maasha::Common::run( "formatdb", "-p T -i $path -t $options->{ 'database' }" );
3663 Maasha::Common::run( "formatdb", "-p F -i $path -t $options->{ 'database' }" );
3670 sub script_blast_seq
3672 # Martin A. Hansen, September 2007.
3674 # BLASTs sequences in stream against a given database.
3676 my ( $in, # handle to in stream
3677 $out, # handle to out stream
3678 $options, # options hash
3683 my ( $genome, $q_type, $s_type, $tmp_in, $tmp_out, $fh_in, $fh_out, $record, $line, @fields, $entry );
3685 $options->{ "e_val" } = 10 if not defined $options->{ "e_val" };
3686 $options->{ "filter" } = "F";
3687 $options->{ "filter" } = "T" if $options->{ "filter" };
3688 $options->{ "cpus" } ||= 1;
3690 $options->{ "database" } = "$ENV{ 'BP_DATA' }/genomes/$options->{ 'genome' }/blast/$options->{ 'genome' }.fna" if $options->{ 'genome' };
3692 $tmp_in = "$BP_TMP/blast_query.seq";
3693 $tmp_out = "$BP_TMP/blast.result";
3695 $fh_out = Maasha::Filesys::file_write_open( $tmp_in );
3697 while ( $record = get_record( $in ) )
3699 if ( $entry = Maasha::Fasta::biopiece2fasta( $record ) )
3701 $q_type = Maasha::Seq::seq_guess_type( $entry->[ SEQ ] ) if not $q_type;
3703 Maasha::Fasta::put_entry( $entry, $fh_out );
3706 put_record( $record, $out );
3711 if ( -f $options->{ 'database' } . ".phr" ) {
3712 $s_type = "protein";
3714 $s_type = "nucleotide";
3717 if ( not $options->{ 'program' } )
3719 if ( $q_type ne "protein" and $s_type ne "protein" ) {
3720 $options->{ 'program' } = "blastn";
3721 } elsif ( $q_type eq "protein" and $s_type eq "protein" ) {
3722 $options->{ 'program' } = "blastp";
3723 } elsif ( $q_type ne "protein" and $s_type eq "protein" ) {
3724 $options->{ 'program' } = "blastx";
3725 } elsif ( $q_type eq "protein" and $s_type ne "protein" ) {
3726 $options->{ 'program' } = "tblastn";
3730 if ( $options->{ 'verbose' } )
3732 Maasha::Common::run(
3735 "-p $options->{ 'program' }",
3736 "-e $options->{ 'e_val' }",
3737 "-a $options->{ 'cpus' }",
3740 "-d $options->{ 'database' }",
3741 "-F $options->{ 'filter' }",
3749 Maasha::Common::run(
3752 "-p $options->{ 'program' }",
3753 "-e $options->{ 'e_val' }",
3754 "-a $options->{ 'cpus' }",
3757 "-d $options->{ 'database' }",
3758 "-F $options->{ 'filter' }",
3768 $fh_out = Maasha::Filesys::file_read_open( $tmp_out );
3772 while ( $line = <$fh_out> )
3776 next if $line =~ /^#/;
3778 @fields = split /\s+/, $line;
3780 $record->{ "REC_TYPE" } = "BLAST";
3781 $record->{ "Q_ID" } = $fields[ 0 ];
3782 $record->{ "S_ID" } = $fields[ 1 ];
3783 $record->{ "IDENT" } = $fields[ 2 ];
3784 $record->{ "ALIGN_LEN" } = $fields[ 3 ];
3785 $record->{ "MISMATCHES" } = $fields[ 4 ];
3786 $record->{ "GAPS" } = $fields[ 5 ];
3787 $record->{ "Q_BEG" } = $fields[ 6 ] - 1; # BLAST is 1-based
3788 $record->{ "Q_END" } = $fields[ 7 ] - 1; # BLAST is 1-based
3789 $record->{ "S_BEG" } = $fields[ 8 ] - 1; # BLAST is 1-based
3790 $record->{ "S_END" } = $fields[ 9 ] - 1; # BLAST is 1-based
3791 $record->{ "E_VAL" } = $fields[ 10 ];
3792 $record->{ "BIT_SCORE" } = $fields[ 11 ];
3794 if ( $record->{ "S_BEG" } > $record->{ "S_END" } )
3796 $record->{ "STRAND" } = '-';
3798 ( $record->{ "S_BEG" }, $record->{ "S_END" } ) = ( $record->{ "S_END" }, $record->{ "S_BEG" } );
3802 $record->{ "STRAND" } = '+';
3805 put_record( $record, $out );
3816 # Martin A. Hansen, August 2007.
3818 # BLATs sequences in stream against a given genome.
3820 my ( $in, # handle to in stream
3821 $out, # handle to out stream
3822 $options, # options hash
3827 my ( $blat_args, $genome_file, $query_file, $fh_in, $fh_out, $type, $record, $result_file, $entries, $entry );
3829 $genome_file = "$ENV{ 'BP_DATA' }/genomes/$options->{ 'genome' }/fasta/$options->{ 'genome' }.fna";
3831 $options->{ 'tile_size' } ||= 11;
3832 $options->{ 'one_off' } ||= 0;
3833 $options->{ 'min_identity' } ||= 90;
3834 $options->{ 'min_score' } ||= 0;
3835 $options->{ 'step_size' } ||= $options->{ 'tile_size' };
3837 $blat_args .= " -tileSize=$options->{ 'tile_size' }";
3838 $blat_args .= " -oneOff=$options->{ 'one_off' }";
3839 $blat_args .= " -minIdentity=$options->{ 'min_identity' }";
3840 $blat_args .= " -minScore=$options->{ 'min_score' }";
3841 $blat_args .= " -stepSize=$options->{ 'step_size' }";
3842 # $blat_args .= " -ooc=" . Maasha::Config::genome_blat_ooc( $options->{ "genome" }, 11 ) if $options->{ 'ooc' };
3844 $query_file = "$BP_TMP/blat.seq";
3846 $fh_out = Maasha::Common::write_open( $query_file );
3848 while ( $record = get_record( $in ) )
3850 if ( $entry = Maasha::Fasta::biopiece2fasta( $record ) )
3852 $type = Maasha::Seq::seq_guess_type( $entry->[ SEQ ] ) if not $type;
3853 Maasha::Fasta::put_entry( $entry, $fh_out, 80 );
3856 put_record( $record, $out );
3861 $blat_args .= " -t=dnax" if $type eq "protein";
3862 $blat_args .= " -q=$type";
3864 $result_file = "$BP_TMP/blat.psl";
3866 Maasha::Common::run( "blat", "$genome_file $query_file $blat_args $result_file > /dev/null 2>&1" );
3870 $entries = Maasha::UCSC::psl_get_entries( $result_file );
3872 map { put_record( $_, $out ) } @{ $entries };
3874 unlink $result_file;
3880 # Martin A. Hansen, July 2008.
3882 # soap sequences in stream against a given file or genome.
3884 my ( $in, # handle to in stream
3885 $out, # handle to out stream
3886 $options, # options hash
3891 my ( $genome, $tmp_in, $tmp_out, $fh_in, $fh_out, $record, $line, @fields, $entry, $count, $args );
3893 $options->{ "seed_size" } ||= 10;
3894 $options->{ "mismatches" } ||= 2;
3895 $options->{ "gap_size" } ||= 0;
3896 $options->{ "cpus" } ||= 1;
3898 if ( $options->{ "genome" } ) {
3899 $options->{ "in_file" } = "$ENV{ 'BP_DATA' }/genomes/$options->{ 'genome' }/fasta/$options->{ 'genome' }.fna";
3902 $tmp_in = "$BP_TMP/soap_query.seq";
3903 $tmp_out = "$BP_TMP/soap.result";
3905 $fh_out = Maasha::Common::write_open( $tmp_in );
3909 while ( $record = get_record( $in ) )
3911 if ( $entry = Maasha::Fasta::biopiece2fasta( $record ) )
3913 Maasha::Fasta::put_entry( $entry, $fh_out );
3918 put_record( $record, $out );
3926 "-s $options->{ 'seed_size' }",
3929 "-v $options->{ 'mismatches' }",
3930 "-g $options->{ 'gap_size' }",
3931 "-p $options->{ 'cpus' }",
3932 "-d $options->{ 'in_file' }",
3936 $args .= " > /dev/null 2>&1" if not $options->{ 'verbose' };
3938 Maasha::Common::run( "soap", $args, 1 );
3942 $fh_out = Maasha::Common::read_open( $tmp_out );
3946 while ( $line = <$fh_out> )
3950 @fields = split /\t/, $line;
3952 $record->{ "REC_TYPE" } = "SOAP";
3953 $record->{ "Q_ID" } = $fields[ 0 ];
3954 $record->{ "SCORE" } = $fields[ 3 ];
3955 $record->{ "STRAND" } = $fields[ 6 ];
3956 $record->{ "S_ID" } = $fields[ 7 ];
3957 $record->{ "S_BEG" } = $fields[ 8 ] - 1; # soap is 1-based
3958 $record->{ "S_END" } = $fields[ 8 ] + $fields[ 5 ] - 2;
3960 put_record( $record, $out );
3970 sub script_match_seq
3972 # Martin A. Hansen, August 2007.
3974 # BLATs sequences in stream against a given genome.
