Bio-ViennaNGS
view release on metacpan or search on metacpan
INHERIT_DOCS = YES
# If the SEPARATE_MEMBER_PAGES tag is set to YES, then doxygen will produce a
# new page for each member. If set to NO, the documentation of a member will be
# part of the file/class/namespace that contains it.
# The default value is: NO.
SEPARATE_MEMBER_PAGES = NO
# The TAB_SIZE tag can be used to set the number of spaces in a tab. Doxygen
# uses this value to replace tabs by spaces in code fragments.
# Minimum value: 1, maximum value: 16, default value: 4.
TAB_SIZE = 4
# This tag can be used to specify a number of aliases that act as commands in
# the documentation. An alias has the form:
# name=value
# For example adding
# "sideeffect=@par Side Effects:\n"
# will allow you to put the command \sideeffect (or @sideeffect) in the
# output. The symbol name can be a fully qualified name, a word, or if the
# wildcard * is used, a substring. Examples: ANamespace, AClass,
# AClass::ANamespace, ANamespace::*Test
#
# Note that the wildcards are matched against the file with absolute path, so to
# exclude all test directories use the pattern */test/*
EXCLUDE_SYMBOLS =
# The EXAMPLE_PATH tag can be used to specify one or more files or directories
# that contain example code fragments that are included (see the \include
# command).
EXAMPLE_PATH =
# If the value of the EXAMPLE_PATH tag contains directories, you can use the
# EXAMPLE_PATTERNS tag to specify one or more wildcard pattern (like *.cpp and
# *.h) to filter out the source-files in the directories. If left blank all
# files are included.
EXAMPLE_PATTERNS =
SOURCE_BROWSER = NO
# Setting the INLINE_SOURCES tag to YES will include the body of functions,
# classes and enums directly into the documentation.
# The default value is: NO.
INLINE_SOURCES = NO
# Setting the STRIP_CODE_COMMENTS tag to YES will instruct doxygen to hide any
# special comment blocks from generated source code fragments. Normal C, C++ and
# Fortran comments will always remain visible.
# The default value is: YES.
STRIP_CODE_COMMENTS = YES
# If the REFERENCED_BY_RELATION tag is set to YES then for each documented
# function all documented functions referencing it will be listed.
# The default value is: NO.
REFERENCED_BY_RELATION = NO
lib/Bio/ViennaNGS/Bam.pm view on Meta::CPAN
$data{count}{neg}++; $eff_strand=$strand;
if ($want_bed){printf $bed_neg "%s\n", "-";}
}
else {
$data{count}{pos}++;$eff_strand=-1*$strand;
if ($want_bed){printf $bed_neg "%s\n", "+";}
}
}
else {croak "Strand neither + nor - ...exiting!\n";}
}
else{ # 2nd mate; reverse strand since the fragment it belongs to is ALWAYS located
# on the other strand
if($verbose == 1) {print STDERR "SECOND_MATE\t".$strand." ";}
if ( $strand eq "1" ) {
$bam_neg->write1($read);
if ($want_bed){printf $bed_neg "%s\t%d\t%d\t%s\t%d\t",$seq_id,eval($start-1),$stop,$id,$score;}
if ($reverse == 0){
$data{count}{neg}++;$eff_strand=$strand;
if ($want_bed){printf $bed_neg "%s\n", "-";}
}
else {
lib/Bio/ViennaNGS/Bam.pm view on Meta::CPAN
push (@processed_files, ($bedname_pos,$bedname_neg))
}
# error checks
unless ($data{count}{pe_alis} + $data{count}{se_alis} == $data{count}{cur}) {
printf "ERROR: paired-end + single-end != total alignments\n";
print Dumper(\%data);
croak $!;
}
unless ($data{count}{pos} + $data{count}{neg} == $data{count}{cur}) {
printf STDERR "%20d fragments on [+] strand\n",$data{count}{pos};
printf STDERR "%20d fragments on [-] strand\n",$data{count}{neg};
printf STDERR "%20d sum\n",eval($data{count}{pos}+$data{count}{neg});
printf STDERR "%20d unmapped reads\n",$data{count}{unmapped};
printf STDERR "%20d total alignment/read count\n",$data{count}{cur};
printf STDERR "ERROR: pos alignments + neg alignments != total alignments\n";
print Dumper(\%data);
croak $!;
}
foreach (keys %{$data{flag}}){
$data{count}{flag} += $data{flag}{$_};
}
lib/Bio/ViennaNGS/Bam.pm view on Meta::CPAN
printf LOG "\n";
printf LOG "%20d multi-mappers (%7.2f%% of total) ",
$data{count}{mult},eval(100*$data{count}{mult}/$data{count}{total});
if ($data{nh_issues}){printf LOG " *** NH attribute issues ***";}
printf LOG "\n";
printf LOG "%20d skipped\n", $data{count}{skip};
printf LOG "%20d alignments considered\n", $data{count}{cur};
printf LOG "%20d paired-end\n", $data{count}{pe_alis};
printf LOG "%20s single-end\n", $data{count}{se_alis};
if($data{count}{cur}>0){
printf LOG "%20d fragments on [+] strand (%7.2f%% of considered)\n",
$data{count}{pos},eval(100*$data{count}{pos}/$data{count}{cur});
printf LOG "%20d fragments on [-] strand (%7.2f%% of considered)\n",
$data{count}{neg},eval(100*$data{count}{neg}/$data{count}{cur});
}
else{
printf LOG "%20d fragments on [+] strand\n",$data{count}{pos};
printf LOG "%20d fragments on [-] strand\n",$data{count}{neg};
}
printf LOG "%20d unmapped\n", $data{count}{unmapped};
printf LOG "#-----------------------------------------------------------------\n";
printf LOG "Dumper output:\n". Dumper(\%data);
close(LOG);
return @processed_files;
}
sub uniquify_bam {
my %data = ();
lib/Bio/ViennaNGS/Bam.pm view on Meta::CPAN
Splits BAM file $bam according to [+] and [-] strand. C<$reverse>,
C<$want_uniq> and C<$want_bed> are switches with values of 0 or 1,
triggering forced reversion of strand mapping (due to RNA-seq protocol
constraints), filtering of unique mappers (identified via NH:i:1 SAM
argument), and forced output of a BED file corresponding to
strand-specific mapping, respectively. C<$log> holds name and path of
the log file.
