.\" Automatically generated by Pod::Man 4.09 (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
..
.if !\nF .nr F 0
.if \nF>0 \{\
.    de IX
.    tm Index:\\$1\t\\n%\t"\\$2"
..
.    if !\nF==2 \{\
.        nr % 0
.        nr F 2
.    \}
.\}
.\"
.\" 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-MUSIC-PATH-SCAN 1p"
.TH GENOME-MUSIC-PATH-SCAN 1p "2018-07-05" "perl v5.26.2" "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
.SH "genome music path-scan"
.IX Header "genome music path-scan"
.SH "NAME"
genome music path\-scan \- Find significantly mutated pathways in a cohort given a list of somatic mutations.
.SH "VERSION"
.IX Header "VERSION"
This document describes genome music path-scan version 0.04 (2018\-07\-05 at 09:17:13)
.SH "SYNOPSIS"
.IX Header "SYNOPSIS"
genome music path-scan \-\-gene\-covg\-dir=? \-\-bam\-list=? \-\-pathway\-file=? \-\-maf\-file=? \-\-output\-file=? [\-\-bmr=?] [\-\-genes\-to\-ignore=?] [\-\-min\-mut\-genes\-per\-path=?] [\-\-skip\-non\-coding] [\-\-skip\-silent]
.PP
.Vb 7
\& ... music path\-scan \e
\&        \-\-bam\-list input_dir/bam_file_list \e
\&        \-\-gene\-covg\-dir output_dir/gene_covgs/ \e
\&        \-\-maf\-file input_dir/myMAF.tsv \e
\&        \-\-output\-file output_dir/sm_pathways \e
\&        \-\-pathway\-file input_dir/pathway_dbs/KEGG.txt \e
\&        \-\-bmr 8.7E\-07
.Ve
.SH "REQUIRED ARGUMENTS"
.IX Header "REQUIRED ARGUMENTS"
.IP "gene-covg-dir  \fIText\fR" 4
.IX Item "gene-covg-dir Text"
Directory containing per-gene coverage files (Created using music bmr calc-covg)
.IP "bam-list  \fIText\fR" 4
.IX Item "bam-list Text"
Tab delimited list of \s-1BAM\s0 files [sample_name, normal_bam, tumor_bam] (See Description)
.IP "pathway-file  \fIText\fR" 4
.IX Item "pathway-file Text"
Tab-delimited file of pathway information (See Description)
.IP "maf-file  \fIText\fR" 4
.IX Item "maf-file Text"
List of mutations using \s-1TCGA MAF\s0 specifications v2.3
.IP "output-file  \fIText\fR" 4
.IX Item "output-file Text"
Output file that will list the significant pathways and their p\-values
.SH "OPTIONAL ARGUMENTS"
.IX Header "OPTIONAL ARGUMENTS"
.IP "bmr  \fINumber\fR" 4
.IX Item "bmr Number"
Background mutation rate in the targeted regions
.Sp
Default value '1e\-06' if not specified
.IP "genes-to-ignore  \fIText\fR" 4
.IX Item "genes-to-ignore Text"
Comma-delimited list of genes whose mutations should be ignored
.IP "min-mut-genes-per-path  \fINumber\fR" 4
.IX Item "min-mut-genes-per-path Number"
Pathways with fewer mutated genes than this, will be ignored
.Sp
Default value '1' if not specified
.IP "skip-non-coding  \fIBoolean\fR" 4
.IX Item "skip-non-coding Boolean"
Skip non-coding mutations from the provided \s-1MAF\s0 file
.Sp
Default value 'true' if not specified
.IP "noskip-non-coding  \fIBoolean\fR" 4
.IX Item "noskip-non-coding Boolean"
Make skip-non-coding 'false'
.IP "skip-silent  \fIBoolean\fR" 4
.IX Item "skip-silent Boolean"
Skip silent mutations from the provided \s-1MAF\s0 file
.Sp
Default value 'true' if not specified
.IP "noskip-silent  \fIBoolean\fR" 4
.IX Item "noskip-silent Boolean"
Make skip-silent 'false'
.SH "DESCRIPTION"
.IX Header "DESCRIPTION"
Only the following four columns in the \s-1MAF\s0 are used. All other columns may be left blank.