3976 my ( $in, # handle to in stream
3977 $out, # handle to out stream
3978 $options, # options hash
3983 my ( $record, @entries, $results );
3985 $options->{ "word_size" } ||= 20;
3986 $options->{ "direction" } ||= "both";
3988 while ( $record = get_record( $in ) )
3990 if ( $record->{ "SEQ_NAME" } and $record->{ "SEQ" } ) {
3991 push @entries, [ $record->{ "SEQ_NAME" }, $record->{ "SEQ" } ];
3994 put_record( $record, $out );
3997 if ( @entries == 1 )
3999 $results = Maasha::Match::match_mummer( [ $entries[ 0 ] ], [ $entries[ 0 ] ], $options, $BP_TMP );
4001 map { put_record( $_, $out ) } @{ $results };
4003 elsif ( @entries == 2 )
4005 $results = Maasha::Match::match_mummer( [ $entries[ 0 ] ], [ $entries[ 1 ] ], $options, $BP_TMP );
4007 map { put_record( $_, $out ) } @{ $results };
4012 sub script_create_vmatch_index
4014 # Martin A. Hansen, January 2008.
4016 # Create a vmatch index from sequences in the stream.
4018 my ( $in, # handle to in stream
4019 $out, # handle to out stream
4020 $options, # options hash
4025 my ( $record, $file_tmp, $fh_tmp, $type, $entry );
4027 if ( $options->{ "index_name" } )
4029 $file_tmp = $options->{ 'index_name' };
4030 $fh_tmp = Maasha::Common::write_open( $file_tmp );
4033 while ( $record = get_record( $in ) )
4035 if ( $options->{ "index_name" } and $entry = Maasha::Fasta::biopiece2fasta( $record ) )
4037 Maasha::Fasta::put_entry( $entry, $fh_tmp );
4039 $type = Maasha::Seq::seq_guess_type( $entry->[ SEQ ] ) if not defined $type;
4042 put_record( $record, $out ) if not $options->{ "no_stream" };
4045 if ( $options->{ "index_name" } )
4049 if ( $type eq "protein" ) {
4050 Maasha::Common::run( "mkvtree", "-db $file_tmp -protein -pl $options->{ 'prefix_length' } -allout -indexname $file_tmp > /dev/null 2>&1" );
4052 Maasha::Common::run( "mkvtree", "-db $file_tmp -dna -pl $options->{ 'prefix_length' } -allout -indexname $file_tmp > /dev/null 2>&1" );
4060 sub script_vmatch_seq
4062 # Martin A. Hansen, August 2007.
4064 # Vmatches sequences in stream against a given genome.
4066 my ( $in, # handle to in stream
4067 $out, # handle to out stream
4068 $options, # options hash
4073 my ( @index_files, @records, $result_file, $fh_in, $record, %hash );
4075 $options->{ 'count' } = 1 if $options->{ 'max_hits' };
4077 if ( $options->{ "index_name" } )
4079 @index_files = $options->{ "index_name" };
4083 @index_files = Maasha::Common::ls_files( "$ENV{ 'BP_DATA' }/genomes/$options->{ 'genome' }/vmatch" );
4085 map { $_ =~ /^(.+)\.[a-z1]{3,4}$/; $hash{ $1 } = 1 } @index_files;
4087 @index_files = sort keys %hash;
4090 while ( $record = get_record( $in ) )
4092 push @records, $record;
4094 put_record( $record, $out );
4097 $result_file = Maasha::Match::match_vmatch( $BP_TMP, \@records, \@index_files, $options );
4101 $fh_in = Maasha::Common::read_open( $result_file );
4103 while ( $record = Maasha::Match::vmatch_get_entry( $fh_in ) ) {
4104 put_record( $record, $out );
4109 unlink $result_file;
4113 sub script_write_fasta
4115 # Martin A. Hansen, August 2007.
4117 # Write FASTA entries from sequences in stream.
4119 my ( $in, # handle to in stream
4120 $out, # handle to out stream
4121 $options, # options hash
4126 my ( $record, $fh, $entry );
4128 $fh = write_stream( $options->{ "data_out" }, $options->{ "compress" } );
4130 while ( $record = get_record( $in ) )
4132 if ( $entry = Maasha::Fasta::biopiece2fasta( $record ) ) {
4133 Maasha::Fasta::put_entry( $entry, $fh, $options->{ "wrap" } );
4136 put_record( $record, $out ) if not $options->{ "no_stream" };
4143 sub script_write_align
4145 # Martin A. Hansen, August 2007.
4147 # Write pretty alignments aligned sequences in stream.
4149 my ( $in, # handle to in stream
4150 $out, # handle to out stream
4151 $options, # options hash
4156 my ( $fh, $record, @entries );
4158 $fh = write_stream( $options->{ "data_out" } ) ;
4160 while ( $record = get_record( $in ) )
4162 if ( $record->{ "SEQ_NAME" } and $record->{ "SEQ" } ) {
4163 push @entries, [ $record->{ "SEQ_NAME" }, $record->{ "SEQ" } ];
4166 put_record( $record, $out ) if not $options->{ "no_stream" };
4169 if ( scalar( @entries ) == 2 ) {
4170 Maasha::Align::align_print_pairwise( $entries[ 0 ], $entries[ 1 ], $fh, $options->{ "wrap" } );
4171 } elsif ( scalar ( @entries ) > 2 ) {
4172 Maasha::Align::align_print_multi( \@entries, $fh, $options->{ "wrap" }, $options->{ "no_ruler" }, $options->{ "no_consensus" } );
4179 sub script_write_blast
4181 # Martin A. Hansen, November 2007.
4183 # Write data in blast table format (-m8 and 9).
4185 my ( $in, # handle to in stream
4186 $out, # handle to out stream
4187 $options, # options hash
4192 my ( $fh, $record, $first );
4194 $fh = write_stream( $options->{ "data_out" }, $options->{ "compress" } ) ;
4198 while ( $record = get_record( $in ) )
4200 if ( $record->{ "REC_TYPE" } eq "BLAST" )
4202 if ( $options->{ "comment" } and $first )
4204 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";
4209 if ( $record->{ "STRAND" } eq "-" ) {
4210 ( $record->{ "S_BEG" }, $record->{ "S_END" } ) = ( $record->{ "S_END" }, $record->{ "S_BEG" } );
4213 print $fh join( "\t",
4214 $record->{ "Q_ID" },
4215 $record->{ "S_ID" },
4216 $record->{ "IDENT" },
4217 $record->{ "ALIGN_LEN" },
4218 $record->{ "MISMATCHES" },
4219 $record->{ "GAPS" },
4220 $record->{ "Q_BEG" } + 1,
4221 $record->{ "Q_END" } + 1,
4222 $record->{ "S_BEG" } + 1,
4223 $record->{ "S_END" } + 1,
4224 $record->{ "E_VAL" },
4225 $record->{ "BIT_SCORE" }
4229 put_record( $record, $out ) if not $options->{ "no_stream" };
4236 sub script_write_tab
4238 # Martin A. Hansen, August 2007.
4240 # Write data as table.
4242 my ( $in, # handle to in stream
4243 $out, # handle to out stream
4244 $options, # options hash
4249 my ( $fh, $record, $key, @keys, @vals, $ok, %no_keys, $A, $B );
4251 $options->{ "delimit" } ||= "\t";
4253 map { $no_keys{ $_ } = 1 } @{ $options->{ "no_keys" } };
4255 $fh = write_stream( $options->{ "data_out" }, $options->{ "compress" } );
4257 while ( $record = get_record( $in ) )
4262 if ( $options->{ "keys" } )
4264 map { $ok = 0 if not exists $record->{ $_ } } @{ $options->{ "keys" } };
4268 foreach $key ( @{ $options->{ "keys" } } )
4270 if ( exists $record->{ $key } )
4272 push @keys, $key if $options->{ "comment" };
4273 push @vals, $record->{ $key };
4280 foreach $key ( sort { $A = $a; $B = $b; $A =~ s/^V(\d+)$/$1/; $B =~ s/^V(\d+)$/$1/; $A <=> $B } keys %{ $record } )
4282 next if exists $no_keys{ $key };
4284 push @keys, $key if $options->{ "comment" };
4285 push @vals, $record->{ $key };
4289 if ( @keys and $options->{ "comment" } )
4291 print $fh "#", join( $options->{ "delimit" }, @keys ), "\n";
4293 delete $options->{ "comment" };
4296 print $fh join( $options->{ "delimit" }, @vals ), "\n" if @vals;
4298 put_record( $record, $out ) if not $options->{ "no_stream" };
4305 sub script_write_bed
4307 # Martin A. Hansen, August 2007.
4309 # Write BED format for the UCSC genome browser using records in stream.
4311 my ( $in, # handle to in stream
4312 $out, # handle to out stream
4313 $options, # options hash
4318 my ( $cols, $fh, $record, $bed_entry, $new_record );
4320 $cols = $options->{ 'cols' }->[ 0 ];
4322 $fh = write_stream( $options->{ 'data_out' }, $options->{ 'compress' } );
4324 while ( $record = get_record( $in ) )
4326 $record = Maasha::UCSC::psl2record( $record ) if $record->{ 'tBaseInsert' }; # Dirty addition to allow Affy data from MySQL to be dumped
4328 if ( $bed_entry = Maasha::UCSC::BED::biopiece2bed( $record, $cols ) ) {
4329 Maasha::UCSC::BED::bed_entry_put( $bed_entry, $fh, $cols, $options->{ 'check' } );
4332 put_record( $record, $out ) if not $options->{ 'no_stream' };
4339 sub script_write_psl
4341 # Martin A. Hansen, August 2007.
4343 # Write PSL output from stream.
4345 my ( $in, # handle to in stream
4346 $out, # handle to out stream
4347 $options, # options hash
4352 my ( $fh, $record, @output, $first );
4356 $fh = write_stream( $options->{ "data_out" }, $options->{ "compress" } );
4358 while ( $record = get_record( $in ) )
4360 put_record( $record, $out ) if not $options->{ "no_stream" };
4362 if ( $record->{ "REC_TYPE" } and $record->{ "REC_TYPE" } eq "PSL" )
4364 Maasha::UCSC::psl_put_header( $fh ) if $first;
4365 Maasha::UCSC::psl_put_entry( $record, $fh );
4374 sub script_write_fixedstep
4376 # Martin A. Hansen, Juli 2008.
