.\" 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::ClinicalCorrelation 3pm"
.TH Genome::Model::Tools::Music::ClinicalCorrelation 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
Each file must include at least 1 sample_id column and 1 attribute column, with the format being [sample_id  clinical_data_attribute_1 clinical_data_attribute_2 ...]
.IP "\(bu" 4
The sample \s-1ID\s0 must match the sample \s-1ID\s0 listed in the \s-1MAF\s0 under \*(L"Tumor_Sample_Barcode\*(R" for relating the mutations of this sample.
.PP
Note the importance of the headers: the header for each clinical_data_attribute will appear in the
output file to denote relationships with the mutation data from the \s-1MAF.\s0
.PP
Internally, the input data is fed into an R script which calculates a P\-value representing the
probability that the correlation seen between the mutations in each gene (or variant) and each
phenotype trait are random. Lower P\-values indicate lower randomness, or likely true correlations.
.PP
The results are saved to the output filename given with a suffix appended; \*(L".numeric.csv\*(R" will be
appended for results derived from numeric clinical data, and \*(L".categorical.csv\*(R" will be appended for results
derived from categorical clinical data. Also, \*(L".glm.csv\*(R" will be appended to the output filename for \s-1GLM\s0 results.
.PP
The \s-1GLM\s0 analysis accepts a mixed numeric and categoric clinical data file, input using the parameter \-\-glm\-clinical\-data\-file. \s-1GLM\s0 clinical data must adhere to the formats described above for the correlation clinical data files. \s-1GLM\s0 also requires the user to input a \-\-glm\-model\-file. This file requires specific headers and defines the analysis to be performed rather exactly. Here are the conventions required for this file:
.IP "\(bu" 4
Columns must be ordered as such:
.IP "\(bu" 4
[ analysis_type    clinical_data_trait_name    variant/gene_name   covariates  memo ]
.IP "\(bu" 4
The 'analysis_type' column must contain either \*(L"Q\*(R", indicating a quantative trait, or \*(L"B\*(R", indicating a binary trait will be examined.
.IP "\(bu" 4
The 'clinical_data_trait_name' is the name of a clinical data trait defined by being a header in the \-\-glm\-clinical\-data\-file.
.IP "\(bu" 4
The 'variant/gene_name' can either be the name of one or more columns from the \-\-glm\-clinical\-data\-file, or the name of one or more mutated gene names from the \s-1MAF,\s0 separated by \*(L"|\*(R". If this column is left blank, or instead contains \*(L"\s-1NA\*(R",\s0 then each column from either the variant mutation matrix (\-\-use\-maf\-in\-glm) or alternatively the \-\-glm\-clinical\-data\-file is used consecutively as the variant column in independent analyses.
.IP "\(bu" 4
\&'covariates' are the names of one or more columns from the \-\-glm\-clinical\-data\-file, separated by \*(L"+\*(R".
.IP "\(bu" 4
\&'memo' is any note deemed useful to the user. It will be printed in the output data file for reference.
.PP
\&\s-1GLM\s0 analysis may be performed using solely the data input into \-\-glm\-clinical\-data\-file, as described above, or alternatively, mutational data from the \s-1MAF\s0 may be included as variants in the \s-1GLM\s0 analysis, as also described above. Use the \-\-use\-maf\-in\-glm flag to include the mutation matrix derived from the maf as variant data.
.PP
Note that all input files for both correlation and \s-1GLM\s0 analysis 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.
 William Schierding, M.S.
