| 1 |
.\" DO NOT MODIFY THIS FILE! It was generated by help2man 1.49.3. |
| 2 |
.TH CNVKIT_BATCH "1" "July 2023" "cnvkit.py batch 0.9.10" "User Commands" |
| 3 |
.SH NAME |
| 4 |
cnvkit_batch \- Run the complete CNVkit pipeline on one or more BAM files. |
| 5 |
.SH DESCRIPTION |
| 6 |
usage: cnvkit.py batch [\-h] [\-m {hybrid,amplicon,wgs}] |
| 7 |
.TP |
| 8 |
[\-\-segment\-method {cbs,flasso,haar,none,hmm,hmm\-tumor,hmm\-germline}] |
| 9 |
[\-y] [\-c] [\-\-drop\-low\-coverage] [\-p [PROCESSES]] |
| 10 |
[\-\-rscript\-path PATH] [\-n [FILES ...]] [\-f FILENAME] |
| 11 |
[\-t FILENAME] [\-a FILENAME] [\-\-annotate FILENAME] |
| 12 |
[\-\-short\-names] [\-\-target\-avg\-size TARGET_AVG_SIZE] |
| 13 |
[\-g FILENAME] |
| 14 |
[\-\-antitarget\-avg\-size ANTITARGET_AVG_SIZE] |
| 15 |
[\-\-antitarget\-min\-size ANTITARGET_MIN_SIZE] |
| 16 |
[\-\-output\-reference FILENAME] [\-\-cluster] |
| 17 |
[\-r REFERENCE] [\-d DIRECTORY] [\-\-scatter] [\-\-diagram] |
| 18 |
[bam_files ...] |
| 19 |
.SS "positional arguments:" |
| 20 |
.TP |
| 21 |
bam_files |
| 22 |
Mapped sequence reads (.bam) |
| 23 |
.SS "options:" |
| 24 |
.TP |
| 25 |
\fB\-h\fR, \fB\-\-help\fR |
| 26 |
show this help message and exit |
| 27 |
.TP |
| 28 |
\fB\-m\fR {hybrid,amplicon,wgs}, \fB\-\-seq\-method\fR {hybrid,amplicon,wgs}, \fB\-\-method\fR {hybrid,amplicon,wgs} |
| 29 |
Sequencing assay type: hybridization capture |
| 30 |
('hybrid'), targeted amplicon sequencing ('amplicon'), |
| 31 |
or whole genome sequencing ('wgs'). Determines whether |
| 32 |
and how to use antitarget bins. [Default: hybrid] |
| 33 |
.TP |
| 34 |
\fB\-\-segment\-method\fR {cbs,flasso,haar,none,hmm,hmm\-tumor,hmm\-germline} |
| 35 |
Method used in the 'segment' step. [Default: cbs] |
| 36 |
.TP |
| 37 |
\fB\-y\fR, \fB\-\-male\-reference\fR, \fB\-\-haploid\-x\-reference\fR |
| 38 |
Use or assume a male reference (i.e. female samples |
| 39 |
will have +1 log\-CNR of chrX; otherwise male samples |
| 40 |
would have \fB\-1\fR chrX). |
| 41 |
.TP |
| 42 |
\fB\-c\fR, \fB\-\-count\-reads\fR |
| 43 |
Get read depths by counting read midpoints within each |
| 44 |
bin. (An alternative algorithm). |
| 45 |
.TP |
| 46 |
\fB\-\-drop\-low\-coverage\fR |
| 47 |
Drop very\-low\-coverage bins before segmentation to |
| 48 |
avoid false\-positive deletions in poor\-quality tumor |
| 49 |
samples. |
| 50 |
.TP |
| 51 |
\fB\-p\fR [PROCESSES], \fB\-\-processes\fR [PROCESSES] |
| 52 |
Number of subprocesses used to running each of the BAM |
| 53 |
files in parallel. Without an argument, use the |
| 54 |
maximum number of available CPUs. [Default: process |
| 55 |
each BAM in serial] |
| 56 |
.TP |
| 57 |
\fB\-\-rscript\-path\fR PATH |
| 58 |
Path to the Rscript executable to use for running R |
| 59 |
code. Use this option to specify a non\-default R |
| 60 |
installation. [Default: Rscript] |
