X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=bp_bin%2Fget_genome_seq;h=e219c5188a993fd54e0af1b2c363abbb45ba9720;hb=2f0fd91b461033529a4a72e161bd133252a22eb6;hp=fdf5bd287f78613d2aea83bb9b15f855cad57e77;hpb=e8e32d43d674573ff4a66fe77780cc18cb02d430;p=biopieces.git diff --git a/bp_bin/get_genome_seq b/bp_bin/get_genome_seq index fdf5bd2..e219c51 100755 --- a/bp_bin/get_genome_seq +++ b/bp_bin/get_genome_seq @@ -1,6 +1,223 @@ #!/usr/bin/env perl +# Copyright (C) 2007-2009 Martin A. Hansen. + +# This program is free software; you can redistribute it and/or +# modify it under the terms of the GNU General Public License +# as published by the Free Software Foundation; either version 2 +# of the License, or (at your option) any later version. + +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. + +# You should have received a copy of the GNU General Public License +# along with this program; if not, write to the Free Software +# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. + +# http://www.gnu.org/copyleft/gpl.html + + +# >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> DESCRIPTION <<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< + +# Extract subsequences from a genome sequence. + +# >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< + + use warnings; use strict; +use Data::Dumper; +use Maasha::Biopieces; +use Maasha::Filesys; +use Maasha::Fasta; +use Maasha::Seq; + + +# >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< + + +my ( $options, $in, $out, $record, $genome_file, $index_file, $fh, $genome, + $beg, $end, $len, $index_beg, $index_len, @begs, @lens, $index, $seq, $i ); + +$options = Maasha::Biopieces::parse_options( + [ + { long => 'genome', short => 'g', type => 'genome', mandatory => 'yes', default => undef, allowed => undef, disallowed => undef }, + { long => 'chr', short => 'c', type => 'string', mandatory => 'no', default => undef, allowed => undef, disallowed => undef }, + { long => 'beg', short => 'b', type => 'uint', mandatory => 'no', default => undef, allowed => undef, disallowed => 0 }, + { long => 'end', short => 'e', type => 'uint', mandatory => 'no', default => undef, allowed => undef, disallowed => 0 }, + { long => 'len', short => 'l', type => 'uint', mandatory => 'no', default => undef, allowed => undef, disallowed => 0 }, + { long => 'flank', short => 'f', type => 'uint', mandatory => 'no', default => 0, allowed => undef, disallowed => undef }, + { long => 'mask', short => 'm', type => 'flag', mandatory => 'no', default => undef, allowed => undef, disallowed => undef }, + { long => 'splice', short => 's', type => 'flag', mandatory => 'no', default => undef, allowed => undef, disallowed => undef }, + ] +); + +$in = Maasha::Biopieces::read_stream( $options->{ "stream_in" } ); +$out = Maasha::Biopieces::write_stream( $options->{ "stream_out" } ); + +if ( $options->{ "genome" } ) +{ + $genome = $options->{ "genome" }; + + $genome_file = "$ENV{ 'BP_DATA' }/genomes/$genome/fasta/$genome.fna"; + $index_file = "$ENV{ 'BP_DATA' }/genomes/$genome/fasta/$genome.index"; + + $fh = Maasha::Filesys::file_read_open( $genome_file ); + $index = Maasha::Fasta::index_retrieve( $index_file ); + + if ( defined $options->{ "chr" } and exists $index->{ $options->{ "chr" } } and defined $options->{ "beg" } and ( defined $options->{ "end" } or defined $options->{ "len" } ) ) + { + ( $index_beg, $index_len ) = @{ $index->{ $options->{ "chr" } } }; + + $beg = $index_beg + $options->{ "beg" } - 1; + + if ( $options->{ "len" } ) { + $len = $options->{ "len" }; + } elsif ( $options->{ "end" } ) { + $len = ( $options->{ "end" } - $options->{ "beg" } + 1 ); + } + + $beg -= $options->{ "flank" }; + $len += 2 * $options->{ "flank" }; + + if ( $beg <= $index_beg ) + { + $len -= $index_beg - $beg; + $beg = $index_beg; + } + + if ( $beg + $len > $index_beg + $index_len ) { + $len = $index_beg + $index_len - $beg; + } + + next if $beg > $index_beg + $index_len; + + $record->{ "CHR" } = $options->{ "chr" }; + $record->{ "CHR_BEG" } = $beg - $index_beg; + $record->{ "CHR_END" } = $record->{ "CHR_BEG" } + $len - 1; + + $record->{ "SEQ" } = Maasha::Filesys::file_read( $fh, $beg, $len ); + $record->{ "SEQ_LEN" } = $len; + + Maasha::Biopieces::put_record( $record, $out ); + } +} + +while ( $record = Maasha::Biopieces::get_record( $in ) ) +{ + if ( $options->{ "genome" } and not $record->{ "SEQ" } ) + { + if ( $record->{ "REC_TYPE" } eq "BED" and exists $index->{ $record->{ "CHR" } } ) + { + ( $index_beg, $index_len ) = @{ $index->{ $record->{ "CHR" } } }; + + $beg = $record->{ "CHR_BEG" } + $index_beg; + $len = $record->{ "CHR_END" } - $record->{ "CHR_BEG" } + 1; + } + elsif ( $record->{ "REC_TYPE" } eq "PSL" and exists $index->{ $record->{ "S_ID" } } ) + { + ( $index_beg, $index_len ) = @{ $index->{ $record->{ "S_ID" } } }; + + $beg = $record->{ "S_BEG" } + $index_beg; + $len = $record->{ "S_END" } - $record->{ "S_BEG" } + 1; + } + elsif ( $record->{ "REC_TYPE" } eq "VMATCH" and exists $index->{ $record->{ "S_ID" } } ) + { + ( $index_beg, $index_len ) = @{ $index->{ $record->{ "S_ID" } } }; + + $beg = $record->{ "S_BEG" } + $index_beg; + $len = $record->{ "S_END" } - $record->{ "S_BEG" } + 1; + } + elsif ( $record->{ "REC_TYPE" } eq "BLAST" and exists $index->{ $record->{ "S_ID" } } ) + { + ( $index_beg, $index_len ) = @{ $index->{ $record->{ "S_ID" } } }; + + $beg = $record->{ "S_BEG" } + $index_beg; + $len = $record->{ "S_END" } - $record->{ "S_BEG" } + 1; + } + + $beg -= $options->{ "flank" }; + $len += 2 * $options->{ "flank" }; + + if ( $beg <= $index_beg ) + { + $len -= $index_beg - $beg; + $beg = $index_beg; + } + + $len = $index_beg + $index_len - $beg if $beg + $len > $index_beg + $index_len; + + next if $beg > $index_beg + $index_len; + + $record->{ "CHR_BEG" } = $beg - $index_beg; + $record->{ "CHR_END" } = $record->{ "CHR_BEG" } + $len - 1; + + $record->{ "SEQ" } = Maasha::Filesys::file_read( $fh, $beg, $len ); + + if ( $record->{ "STRAND" } and $record->{ "STRAND" } eq "-" ) + { + Maasha::Seq::dna_comp( \$record->{ "SEQ" } ); + $record->{ "SEQ" } = reverse $record->{ "SEQ" }; + } + + if ( $options->{ "mask" } ) + { + if ( $record->{ "BLOCK_COUNT" } > 1 ) # uppercase hit block segments and lowercase the rest. + { + $record->{ "SEQ" } = lc $record->{ "SEQ" }; + + @begs = split ",", $record->{ "Q_BEGS" }; + @lens = split ",", $record->{ "BLOCK_LENS" }; + + for ( $i = 0; $i < @begs; $i++ ) { + substr $record->{ "SEQ" }, $begs[ $i ], $lens[ $i ], uc substr $record->{ "SEQ" }, $begs[ $i ], $lens[ $i ]; + } + } + } + elsif ( $options->{ "splice" } ) + { + if ( $record->{ "BLOCK_COUNT" } > 1 ) # splice block sequences + { + $seq = ""; + @begs = split ",", $record->{ "Q_BEGS" }; + @lens = split ",", $record->{ "BLOCK_LENS" }; + + for ( $i = 0; $i < @begs; $i++ ) { + $seq .= substr $record->{ "SEQ" }, $begs[ $i ], $lens[ $i ]; + } + + $record->{ "SEQ" } = $seq; + } + } + + $record->{ "SEQ_LEN" } = length $record->{ "SEQ" }; + } + + Maasha::Biopieces::put_record( $record, $out ); +} + +Maasha::Biopieces::close_stream( $in ); +Maasha::Biopieces::close_stream( $out ); + + +# >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< + + +BEGIN +{ + Maasha::Biopieces::status_set(); +} + + +END +{ + Maasha::Biopieces::status_log(); +} + + +# >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< + -use Maasha::BioRun; +__END__