.\" Automatically generated by Pod::Man 4.11 (Pod::Simple 3.35)
.\"
.\" Standard preamble:
.\" ========================================================================
.de Sp \" Vertical space (when we can't use .PP)
.if t .sp .5v
.if n .sp
..
.de Vb \" Begin verbatim text
.ft CW
.nf
.ne \\$1
..
.de Ve \" End verbatim text
.ft R
.fi
..
.\" Set up some character translations and predefined strings.  \*(-- will
.\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left
.\" double quote, and \*(R" will give a right double quote.  \*(C+ will
.\" give a nicer C++.  Capital omega is used to do unbreakable dashes and
.\" therefore won't be available.  \*(C` and \*(C' expand to `' in nroff,
.\" nothing in troff, for use with C<>.
.tr \(*W-
.ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p'
.ie n \{\
.    ds -- \(*W-
.    ds PI pi
.    if (\n(.H=4u)&(1m=24u) .ds -- \(*W\h'-12u'\(*W\h'-12u'-\" diablo 10 pitch
.    if (\n(.H=4u)&(1m=20u) .ds -- \(*W\h'-12u'\(*W\h'-8u'-\"  diablo 12 pitch
.    ds L" ""
.    ds R" ""
.    ds C` ""
.    ds C' ""
'br\}
.el\{\
.    ds -- \|\(em\|
.    ds PI \(*p
.    ds L" ``
.    ds R" ''
.    ds C`
.    ds C'
'br\}
.\"
.\" Escape single quotes in literal strings from groff's Unicode transform.
.ie \n(.g .ds Aq \(aq
.el       .ds Aq '
.\"
.\" If the F register is >0, we'll generate index entries on stderr for
.\" titles (.TH), headers (.SH), subsections (.SS), items (.Ip), and index
.\" entries marked with X<> in POD.  Of course, you'll have to process the
.\" output yourself in some meaningful fashion.
.\"
.\" Avoid warning from groff about undefined register 'F'.
.de IX
..
.nr rF 0
.if \n(.g .if rF .nr rF 1
.if (\n(rF:(\n(.g==0)) \{\
.    if \nF \{\
.        de IX
.        tm Index:\\$1\t\\n%\t"\\$2"
..
.        if !\nF==2 \{\
.            nr % 0
.            nr F 2
.        \}
.    \}
.\}
.rr rF
.\"
.\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2).
.\" Fear.  Run.  Save yourself.  No user-serviceable parts.
.    \" fudge factors for nroff and troff
.if n \{\
.    ds #H 0
.    ds #V .8m
.    ds #F .3m
.    ds #[ \f1
.    ds #] \fP
.\}
.if t \{\
.    ds #H ((1u-(\\\\n(.fu%2u))*.13m)
.    ds #V .6m
.    ds #F 0
.    ds #[ \&
.    ds #] \&
.\}
.    \" simple accents for nroff and troff
.if n \{\
.    ds ' \&
.    ds ` \&
.    ds ^ \&
.    ds , \&
.    ds ~ ~
.    ds /
.\}
.if t \{\
.    ds ' \\k:\h'-(\\n(.wu*8/10-\*(#H)'\'\h"|\\n:u"
.    ds ` \\k:\h'-(\\n(.wu*8/10-\*(#H)'\`\h'|\\n:u'
.    ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'^\h'|\\n:u'
.    ds , \\k:\h'-(\\n(.wu*8/10)',\h'|\\n:u'
.    ds ~ \\k:\h'-(\\n(.wu-\*(#H-.1m)'~\h'|\\n:u'
.    ds / \\k:\h'-(\\n(.wu*8/10-\*(#H)'\z\(sl\h'|\\n:u'
.\}
.    \" troff and (daisy-wheel) nroff accents
.ds : \\k:\h'-(\\n(.wu*8/10-\*(#H+.1m+\*(#F)'\v'-\*(#V'\z.\h'.2m+\*(#F'.\h'|\\n:u'\v'\*(#V'
.ds 8 \h'\*(#H'\(*b\h'-\*(#H'
.ds o \\k:\h'-(\\n(.wu+\w'\(de'u-\*(#H)/2u'\v'-.3n'\*(#[\z\(de\v'.3n'\h'|\\n:u'\*(#]
