.\" 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::CalcWigCovg 3pm"
.TH Genome::Model::Tools::Music::Bmr::CalcWigCovg 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). 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). 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 "\-\-wig\-list" 4
.IX Item "--wig-list"
.RS 4
.IP "Provide a file containing sample names and the wiggle track format file locations for each. Use the tab-delimited format [sample_name wig_file] 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 the wiggle track format file locations for each. Use the tab-delimited format [sample_name wig_file] 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
.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$self\fR\->reference_sequence;
    my \f(CW$wig_list\fR = \f(CW$self\fR\->wig_list;
    my \f(CW$output_dir\fR = \f(CW$self\fR\->output_dir;
.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 "List of WIGs not found or is empty: $wig_list\en" unless( \-s $wig_list );
\&    print STDERR "Output directory not found: $output_dir\en" unless( \-e $output_dir );
\&    return undef unless( \-s $roi_file && \-e $ref_seq && \-s $wig_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
\&
\&    # If the reference sequence FASTA file hasn\*(Aqt been indexed, do it
\&    my $ref_seq_idx = "$ref_seq.fai";
\&    unless( \-e $ref_seq_idx ) {
\&        print "Reference fasta index not found. Creating one at: $ref_seq.fai\en";
\&        system( "samtools faidx $ref_seq" ) or die "Failed to run samtools! $!\en";
\&    }
\&
\&    # Create a temporary 0\-based ROI BED\-file that we can use with joinx, and also measure gene lengths
\&    my %geneLen = ();
\&    my $roi_bed = Genome::Sys\->create_temp_file_path();
\&    my $roiBedFh = IO::File\->new( $roi_bed, ">" ) or die "Temporary ROI BED file could not be created. $!\en";
\&    my $roiFh = IO::File\->new( $roi_file ) or die "ROI file could not be opened. $!\en";
\&    while( my $line = $roiFh\->getline ) {
\&        chomp( $line );
\&        my ( $chr, $start, $stop, $gene ) = split( /\et/, $line );
\&        \-\-$start;
\&        unless( $start >= 0 && $start < $stop ) {
\&            print STDERR "Invalid ROI: $line\enPlease use 1\-based loci and ensure that start <= stop\en";
\&            return undef;
\&        }
\&        $geneLen{$gene} += ( $stop \- $start );
\&        $roiBedFh\->print( "$chr\et$start\et$stop\et$gene\en" );
\&    }
\&    $roiFh\->close;
\&    $roiBedFh\->close;
\&
\&    # Also create a merged BED file where overlapping ROIs are joined together into contiguous regions
\&    # ::TODO:: Use joinx instead of mergeBed, because we\*(Aqd rather add an in\-house dependency
\&    my $merged_roi_bed = Genome::Sys\->create_temp_file_path();
\&    system( "mergeBed \-i $roi_bed | joinx sort \-s \- \-o $merged_roi_bed" );# or die "Failed to run mergeBed or joinx!\en$roi_bed\en$merged_roi_bed\en $!\en";
\&
\&    # 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 );
\&
\&    # This is a file that will report the overall non\-overlapping coverages per WIG
\&    my $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 WIG files provided and run calcRoiCovg as necessary
\&    my $wigFh = IO::File\->new( $wig_list );
\&    while( my $line = $wigFh\->getline ) {
\&        next if( $line =~ m/^#/ );
\&        chomp( $line );
\&        my ( $sample, $wig_file ) = split( /\et/, $line );
\&        $wig_file = \*(Aq\*(Aq unless( defined $wig_file );
\&        print STDERR "Wiggle track format file for $sample not found: \e"$wig_file\e"\en" unless( \-e $wig_file );
\&        next unless( \-e $wig_file );
\&
\&        # Use joinx to parse the WIG file and return per\-ROI coverages of AT, CG (non\-CpG), and CpG
\&        system( "joinx wig2bed \-Zc $wig_file | joinx sort \-s | joinx intersect \-F \e"I A3\e" $roi_bed \- | joinx ref\-stats \- $ref_seq | cut \-f 1\-7 > $roi_covg_dir/$sample.covg" );# or die "Failed to run joinx to calculate per\-gene coverages in $sample! $!\en";
\&
\&        # Read the joinx formatted coverage file and count covered bases per gene
\&        my %geneCovg = ();
\&        my $roiCovgFh = IO::File\->new( "$roi_covg_dir/$sample.covg" );
\&        while( my $line = $roiCovgFh\->getline ) {
\&            chomp( $line );
\&            if( $line !~ m/^#/ ) {
\&                my ( undef, undef, undef, $gene, $at_covd, $cg_covd, $cpg_covd ) = split( /\et/, $line );
\&                $geneCovg{$gene}{covd} += ( $at_covd + $cg_covd + $cpg_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 %geneLen ) {
\&            if( defined $geneCovg{$gene} ) {
\&                $geneCovgFh\->print( join( "\et", $gene, $geneLen{$gene}, $geneCovg{$gene}{covd},
\&                                    $geneCovg{$gene}{at}, $geneCovg{$gene}{cg}, $geneCovg{$gene}{cpg} ), "\en" );
\&            }
\&            else {
\&                $geneCovgFh\->print( "$gene\et" . $geneLen{$gene} . "\et0\et0\et0\et0\en" );
\&            }
\&        }
\&        $geneCovgFh\->close;
\&
\&        # Measure coverage stats on the merged ROI file, so that bps across the genome are not counted twice
\&        my $merged_roi_bed_covg = Genome::Sys\->create_temp_file_path();
\&        system( "joinx wig2bed \-Zc $wig_file | joinx sort \-s | joinx intersect $merged_roi_bed \- | joinx ref\-stats \- $ref_seq | cut \-f 1\-6 > $merged_roi_bed_covg" );# or die "Failed to run joinx to calculate overall coverages in $sample! $!\en";
\&
\&        # Read the joinx formatted coverage file and sum up the coverage stats per region
\&        my ( $tot_covd, $tot_at_covd, $tot_cg_covg, $tot_cpg_covd );
\&        my $totRoiCovgFh = IO::File\->new( $merged_roi_bed_covg );
\&        while( my $line = $totRoiCovgFh\->getline ) {
\&            chomp( $line );
\&            if( $line !~ m/^#/ ) {
\&                my ( $chr, $start, $stop, $at_covd, $cg_covd, $cpg_covd ) = split( /\et/, $line );
\&                $tot_covd += ( $at_covd + $cg_covd + $cpg_covd );
\&                $tot_at_covd += $at_covd;
\&                $tot_cg_covg += $cg_covd;
\&                $tot_cpg_covd += $cpg_covd;
\&            }
\&        }
\&        $totRoiCovgFh\->close;
\&        $totCovgFh\->print( "$sample\et$tot_covd\et$tot_at_covd\et$tot_cg_covg\et$tot_cpg_covd\en" );
\&    }
\&    $wigFh\->close;
\&    $totCovgFh\->close;
\&
\&    return 1;
\&}
.Ve
.PP
1;