.\" 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::MutationRelation 3pm"
.TH Genome::Model::Tools::Music::MutationRelation 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 "\-\-bam\-list" 4
.IX Item "--bam-list"
.RS 4
.PD 0
.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. This tool only needs sample_name, so all other columns can be skipped. 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. This tool only needs sample_name, so all other columns can be skipped. 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
.PD
.PP
\&\s-1EOS\s0
    );
}
.PP
sub _doc_authors {
  return <<\s-1EOS\s0
 Nathan D. Dees, Ph.D.
 Qunyuan Zhang, Ph.D.
\&\s-1EOS\s0
}
.PP
sub execute {
  # Parse input arguments
  my \f(CW$self\fR = shift;
  my \f(CW$bam_list\fR = \f(CW$self\fR\->bam_list;
  my \f(CW$maf_file\fR = \f(CW$self\fR\->maf_file;
  my \f(CW$output_file\fR = \f(CW$self\fR\->output_file;
  my \f(CW$gene_list\fR = \f(CW$self\fR\->gene_list;
  my \f(CW$permutations\fR = \f(CW$self\fR\->permutations;
  my \f(CW@all_sample_names\fR; # names of all the samples, no matter if it's mutated or not
  my \f(CW@genes_to_test\fR; # the genes which will be tested for relationships
  my \f(CW$skip_non_coding\fR = \f(CW$self\fR\->skip_non_coding;
  my \f(CW$skip_silent\fR = \f(CW$self\fR\->skip_silent;
.PP
.Vb 10
\&  # Parse out the names of the samples which should match the names in the MAF file
\&  my $sampleFh = IO::File\->new( $bam_list ) or die "Couldn\*(Aqt open $bam_list. $!\en";
\&  my $line_count = 0;
\&  while( my $line = $sampleFh\->getline )
\&  {
\&      $line_count++;
\&      next if ( $line =~ m/^#/ );
\&      chomp( $line );
\&      my ( $sample ) = split( /\et/, $line );
\&      if ($sample) {
\&          push( @all_sample_names, $sample );
\&      } else {
\&          warn("could not parse sample name from line $line_count of \-\-bam_list");
\&      }
\&  }
\&  $sampleFh\->close;
\&
\&  # If user\-specified, parse out the names of the genes that we are limiting our tests to
\&  if( defined $gene_list )
\&  {
\&      my $geneFh = IO::File\->new( $gene_list ) or die "Couldn\*(Aqt open $gene_list. $!\en";
\&      while( my $line = $geneFh\->getline )
\&      {
\&          next if ( $line =~ m/^#/ );
\&          chomp( $line );
\&          my ( $gene ) = split( /\et/, $line );
\&          push( @genes_to_test, $gene );
\&      }
\&      $geneFh\->close;
\&  }
\&
\&  # Create sample\-gene matrix
\&  my $matrix_file = $self\->create_sample_gene_matrix($maf_file, \e@all_sample_names, \e@genes_to_test, $skip_non_coding, $skip_silent);
\&
\&  # Perform mutation\-relation test using R
\&  my $R_cmd = "R \-\-slave \-\-args < " . _\|_FILE_\|_ . ".R $matrix_file $permutations $output_file";
\&  print "$R_cmd\en";
\&  WIFEXITED(system $R_cmd) or croak "Couldn\*(Aqt run: $R_cmd ($?)";
\&
\&  return(1);
\&}
.Ve
.PP
sub create_sample_gene_matrix {
    my \f(CW$self\fR = shift;
    my ( \f(CW$maf_file\fR, \f(CW$all_sample_names_ref\fR, \f(CW$genes_to_test_ref\fR, \f(CW$skip_non_coding\fR, \f(CW$skip_silent\fR ) = \f(CW@_\fR;
    my \f(CW@all_sample_names\fR = @{$all_sample_names_ref};
    my \f(CW@genes_to_test\fR = @{$genes_to_test_ref};