.ds d- \h'\*(#H'\(pd\h'-\w'~'u'\v'-.25m'\f2\(hy\fP\v'.25m'\h'-\*(#H'
.ds D- D\\k:\h'-\w'D'u'\v'-.11m'\z\(hy\v'.11m'\h'|\\n:u'
.ds th \*(#[\v'.3m'\s+1I\s-1\v'-.3m'\h'-(\w'I'u*2/3)'\s-1o\s+1\*(#]
.ds Th \*(#[\s+2I\s-2\h'-\w'I'u*3/5'\v'-.3m'o\v'.3m'\*(#]
.ds ae a\h'-(\w'a'u*4/10)'e
.ds Ae A\h'-(\w'A'u*4/10)'E
.    \" corrections for vroff
.if v .ds ~ \\k:\h'-(\\n(.wu*9/10-\*(#H)'\s-2\u~\d\s+2\h'|\\n:u'
.if v .ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'\v'-.4m'^\v'.4m'\h'|\\n:u'
.    \" for low resolution devices (crt and lpr)
.if \n(.H>23 .if \n(.V>19 \
\{\
.    ds : e
.    ds 8 ss
.    ds o a
.    ds d- d\h'-1'\(ga
.    ds D- D\h'-1'\(hy
.    ds th \o'bp'
.    ds Th \o'LP'
.    ds ae ae
.    ds Ae AE
.\}
.rm #[ #] #H #V #F C
.\" ========================================================================
.\"
.IX Title "Genome::Model::Tools::Music::Bmr::CalcCovgHelper 3pm"
.TH Genome::Model::Tools::Music::Bmr::CalcCovgHelper 3pm "2020-11-06" "perl v5.30.3" "User Contributed Perl Documentation"
.\" For nroff, turn off justification.  Always turn off hyphenation; it makes
.\" way too many mistakes in technical documents.
.if n .ad l
.nh
.IP "\-\-roi\-file" 4
.IX Item "--roi-file"
.RS 4
.PD 0
.IP "The regions of interest (ROIs) of each gene are typically regions targeted for sequencing or are merged exon loci (from multiple transcripts) of genes with 2\-bp flanks (splice junctions). ROIs from the same chromosome must be listed adjacent to each other in this file. This allows the underlying C\-based code to run much more efficiently and avoid re-counting bases seen in overlapping ROIs (for overall covered base counts). For per-gene base counts, an overlapping base will be counted each time it appears in an \s-1ROI\s0 of the same gene. To avoid this, be sure to merge together overlapping ROIs of the same gene. BEDtools' mergeBed can help if used per gene." 8
.IX Item "The regions of interest (ROIs) of each gene are typically regions targeted for sequencing or are merged exon loci (from multiple transcripts) of genes with 2-bp flanks (splice junctions). ROIs from the same chromosome must be listed adjacent to each other in this file. This allows the underlying C-based code to run much more efficiently and avoid re-counting bases seen in overlapping ROIs (for overall covered base counts). For per-gene base counts, an overlapping base will be counted each time it appears in an ROI of the same gene. To avoid this, be sure to merge together overlapping ROIs of the same gene. BEDtools' mergeBed can help if used per gene."
.RE
.RS 4
.RE
.IP "\-\-reference\-sequence" 4
.IX Item "--reference-sequence"
.RS 4
.IP "The reference sequence in \s-1FASTA\s0 format. If a reference sequence index is not found next to this file (a .fai file), it will be created." 8
.IX Item "The reference sequence in FASTA format. If a reference sequence index is not found next to this file (a .fai file), it will be created."