4378 # Write fixedStep entries from recrods in the stream.
4380 my ( $in, # handle to in stream
4381 $out, # handle to out stream
4382 $options, # options hash
4387 my ( $fh, $record, $entry );
4389 $fh = write_stream( $options->{ "data_out" }, $options->{ "compress" } );
4391 while ( $record = get_record( $in ) )
4393 if ( $entry = Maasha::UCSC::Wiggle::biopiece2fixedstep( $record ) ) {
4394 Maasha::UCSC::Wiggle::fixedstep_entry_put( $entry, $fh );
4397 put_record( $record, $out ) if not $options->{ "no_stream" };
4404 sub script_write_2bit
4406 # Martin A. Hansen, March 2008.
4408 # Write sequence entries from stream in 2bit format.
4410 my ( $in, # handle to in stream
4411 $out, # handle to out stream
4412 $options, # options hash
4417 my ( $record, $mask, $tmp_file, $fh_tmp, $fh_in, $fh_out, $entry );
4419 $mask = 1 if not $options->{ "no_mask" };
4421 $tmp_file = "$BP_TMP/write_2bit.fna";
4422 $fh_tmp = Maasha::Common::write_open( $tmp_file );
4424 $fh_out = write_stream( $options->{ "data_out" } );
4426 while ( $record = get_record( $in ) )
4428 if ( $entry = Maasha::Fasta::biopiece2fasta( $record ) ) {
4429 Maasha::Fasta::put_entry( $entry, $fh_tmp );
4432 put_record( $record, $out ) if not $options->{ "no_stream" };
4437 $fh_in = Maasha::Common::read_open( $tmp_file );
4439 Maasha::TwoBit::fasta2twobit( $fh_in, $fh_out, $mask );
4448 sub script_write_solid
4450 # Martin A. Hansen, April 2008.
4452 # Write di-base encoded Solid sequence from entries in stream.
4454 my ( $in, # handle to in stream
4455 $out, # handle to out stream
4456 $options, # options hash
4461 my ( $record, $fh, $entry );
4463 $fh = write_stream( $options->{ "data_out" }, $options->{ "compress" } );
4465 while ( $record = get_record( $in ) )
4467 if ( $entry = Maasha::Fasta::biopiece2fasta( $record ) )
4469 $entry->[ SEQ ] = Maasha::Solid::seq2color_space( uc $entry->[ SEQ ] );
4471 Maasha::Fasta::put_entry( $entry, $fh, $options->{ "wrap" } );
4474 put_record( $record, $out ) if not $options->{ "no_stream" };
4481 sub script_write_ucsc_config
4483 # Martin A. Hansen, November 2008.
4485 # Write UCSC Genome Broser configuration (.ra file type) from
4486 # records in the stream.
4488 my ( $in, # handle to in stream
4489 $out, # handle to out stream
4490 $options, # options hash
4495 my ( $record, $fh );
4497 $fh = write_stream( $options->{ "data_out" } );
4499 while ( $record = get_record( $in ) )
4501 Maasha::UCSC::ucsc_config_entry_put( $record, $fh ) if $record->{ "REC_TYPE" } eq "UCSC Config";
4503 put_record( $record, $out ) if not $options->{ "no_stream" };
4510 sub script_plot_seqlogo
4512 # Martin A. Hansen, August 2007.
4514 # Calculates and writes a sequence logo for alignments.
4516 my ( $in, # handle to in stream
4517 $out, # handle to out stream
4518 $options, # options hash
4523 my ( $record, @entries, $logo, $fh );
4525 while ( $record = get_record( $in ) )
4527 if ( $record->{ "SEQ_NAME" } and $record->{ "SEQ" } ) {
4528 push @entries, [ $record->{ "SEQ_NAME" }, $record->{ "SEQ" } ];
4531 put_record( $record, $out ) if not $options->{ "no_stream" };
4534 $logo = Maasha::Plot::seq_logo( \@entries );
4536 $fh = write_stream( $options->{ "data_out" } );
4544 sub script_plot_phastcons_profiles
4546 # Martin A. Hansen, January 2008.
4548 # Plots PhastCons profiles.
4550 my ( $in, # handle to in stream
4551 $out, # handle to out stream
4552 $options, # options hash
4557 my ( $phastcons_file, $phastcons_index, $index, $fh_phastcons, $record, $scores, $AoA, $plot, $fh );
4559 $options->{ "title" } ||= "PhastCons Profiles";
4561 $phastcons_file = Maasha::Config::genome_phastcons( $options->{ "genome" } );
4562 $phastcons_index = Maasha::Config::genome_phastcons_index( $options->{ "genome" } );
4564 $index = Maasha::UCSC::fixedstep_index_retrieve( $phastcons_index );
4565 $fh_phastcons = Maasha::Common::read_open( $phastcons_file );
4567 while ( $record = get_record( $in ) )
4569 if ( $record->{ "CHR" } and $record->{ "CHR_BEG" } and $record->{ "CHR_END" } )
4571 $scores = Maasha::UCSC::fixedstep_index_lookup( $index, $fh_phastcons, $record->{ "CHR" },
4572 $record->{ "CHR_BEG" },
4573 $record->{ "CHR_END" },
4574 $options->{ "flank" } );
4576 push @{ $AoA }, [ @{ $scores } ];
4579 put_record( $record, $out ) if not $options->{ "no_stream" };
4582 Maasha::UCSC::phastcons_normalize( $AoA );
4584 $AoA = [ [ Maasha::UCSC::phastcons_mean( $AoA ) ] ] if $options->{ "mean" };
4585 $AoA = [ [ Maasha::UCSC::phastcons_median( $AoA ) ] ] if $options->{ "median" };
4587 $AoA = Maasha::Matrix::matrix_flip( $AoA );
4589 $plot = Maasha::Plot::lineplot_simple( $AoA, $options, $BP_TMP );
4591 $fh = write_stream( $options->{ "data_out" } );
4593 print $fh "$_\n" foreach @{ $plot };
4599 sub script_analyze_bed
4601 # Martin A. Hansen, March 2008.
4603 # Analyze BED entries in stream.
4605 my ( $in, # handle to in stream
4606 $out, # handle to out stream
4607 $options, # options hash
4614 while ( $record = get_record( $in ) )
4616 $record = Maasha::UCSC::bed_analyze( $record ) if $record->{ "REC_TYPE" } eq "BED";
4618 put_record( $record, $out );
4623 sub script_analyze_vals
4625 # Martin A. Hansen, August 2007.
4627 # Analyze values for given keys in stream.
4629 my ( $in, # handle to in stream
4630 $out, # handle to out stream
4631 $options, # options hash
4636 my ( $record, $key, @keys, %key_hash, $analysis, $len );
4638 map { $key_hash{ $_ } = 1 } @{ $options->{ "keys" } };
4640 while ( $record = get_record( $in ) )
4642 foreach $key ( keys %{ $record } )
4644 next if $options->{ "keys" } and not exists $key_hash{ $key };
4646 $analysis->{ $key }->{ "COUNT" }++;
4648 if ( Maasha::Calc::is_a_number( $record->{ $key } ) )
4650 $analysis->{ $key }->{ "TYPE" } = "num";
4651 $analysis->{ $key }->{ "SUM" } += $record->{ $key };
4652 $analysis->{ $key }->{ "MAX" } = $record->{ $key } if $record->{ $key } > $analysis->{ $key }->{ "MAX" } or not $analysis->{ $key }->{ "MAX" };
4653 $analysis->{ $key }->{ "MIN" } = $record->{ $key } if $record->{ $key } < $analysis->{ $key }->{ "MIN" } or not $analysis->{ $key }->{ "MIN" };
4657 $len = length $record->{ $key };
4659 $analysis->{ $key }->{ "TYPE" } = "alph";
4660 $analysis->{ $key }->{ "SUM" } += $len;
4661 $analysis->{ $key }->{ "MAX" } = $len if $len > $analysis->{ $key }->{ "MAX" } or not $analysis->{ $key }->{ "MAX" };
4662 $analysis->{ $key }->{ "MIN" } = $len if $len < $analysis->{ $key }->{ "MIM" } or not $analysis->{ $key }->{ "MIN" };
4666 put_record( $record, $out ) if not $options->{ "no_stream" };
4669 foreach $key ( keys %{ $analysis } )
4671 $analysis->{ $key }->{ "MEAN" } = sprintf "%.2f", $analysis->{ $key }->{ "SUM" } / $analysis->{ $key }->{ "COUNT" };
4672 $analysis->{ $key }->{ "SUM" } = sprintf "%.2f", $analysis->{ $key }->{ "SUM" };
4675 my ( $keys, $types, $counts, $mins, $maxs, $sums, $means );
4685 if ( $options->{ "keys" } ) {
4686 @keys = @{ $options->{ "keys" } };
4688 @keys = keys %{ $analysis };
4691 foreach $key ( @keys )
4693 $keys .= sprintf "% 15s", $key;
4694 $types .= sprintf "% 15s", $analysis->{ $key }->{ "TYPE" };
4695 $counts .= sprintf "% 15s", $analysis->{ $key }->{ "COUNT" };
4696 $mins .= sprintf "% 15s", $analysis->{ $key }->{ "MIN" };
4697 $maxs .= sprintf "% 15s", $analysis->{ $key }->{ "MAX" };
4698 $sums .= sprintf "% 15s", $analysis->{ $key }->{ "SUM" };
4699 $means .= sprintf "% 15s", $analysis->{ $key }->{ "MEAN" };
4702 print $out "$keys\n";
4703 print $out "$types\n";
4704 print $out "$counts\n";
4705 print $out "$mins\n";
4706 print $out "$maxs\n";
4707 print $out "$sums\n";
4708 print $out "$means\n";
4712 sub script_head_records
4714 # Martin A. Hansen, August 2007.