.PP
.Vb 4
\& Col 1: Hugo_Symbol (Need not be HUGO, but must match gene names used in the pathway file)
\& Col 2: Entrez_Gene_Id (Matching Entrez ID trump gene name matches between pathway file and MAF)
\& Col 9: Variant_Classification
\& Col 16: Tumor_Sample_Barcode (Must match the name in sample\-list, or contain it as a substring)
.Ve
.PP
The Entrez_Gene_Id can also be left blank (or set to 0), but it is highly recommended, in case
genes are named differently in the pathway file and the \s-1MAF\s0 file.
.SH "ARGUMENTS"
.IX Header "ARGUMENTS"
.IP "\-\-pathway\-file" 4
.IX Item "--pathway-file"
.RS 4
.PD 0
.ie n .IP "This is a tab-delimited file prepared from a pathway database (such as \s-1KEGG\s0), with the columns: [path_id, path_name, class, gene_line, diseases, drugs, description] The latter three columns are optional (but are available on \s-1KEGG\s0). The gene_line contains the ""entrez_id:gene_name"" of all genes involved in this pathway, each separated by a ""|"" symbol." 8
.el .IP "This is a tab-delimited file prepared from a pathway database (such as \s-1KEGG\s0), with the columns: [path_id, path_name, class, gene_line, diseases, drugs, description] The latter three columns are optional (but are available on \s-1KEGG\s0). The gene_line contains the ``entrez_id:gene_name'' of all genes involved in this pathway, each separated by a ``|'' symbol." 8
.IX Item "This is a tab-delimited file prepared from a pathway database (such as KEGG), with the columns: [path_id, path_name, class, gene_line, diseases, drugs, description] The latter three columns are optional (but are available on KEGG). The gene_line contains the entrez_id:gene_name of all genes involved in this pathway, each separated by a | symbol."
.PD
For example, a line in the pathway-file would look like:
.Sp
.Vb 1
\&  hsa00061    Fatty acid biosynthesis    Lipid Metabolism    31:ACACA|32:ACACB|27349:MCAT|2194:FASN|54995:OXSM|55301:OLAH
.Ve
.Sp
Ensure that the gene names and entrez IDs used match those used in the \s-1MAF\s0 file. Entrez IDs are
not mandatory (use a 0 if Entrez \s-1ID\s0 unknown). But if a gene name in the \s-1MAF\s0 does not match any
gene name in this file, the entrez IDs are used to find a match (unless it's a 0).
.RE
.RS 4
.RE
.IP "\-\-gene\-covg\-dir" 4
.IX Item "--gene-covg-dir"
.RS 4
.PD 0
.ie n .IP "This is usually the gene_covgs subdirectory created when you run ""music bmr calc-covg"". It should contain files for each sample that report per-gene covered base counts." 8
.el .IP "This is usually the gene_covgs subdirectory created when you run ``music bmr calc-covg''. It should contain files for each sample that report per-gene covered base counts." 8
.IX Item "This is usually the gene_covgs subdirectory created when you run music bmr calc-covg. It should contain files for each sample that report per-gene covered base counts."
.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. 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
.IP "\-\-bmr" 4
.IX Item "--bmr"
.RS 4
.ie n .IP "The overall background mutation rate. This can be calculated using ""music bmr calc-bmr""." 8
.el .IP "The overall background mutation rate. This can be calculated using ``music bmr calc-bmr''." 8
.IX Item "The overall background mutation rate. This can be calculated using music bmr calc-bmr."
.RE
.RS 4
.RE
.IP "\-\-genes\-to\-ignore" 4
.IX Item "--genes-to-ignore"
.RS 4
.IP "A comma-delimited list of genes to ignore from the \s-1MAF\s0 file. This is useful when there are recurrently mutated genes like \s-1TP53\s0 which might mask the significance of other genes." 8
.IX Item "A comma-delimited list of genes to ignore from the MAF file. This is useful when there are recurrently mutated genes like TP53 which might mask the significance of other genes."
.RE
.RS 4
.RE
.PD
.SH "AUTHORS"
.IX Header "AUTHORS"
.Vb 1
\& Michael Wendl, Ph.D.
.Ve
.SH "CREDITS"
.IX Header "CREDITS"
This module uses reformatted copies of data from the Kyoto Encyclopedia of Genes and Genomes (\s-1KEGG\s0) database:
.PP
.Vb 1
\& * KEGG \- http://www.genome.jp/kegg/
.Ve