.\" 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::CalcCovg 3pm"
.TH Genome::Model::Tools::Music::Bmr::CalcCovg 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 "\(bu" 4
Define cmd-list-file and cmd-prefix to generate a file with commands that can be submitted to a
cluster or run manually. These jobs will write per-ROI base counts in a subdirectory roi_covgs.
.IP "\(bu" 4
After all the parallelized calcRoiCovg jobs are completed, run this script again to add them up
and generate the final per-gene base counts in a subdirectory gene_covgs. Remember to remove the
cmd-list-file and cmd-prefix arguments or you will just be re-creating a list of commands.
.PP
\&\s-1HELP\s0
}
.PP
sub _additional_help_sections {
  return (
    \*(L"\s-1ARGUMENTS\*(R",\s0
<<\s-1EOS\s0
.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 "\-\-bam\-list" 4
.IX Item "--bam-list"
.RS 4
.IP "Provide a file containing sample names and normal/tumor \s-1BAM\s0 locations for each. Use the tab\- delimited format [sample_name normal_bam tumor_bam] per line. Additional columns like clinical data are allowed, but ignored. The sample_name must be the same as the tumor sample names used in the \s-1MAF\s0 file (16th column, with the header Tumor_Sample_Barcode)." 8
.IX Item "Provide a file containing sample names and normal/tumor BAM locations for each. Use the tab- delimited format [sample_name normal_bam tumor_bam] per line. Additional columns like clinical data are allowed, but ignored. The sample_name must be the same as the tumor sample names used in the MAF file (16th column, with the header Tumor_Sample_Barcode)."
.RE
.RS 4
.RE
.IP "\-\-output\-dir" 4
.IX Item "--output-dir"
.RS 4
.IP "Specify an output directory where the following will be created/written: roi_covgs: Subdirectory containing per-ROI covered base counts for each sample. gene_covgs: Subdirectory containing per-gene covered base counts for each sample. total_covgs: File containing the overall non-overlapping coverages per sample." 8
.IX Item "Specify an output directory where the following will be created/written: roi_covgs: Subdirectory containing per-ROI covered base counts for each sample. gene_covgs: Subdirectory containing per-gene covered base counts for each sample. total_covgs: File containing the overall non-overlapping coverages per sample."
.RE
.RS 4
.RE
.IP "\-\-cmd\-list\-file" 4
.IX Item "--cmd-list-file"
.RS 4
.IP "Specify a file into which a list of calcRoiCovg jobs will be written to. These can be scheduled in parallel, and will write per-ROI covered base-counts into the output subdirectory roi_covgs. If cmd-list-file is left unspecified, this script runs calcRoiCovg per sample one after another, taking ~30 mins per sample, but it skips samples whose output is already in roi_covgs." 8
.IX Item "Specify a file into which a list of calcRoiCovg jobs will be written to. These can be scheduled in parallel, and will write per-ROI covered base-counts into the output subdirectory roi_covgs. If cmd-list-file is left unspecified, this script runs calcRoiCovg per sample one after another, taking ~30 mins per sample, but it skips samples whose output is already in roi_covgs."
.RE
.RS 4
.RE
.IP "\-\-cmd\-prefix" 4
.IX Item "--cmd-prefix"
.RS 4
.ie n .IP "Specify a job submission command that will be prefixed to each command in cmd-list-file. This makes batch submission easier. Just run the cmd-list-file file as a shell script to submit jobs. cmd-prefix is ""bsub"" if your cluster uses the \s-1LSF\s0 job scheduler, or ""qsub"" in Torque. Add arguments as necessary. For example, ""bsub \-M 4GB"" sets a soft memory limit of 4GB." 8
.el .IP "Specify a job submission command that will be prefixed to each command in cmd-list-file. This makes batch submission easier. Just run the cmd-list-file file as a shell script to submit jobs. cmd-prefix is ``bsub'' if your cluster uses the \s-1LSF\s0 job scheduler, or ``qsub'' in Torque. Add arguments as necessary. For example, ``bsub \-M 4GB'' sets a soft memory limit of 4GB." 8
.IX Item "Specify a job submission command that will be prefixed to each command in cmd-list-file. This makes batch submission easier. Just run the cmd-list-file file as a shell script to submit jobs. cmd-prefix is bsub if your cluster uses the LSF job scheduler, or qsub in Torque. Add arguments as necessary. For example, bsub -M 4GB sets a soft memory limit of 4GB."
