.\" 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-BMR-CALC-BMR 1p" .TH GENOME-MUSIC-BMR-CALC-BMR 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 bmr calc-bmr" .IX Header "genome music bmr calc-bmr" .SH "NAME" genome music bmr calc\-bmr \- Calculates mutation rates given per\-gene coverage (from "music bmr calc\-covg"), and a mutation list .SH "VERSION" .IX Header "VERSION" This document describes genome music bmr calc-bmr version 0.04 (2018\-07\-05 at 09:17:13) .SH "SYNOPSIS" .IX Header "SYNOPSIS" genome music bmr calc-bmr \-\-bmr\-output=? \-\-roi\-file=? \-\-gene\-mr\-file=? \-\-reference\-sequence=? \-\-bam\-list=? \-\-output\-dir=? \-\-maf\-file=? [\-\-skip\-non\-coding] [\-\-skip\-silent] [\-\-bmr\-groups=?] [\-\-show\-skipped] [\-\-separate\-truncations] [\-\-merge\-concurrent\-muts] [\-\-genes\-to\-ignore=?] .PP .Vb 6 \& ... music bmr calc\-bmr \e \& \-\-bam\-list input_dir/bam_list \e \& \-\-maf\-file input_dir/myMAF.tsv \e \& \-\-output\-dir output_dir/ \e \& \-\-reference\-sequence input_dir/all_sequences.fa \e \& \-\-roi\-file input_dir/all_coding_exons.tsv \& \& ... music bmr calc\-bmr \e \& \-\-bam\-list input_dir/bam_list \e \& \-\-maf\-file input_dir/myMAF.tsv \e \& \-\-output\-dir output_dir/ \e \& \-\-reference\-sequence input_dir/all_sequences.fa \e \& \-\-roi\-file input_dir/all_coding_exons.tsv \e \& \-\-genes\-to\-ignore GENE1,GENE2 .Ve .SH "REQUIRED ARGUMENTS" .IX Header "REQUIRED ARGUMENTS" .IP "bmr-output \fINumber\fR" 4 .IX Item "bmr-output Number" \&\s-1TODO\s0 .IP "roi-file \fIText\fR" 4 .IX Item "roi-file Text" Tab delimited list of ROIs [chr start stop gene_name] (See \s-1DESCRIPTION\s0) .IP "gene-mr-file \fIText\fR" 4 .IX Item "gene-mr-file Text" \&\s-1TODO\s0 .IP "reference-sequence \fIText\fR" 4 .IX Item "reference-sequence Text" Path to reference sequence in \s-1FASTA\s0 format .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 \s-1DESCRIPTION\s0) .IP "output-dir \fIText\fR" 4 .IX Item "output-dir Text" Directory where output files will be written (Use the same one used with calc-covg) .IP "maf-file \fIText\fR" 4 .IX Item "maf-file Text" List of mutations using \s-1TCGA MAF\s0 specification v2.3 .SH "OPTIONAL ARGUMENTS" .IX Header "OPTIONAL ARGUMENTS" .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' .IP "bmr-groups \fIInteger\fR" 4 .IX Item "bmr-groups Integer" Number of clusters of samples with comparable BMRs (See \s-1DESCRIPTION\s0) .Sp Default value '1' if not specified .IP "show-skipped \fIBoolean\fR" 4 .IX Item "show-skipped Boolean" Report each skipped mutation, not just how many .Sp Default value 'false' (\-\-noshow\-skipped) if not specified .IP "noshow-skipped \fIBoolean\fR" 4 .IX Item "noshow-skipped Boolean" Make show-skipped 'false' .IP "separate-truncations \fIBoolean\fR" 4 .IX Item "separate-truncations Boolean" Group truncational mutations as a separate category .Sp Default value 'false' (\-\-noseparate\-truncations) if not specified .IP "noseparate-truncations \fIBoolean\fR" 4 .IX Item "noseparate-truncations Boolean" Make separate-truncations 'false' .IP "merge-concurrent-muts \fIBoolean\fR" 4 .IX Item "merge-concurrent-muts Boolean" Multiple mutations of a gene in the same sample are treated as 1 .Sp Default value 'false' (\-\-nomerge\-concurrent\-muts) if not specified .IP "nomerge-concurrent-muts \fIBoolean\fR" 4 .IX Item "nomerge-concurrent-muts Boolean" Make merge-concurrent-muts 'false' .IP "genes-to-ignore \fIText\fR" 4 .IX Item "genes-to-ignore Text" Comma-delimited list of genes to ignore for background mutation rates .SH "DESCRIPTION" .IX Header "DESCRIPTION" Given a mutation list (\s-1MAF\s0), and per-gene coverage data calculated using \*(L"music bmr calc-covg\*(R"), this script calculates overall Background Mutation Rate (\s-1BMR\s0) and BMRs in the categories of AT/CG/CpG Transitions, AT/CG/CpG Transversions, and Indels. An optional category for truncational mutations can also be specified. The script generates a file with per-gene mutation rates that can be used with the tool that tests for significantly mutated genes (music smg). .SH "ARGUMENTS" .IX Header "ARGUMENTS" .