.PP
.Vb 3
\&    # Create hash of mutations from the MAF file
\&    my %mutations;
\&    my %all_genes;
\&
\&    # Parse the MAF file
\&    my $mafFh = IO::File\->new( $maf_file ) or die "Couldn\*(Aqt open $maf_file. $!\en";
\&    while( my $line = $mafFh\->getline )
\&    {
\&        next if( $line =~ m/^(#|Hugo_Symbol)/ );
\&        chomp $line;
\&        my @cols = split( /\et/, $line );
\&        my ( $gene, $mutation_class, $sample ) = ( $cols[0], $cols[8], $cols[15] );
\&
\&        # If the mutation classification is odd, quit with error
\&        if( $mutation_class !~ m/^(Missense_Mutation|Nonsense_Mutation|Nonstop_Mutation|Splice_Site|Translation_Start_Site|Frame_Shift_Del|Frame_Shift_Ins|In_Frame_Del|In_Frame_Ins|Silent|Intron|RNA|3\*(AqFlank|3\*(AqUTR|5\*(AqFlank|5\*(AqUTR|IGR|Targeted_Region|De_novo_Start_InFrame|De_novo_Start_OutOfFrame)$/ )
\&        {
\&            print STDERR "Unrecognized Variant_Classification \e"$mutation_class\e" in MAF file for gene $gene\en";
\&            print STDERR "Please use TCGA MAF Specification v2.3.\en";
\&            return undef;
\&        }
\&
\&        # If user wants, skip Silent mutations, or those in Introns, RNA, UTRs, Flanks, IGRs, or the ubiquitous Targeted_Region
\&        if(( $skip_non_coding && $mutation_class =~ m/^(Intron|RNA|3\*(AqFlank|3\*(AqUTR|5\*(AqFlank|5\*(AqUTR|IGR|Targeted_Region)$/ ) ||
\&            ( $skip_silent && $mutation_class =~ m/^Silent$/ ))
\&        {
\&            print "Skipping $mutation_class mutation in gene $gene.\en";
\&            next;
\&        }
\&
\&        $all_genes{$gene}++;
\&        $mutations{$sample}{$gene}++;
\&    }
\&    $mafFh\->close;
\&
\&    # If the user specified a gene list, then check for genes that are not in the MAF
\&    if( scalar( @genes_to_test ) > 0 )
\&    {
\&        for( my $i = 0; $i < scalar( @genes_to_test ); ++$i )
\&        {
\&            unless( defined $all_genes{$genes_to_test[$i]} )
\&            {
\&                print "Skipping ", $genes_to_test[$i], " from specified gene\-list since it was not found in the MAF file\en";
\&                splice( @genes_to_test, $i, 1 );
\&            }
\&        }
\&    }
\&    else
\&    {
\&        @genes_to_test = sort keys %all_genes;
\&    }
\&
\&    # Write the input matrix to a file for use by the R code
\&    my $matrix_file;
\&    unless( $matrix_file = $self\->mutation_matrix_file ) {
\&        $matrix_file = Genome::Sys\->create_temp_file_path();
\&    }
\&
\&    my $matrix_fh = new IO::File $matrix_file,"w";
\&    # Print input matrix file header
\&    my $header = join("\et","Sample",@genes_to_test);
\&    $matrix_fh\->print("$header\en");
\&
\&    # Print mutation relation input matrix
\&    for my $sample (sort @all_sample_names) {
\&        $matrix_fh\->print($sample);
\&        for my $gene (@genes_to_test) {
\&            if (exists $mutations{$sample}{$gene}) {
\&                $matrix_fh\->print("\et1");
\&            }
\&            else {
\&                $matrix_fh\->print("\et0");
\&            }
\&        }
\&        $matrix_fh\->print("\en");
\&    }
\&
\&    return $matrix_file;
\&}
.Ve
.PP
1;