.RE
.RS 4
.RE
.IP "\-\-normal\-tumor\-bam\-pair" 4
.IX Item "--normal-tumor-bam-pair"
.RS 4
.ie n .IP """sample-name path/to/normal_bam path/to/tumor_bam""" 8
.el .IP "``sample-name path/to/normal_bam path/to/tumor_bam''" 8
.IX Item "sample-name path/to/normal_bam path/to/tumor_bam"
.RE
.RS 4
.RE
.IP "\-\-output\-file" 4
.IX Item "--output-file"
.RS 4
.IP "Specify an output file where the per-ROI covered base counts will be written" 8
.IX Item "Specify an output file where the per-ROI covered base counts will be written"
.RE
.RS 4
.RE
.PD
.PP
\&\s-1EOS\s0
  );
}
.PP
sub _doc_authors {
  return \*(L" Cyriac Kandoth, Ph.D.\*(R";
}
.PP
sub _doc_see_also {
  return <<\s-1EOS\s0
\&\fBgenome-music-bmr\fR(1),
\&\fBgenome-music\fR(1),
\&\fBgenome\fR(1)
\&\s-1EOS\s0
}
.PP
sub execute {
  my \f(CW$self\fR = shift;
  my \f(CW$roi_file\fR = \f(CW$self\fR\->roi_file;
  my \f(CW$ref_seq\fR = \f(CW$self\fR\->reference_sequence;
  my \f(CW$tumor_bam\fR = \f(CW$self\fR\->tumor_bam;
  my \f(CW$normal_bam\fR = \f(CW$self\fR\->normal_bam;
  my \f(CW$output_file\fR = \f(CW$self\fR\->final_output_file;
  my \f(CW$normal_min_depth\fR = \f(CW$self\fR\->normal_min_depth;
  my \f(CW$tumor_min_depth\fR = \f(CW$self\fR\->tumor_min_depth;
  my \f(CW$min_mapq\fR = \f(CW$self\fR\->min_mapq;
.PP
.Vb 6
\&  # Check on all the input data before starting work
\&  print STDERR "ROI file not found or is empty: $roi_file\en" unless( \-s $roi_file );
\&  print STDERR "Reference sequence file not found: $ref_seq\en" unless( \-e $ref_seq );
\&  print STDERR "Normal BAM file not found or is empty: $normal_bam\en" unless( \-s $normal_bam );
\&  print STDERR "Tumor BAM file not found or is empty: $tumor_bam\en" unless( \-s $tumor_bam );
\&  return undef unless( \-s $roi_file && \-e $ref_seq && \-s $normal_bam && \-s $tumor_bam );
\&
\&  # Check whether the annotated regions of interest are clumped together by chromosome
\&  my $roiFh = IO::File\->new( $roi_file ) or die "ROI file could not be opened. $!\en";
\&  my @chroms = ( "" );
\&  while( my $line = $roiFh\->getline ) # Emulate Unix\*(Aqs uniq command on the chromosome column
\&  {
\&    my ( $chrom ) = ( $line =~ m/^(\eS+)/ );
\&    push( @chroms, $chrom ) if( $chrom ne $chroms[\-1] );
\&  }
\&  $roiFh\->close;
\&  my %chroms = map { $_ => 1 } @chroms; # Get the actual number of unique chromosomes
\&  if( scalar( @chroms ) != scalar( keys %chroms ))
\&  {
\&    print STDERR "ROIs from the same chromosome must be listed adjacent to each other in file. ";
\&    print STDERR "If in UNIX, try:\ensort \-k 1,1 $roi_file\en";
\&    return undef;
\&  }
\&
\&  # If the reference sequence FASTA file hasn\*(Aqt been indexed, do it
\&  my $ref_seq_idx = "$ref_seq.fai";
\&  system( "samtools faidx $ref_seq" ) unless( \-e $ref_seq_idx );
\&
\&  $normal_bam = \*(Aq\*(Aq unless( defined $normal_bam );
\&  $tumor_bam = \*(Aq\*(Aq unless( defined $tumor_bam );
\&  print STDERR "Normal BAM not found: \e"$normal_bam\e"\en" unless( \-e $normal_bam );
\&  print STDERR "Tumor BAM not found: \e"$tumor_bam\e"\en" unless( \-e $tumor_bam );
\&  next unless( \-e $normal_bam && \-e $tumor_bam );
\&
\&  # Construct the command that calculates coverage per ROI
\&  my $calcRoiCovg_cmd = "calcRoiCovg $normal_bam $tumor_bam $roi_file $ref_seq $output_file $normal_min_depth $tumor_min_depth $min_mapq";
\&
\&  # If the calcRoiCovg output was already generated, then don\*(Aqt rerun it
\&  if( \-s $output_file )
\&  {
\&    print "Output file $output_file found. Skipping re\-calculation.\en";
\&  }
\&  # Run the calcRoiCovg command on this tumor\-normal pair. This could take a while
\&  elsif( system( "$calcRoiCovg_cmd" ) != 0 )
\&  {
\&    print STDERR "Failed to execute: $calcRoiCovg_cmd\en";
\&    return;
\&  }
\&  else
\&  {
\&    print "$output_file generated and stored.\en";
\&    return 1;
\&  }
.Ve
.PP
}
.PP
1;