4716 # Display the first sequences in stream.
4718 my ( $in, # handle to in stream
4719 $out, # handle to out stream
4720 $options, # options hash
4725 my ( $record, $count );
4727 $options->{ "num" } ||= 10;
4731 while ( $record = get_record( $in ) )
4735 put_record( $record, $out );
4737 last if $count == $options->{ "num" };
4742 sub script_remove_keys
4744 # Martin A. Hansen, August 2007.
4746 # Remove keys from stream.
4748 my ( $in, # handle to in stream
4749 $out, # handle to out stream
4750 $options, # options hash
4755 my ( $record, $new_record );
4757 while ( $record = get_record( $in ) )
4759 if ( $options->{ "keys" } )
4761 map { delete $record->{ $_ } } @{ $options->{ "keys" } };
4763 elsif ( $options->{ "save_keys" } )
4765 map { $new_record->{ $_ } = $record->{ $_ } if exists $record->{ $_ } } @{ $options->{ "save_keys" } };
4767 $record = $new_record;
4770 put_record( $record, $out ) if keys %{ $record };
4775 sub script_remove_adaptor
4777 # Martin A. Hansen, August 2008.
4779 # Find and remove adaptor from sequences in the stream.
4781 my ( $in, # handle to in stream
4782 $out, # handle to out stream
4783 $options, # options hash
4788 my ( $record, $adaptor, $seq, $adaptor_len, $seq_len, $offset, $max_match, $max_mismatch, $pos );
4790 $options->{ "remove" } ||= "after";
4792 $max_mismatch = $options->{ "mismatches" } || 0;
4793 $offset = $options->{ "offset" };
4795 if ( not defined $offset ) {
4801 $adaptor = uc $options->{ "adaptor" };
4802 $adaptor_len = length $adaptor;
4804 while ( $record = get_record( $in ) )
4806 if ( $record->{ "SEQ" } )
4808 $seq = uc $record->{ "SEQ" };
4809 $seq_len = length $seq;
4811 $pos = Maasha::Common::index_m( $seq, $adaptor, $seq_len, $adaptor_len, $offset, $max_mismatch );
4813 $record->{ "ADAPTOR_POS" } = $pos;
4815 if ( $pos >= 0 and $options->{ "remove" } ne "skip" )
4817 if ( $options->{ "remove" } eq "after" )
4819 $record->{ "SEQ" } = substr $record->{ "SEQ" }, 0, $pos;
4820 $record->{ "SEQ_LEN" } = $pos;
4824 $record->{ "SEQ" } = substr $record->{ "SEQ" }, $pos + $adaptor_len;
4825 $record->{ "SEQ_LEN" } = length $record->{ "SEQ" };
4829 put_record( $record, $out );
4833 put_record( $record, $out );
4839 sub script_remove_mysql_tables
4841 # Martin A. Hansen, November 2008.
4843 # Remove MySQL tables from values in stream.
4845 my ( $in, # handle to in stream
4846 $out, # handle to out stream
4847 $options, # options hash
4852 my ( $record, %table_hash, $dbh, $table );
4854 $options->{ "user" } ||= Maasha::UCSC::ucsc_get_user();
4855 $options->{ "password" } ||= Maasha::UCSC::ucsc_get_password();
4857 map { $table_hash{ $_ } = 1 } @{ $options->{ 'tables' } };
4859 while ( $record = get_record( $in ) )
4861 map { $table_hash{ $record->{ $_ } } = 1 } @{ $options->{ 'keys' } };
4863 put_record( $record, $out ) if not $options->{ 'no_stream' };
4866 $dbh = Maasha::SQL::connect( $options->{ "database" }, $options->{ "user" }, $options->{ "password" } );
4868 foreach $table ( sort keys %table_hash )
4870 if ( Maasha::SQL::table_exists( $dbh, $table ) )
4872 print STDERR qq(Removing table "$table" from database "$options->{ 'database' }" ... ) if $options->{ 'verbose' };
4873 Maasha::SQL::delete_table( $dbh, $table );
4874 print STDERR "done.\n" if $options->{ 'verbose' };
4878 print STDERR qq(WARNING: table "$table" not found in database "$options->{ 'database' }\n");
4882 Maasha::SQL::disconnect( $dbh );
4886 sub script_remove_ucsc_tracks
4888 # Martin A. Hansen, November 2008.
4890 # Remove track from MySQL tables and config file.
4892 my ( $in, # handle to in stream
4893 $out, # handle to out stream
4894 $options, # options hash
4899 my ( $record, %track_hash, $fh_in, $fh_out, $track, @tracks, @new_tracks, $dbh );
4901 $options->{ 'user' } ||= Maasha::UCSC::ucsc_get_user();
4902 $options->{ 'password' } ||= Maasha::UCSC::ucsc_get_password();
4903 $options->{ 'config_file' } ||= "$ENV{ 'HOME' }/ucsc/my_tracks.ra";
4905 map { $track_hash{ $_ } = 1 } @{ $options->{ 'tracks' } };
4907 while ( $record = get_record( $in ) )
4909 map { $track_hash{ $record->{ $_ } } = 1 } @{ $options->{ 'keys' } };
4911 put_record( $record, $out ) if not $options->{ 'no_stream' };
4914 # ---- locate track in config file ----
4916 $fh_in = Maasha::Common::read_open( $options->{ 'config_file' } );
4918 while ( $track = Maasha::UCSC::ucsc_config_entry_get( $fh_in ) ) {
4919 push @tracks, $track;
4924 map { push @new_tracks, $_ if not exists $track_hash{ $_->{ 'track' } } } @tracks;
4926 print STDERR qq(WARNING: track not found in config file: "$options->{ 'config_file' }"\n) if scalar @tracks == scalar @new_tracks;
4928 rename "$options->{ 'config_file' }", "$options->{ 'config_file' }~";
4930 $fh_out = Maasha::Common::write_open( $options->{ 'config_file' } );
4932 map { Maasha::UCSC::ucsc_config_entry_put( $_, $fh_out ) } @new_tracks;
4936 # ---- locate track in database ----
4938 $dbh = Maasha::SQL::connect( $options->{ "database" }, $options->{ "user" }, $options->{ "password" } );
4940 foreach $track ( sort keys %track_hash )
4942 if ( Maasha::SQL::table_exists( $dbh, $track ) )
4944 print STDERR qq(Removing table "$track" from database "$options->{ 'database' }" ... ) if $options->{ 'verbose' };
4945 Maasha::SQL::delete_table( $dbh, $track );
4946 print STDERR "done.\n" if $options->{ 'verbose' };
4950 print STDERR qq(WARNING: table "$track" not found in database "$options->{ 'database' }\n");
4954 Maasha::SQL::disconnect( $dbh );
4956 Maasha::Common::run( "ucscMakeTracks.pl", "-b > /dev/null 2>&1" );
4960 sub script_rename_keys
4962 # Martin A. Hansen, August 2007.
4964 # Rename keys in stream.
4966 my ( $in, # handle to in stream
4967 $out, # handle to out stream
4968 $options, # options hash
4975 while ( $record = get_record( $in ) )
4977 if ( exists $record->{ $options->{ "keys" }->[ 0 ] } )
4979 $record->{ $options->{ "keys" }->[ 1 ] } = $record->{ $options->{ "keys" }->[ 0 ] };
4981 delete $record->{ $options->{ "keys" }->[ 0 ] };
4984 put_record( $record, $out );
4989 sub script_uniq_vals
4991 # Martin A. Hansen, August 2007.
4993 # Find unique values in stream.
4995 my ( $in, # handle to in stream
4996 $out, # handle to out stream
4997 $options, # options hash
5002 my ( %hash, $record );
5004 while ( $record = get_record( $in ) )
5006 if ( $record->{ $options->{ "key" } } )
5008 if ( not $hash{ $record->{ $options->{ "key" } } } and not $options->{ "invert" } )
5010 put_record( $record, $out );
5012 $hash{ $record->{ $options->{ "key" } } } = 1;
5014 elsif ( $hash{ $record->{ $options->{ "key" } } } and $options->{ "invert" } )
5016 put_record( $record, $out );
5020 $hash{ $record->{ $options->{ "key" } } } = 1;
5025 put_record( $record, $out );
5031 sub script_merge_vals
5033 # Martin A. Hansen, August 2007.
5035 # Rename keys in stream.
5037 my ( $in, # handle to in stream
5038 $out, # handle to out stream
5039 $options, # options hash
5044 my ( $record, @join, $i );
5046 $options->{ "delimit" } ||= '_';
5048 while ( $record = get_record( $in ) )
5050 if ( exists $record->{ $options->{ "keys" }->[ 0 ] } )
5052 @join = $record->{ $options->{ "keys" }->[ 0 ] };
5054 for ( $i = 1; $i < @{ $options->{ "keys" } }; $i++ ) {
5055 push @join, $record->{ $options->{ "keys" }->[ $i ] } if exists $record->{ $options->{ "keys" }->[ $i ] };
5058 $record->{ $options->{ "keys" }->[ 0 ] } = join $options->{ "delimit" }, @join;
5061 put_record( $record, $out );
5066 sub script_merge_records
5068 # Martin A. Hansen, July 2008.
5070 # Merges records in the stream based on identical values of two given keys.
