.\" 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::Survival 3pm"
.TH Genome::Model::Tools::Music::Survival 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
Headers are required.
.IP "\(bu" 4
The first column of each clinical data file must contain sample IDs which match those in both the \-\-bam\-list and the \s-1MAF\s0 variant list (in the \s-1MAF,\s0 this is the Tumor_Sample_Barcode column, specifically).
.IP "\(bu" 4
In at least one of the clinical data files input, columns with headers \*(L"vital_status\*(R" and \*(L"days_to_last_followup\*(R" (case insensitive) must exist. \*(L"vital_status\*(R" must be delineated by 1's and 0's, where 0 denotes 'living', and 1 denotes 'deceased'.
.PP
Note that all input files must be tab-separated.
.PP
\&\s-1HELP\s0
}
.PP
sub _additional_help_sections {
    return (
        \*(L"\s-1ARGUMENTS\*(R",\s0
        <<\s-1EOS\s0
.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 {
.PP
.Vb 5
\&    # parse input arguments
\&    my $self = shift;
\&    my $bam_list = $self\->bam_list;
\&    my $genetic_data_type = $self\->genetic_data_type;
\&    my $legend_placement = $self\->legend_placement;
\&
\&    # handle phenotype inclusions
\&    my @phenotypes_to_include;
\&    my @clinical_phenotypes_to_include;
\&    my @mutated_genes_to_include;
\&    if ($self\->phenotypes_to_include) { @phenotypes_to_include = split /,/,$self\->phenotypes_to_include; }
\&
\&    # check genetic data type
\&    unless ($genetic_data_type =~ /^gene|variant$/i) {
\&        $self\->error_message("Please enter either \e"gene\e" or \e"variant\e" for the \-\-genetic\-data\-type parameter.");
\&        return;
\&    }
\&
\&    # load clinical data and analysis types
\&    my %clinical_data;
\&    if ($self\->numeric_clinical_data_file) {
\&        $clinical_data{\*(Aqnumeric\*(Aq} = $self\->numeric_clinical_data_file;
\&    }
\&    if ($self\->categorical_clinical_data_file) {
\&        $clinical_data{\*(Aqcateg\*(Aq} = $self\->categorical_clinical_data_file;
\&    }
\&    if ($self\->glm_clinical_data_file) {
\&        $clinical_data{\*(Aqglm\*(Aq} = $self\->glm_clinical_data_file;
\&    }
\&
\&    # create array of all sample names possibly included from clinical data and MAF
\&    my @all_sample_names; # names of all the samples, no matter if they are mutated or not
\&    my $sampleFh = IO::File\->new( $bam_list ) or die "Couldn\*(Aqt open $bam_list. $!\en";
\&    while( my $line = $sampleFh\->getline )
\&    {
\&        next if ( $line =~ m/^#/ );
\&        chomp( $line );
\&        my ( $sample ) = split( /\et/, $line );
\&        push( @all_sample_names, $sample );
\&    }
\&    $sampleFh\->close;
\&
\&    # loop through clinical data files and assemble survival data hash (vital_status and days_to_last_followup required);
\&    my %survival_data;
\&    my $vital_status_flag = 0;
\&    my $days_to_last_follow_flag = 0;
\&
\&    for my $clin_file (keys %clinical_data) {
\&
\&        #check filehandle
\&        my $clin_fh = new IO::File $clinical_data{$clin_file},"r";
\&        unless ($clin_fh) {
\&            $self\->error_message("Failed to open $clinical_data{$clin_file} for reading: $!");
\&            return;
\&        }
\&
\&        #initiate variables to hold column info
\&        my %phenotypes_to_print;
\&        my $vital_status_col = 0;
\&        my $days_to_last_follow_col = 0;
\&
\&        #parse header and record column locations for needed data
\&        my $header = $clin_fh\->getline;
\&        my @header_fields = split /\et/,$header;
\&        for (my $i = 1; $i <= $#header_fields; $i++) { #sample ID should be in first column of file
\&            my $field = $header_fields[$i];
\&            if ($field =~ /vital_status|vitalstatus/i) { $vital_status_col = $i; $vital_status_flag++; }
\&            if ($field =~ /days_to_last_(follow_up|followup)|daystolastfollowup/i) { $days_to_last_follow_col = $i; $days_to_last_follow_flag++; }