Strand-splitting is done in a way that in paired-end alignments, FIRST
and SECOND mates (reads) are treated as _one_ fragment, ie FIRST_MATE
reads determine the strand, while SECOND_MATE reads are assigned the
opposite strand I<per definitionem>. This also holds if the reads are
not mapped in proper pairs and even if there is no mapping partner at
all.
Sometimes the library preparation protocol causes inversion of the
read assignment (with respect to the underlying annotation). In those
cases, the natural mapping of the reads can be obtained by the
C<$reverse> flag.
This routine returns an array whose fist two elements are the file
names of the newly generate BAM files with reads mapped to the
positive, and negative strand, respectively. Elements three and four
are the number of fragments mapped to the positive and negative
strand. If the C<$want_bed> option was given elements five and six are
the file names of the output BED files for positive and negative
strand, respectively.
NOTE: Filtering of unique mappers is only safe for single-end
experiments; In paired-end experiments, read and mate are treated
separately, thus allowing for scenarios where eg. one read is a
multi-mapper, whereas its associate mate is a unique mapper, resulting
in an ambiguous alignment of the entire fragment.
As mentioned above, the NH:i: SAM attribute is used for discriminating
unique and multi mappers, thus requiring this attribute to be present
in every SAM record. If this attribute is not found in I<all> SAM
entries, a warning will be issued and the log file will contain a note
indicating that there were issues with the NH attribute.
=item uniquify_bam($bam,$dest,$log)
Extract I<uniquely> and I<multiply> aligned reads from BAM file
lib/Bio/ViennaNGS/Util.pm view on Meta::CPAN
=item bed_or_bam2bw($type,$infile,$chromsizes,$strand,$dest,$want_norm,$size,$scale,$log)
Creates stranded, normalized BigWig coverage profiles from
strand-specific BAM or BED files (provided via C<$infile>). The
routine expects a file type 'bam' or 'bed' via the C<$type>
argument. C<$chromsizes> is the chromosome.sizes files, C<$strand> is
either "+" or "-" and C<$dest> contains the output path for
results. For normlization of bigWig profiles, additional attributes
are required: C<$want_norm> triggers normalization with values 0 or
1. C<$size> is the number of fragments/elements in the BAM or BED file
and C<$scale> gives the number to which data is normalized (ie. every
bedGraph entry is multiplied by a factor (C<$scale>/C<$size>). C<$log>
is expected to contain either the full path and file name of log file
or 'undef'. The routine returns the full file name of the newly
generated bigWig file.
While this routine can handle non-straned BAM/BED files (in which case
C<$strand> should be set to "+" and hence all coverage profiles will
be created with a positive sign, even if they map to the negative
strand), usage of strand-specific data is highly recommended. For BAM
scripts/bam_split.pl view on Meta::CPAN
}
#TODO check if we are allowed to write to $outdir
unless (-d $outdir){mkdircheck($outdir)}
($basename,$bamdir,$bamext) = fileparse($bam_in,qr/\..*/);
$lf = file($outdir,$basename.$logext);
@result = split_bam($bam_in,$rev,$wantuniq,$wantbed,$outdir,$lf);
$bam_p = $result[0]; # BAM file containing fragments of [+] strand
$bam_n = $result[1]; # BAM file containing fragments of [-] strand
$size_p = $result[2]; # of alignments on [+] strand
$size_n = $result[3]; # of alignments on [-] srand
$bed_p = $result[4]; # BED file containing fragments of [+] strand
$bed_n = $result[5]; # BED file containing fragments of [-] strand
if ($bw == 1) {
my $od = dir($outdir,$visdir);
mkdircheck($od->stringify());
bed_or_bam2bw("bed",$bed_p,$cs_in,"+",$od,$wantnorm,$size_p,$scale,$lf);
bed_or_bam2bw("bed",$bed_n,$cs_in,"-",$od,$wantnorm,$size_n,$scale,$lf);
}
__END__
scripts/gff2bed.pl view on Meta::CPAN
=head1 SYNOPSIS
gff2bed.pl [--gff I<FILE>] [options]
=head1 DESCRIPTION
Convert feature annotation of non-spliced organisms in GFF3 format to
BED12. A separate BED12 file will be created for each genomic feature
type (eg CDS, tRNA, rRNA, ncRNA, etc.).
This script serves as a reference implementation of code fragments
from bio::ViennaNGS::AnnoC and has been successfully tested with
NCBI's bacterial annotation in GFF3 format.
Please note that this script is NOT meant to be run on GFF genome
annotation other than bacteria since it DOES NOT consider splice
events present in most higher organisms.
=head1 OPTIONS
=over
( run in 1.612 second using v1.01-cache-2.11-cpan-364913b4093 )