5072 my ( $in, # handle to in stream
5073 $out, # handle to out stream
5074 $options, # options hash
5079 my ( $merge, $record, $file1, $file2, $fh1, $fh2, $key1, $key2, @keys1, @keys2, @vals1, @vals2,
5080 $num1, $num2, $num, $cmp, $i );
5082 $merge = $options->{ "merge" } || "AandB";
5084 $file1 = "$BP_TMP/merge_records1.tmp";
5085 $file2 = "$BP_TMP/merge_records2.tmp";
5087 $fh1 = Maasha::Common::write_open( $file1 );
5088 $fh2 = Maasha::Common::write_open( $file2 );
5090 $key1 = $options->{ "keys" }->[ 0 ];
5091 $key2 = $options->{ "keys" }->[ 1 ];
5093 $num = $key2 =~ s/n$//;
5097 while ( $record = get_record( $in ) )
5099 if ( exists $record->{ $key1 } )
5102 @vals1 = $record->{ $key1 };
5104 delete $record->{ $key1 };
5106 map { push @keys1, $_; push @vals1, $record->{ $_ } } keys %{ $record };
5108 print $fh1 join( "\t", @vals1 ), "\n";
5112 elsif ( exists $record->{ $key2 } )
5115 @vals2 = $record->{ $key2 };
5117 delete $record->{ $key2 };
5119 map { push @keys2, $_; push @vals2, $record->{ $_ } } keys %{ $record };
5121 print $fh2 join( "\t", @vals2 ), "\n";
5132 Maasha::Common::run( "sort", "-k 1,1n $file1 > $file1.sort" ) and rename "$file1.sort", $file1;
5133 Maasha::Common::run( "sort", "-k 1,1n $file2 > $file2.sort" ) and rename "$file2.sort", $file2;
5137 Maasha::Common::run( "sort", "-k 1,1 $file1 > $file1.sort" ) and rename "$file1.sort", $file1;
5138 Maasha::Common::run( "sort", "-k 1,1 $file2 > $file2.sort" ) and rename "$file2.sort", $file2;
5141 $fh1 = Maasha::Common::read_open( $file1 );
5142 $fh2 = Maasha::Common::read_open( $file2 );
5144 @vals1 = Maasha::Common::get_fields( $fh1 );
5145 @vals2 = Maasha::Common::get_fields( $fh2 );
5147 while ( $num1 > 0 and $num2 > 0 )
5152 $cmp = $vals1[ 0 ] <=> $vals2[ 0 ];
5154 $cmp = $vals1[ 0 ] cmp $vals2[ 0 ];
5159 if ( $merge =~ /^(AorB|AnotB)$/ )
5161 for ( $i = 0; $i < @keys1; $i++ ) {
5162 $record->{ $keys1[ $i ] } = $vals1[ $i ];
5165 put_record( $record, $out );
5168 @vals1 = Maasha::Common::get_fields( $fh1 );
5173 if ( $merge =~ /^(BorA|BnotA)$/ )
5175 for ( $i = 0; $i < @keys2; $i++ ) {
5176 $record->{ $keys2[ $i ] } = $vals2[ $i ];
5179 put_record( $record, $out );
5182 @vals2 = Maasha::Common::get_fields( $fh2 );
5187 if ( $merge =~ /^(AandB|AorB|BorA)$/ )
5189 for ( $i = 0; $i < @keys1; $i++ ) {
5190 $record->{ $keys1[ $i ] } = $vals1[ $i ];
5193 for ( $i = 1; $i < @keys2; $i++ ) {
5194 $record->{ $keys2[ $i ] } = $vals2[ $i ];
5197 put_record( $record, $out );
5200 @vals1 = Maasha::Common::get_fields( $fh1 );
5201 @vals2 = Maasha::Common::get_fields( $fh2 );
5213 if ( $num1 > 0 and $merge =~ /^(AorB|AnotB)$/ )
5217 for ( $i = 0; $i < @keys1; $i++ ) {
5218 $record->{ $keys1[ $i ] } = $vals1[ $i ];
5221 put_record( $record, $out );
5224 if ( $num2 > 0 and $merge =~ /^(BorA|BnotA)$/ )
5228 for ( $i = 0; $i < @keys2; $i++ ) {
5229 $record->{ $keys2[ $i ] } = $vals2[ $i ];
5232 put_record( $record, $out );
5239 # Martin A. Hansen, August 2007.
5241 # Grab for records in stream.
5243 my ( $in, # handle to in stream
5244 $out, # handle to out stream
5245 $options, # options hash
5250 my ( $keys, $vals_only, $keys_only, $invert, $patterns, $pattern, $regex, $record, $key, $op, $val, %lookup_hash, $found );
5252 $keys = $options->{ 'keys' };
5253 $vals_only = $options->{ 'vals_only' };
5254 $keys_only = $options->{ 'keys_only' };
5255 $invert = $options->{ 'invert' };
5257 if ( $options->{ 'patterns' } )
5259 $patterns = [ split ",", $options->{ 'patterns' } ];
5261 elsif ( -f $options->{ 'patterns_in' } )
5263 $patterns = Maasha::Patscan::read_patterns( $options->{ 'patterns_in' } );
5265 elsif ( $options->{ 'regex' } )
5267 if ( $options->{ 'case_insensitive' } ) {
5268 $regex = qr/$options->{ 'regex' }/i;
5270 $regex = qr/$options->{ 'regex' }/;
5273 elsif ( -f $options->{ 'exact_in' } )
5275 $patterns = Maasha::Patscan::read_patterns( $options->{ 'exact_in' } );
5277 map { $lookup_hash{ $_ } = 1 } @{ $patterns };
5281 elsif ( $options->{ 'eval' } )
5283 if ( $options->{ 'eval' } =~ /^([^><=! ]+)\s*(>=|<=|>|<|=|!=|eq|ne)\s*(.+)$/ )
5291 while ( $record = get_record( $in ) )
5295 if ( %lookup_hash ) {
5296 $found = grab_lookup( \%lookup_hash, $record, $keys, $vals_only, $keys_only );
5297 } elsif ( $patterns ) {
5298 $found = grab_patterns( $patterns, $record, $keys, $vals_only, $keys_only );
5299 } elsif ( $regex ) {
5300 $found = grab_regex( $regex, $record, $keys, $vals_only, $keys_only );
5302 $found = grab_eval( $key, $op, $val, $record );
5305 if ( $found and not $invert ) {
5306 put_record( $record, $out );
5307 } elsif ( not $found and $invert ) {
5308 put_record( $record, $out );
5316 # Martin A. Hansen, August 2007.
5318 # Evaluate extression for records in stream.
5320 my ( $in, # handle to in stream
5321 $out, # handle to out stream
5322 $options, # options hash
5327 my ( $record, $eval_key, @keys, $eval_val );
5329 while ( $record = get_record( $in ) )
5331 if ( $options->{ "eval" } )
5333 if ( $options->{ "eval" } =~ /^(\S+)\s*=\s*(.+)$/ )
5340 @keys = split /\s+|\+|-|\*|\/|\*\*/, $eval_val;
5342 @keys = grep { exists $record->{ $_ } } @keys;
5345 map { $eval_val =~ s/\Q$_\E/$record->{ $_ }/g } @keys;
5347 $record->{ $eval_key } = eval "$eval_val";
5348 Maasha::Common::error( qq(eval "$eval_key = $eval_val" failed -> $@) ) if $@;
5352 Maasha::Common::error( qq(Bad compute expression: "$options->{ 'eval' }"\n) );
5356 put_record( $record, $out );
5363 # Martin A. Hansen, June 2008.
5367 my ( $in, # handle to in stream
5368 $out, # handle to out stream
5369 $options, # options hash
5374 my ( $record, $key, $A, $B, @rows, @matrix, $row, $i );
5376 while ( $record = get_record( $in ) )
5380 foreach $key ( sort { $A = $a; $B = $b; $A =~ s/^V(\d+)$/$1/; $B =~ s/^V(\d+)$/$1/; $A <=> $B } keys %{ $record } )
5382 push @rows, $record->{ $key };
5386 push @matrix, [ @rows ];
5391 @matrix = Maasha::Matrix::matrix_flip( \@matrix );
5393 foreach $row ( @matrix )
5395 for ( $i = 0; $i < @{ $row }; $i++ ) {
5396 $record->{ "V$i" } = $row->[ $i ];
5399 put_record( $record, $out );
5404 sub script_add_ident
5406 # Martin A. Hansen, May 2008.
5408 # Add a unique identifier to each record in stream.
5410 my ( $in, # handle to in stream
5411 $out, # handle to out stream
5412 $options, # options hash
5417 my ( $record, $key, $prefix, $i );
5419 $key = $options->{ "key" } || "ID";
5420 $prefix = $options->{ "prefix" } || "ID";
5424 while ( $record = get_record( $in ) )
5426 $record->{ $key } = sprintf( "$prefix%08d", $i );
5428 put_record( $record, $out );
5435 sub script_count_records
5437 # Martin A. Hansen, August 2007.
5439 # Count records in stream.
5441 my ( $in, # handle to in stream
5442 $out, # handle to out stream
5443 $options, # options hash
5448 my ( $record, $count, $result, $fh, $line );
5452 if ( $options->{ "no_stream" } )
5454 while ( $line = <$in> )
5458 $count++ if $line eq "---";
5463 while ( $record = get_record( $in ) )
5465 put_record( $record, $out );
5471 $result = { "RECORDS_COUNT" => $count };
5473 $fh = write_stream( $options->{ "data_out" } );
5475 put_record( $result, $fh );
5481 sub script_random_records
5483 # Martin A. Hansen, August 2007.
5485 # Pick a number or random records from stream.