\&            if (scalar grep { /^$field$/i } @phenotypes_to_include) { $phenotypes_to_print{$field} = $i; }
\&        }
\&
\&        #read through clinical data file and store needed data in a hash
\&        while (my $line = $clin_fh\->getline) {
\&            chomp $line;
\&            my @fields = split /\et/,$line;
\&            my $sample = $fields[0];
\&            unless (scalar grep { m/^$sample$/ } @all_sample_names) {
\&                $self\->status_message("Skipping sample $sample. (Sample is not in \-\-bam\-list).");
\&                next;
\&            }
\&            if ($vital_status_col) {
\&                my $vital_status;
\&                if ($fields[$vital_status_col] =~ /^(0|living)$/i) { $vital_status = 0; }
\&                elsif ($fields[$vital_status_col] =~ /^(1|deceased)$/i) { $vital_status = 1; }
\&                else { $vital_status = "NA"; }
\&                $survival_data{$sample}{\*(Aqvital_status\*(Aq} = $vital_status;
\&            }
\&            if ($days_to_last_follow_col) { $survival_data{$sample}{\*(Aqdays\*(Aq} = $fields[$days_to_last_follow_col]; }
\&            for my $pheno (keys %phenotypes_to_print) { $survival_data{$sample}{$pheno} = $fields[$phenotypes_to_print{$pheno}]; }
\&        }
\&        $clin_fh\->close;
\&
\&        # record phenotypes included from clinical data
\&        push @clinical_phenotypes_to_include, keys %phenotypes_to_print;
\&
\&    }
\&
\&    # check for necessary header fields
\&    unless ($vital_status_flag) {
\&        $self\->error_message(\*(AqClinical data does not seem to contain a column labeled "vital_status".\*(Aq);
\&        return;
\&    }
\&    unless ($days_to_last_follow_flag) {
\&        $self\->error_message(\*(AqClnical data does not seem to contain a column labeled "days_to_last_followup".\*(Aq);
\&        return;
\&    }
\&
\&    # create temporary files for R command
\&    my $survival_data_file = Genome::Sys\->create_temp_file_path();
\&    my $mutation_matrix = Genome::Sys\->create_temp_file_path();
\&
\&    # print survival data (temp file)
\&    my $surv_fh = new IO::File $survival_data_file,"w" or die "Couldn\*(Aqt open survival data filehandle.";
\&    print $surv_fh join("\et","Sample","Days_To_Last_Followup","Vital_Status");
\&    if (@clinical_phenotypes_to_include) { print $surv_fh "\et" . join("\et",@clinical_phenotypes_to_include); }
\&    print $surv_fh "\en";
\&    for my $sample (keys %survival_data) {
\&        unless (exists $survival_data{$sample}{\*(Aqdays\*(Aq}) { $survival_data{$sample}{\*(Aqdays\*(Aq} = "NA"; }
\&        unless (exists $survival_data{$sample}{\*(Aqvital_status\*(Aq}) { $survival_data{$sample}{\*(Aqvital_status\*(Aq} = "NA"; }
\&        print $surv_fh join("\et",$sample,$survival_data{$sample}{\*(Aqdays\*(Aq},$survival_data{$sample}{\*(Aqvital_status\*(Aq});
\&        for my $pheno (@clinical_phenotypes_to_include) {
\&            unless (exists $survival_data{$sample}{$pheno}) { $survival_data{$sample}{$pheno} = "NA"; }
\&            print $surv_fh "\et" . $survival_data{$sample}{$pheno};
\&        }
\&        print $surv_fh "\en";
\&    }
\&    $surv_fh\->close;
\&
\&    # find if any of the "phenotypes_to_include" are genes, and if so, limit the MAF mutation matrix to those genes
\&    my %clinical_pheno_to_include;
\&    @clinical_pheno_to_include{@clinical_phenotypes_to_include} = ();
\&    for my $item (@phenotypes_to_include) {
\&        push @mutated_genes_to_include,$item unless exists $clinical_pheno_to_include{$item};
\&    }
\&    my $mutated_genes_to_include = \e@mutated_genes_to_include;
\&
\&    # create mutation matrix file
\&    if( $genetic_data_type =~ /^gene$/i ) {
\&        $self\->create_sample_gene_matrix_gene( $mutation_matrix, $mutated_genes_to_include, @all_sample_names );
\&    }
\&    elsif( $genetic_data_type =~ /^variant$/i ) {