.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$self\fR\->reference_sequence;
  my \f(CW$bam_list\fR = \f(CW$self\fR\->bam_list;
  my \f(CW$output_dir\fR = \f(CW$self\fR\->output_dir;
  my \f(CW$cmd_list_file\fR = \f(CW$self\fR\->cmd_list_file;
  my \f(CW$cmd_prefix\fR = \f(CW$self\fR\->cmd_prefix;
  my \f(CW$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 1
\&  my $optional_params = "";
\&
\&  if ($normal_min_depth) {
\&    $optional_params .= " \-\-normal\-min\-depth $normal_min_depth";
\&  }
\&  if ($tumor_min_depth) {
\&    $optional_params .= " \-\-tumor\-min\-depth $tumor_min_depth";
\&  }
\&  if ($min_mapq) {
\&    $optional_params .= " \-\-min\-mapq $min_mapq";
\&  }
\&
\&  # 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 "List of BAMs not found or is empty: $bam_list\en" unless( \-s $bam_list );
\&  print STDERR "Output directory not found: $output_dir\en" unless( \-e $output_dir );
\&  return undef unless( \-s $roi_file && \-e $ref_seq && \-s $bam_list && \-e $output_dir );
\&
\&  # Outputs of this script will be written to these locations in the output directory
\&  $output_dir =~ s/(\e/)+$//; # Remove trailing forward slashes if any
\&  my $roi_covg_dir = "$output_dir/roi_covgs"; # Stores output from calcRoiCovg per sample
\&  my $gene_covg_dir = "$output_dir/gene_covgs"; # Stores per\-gene coverages per sample
\&  my $tot_covg_file = "$output_dir/total_covgs"; # Stores total coverages per sample
\&
\&  $self\->gene_covg_dir($gene_covg_dir);
\&
\&  # 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 );
\&
\&  # Create the output directories unless they already exist
\&  mkdir $roi_covg_dir unless( \-e $roi_covg_dir );
\&  mkdir $gene_covg_dir unless( \-e $gene_covg_dir );
\&
\&  my ( $cmdFh, $totCovgFh );
\&  if( defined $cmd_list_file )
\&  {
\&    $cmdFh = IO::File\->new( $cmd_list_file, ">" );
\&    print "Creating a list of parallelizable jobs at $cmd_list_file.\en";
\&    print "After successfully running all the jobs in $cmd_list_file,\en",
\&          "be sure to run this script a second time (without defining the cmd\-list\-file argument) to merge results in roi_covgs.\en";
\&  }
\&  else
\&  {
\&    $totCovgFh = IO::File\->new( $tot_covg_file, ">" );
\&    $totCovgFh\->print( "#Sample\etCovered_Bases\etAT_Bases_Covered\etCG_Bases_Covered\etCpG_Bases_Covered\en" );
\&  }
\&
\&  # Parse through each pair of BAM files provided and run calcRoiCovg as necessary
\&  my $bamFh = IO::File\->new( $bam_list );
\&  while( my $line = $bamFh\->getline )
\&  {
\&    next if( $line =~ m/^#/ );
\&    chomp( $line );
\&    my ( $sample, $normal_bam, $tumor_bam ) = split( /\et/, $line );
\&    $normal_bam = \*(Aq\*(Aq unless( defined $normal_bam );
\&    $tumor_bam = \*(Aq\*(Aq unless( defined $tumor_bam );
\&    print STDERR "Normal BAM for $sample not found: \e"$normal_bam\e"\en" unless( \-e $normal_bam );
\&    print STDERR "Tumor BAM for $sample not found: \e"$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 $calcRoiCovg_cmd = "\e\*(Aqgmt music bmr calc\-covg\-helper \-\-normal\-tumor\-bam\-pair \e"$line\e" \-\-roi\-file \e"$roi_file\e" ".