5487 my ( $in, # handle to in stream
5488 $out, # handle to out stream
5489 $options, # options hash
5494 my ( $record, $tmp_file, $fh_out, $fh_in, $count, $i, %rand_hash, $rand, $max );
5496 $options->{ "num" } ||= 10;
5498 $tmp_file = "$BP_TMP/random_records.tmp";
5500 $fh_out = Maasha::Common::write_open( $tmp_file );
5504 while ( $record = get_record( $in ) )
5506 put_record( $record, $fh_out );
5516 Maasha::Common::error( qq(Requested random records > records in stream) ) if $options->{ "num" } > $count;
5518 while ( $i < $options->{ "num" } )
5520 $rand = int( rand( $count ) );
5522 if ( not exists $rand_hash{ $rand } )
5524 $rand_hash{ $rand } = 1;
5526 $max = $rand if $rand > $max;
5532 $fh_in = Maasha::Common::read_open( $tmp_file );
5536 while ( $record = get_record( $fh_in ) )
5538 put_record( $record, $out ) if exists $rand_hash{ $count };
5540 last if $count == $max;
5551 sub script_sort_records
5553 # Martin A. Hansen, August 2007.
5555 # Sort to sort records according to keys.
5557 my ( $in, # handle to in stream
5558 $out, # handle to out stream
5559 $options, # options hash
5564 my ( @keys, $key, @sort_cmd, $sort_str, $sort_sub, @records, $record, $i );
5566 foreach $key ( @{ $options->{ "keys" } } )
5568 if ( $key =~ s/n$// ) {
5569 push @sort_cmd, qq(\$a->{ "$key" } <=> \$b->{ "$key" });
5571 push @sort_cmd, qq(\$a->{ "$key" } cmp \$b->{ "$key" });
5575 $sort_str = join " or ", @sort_cmd;
5576 $sort_sub = eval "sub { $sort_str }"; # NB security issue!
5578 while ( $record = get_record( $in ) ) {
5579 push @records, $record;
5582 @records = sort $sort_sub @records;
5584 if ( $options->{ "reverse" } )
5586 for ( $i = scalar @records - 1; $i >= 0; $i-- ) {
5587 put_record( $records[ $i ], $out );
5592 for ( $i = 0; $i < scalar @records; $i++ ) {
5593 put_record( $records[ $i ], $out );
5599 sub script_count_vals
5601 # Martin A. Hansen, August 2007.
5603 # Count records in stream.
5605 my ( $in, # handle to in stream
5606 $out, # handle to out stream
5607 $options, # options hash
5612 my ( $num, $record, %count_hash, @records, $tmp_file, $fh_out, $fh_in, $cache );
5614 $tmp_file = "$BP_TMP/count_cache.tmp";
5616 $fh_out = Maasha::Common::write_open( $tmp_file );
5621 while ( $record = get_record( $in ) )
5623 map { $count_hash{ $_ }{ $record->{ $_ } }++ if exists $record->{ $_ } } @{ $options->{ "keys" } };
5625 push @records, $record;
5627 if ( scalar @records > 5_000_000 ) # too many records to hold in memory - use disk cache
5629 map { put_record( $_, $fh_out ) } @records;
5636 print STDERR "verbose: records read $num\n" if ( $options->{ 'verbose' } and ( $num % 1_000_000 ) == 0 );
5647 $fh_in = Maasha::Common::read_open( $tmp_file );
5649 while ( $record = get_record( $fh_in ) )
5651 map { $record->{ $_ . "_COUNT" } = $count_hash{ $_ }{ $record->{ $_ } } if exists $record->{ $_ } } @{ $options->{ "keys" } };
5653 put_record( $record, $out );
5655 print STDERR "verbose: cache read $num\n" if ( $options->{ 'verbose' } and ( $num % 1_000_000 ) == 0 );
5663 foreach $record ( @records )
5665 map { $record->{ $_ . "_COUNT" } = $count_hash{ $_ }{ $record->{ $_ } } if exists $record->{ $_ } } @{ $options->{ "keys" } };
5667 put_record( $record, $out );
5674 sub script_plot_histogram
5676 # Martin A. Hansen, September 2007.
5678 # Plot a simple histogram for a given key using GNU plot.
5680 my ( $in, # handle to in stream
5681 $out, # handle to out stream
5682 $options, # options hash
5687 my ( $record, %data_hash, $max, @data_list, $i, $result, $fh );
5689 $options->{ "title" } ||= "Histogram";
5690 $options->{ "sort" } ||= "num";
5692 while ( $record = get_record( $in ) )
5694 $data_hash{ $record->{ $options->{ "key" } } }++ if defined $record->{ $options->{ "key" } };
5696 put_record( $record, $out ) if not $options->{ "no_stream" };
5699 if ( $options->{ "sort" } eq "num" ) {
5700 map { push @data_list, [ $_, $data_hash{ $_ } ] } sort { $a <=> $b } keys %data_hash;
5702 map { push @data_list, [ $_, $data_hash{ $_ } ] } sort keys %data_hash;
5705 $result = Maasha::Plot::histogram_simple( \@data_list, $options );
5707 $fh = write_stream( $options->{ "data_out" } );
5709 print $fh "$_\n" foreach @{ $result };
5715 sub script_plot_lendist
5717 # Martin A. Hansen, August 2007.
5719 # Plot length distribution using GNU plot.
5721 my ( $in, # handle to in stream
5722 $out, # handle to out stream
5723 $options, # options hash
5728 my ( $record, %data_hash, $max, @data_list, $i, $result, $fh );
5730 $options->{ "title" } ||= "Length Distribution";
5732 while ( $record = get_record( $in ) )
5734 $data_hash{ $record->{ $options->{ "key" } } }++ if defined $record->{ $options->{ "key" } };
5736 put_record( $record, $out ) if not $options->{ "no_stream" };
5739 $max = Maasha::Calc::list_max( [ keys %data_hash ] );
5741 for ( $i = 0; $i < $max; $i++ ) {
5742 push @data_list, [ $i, $data_hash{ $i } || 0 ];
5745 $result = Maasha::Plot::histogram_lendist( \@data_list, $options );
5747 $fh = write_stream( $options->{ "data_out" } );
5749 print $fh "$_\n" foreach @{ $result };
5755 sub script_plot_chrdist
5757 # Martin A. Hansen, August 2007.
5759 # Plot chromosome distribution using GNU plot.
5761 my ( $in, # handle to in stream
5762 $out, # handle to out stream
5763 $options, # options hash
5768 my ( $record, %data_hash, @data_list, $elem, $sort_key, $count, $result, $fh );
5770 $options->{ "title" } ||= "Chromosome Distribution";
5772 while ( $record = get_record( $in ) )
5774 if ( $record->{ "CHR" } ) { # generic
5775 $data_hash{ $record->{ "CHR" } }++;
5776 } elsif ( $record->{ "REC_TYPE" } eq "PATSCAN" and $record->{ "S_ID" } =~ /^chr/i ) { # patscan
5777 $data_hash{ $record->{ "S_ID" } }++;
5778 } elsif ( $record->{ "REC_TYPE" } eq "PSL" and $record->{ "S_ID" } =~ /^chr/i ) { # BLAT / PSL
5779 $data_hash{ $record->{ "S_ID" } }++;
5780 } elsif ( $record->{ "REC_TYPE" } eq "BLAST" and $record->{ "S_ID" } =~ /^chr/i ) { # BLAST
5781 $data_hash{ $record->{ "S_ID" } }++;
5784 put_record( $record, $out ) if not $options->{ "no_stream" };
5787 foreach $elem ( keys %data_hash )
5791 $sort_key =~ s/chr//i;
5793 $sort_key =~ s/^X(.*)/99$1/;
5794 $sort_key =~ s/^Y(.*)/99$1/;
5795 $sort_key =~ s/^Z(.*)/999$1/;
5796 $sort_key =~ s/^M(.*)/9999$1/;
5797 $sort_key =~ s/^U(.*)/99999$1/;
5799 $count = $sort_key =~ tr/_//;
5801 $sort_key =~ s/_.*/"999999" x $count/ex;
5803 push @data_list, [ $elem, $data_hash{ $elem }, $sort_key ];
5806 @data_list = sort { $a->[ 2 ] <=> $b->[ 2 ] } @data_list;
5808 $result = Maasha::Plot::histogram_chrdist( \@data_list, $options );
5810 $fh = write_stream( $options->{ "data_out" } );
5812 print $fh "$_\n" foreach @{ $result };
5818 sub script_plot_karyogram
5820 # Martin A. Hansen, August 2007.
5822 # Plot hits on karyogram.
5824 my ( $in, # handle to in stream
5825 $out, # handle to out stream
5826 $options, # options hash
5831 my ( %options, $record, @data, $fh, $result, %data_hash );
5833 $options->{ "genome" } ||= "human";
5834 $options->{ "feat_color" } ||= "black";
5836 while ( $record = get_record( $in ) )
5838 if ( $record->{ "CHR" } and $record->{ "CHR_BEG" } and $record->{ "CHR_END" } )
5840 push @{ $data_hash{ $record->{ "CHR" } } }, [ $record->{ "CHR_BEG" }, $record->{ "CHR_END" }, $options->{ "feat_color" } ];
5843 put_record( $record, $out ) if not $options->{ "no_stream" };
5846 $result = Maasha::Plot::karyogram( \%data_hash, \%options );
5848 $fh = write_stream( $options->{ "data_out" } );
5856 sub script_plot_matches
5858 # Martin A. Hansen, August 2007.
5860 # Plot matches in 2D generating a dotplot.