\&        $self\->create_sample_gene_matrix_variant( $mutation_matrix, $mutated_genes_to_include, @all_sample_names );
\&    }
\&    else {
\&        $self\->error_message( "Please enter either \e"gene\e" or \e"variant\e" for the \-\-genetic\-data\-type parameter." );
\&        return;
\&    }
\&
\&    # check and prepare output directory
\&    my $output_dir = $self\->output_dir . "/";
\&    unless (\-e $output_dir) {
\&        $self\->status_message("Creating output directory: $output_dir...");
\&        unless(mkdir $output_dir) {
\&            $self\->error_message("Failed to create output directory: $!");
\&            return;
\&        }
\&    }
\&
\&    # set up R command
\&    my $R_cmd = "R \-\-slave \-\-args < " . _\|_FILE_\|_ . ".R " . join( " ", $survival_data_file, $mutation_matrix, $legend_placement, $output_dir );
\&    print "R_cmd:\en$R_cmd\en";
\&
\&    #run R command
\&    WIFEXITED( system $R_cmd ) or croak "Couldn\*(Aqt run: $R_cmd ($?)";
\&
\&    return(1);
\&}
.Ve
.PP
sub create_sample_gene_matrix_gene {
.PP
.Vb 1
\&    my ( $self, $mutation_matrix, $mutated_genes_to_include, @all_sample_names ) = @_;
\&
\&    #create hash of mutations from the MAF file
\&    my ( %mutations, %all_genes );
\&
\&    #parse the MAF file and fill up the mutation status hashes
\&    my $maf_fh = IO::File\->new( $self\->maf_file ) or die "Couldn\*(Aqt open MAF file!\en";
\&    while( my $line = $maf_fh\->getline ) {
\&        next if( $line =~ m/^(#|Hugo_Symbol)/ );
\&        chomp $line;
\&        my @cols = split( /\et/, $line );
\&        my ( $gene, $mutation_class, $sample ) = @cols[0,8,15];
\&
\&        #check that the mutation class is valid
\&        if( $mutation_class !~ m/^(Missense_Mutation|Nonsense_Mutation|Nonstop_Mutation|Splice_Site|Translation_Start_Site|Frame_Shift_Del|Frame_Shift_Ins|In_Frame_Del|In_Frame_Ins|Silent|Intron|RNA|3\*(AqFlank|3\*(AqUTR|5\*(AqFlank|5\*(AqUTR|IGR|Targeted_Region|De_novo_Start_InFrame|De_novo_Start_OutOfFrame)$/ ) {
\&            $self\->error_message( "Unrecognized Variant_Classification \e"$mutation_class\e" in MAF file for gene $gene\enPlease use TCGA MAF v2.3.\en" );
\&            return;
\&        }
\&
\&        #check to see if this gene is on the list (if there is a list at all)
\&        if( @{$mutated_genes_to_include} ) {
\&            next unless( scalar grep { m/^$gene$/ } @{$mutated_genes_to_include} );
\&        }
\&
\&        # If user wants, skip Silent mutations, or those in Introns, RNA, UTRs, Flanks, IGRs, or the ubiquitous Targeted_Region
\&        if(( $self\->skip_non_coding && $mutation_class =~ m/^(Intron|RNA|3\*(AqFlank|3\*(AqUTR|5\*(AqFlank|5\*(AqUTR|IGR|Targeted_Region)$/ ) ||
\&           ( $self\->skip_silent && $mutation_class =~ m/^Silent$/ )) {
\&            print "Skipping $mutation_class mutation in gene $gene.\en";
\&            next;
\&        }
\&
\&        $all_genes{$gene}++;
\&        $mutations{$sample}{$gene}++;
\&    }
\&    $maf_fh\->close;
\&
\&    #sort @all_genes for consistency in header and loops
\&    my @all_genes = sort keys %all_genes;
\&
\&    #write the input matrix for R code to a temp file
\&    my $matrix_fh = new IO::File $mutation_matrix,"w" or die "Failed to create matrix file $mutation_matrix!: $!";
\&
\&    #print input matrix file header
\&    my $header = join( "\et", "Sample", @all_genes );
\&    $matrix_fh\->print( "$header\en" );
\&
\&    #print mutation relation input matrix
\&    for my $sample ( sort @all_sample_names ) {
\&        $matrix_fh\->print( $sample );
\&        for my $gene ( @all_genes ) {
\&            if( exists $mutations{$sample}{$gene} ) {
\&                $matrix_fh\->print( "\et$mutations{$sample}{$gene}" );
\&            }
\&            else {
\&                $matrix_fh\->print( "\et0" );
\&            }
\&        }
\&        $matrix_fh\->print( "\en" );
\&    }
\&}
.Ve
.PP
sub create_sample_gene_matrix_variant {