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). ROIs from the same chromosome must be listed adjacent to each other in this file. This allows the underlying C\-based code to run much more efficiently and avoid re-counting bases seen in overlapping ROIs (for overall covered base counts). 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). ROIs from the same chromosome must be listed adjacent to each other in this file. This allows the underlying C-based code to run much more efficiently and avoid re-counting bases seen in overlapping ROIs (for overall covered base counts). 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 "\-\-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. 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 normal/tumor BAM locations for each. Use the tab- delimited format [sample_name normal_bam tumor_bam] 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 "\-\-bmr\-groups" 4 .IX Item "--bmr-groups" .RS 4 .IP "Ideally, we want to test the mutation rate (\s-1MR\s0) of a gene in a sample against the background mutation rate (\s-1BMR\s0) across that sample. But if the BMRs of some samples are comparable, we can instead test the \s-1MR\s0 of a gene across a group of samples with comparable \s-1BMR,\s0 against the overall \s-1BMR\s0 of that group. This argument specifies how many such groups you want to cluster samples into. By default, it is assumed that all samples have comparable BMRs (bmr-groups = 1)." 8 .IX Item "Ideally, we want to test the mutation rate (MR) of a gene in a sample against the background mutation rate (BMR) across that sample. But if the BMRs of some samples are comparable, we can instead test the MR of a gene across a group of samples with comparable BMR, against the overall BMR of that group. This argument specifies how many such groups you want to cluster samples into. By default, it is assumed that all samples have comparable BMRs (bmr-groups = 1)." .RE .RS 4 .RE .IP "\-\-output\-dir" 4 .IX Item "--output-dir" .RS 4 .ie n .IP "This should be the same output directory used when running ""music bmr calc-covg"". The following outputs of this script will also be created/written: overall_bmrs: File containing categorized overall background mutation rates. gene_mrs: File containing categorized per-gene mutation rates." 8 .el .IP "This should be the same output directory used when running ``music bmr calc-covg''. The following outputs of this script will also be created/written: overall_bmrs: File containing categorized overall background mutation rates. gene_mrs: File containing categorized per-gene mutation rates." 8 .IX Item "This should be the same output directory used when running music bmr calc-covg. The following outputs of this script will also be created/written: overall_bmrs: File containing categorized overall background mutation rates. gene_mrs: File containing categorized per-gene mutation rates." .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 for overall \s-1BMR\s0 calculations. List genes that are known factors in this disease and whose mutations should not be classified as background." 8 .IX Item "A comma-delimited list of genes to ignore for overall BMR calculations. List genes that are known factors in this disease and whose mutations should not be classified as background." .RE .RS 4 .RE .PD .SH "LICENSE" .IX Header "LICENSE" Copyright (C) 2010\-2011 Washington University in St. Louis. .PP It is released under the Lesser \s-1GNU\s0 Public License (\s-1LGPL\s0) version 3. See the associated \s-1LICENSE\s0 file in this distribution. .SH "AUTHORS" .IX Header "AUTHORS" .Vb 1 \& Cyriac Kandoth, Ph.D. .Ve .SH "SEE ALSO" .IX Header "SEE ALSO" \&\fBgenome-music-bmr\fR(1), \&\fBgenome-music\fR(1), \&\fBgenome\fR(1)