5862 my ( $in, # handle to in stream
5863 $out, # handle to out stream
5864 $options, # options hash
5869 my ( $record, @data, $fh, $result, %data_hash );
5871 $options->{ "direction" } ||= "both";
5873 while ( $record = get_record( $in ) )
5875 if ( defined $record->{ "Q_BEG" } and defined $record->{ "S_BEG" } and $record->{ "Q_END" } and $record->{ "S_END" } ) {
5876 push @data, $record;
5879 put_record( $record, $out ) if not $options->{ "no_stream" };
5882 $options->{ "title" } ||= "plot_matches";
5883 $options->{ "xlabel" } ||= $data[ 0 ]->{ "Q_ID" };
5884 $options->{ "ylabel" } ||= $data[ 0 ]->{ "S_ID" };
5886 $result = Maasha::Plot::dotplot_matches( \@data, $options, $BP_TMP );
5888 $fh = write_stream( $options->{ "data_out" } );
5890 print $fh "$_\n" foreach @{ $result };
5896 sub script_length_vals
5898 # Martin A. Hansen, August 2007.
5900 # Determine the length of the value for given keys.
5902 my ( $in, # handle to in stream
5903 $out, # handle to out stream
5904 $options, # options hash
5909 my ( $record, $key );
5911 while ( $record = get_record( $in ) )
5913 foreach $key ( @{ $options->{ "keys" } } )
5915 if ( $record->{ $key } ) {
5916 $record->{ $key . "_LEN" } = length $record->{ $key };
5920 put_record( $record, $out );
5927 # Martin A. Hansen, August 2007.
5929 # Calculates the sums for values of given keys.
5931 my ( $in, # handle to in stream
5932 $out, # handle to out stream
5933 $options, # options hash
5938 my ( $record, $key, %sum_hash, $fh );
5940 while ( $record = get_record( $in ) )
5942 foreach $key ( @{ $options->{ "keys" } } )
5944 if ( $record->{ $key } ) {
5945 $sum_hash{ $key } += $record->{ $key };
5949 put_record( $record, $out ) if not $options->{ "no_stream" };
5952 $fh = write_stream( $options->{ "data_out" } );
5954 foreach $key ( @{ $options->{ "keys" } } ) {
5955 put_record( { $key . "_SUM" => $sum_hash{ $key } || 0 } , $fh );
5962 sub script_mean_vals
5964 # Martin A. Hansen, August 2007.
5966 # Calculate the mean of values of given keys.
5968 my ( $in, # handle to in stream
5969 $out, # handle to out stream
5970 $options, # options hash
5975 my ( $record, $key, %sum_hash, %count_hash, $mean, $fh );
5977 while ( $record = get_record( $in ) )
5979 foreach $key ( @{ $options->{ "keys" } } )
5981 if ( $record->{ $key } )
5983 $sum_hash{ $key } += $record->{ $key };
5984 $count_hash{ $key }++;
5988 put_record( $record, $out ) if not $options->{ "no_stream" };
5991 $fh = write_stream( $options->{ "data_out" } );
5993 foreach $key ( @{ $options->{ "keys" } } )
5995 if ( $count_hash{ $key } ) {
5996 $mean = sprintf( "%.2f", ( $sum_hash{ $key } / $count_hash{ $key } ) );
6001 put_record( { $key . "_MEAN" => $mean } , $fh );
6008 sub script_median_vals
6010 # Martin A. Hansen, March 2008.
6012 # Calculate the median values of given keys.
6014 my ( $in, # handle to in stream
6015 $out, # handle to out stream
6016 $options, # options hash
6021 my ( $record, $key, %median_hash, $median, $fh );
6023 while ( $record = get_record( $in ) )
6025 foreach $key ( @{ $options->{ "keys" } } ) {
6026 push @{ $median_hash{ $key } }, $record->{ $key } if defined $record->{ $key };
6029 put_record( $record, $out ) if not $options->{ "no_stream" };
6032 $fh = write_stream( $options->{ "data_out" } );
6034 foreach $key ( @{ $options->{ "keys" } } )
6036 if ( $median_hash{ $key } ) {
6037 $median = Maasha::Calc::median( $median_hash{ $key } );
6042 put_record( { $key . "_MEDIAN" => $median } , $fh );
6051 # Martin A. Hansen, February 2008.
6053 # Determine the maximum values of given keys.
6055 my ( $in, # handle to in stream
6056 $out, # handle to out stream
6057 $options, # options hash
6062 my ( $record, $key, $fh, %max_hash, $max_record );
6064 while ( $record = get_record( $in ) )
6066 foreach $key ( @{ $options->{ "keys" } } )
6068 if ( $record->{ $key } )
6070 $max_hash{ $key } = $record->{ $key } if $record->{ $key } > $max_hash{ $key };
6074 put_record( $record, $out ) if not $options->{ "no_stream" };
6077 $fh = write_stream( $options->{ "data_out" } );
6079 foreach $key ( @{ $options->{ "keys" } } )
6081 $max_record->{ $key . "_MAX" } = $max_hash{ $key };
6084 put_record( $max_record, $fh );
6092 # Martin A. Hansen, February 2008.
6094 # Determine the minimum values of given keys.
6096 my ( $in, # handle to in stream
6097 $out, # handle to out stream
6098 $options, # options hash
6103 my ( $record, $key, $fh, %min_hash, $min_record );
6105 while ( $record = get_record( $in ) )
6107 foreach $key ( @{ $options->{ "keys" } } )
6109 if ( defined $record->{ $key } )
6111 if ( exists $min_hash{ $key } ) {
6112 $min_hash{ $key } = $record->{ $key } if $record->{ $key } < $min_hash{ $key };
6114 $min_hash{ $key } = $record->{ $key };
6119 put_record( $record, $out ) if not $options->{ "no_stream" };
6122 $fh = write_stream( $options->{ "data_out" } );
6124 foreach $key ( @{ $options->{ "keys" } } )
6126 $min_record->{ $key . "_MIN" } = $min_hash{ $key };
6129 put_record( $min_record, $fh );
6135 sub script_upload_to_ucsc
6137 # Martin A. Hansen, August 2007.
6139 # Calculate the mean of values of given keys.
6141 # This routine has developed into the most ugly hack. Do something!
6143 my ( $in, # handle to in stream
6144 $out, # handle to out stream
6145 $options, # options hash
6150 my ( $record, $file, $wib_file, $wig_file, $wib_dir, $fh_out, $i, $first, $format, $type, $columns, $append, $entry );
6152 $options->{ "short_label" } ||= $options->{ 'table' };
6153 $options->{ "long_label" } ||= $options->{ 'table' };
6154 $options->{ "group" } ||= $ENV{ "LOGNAME" };
6155 $options->{ "priority" } ||= 1;
6156 $options->{ "visibility" } ||= "pack";
6157 $options->{ "color" } ||= join( ",", int( rand( 255 ) ), int( rand( 255 ) ), int( rand( 255 ) ) );
6158 $options->{ "chunk_size" } ||= 10_000_000_000; # Due to 32-bit UCSC compilation really large tables cannot be loaded in one go.
6160 $file = "$BP_TMP/ucsc_upload.tmp";
6165 $fh_out = Maasha::Common::write_open( $file );
6167 while ( $record = get_record( $in ) )
6169 put_record( $record, $out ) if not $options->{ "no_stream" };
6171 if ( $record->{ "REC_TYPE" } eq "fixed_step" )
6175 if ( $entry = Maasha::UCSC::Wiggle::biopiece2fixedstep( $record ) ) {
6176 Maasha::UCSC::Wiggle::fixedstep_entry_put( $entry, $fh_out );
6179 elsif ( $record->{ "REC_TYPE" } eq "PSL" )
6183 Maasha::UCSC::psl_put_header( $fh_out ) if $first;
6184 Maasha::UCSC::psl_put_entry( $record, $fh_out );
6188 elsif ( $record->{ "REC_TYPE" } eq "BED" and $record->{ "SEC_STRUCT" } )
6190 # chrom chromStart chromEnd name score strand size secStr conf
6194 print $fh_out join ( "\t",
6196 $record->{ "CHR_BEG" },
6197 $record->{ "CHR_END" } + 1,
6198 $record->{ "Q_ID" },
6199 $record->{ "SCORE" },
6200 $record->{ "STRAND" },
6201 $record->{ "SIZE" },
6202 $record->{ "SEC_STRUCT" },
6203 $record->{ "CONF" },
6206 elsif ( $record->{ "REC_TYPE" } eq "BED" )
6209 $columns = $record->{ "BED_COLS" };
6211 if ( $entry = Maasha::UCSC::BED::biopiece2bed( $record, $columns ) ) {
6212 Maasha::UCSC::BED::bed_entry_put( $entry, $fh_out, $columns, $options->{ 'check' } );
6215 elsif ( $record->{ "REC_TYPE" } eq "PATSCAN" and $record->{ "CHR" } )
6220 if ( $entry = Maasha::UCSC::BED::biopiece2bed( $record, $columns ) ) {
6221 Maasha::UCSC::BED::bed_entry_put( $entry, $fh_out, $columns, $options->{ 'check' } );
6224 elsif ( $record->{ "REC_TYPE" } eq "BLAST" and $record->{ "S_ID" } =~ /^chr/ )
6229 $record->{ "SCORE" } = $record->{ "BIT_SCORE" } * 1000;
6231 if ( $entry = Maasha::UCSC::BED::biopiece2bed( $record, $columns ) ) {
6232 Maasha::UCSC::BED::bed_entry_put( $entry, $fh_out, $columns, $options->{ 'check' } );
6235 elsif ( $record->{ "REC_TYPE" } eq "VMATCH" and $record->{ "S_ID" } =~ /^chr/i )
6240 if ( $entry = Maasha::UCSC::BED::biopiece2bed( $record, $columns ) ) {
6241 Maasha::UCSC::BED::bed_entry_put( $entry, $fh_out, $columns, $options->{ 'check' } );
6245 if ( $i == $options->{ "chunk_size" } )
6249 if ( $format eq "BED" ) {
6250 Maasha::UCSC::bed_upload_to_ucsc( $BP_TMP, $file, $options, $append );
6251 } elsif ( $format eq "PSL" ) {
6252 Maasha::UCSC::psl_upload_to_ucsc( $file, $options, $append );
6261 $fh_out = Maasha::Common::write_open( $file );
6269 if ( exists $options->{ "database" } and $options->{ "table" } )
6271 if ( $format eq "BED" )
6273 $type = "bed $columns";
6275 Maasha::UCSC::bed_upload_to_ucsc( $BP_TMP, $file, $options, $append );
6277 elsif ( $format eq "BED_SS" )
6279 $type = "type bed 6 +";
6281 Maasha::UCSC::bed_upload_to_ucsc( $BP_TMP, $file, $options, $append );
6283 elsif ( $format eq "PSL" )
6287 Maasha::UCSC::psl_upload_to_ucsc( $file, $options, $append );
6289 elsif ( $format eq "WIGGLE" )
6291 $options->{ "visibility" } = "full";
6293 $wig_file = "$options->{ 'table' }.wig";
6294 $wib_file = "$options->{ 'table' }.wib";
6296 $wib_dir = "$ENV{ 'HOME' }/ucsc/wib";
6298 Maasha::Common::dir_create_if_not_exists( $wib_dir );
6300 if ( $options->{ 'verbose' } ) {
6301 `cd $BP_TMP && wigEncode $file $wig_file $wib_file`;
6303 `cd $BP_TMP && wigEncode $file $wig_file $wib_file > /dev/null 2>&1`;
6306 Maasha::Common::run( "mv", "$BP_TMP/$wib_file $wib_dir" );
6314 Maasha::UCSC::wiggle_upload_to_ucsc( $BP_TMP, $wib_dir, $file, $options );
6319 Maasha::UCSC::ucsc_update_config( $options, $type );
6324 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<
6329 # Martin A. Hansen, November 2009.