| 61 |
.SS "To construct a new copy number reference:" |
| 62 |
.TP |
| 63 |
\fB\-n\fR [FILES ...], \fB\-\-normal\fR [FILES ...] |
| 64 |
Normal samples (.bam) used to construct the pooled, |
| 65 |
paired, or flat reference. If this option is used but |
| 66 |
no filenames are given, a "flat" reference will be |
| 67 |
built. Otherwise, all filenames following this option |
| 68 |
will be used. |
| 69 |
.TP |
| 70 |
\fB\-f\fR FILENAME, \fB\-\-fasta\fR FILENAME |
| 71 |
Reference genome, FASTA format (e.g. UCSC hg19.fa) |
| 72 |
.TP |
| 73 |
\fB\-t\fR FILENAME, \fB\-\-targets\fR FILENAME |
| 74 |
Target intervals (.bed or .list) |
| 75 |
.TP |
| 76 |
\fB\-a\fR FILENAME, \fB\-\-antitargets\fR FILENAME |
| 77 |
Antitarget intervals (.bed or .list) |
| 78 |
.TP |
| 79 |
\fB\-\-annotate\fR FILENAME |
| 80 |
Use gene models from this file to assign names to the |
| 81 |
target regions. Format: UCSC refFlat.txt or |
| 82 |
ensFlat.txt file (preferred), or BED, interval list, |
| 83 |
GFF, or similar. |
| 84 |
.TP |
| 85 |
\fB\-\-short\-names\fR |
| 86 |
Reduce multi\-accession bait labels to be short and |
| 87 |
consistent. |
| 88 |
.TP |
| 89 |
\fB\-\-target\-avg\-size\fR TARGET_AVG_SIZE |
| 90 |
Average size of split target bins (results are |
| 91 |
approximate). |
| 92 |
.TP |
| 93 |
\fB\-g\fR FILENAME, \fB\-\-access\fR FILENAME |
| 94 |
Regions of accessible sequence on chromosomes (.bed), |
| 95 |
as output by the 'access' command. |
| 96 |
.TP |
| 97 |
\fB\-\-antitarget\-avg\-size\fR ANTITARGET_AVG_SIZE |
| 98 |
Average size of antitarget bins (results are |
| 99 |
approximate). |
| 100 |
.TP |
| 101 |
\fB\-\-antitarget\-min\-size\fR ANTITARGET_MIN_SIZE |
| 102 |
Minimum size of antitarget bins (smaller regions are |
| 103 |
dropped). |
| 104 |
.TP |
| 105 |
\fB\-\-output\-reference\fR FILENAME |
| 106 |
Output filename/path for the new reference file being |
| 107 |
created. (If given, ignores the \fB\-o\fR/\-\-output\-dir option |
| 108 |
and will write the file to the given path. Otherwise, |
| 109 |
"reference.cnn" will be created in the current |
| 110 |
directory or specified output directory.) |
| 111 |
.TP |
| 112 |
\fB\-\-cluster\fR |
| 113 |
Calculate and use cluster\-specific summary stats in |
| 114 |
the reference pool to normalize samples. |
| 115 |
.SS "To reuse an existing reference:" |
| 116 |
.TP |
| 117 |
\fB\-r\fR REFERENCE, \fB\-\-reference\fR REFERENCE |
| 118 |
Copy number reference file (.cnn). |
| 119 |
.SS "Output options:" |
| 120 |
.TP |
| 121 |
\fB\-d\fR DIRECTORY, \fB\-\-output\-dir\fR DIRECTORY |
| 122 |
Output directory. |
| 123 |
.TP |
| 124 |
\fB\-\-scatter\fR |
| 125 |
Create a whole\-genome copy ratio profile as a PDF |
| 126 |
scatter plot. |
| 127 |
.TP |
| 128 |
\fB\-\-diagram\fR |
| 129 |
Create an ideogram of copy ratios on chromosomes as a |
| 130 |
PDF. |