.PP
.Vb 1
\&    my ( $self, $mutation_matrix, $mutated_genes_to_include, @all_sample_names ) = @_;
\&
\&    #create hash of mutations from the MAF file
\&    my ( %variants_hash, %all_variants );
\&
\&    #parse the MAF file and fill up the mutation status hashes
\&    my $maf_fh = IO::File\->new( $self\->maf_file ) or die "Couldn\*(Aqt open MAF file!\en";
\&    while( my $line = $maf_fh\->getline ) {
\&        next if( $line =~ m/^(#|Hugo_Symbol)/ );
\&        chomp $line;
\&        my @cols = split( /\et/, $line );
\&        my ( $gene, $chr, $start, $stop, $mutation_class, $mutation_type, $ref, $var1, $var2, $sample ) = @cols[0,4..6,8..12,15];
\&
\&        #check that the mutation class is valid
\&        if( $mutation_class !~ m/^(Missense_Mutation|Nonsense_Mutation|Nonstop_Mutation|Splice_Site|Translation_Start_Site|Frame_Shift_Del|Frame_Shift_Ins|In_Frame_Del|In_Frame_Ins|Silent|Intron|RNA|3\*(AqFlank|3\*(AqUTR|5\*(AqFlank|5\*(AqUTR|IGR|Targeted_Region|De_novo_Start_InFrame|De_novo_Start_OutOfFrame)$/ ) {
\&            $self\->error_message( "Unrecognized Variant_Classification \e"$mutation_class\e" in MAF file for gene $gene\enPlease use TCGA MAF v2.3.\en" );
\&            return;
\&        }
\&
\&        #check to see if this gene is on the list (if there is a list at all)
\&        if( @{$mutated_genes_to_include} ) {
\&            next unless (scalar grep { m/^$gene$/ } @{$mutated_genes_to_include});
\&        }
\&
\&        # If user wants, skip Silent mutations, or those in Introns, RNA, UTRs, Flanks, IGRs, or the ubiquitous Targeted_Region
\&        if(( $self\->skip_non_coding && $mutation_class =~ m/^(Intron|RNA|3\*(AqFlank|3\*(AqUTR|5\*(AqFlank|5\*(AqUTR|IGR|Targeted_Region)$/ ) ||
\&           ( $self\->skip_silent && $mutation_class =~ m/^Silent$/ )) {
\&            print "Skipping $mutation_class mutation in gene $gene.\en";
\&            next;
\&        }
\&
\&        my $var;
\&        my $variant_name;
\&        if( $ref eq $var1 ) {
\&            $var = $var2;
\&            $variant_name = $gene."_".$chr."_".$start."_".$stop."_".$ref."_".$var;
\&            $variants_hash{$sample}{$variant_name}++;
\&            $all_variants{$variant_name}++;
\&        }
\&        elsif( $ref eq $var2 ) {
\&            $var = $var1;
\&            $variant_name = $gene."_".$chr."_".$start."_".$stop."_".$ref."_".$var;
\&            $variants_hash{$sample}{$variant_name}++;
\&            $all_variants{$variant_name}++;
\&        }
\&        elsif( $ref ne $var1 && $ref ne $var2 ) {
\&            $var = $var1;
\&            $variant_name = $gene."_".$chr."_".$start."_".$stop."_".$ref."_".$var;
\&            $variants_hash{$sample}{$variant_name}++;
\&            $all_variants{$variant_name}++;
\&            $var = $var2;
\&            $variant_name = $gene."_".$chr."_".$start."_".$stop."_".$ref."_".$var;
\&            $variants_hash{$sample}{$variant_name}++;
\&            $all_variants{$variant_name}++;
\&        }
\&    }
\&    $maf_fh\->close;
\&
\&    #sort variants for consistency
\&    my @variant_names = sort keys %all_variants;
\&
\&    #write the input matrix for R code to a file
\&    my $matrix_fh = new IO::File $mutation_matrix,"w" or die "Failed to create matrix file $mutation_matrix!: $!";
\&
\&    #print input matrix file header
\&    my $header = join("\et","Sample",@variant_names);
\&    $matrix_fh\->print("$header\en");
\&
\&    #print mutation relation input matrix
\&    for my $sample (sort @all_sample_names) {
\&        $matrix_fh\->print($sample);
\&        for my $variant (@variant_names) {
\&            if (exists $variants_hash{$sample}{$variant}) {
\&                $matrix_fh\->print("\et$variants_hash{$sample}{$variant}");
\&            }
\&            else {
\&                $matrix_fh\->print("\et0");
\&            }
\&        }
\&        $matrix_fh\->print("\en");
\&    }
\&}
.Ve
.PP
1;