6331 # Uses keys from a lookup hash to search records. Optionally, a list of
6332 # keys can be given so the lookup is limited to these, also, flags
6333 # can be given to limit lookup to keys or vals only. Returns 1 if lookup
6334 # succeeded, else 0.
6336 my ( $lookup_hash, # hashref with patterns
6338 $keys, # list of keys - OPTIONAL
6339 $vals_only, # only vals flag - OPTIONAL
6340 $keys_only, # only keys flag - OPTIONAL
6347 map { return 1 if exists $lookup_hash->{ $record->{ $_ } } } @{ $keys };
6351 if ( not $vals_only ) {
6352 map { return 1 if exists $lookup_hash->{ $_ } } keys %{ $record };
6355 if ( not $keys_only ) {
6356 map { return 1 if exists $lookup_hash->{ $record->{ $_ } } } keys %{ $record };
6366 # Martin A. Hansen, November 2009.
6368 # Uses patterns to match records containing the pattern as a substring.
6369 # Returns 1 if the record is matched, else 0.
6371 my ( $patterns, # list of patterns
6373 $keys, # list of keys - OPTIONAL
6374 $vals_only, # only vals flag - OPTIONAL
6375 $keys_only, # only keys flag - OPTIONAL
6382 foreach $pattern ( @{ $patterns } )
6386 map { return 1 if index( $record->{ $_ }, $pattern ) >= 0 } @{ $keys };
6390 if ( not $vals_only ) {
6391 map { return 1 if index( $_, $pattern ) >= 0 } keys %{ $record };
6394 if ( not $keys_only ) {
6395 map { return 1 if index( $record->{ $_ }, $pattern ) >= 0 } keys %{ $record };
6406 # Martin A. Hansen, November 2009.
6408 # Uses regex to match records.
6409 # Returns 1 if the record is matched, else 0.
6411 my ( $regex, # regex to match
6413 $keys, # list of keys - OPTIONAL
6414 $vals_only, # only vals flag - OPTIONAL
6415 $keys_only, # only keys flag - OPTIONAL
6422 map { return 1 if $record->{ $_ } =~ /$regex/ } @{ $keys };
6426 if ( not $vals_only ) {
6427 map { return 1 if $_ =~ /$regex/ } keys %{ $record };
6430 if ( not $keys_only ) {
6431 map { return 1 if $record->{ $_ } =~ /$regex/ } keys %{ $record };
6441 # Martin A. Hansen, November 2009.
6443 # Test if the value of a given record key evaluates according
6444 # to a given operator. Returns 1 if eval is OK, else 0.
6446 my ( $key, # record key
6454 if ( defined $record->{ $key } )
6456 return 1 if ( $op eq "<" and $record->{ $key } < $val );
6457 return 1 if ( $op eq ">" and $record->{ $key } > $val );
6458 return 1 if ( $op eq ">=" and $record->{ $key } >= $val );
6459 return 1 if ( $op eq "<=" and $record->{ $key } <= $val );
6460 return 1 if ( $op eq "=" and $record->{ $key } == $val );
6461 return 1 if ( $op eq "!=" and $record->{ $key } != $val );
6462 return 1 if ( $op eq "eq" and $record->{ $key } eq $val );
6463 return 1 if ( $op eq "ne" and $record->{ $key } ne $val );
6472 # Martin A. Hansen, July 2007.
6474 # Opens a stream to STDIN or a file,
6476 my ( $path, # path - OPTIONAL
6479 # Returns filehandle.
6483 if ( not -t STDIN ) {
6484 $fh = Maasha::Common::read_stdin();
6485 } elsif ( not $path ) {
6486 # Maasha::Common::error( qq(no data stream) );
6488 $fh = Maasha::Common::read_open( $path );
6491 # $fh->autoflush(1) if $fh; # Disable file buffer for debugging.
6499 # Martin A. Hansen, August 2007.
6501 # Opens a stream to STDOUT or a file.
6503 my ( $path, # path - OPTIONAL
6504 $gzip, # compress data - OPTIONAL
6507 # Returns filehandle.
6512 $fh = Maasha::Common::write_open( $path, $gzip );
6514 $fh = Maasha::Common::write_stdout();
6523 # Martin A. Hansen, July 2007.
6525 # Reads one record at a time and converts that record
6526 # to a Perl data structure (a hash) which is returned.
6528 my ( $fh, # handle to stream
6533 my ( $block, @lines, $line, $key, $value, %record );
6535 local $/ = "\n---\n";
6541 return if not defined $block;
6543 @lines = split "\n", $block;
6545 foreach $line ( @lines )
6547 ( $key, $value ) = split ": ", $line, 2;
6549 $record{ $key } = $value;
6552 return wantarray ? %record : \%record;
6558 # Martin A. Hansen, July 2007.
6560 # Given a Perl datastructure (a hash ref) emits this to STDOUT or a filehandle.
6562 my ( $data, # data structure
6563 $fh, # file handle - OPTIONAL
6568 if ( scalar keys %{ $data } )
6572 map { print $fh "$_: $data->{ $_ }\n" } keys %{ $data };
6577 map { print "$_: $data->{ $_ }\n" } keys %{ $data };
6588 # Martin A. Hansen, November 2007.
6590 # Extracts files from an explicit GetOpt::Long argument
6591 # allowing for the use of glob. E.g.
6592 # --data_in=test.fna
6593 # --data_in=test.fna,test2.fna
6595 # --data_in=test.fna,/dir/*.fna
6597 my ( $option, # option from GetOpt::Long
6602 my ( $elem, @files );
6604 foreach $elem ( split ",", $option )
6608 } elsif ( $elem =~ /\*/ ) {
6609 push @files, glob( $elem );
6613 return wantarray ? @files : \@files;
6619 # Martin A. Hansen, April 2008.
6621 # Removes temporary directory and exits gracefully.
6622 # This subroutine is meant to be run always as the last
6623 # thing even if a script is dies or is interrupted
6626 my ( $sig, # signal from the %SIG
6629 # print STDERR "signal->$sig<-\n";
6637 if ( $sig =~ /MAASHA_ERROR/ ) {
6638 print STDERR "\nProgram '$script' had an error" . " - Please wait for temporary data to be removed\n";
6639 } elsif ( $sig eq "INT" ) {
6640 print STDERR "\nProgram '$script' interrupted (ctrl-c was pressed)" . " - Please wait for temporary data to be removed\n";
6641 } elsif ( $sig eq "TERM" ) {
6642 print STDERR "\nProgram '$script' terminated (someone used kill?)" . " - Please wait for temporary data to be removed\n";
6644 print STDERR "\nProgram '$script' died->$sig" . " - Please wait for temporary data to be removed\n";
6656 # Martin A. Hansen, July 2008.
6658 # Cleans out any unused temporary files and directories in BP_TMP.
6662 my ( $tmpdir, @dirs, $curr_pid, $dir, $user, $sid, $pid );
6664 $tmpdir = $ENV{ 'BP_TMP' } || Maasha::Common::error( 'No BP_TMP variable in environment.' );
6666 $curr_pid = Maasha::Common::get_processid();
6668 @dirs = Maasha::Common::ls_dirs( $tmpdir );
6670 foreach $dir ( @dirs )
6672 if ( $dir =~ /^$tmpdir\/(.+)_(\d+)_(\d+)_bp_tmp$/ )
6678 if ( $user eq Maasha::Common::get_user() )
6680 if ( not Maasha::Common::process_running( $pid ) )
6682 # print STDERR "Removing stale dir: $dir\n";
6683 Maasha::Common::dir_remove( $dir );
6685 elsif ( $pid == $curr_pid )
6687 # print STDERR "Removing current dir: $dir\n";
6688 # Maasha::Common::dir_remove( $dir );
6702 # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<