X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=bp_bin%2Fsplit_seq;h=790aa7cc3c7e32fb1fa86f2339bc534b8c062f2a;hb=5de6112b70b59420b245ce636a8b2e3c90acbe00;hp=274e13306376b98be145540dc9b582519d66e746;hpb=97e32a3f0e6671dad1bf98cabcebc59ea9914000;p=biopieces.git diff --git a/bp_bin/split_seq b/bp_bin/split_seq index 274e133..790aa7c 100755 --- a/bp_bin/split_seq +++ b/bp_bin/split_seq @@ -1,4 +1,4 @@ -#!/usr/bin/env perl -w +#!/usr/bin/env perl # Copyright (C) 2007-2009 Martin A. Hansen. @@ -21,11 +21,12 @@ # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>> DESCRIPTION <<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< -# Split sequences in the stream into overlapping subsequences. +# Split sequences in the stream into subsequences. # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< +use warnings; use strict; use Maasha::Biopieces; @@ -33,48 +34,39 @@ use Maasha::Biopieces; # >>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>><<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<<< -my ( $options, $in, $out, $record, $new_record, $i, $inc, $subseq, %lookup ); +my ( $options, $in, $out, $record, $new_record, $i, $step, $subseq, $subqual ); $options = Maasha::Biopieces::parse_options( [ - { long => 'word_size', short => 'w', type => 'uint', mandatory => 'no', default => 7, allowed => undef, disallowed => 0 }, - { long => 'non_overlapping', short => 'n', type => 'flag', mandatory => 'no', default => undef, allowed => undef, disallowed => undef }, - { long => 'uniq', short => 'u', type => 'flag', mandatory => 'no', default => undef, allowed => undef, disallowed => undef }, + { long => 'word_size', short => 'w', type => 'uint', mandatory => 'no', default => 7, allowed => undef, disallowed => 0 }, + { long => 'step_size', short => 's', type => 'uint', mandatory => 'no', default => 1, allowed => undef, disallowed => 0 }, ] ); +if ( $options->{ "step_size" } > $options->{ "word_size" } ) { + Maasha::Common::error( qq(step_size > word_size: $options->{ "step_size" } > $options->{ "word_size" } ) ); +} + $in = Maasha::Biopieces::read_stream( $options->{ "stream_in" } ); $out = Maasha::Biopieces::write_stream( $options->{ "stream_out" } ); -$inc = 1; -$inc = $options->{ "word_size" } if $options->{ "non_overlapping" }; +$step = $options->{ "step_size" }; while ( $record = Maasha::Biopieces::get_record( $in ) ) { if ( $record->{ "SEQ_NAME" } and $record->{ "SEQ" } ) { - for ( $i = 0; $i < length( $record->{ "SEQ" } ) - $options->{ "word_size" } + 1; $i += $inc ) + for ( $i = 0; $i < length( $record->{ "SEQ" } ) - $options->{ "word_size" } + 1; $i += $step ) { - $subseq = substr $record->{ "SEQ" }, $i, $options->{ "word_size" }; - - if ( $options->{ "uniq" } and not $lookup{ $subseq } ) - { - $new_record->{ "SEQ_NAME" } = $record->{ "SEQ_NAME" } . "[" . ( $i + 1 ) . "-" . ( $i + $options->{ "word_size" } ) . "]"; - $new_record->{ "SEQ" } = $subseq; - $new_record->{ "SEQ_LEN" } = $options->{ "word_size" }; - - Maasha::Biopieces::put_record( $new_record, $out ); - - $lookup{ $subseq } = 1; - } - else - { - $new_record->{ "SEQ_NAME" } = $record->{ "SEQ_NAME" } . "[" . ( $i + 1 ) . "-" . ( $i + $options->{ "word_size" } ) . "]"; - $new_record->{ "SEQ" } = $subseq; - $new_record->{ "SEQ_LEN" } = $options->{ "word_size" }; - - Maasha::Biopieces::put_record( $new_record, $out ); - } + $subseq = substr $record->{ "SEQ" }, $i, $options->{ "word_size" }; + $subqual = substr $record->{ "SCORES" }, $i, $options->{ "word_size" } if $record->{ "SCORES" }; + + $new_record->{ "SEQ_NAME" } = $record->{ "SEQ_NAME" } . "[" . ( $i + 1 ) . "-" . ( $i + $options->{ "word_size" } ) . "]"; + $new_record->{ "SEQ" } = $subseq; + $new_record->{ "SCORES" } = $subqual if $record->{ "SCORES" }; + $new_record->{ "SEQ_LEN" } = $options->{ "word_size" }; + + Maasha::Biopieces::put_record( $new_record, $out ); } } else