\&    "\-\-reference\-sequence \e"$ref_seq\e" \-\-output\-file \e"$roi_covg_dir/$sample.covg\e"$optional_params\e\*(Aq";
\&
\&    # If user only wants the calcRoiCovg commands, write them to file and skip running calcRoiCovg
\&    if( defined $cmd_list_file )
\&    {
\&      $calcRoiCovg_cmd = $cmd_prefix . " $calcRoiCovg_cmd" if( defined $cmd_prefix );
\&      $cmdFh\->print( "$calcRoiCovg_cmd\en" );
\&      next;
\&    }
\&
\&    # If the calcRoiCovg output was already generated, then don\*(Aqt rerun it
\&    if( \-s "$roi_covg_dir/$sample.covg" )
\&    {
\&      print "$sample.covg found in $roi_covg_dir. Skipping re\-calculation.\en";
\&    }
\&    # Run the calcRoiCovg command on this tumor\-normal pair. This could take a while
\&    else {
\&      my %params = (
\&        normal_tumor_bam_pair => $line,
\&        roi_file => $roi_file,
\&        reference_sequence => $ref_seq, 
\&        output_file => $roi_covg_dir."/".$sample.".covg",
\&      );
\&      if ($normal_min_depth) {
\&        $params{"normal_min_depth"} = $normal_min_depth;
\&      }
\&      if ($tumor_min_depth) {
\&        $params{"tumor_min_depth"} = $tumor_min_depth;
\&      }
\&      if ($min_mapq) {
\&        $params{"min_mapq"} = $min_mapq;
\&      }
\&      my $cmd = Genome::Model::Tools::Music::Bmr::CalcCovgHelper\->create(%params);
\&      my $rv = $cmd\->execute;
\&      if(!$rv)
\&      {
\&        print STDERR "Failed to execute: $calcRoiCovg_cmd\en";
\&        next;
\&      }
\&      else
\&      {
\&        print "$sample.covg generated and stored to $roi_covg_dir.\en";
\&      }
\&    }
\&
\&    # Read the calcRoiCovg output and count covered bases per gene
\&    my %geneCovg = ();
\&    my ( $tot_covd, $tot_at_covd, $tot_cg_covg, $tot_cpg_covd );
\&    my $roiCovgFh = IO::File\->new( "$roi_covg_dir/$sample.covg" );
\&    while( my $line = $roiCovgFh\->getline )
\&    {
\&      chomp( $line );
\&      if( $line =~ m/^#NonOverlappingTotals/ )
\&      {
\&        ( undef, undef, undef, $tot_covd, $tot_at_covd, $tot_cg_covg, $tot_cpg_covd ) = split( /\et/, $line );
\&      }
\&      elsif( $line !~ m/^#/ )
\&      {
\&        my ( $gene, undef, $length, $covd, $at_covd, $cg_covd, $cpg_covd ) = split( /\et/, $line );
\&        $geneCovg{$gene}{len} += $length;
\&        $geneCovg{$gene}{covd_len} += $covd;
\&        $geneCovg{$gene}{at} += $at_covd;
\&        $geneCovg{$gene}{cg} += $cg_covd;
\&        $geneCovg{$gene}{cpg} += $cpg_covd;
\&      }
\&    }
\&    $roiCovgFh\->close;
\&
\&    # Write the per\-gene coverages to a file named after this sample_name
\&    my $geneCovgFh = IO::File\->new( "$gene_covg_dir/$sample.covg", ">" );
\&    $geneCovgFh\->print( "#Gene\etLength\etCovered\etAT_covd\etCG_covd\etCpG_covd\en" );
\&    foreach my $gene ( sort keys %geneCovg )
\&    {
\&      $geneCovgFh\->print( join( "\et", $gene, $geneCovg{$gene}{len}, $geneCovg{$gene}{covd_len},
\&         $geneCovg{$gene}{at}, $geneCovg{$gene}{cg}, $geneCovg{$gene}{cpg} ), "\en" );
\&    }
\&    $geneCovgFh\->close;
\&
\&    # Write total coverages for this sample to a file
\&    $totCovgFh\->print( "$sample\et$tot_covd\et$tot_at_covd\et$tot_cg_covg\et$tot_cpg_covd\en" );
\&  }
\&  $bamFh\->close;
\&  $cmdFh\->close if( defined $cmd_list_file );
\&  $totCovgFh\->close unless( defined $cmd_list_file );
\&
\&  return 1;
\&}
.Ve
.PP
1;