\&\s-1EOS\s0
}
.PP
sub execute {
.PP
.Vb 5
\&    # parse input arguments
\&    my $self = shift;
\&    my $bam_list = $self\->bam_list;
\&    my $output_file = $self\->output_file;
\&    my $genetic_data_type = $self\->genetic_data_type;
\&
\&    # 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;
\&    }
\&    my $glm_model = $self\->glm_model_file;
\&
\&    # declarations
\&    my @all_sample_names; # names of all the samples, no matter if it\*(Aqs mutated or not
\&
\&    # parse out the sample names from the bam\-list which should match the names in the MAF file
\&    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
\&    for my $datatype ( keys %clinical_data ) {
\&
\&        my $test_method;
\&        my $full_output_filename;
\&
\&        if( $datatype =~ /numeric/i ) {
\&            $full_output_filename = $output_file . ".numeric.csv";
\&            $test_method = $self\->numerical_data_test_method;
\&        }
\&
\&        if( $datatype =~ /categ/i ) {
\&            $full_output_filename = $output_file . ".categorical.csv";
\&            $test_method = "fisher";
\&        }
\&
\&        if( $datatype =~ /glm/i ) {
\&            $full_output_filename = $output_file . ".glm.csv";
\&            $test_method = "glm";
\&        }
\&
\&        #read through clinical data file to see which samples are represented and create input matrix for R
\&        my %samples;
\&        my $matrix_file;
\&        my $samples = \e%samples;
\&        my $clin_fh = new IO::File $clinical_data{$datatype},"r";
\&        unless( $clin_fh ) {
\&            die "failed to open $clinical_data{$datatype} for reading: $!";
\&        }
\&        my $header = $clin_fh\->getline;
\&        while( my $line = $clin_fh\->getline ) {
\&            chomp $line;
\&            my ( $sample ) = split( /\et/, $line );
\&            $samples{$sample}++;
\&        }
\&        #create correlation matrix unless it\*(Aqs glm analysis without using a maf file
\&        unless(( $datatype =~ /glm/i && !$self\->use_maf_in_glm ) || $self\->input_clinical_correlation_matrix_file ) {
\&
\&            if( $genetic_data_type =~ /^gene$/i ) {
\&                $matrix_file = $self\->create_sample_gene_matrix_gene( $samples, $clinical_data{$datatype}, @all_sample_names );
\&            }
\&            elsif( $genetic_data_type =~ /^variant$/i ) {
\&                $matrix_file = $self\->create_sample_gene_matrix_variant( $samples, $clinical_data{$datatype}, @all_sample_names );
\&            }
\&            else {
\&                $self\->error_message( "Please enter either \e"gene\e" or \e"variant\e" for the \-\-genetic\-data\-type parameter." );
\&                return;
\&            }
\&        }
\&
\&        if( $self\->input_clinical_correlation_matrix_file ) {
\&            $matrix_file = $self\->input_clinical_correlation_matrix_file;
\&        }
\&
\&        unless( defined $matrix_file ) { $matrix_file = "\*(Aq*\*(Aq"; }
\&
\&        #set up R command
\&        my $R_cmd = "R \-\-slave \-\-args < " . _\|_FILE_\|_ . ".R $test_method ";
\&
\&        if( $datatype =~ /glm/i ) {
\&            $R_cmd .= "$glm_model $clinical_data{$datatype} $matrix_file $full_output_filename";
\&        }
\&        else {
\&            $R_cmd .= "$clinical_data{$datatype} $matrix_file $full_output_filename";
\&        }
\&
\&        #run R command
\&        print "R_cmd:\en$R_cmd\en";
\&        WIFEXITED( system $R_cmd ) or croak "Couldn\*(Aqt run: $R_cmd ($?)";
\&    }
\&
\&    return( 1 );
\&}
.Ve
.PP
sub create_sample_gene_matrix_gene {
.PP
.Vb 2
\&    my ( $self, $samples, $clinical_data_file, @all_sample_names ) = @_;
\&    my $output_matrix = $self\->clinical_correlation_matrix_file;
\&
\&    #create a hash of mutations from the MAF file
\&    my ( %mutations, %all_genes, @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 if sample exists in clinical data
\&        unless( defined $samples\->{$sample} ) {
\&            warn "Sample Name: $sample from MAF file does not exist in Clinical Data File";
\&            next;
\&        }
\&
\&        # 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
\&    @all_genes = sort keys %all_genes;
\&
\&    #write the input matrix for R code to a file
\&    my $matrix_fh;
\&    unless (defined $output_matrix) {
\&        $output_matrix = Genome::Sys\->create_temp_file_path();
\&    }
\&    $matrix_fh = new IO::File $output_matrix,"w";
\&    unless ($matrix_fh) {
\&        die "Failed to create matrix file $output_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");
\&    }
\&
\&    return $output_matrix;
\&}
.Ve
.PP
sub create_sample_gene_matrix_variant {
.PP
.Vb 2
\&    my ( $self, $samples, $clinical_data_file, @all_sample_names ) = @_;
\&    my $output_matrix = $self\->clinical_correlation_matrix_file;
\&
\&    #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;
\&        }
\&
\&        unless( exists $samples\->{$sample} ) {
\&            warn "Sample Name: $sample from MAF file does not exist in Clinical Data File";
\&            next;
\&        }
\&
\&        # 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;
\&    unless( defined $output_matrix ) {
\&        $output_matrix = Genome::Sys\->create_temp_file_path();
\&    }
\&    $matrix_fh = new IO::File $output_matrix,"w";
\&    unless( $matrix_fh ) {
\&        die "Failed to create matrix file $output_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");
\&    }
\&
\&    return $output_matrix;
\&}
.Ve
.PP
1;