This is an automated email from the git hooks/post-receive script. tille pushed a commit to branch master in repository ea-utils.
commit 998408fe954cccc2f48d4c244a7ab66903e88900 Author: Andreas Tille <[email protected]> Date: Sat Jul 25 09:08:18 2015 +0200 Add several help2man generated manpages --- debian/createmanpages | 35 +++++++++- debian/man/alc.1 | 14 ++++ debian/man/determine-phred.1 | 11 ++++ debian/man/fastq-clipper.1 | 38 +++++++++++ debian/man/fastq-join.1 | 34 ++++++++++ debian/man/fastq-mcf.1 | 148 +++++++++++++++++++++++++++++++++++++++++++ debian/man/fastq-multx.1 | 50 +++++++++++++++ debian/man/fastq-stats.1 | 66 +++++++++++++++++++ debian/man/fastx-graph.1 | 23 +++++++ debian/manpages | 1 + 10 files changed, 417 insertions(+), 3 deletions(-) diff --git a/debian/createmanpages b/debian/createmanpages index febcd91..6f2851d 100755 --- a/debian/createmanpages +++ b/debian/createmanpages @@ -1,12 +1,41 @@ #!/bin/sh -MANDIR=debian +MANDIR=debian/man mkdir -p $MANDIR VERSION=`dpkg-parsechangelog | awk '/^Version:/ {print $2}' | sed -e 's/^[0-9]*://' -e 's/-.*//' -e 's/[+~]dfsg$//'` help2man --no-info --no-discard-stderr --help-option=" " \ - --name='<optional description of the program>' \ - --version-string="$VERSION" <programname> > $MANDIR/<programname>.1 + --name='ea-utils: Approximate line counts for each file.' \ + --version-string="$VERSION" alc > $MANDIR/alc.1 + +help2man --no-info --no-discard-stderr --help-option="-h" \ + --name='ea-utils: read sam, fastq or pileup and return the phred-scale' \ + --version-string="$VERSION" determine-phred > $MANDIR/determine-phred.1 + +help2man --no-info --no-discard-stderr --help-option="-h" \ + --name='ea-utils: removes one or more adapter sequences from the fastq file' \ + --version-string="$VERSION" fastq-clipper > $MANDIR/fastq-clipper.1 + +help2man --no-info --no-discard-stderr --help-option="-h" \ + --name='ea-utils: join two paired-end reads on the overlapping ends' \ + --version-string="$VERSION" fastq-join > $MANDIR/fastq-join.1 + +help2man --no-info --no-discard-stderr --help-option="-h" \ + --name='ea-utils: detect levels of adapter presence, compute likelihoods and locations of the adapters' \ + --version-string="$VERSION" fastq-mcf > $MANDIR/fastq-mcf.1 + +help2man --no-info --no-discard-stderr --help-option="-h" \ + --name='ea-utils: replace '%' with the barcode id in the barcodes file' \ + --version-string="$VERSION" fastq-multx > $MANDIR/fastq-multx.1 + +help2man --no-info --no-discard-stderr --help-option="-h" \ + --name='ea-utils: produce lots of easily digested statistics' \ + --version-string="$VERSION" fastq-stats > $MANDIR/fastq-stats.1 + +LC_ALL=C help2man --no-info --no-discard-stderr --help-option="-h" \ + --name='ea-utils: R script to process fastq-stats output' \ + --version-string="$VERSION" fastx-graph \ + | sed -e '/^Loading/d' -e '/Attaching package/d' -e '/^The following objects are masked from/d' -e '/^format.pval/d' > $MANDIR/fastx-graph.1 cat <<EOT Please enhance the help2man output. diff --git a/debian/man/alc.1 b/debian/man/alc.1 new file mode 100644 index 0000000..c34d808 --- /dev/null +++ b/debian/man/alc.1 @@ -0,0 +1,14 @@ +.\" DO NOT MODIFY THIS FILE! It was generated by help2man 1.47.1. +.TH ALC "1" "July 2015" "alc 1.1.2" "User Commands" +.SH NAME +alc \- ea-utils: Approximate line counts for each file. +.SH SYNOPSIS +.B alc +[\fI\,-o\/\fR] \fI\,<file1> \/\fR[\fI\,<file2>\/\fR] ... +.SH DESCRIPTION +Approximate line counts for each file. Attempts to be +somewhat compatible with "wc \fB\-l\fR" by default. +.PP +\fB\-o\fR|\-\-only Output line count only for a single file. +\fB\-w\fR|\-\-window <int> Read <int> bytes from head, mid, and tail. +\fB\-s\fR|\-\-segs <int> Divide file & window into <int> segments. diff --git a/debian/man/determine-phred.1 b/debian/man/determine-phred.1 new file mode 100644 index 0000000..61e47d6 --- /dev/null +++ b/debian/man/determine-phred.1 @@ -0,0 +1,11 @@ +.\" DO NOT MODIFY THIS FILE! It was generated by help2man 1.47.1. +.TH DETERMINE-PHRED "1" "July 2015" "determine-phred 1.1.2" "User Commands" +.SH NAME +determine-phred \- ea-utils: read sam, fastq or pileup and return the phred-scale +.SH SYNOPSIS +.B determine-phred +\fI\,FILE\/\fR +.SH DESCRIPTION +Reads a sam, fastq or pileup, possibly gzipped and returns the phred\-scale, +.IP +either 64 or 33, based on a quick scan of the data in the file. diff --git a/debian/man/fastq-clipper.1 b/debian/man/fastq-clipper.1 new file mode 100644 index 0000000..c2e705d --- /dev/null +++ b/debian/man/fastq-clipper.1 @@ -0,0 +1,38 @@ +.\" DO NOT MODIFY THIS FILE! It was generated by help2man 1.47.1. +.TH FASTQ-CLIPPER "1" "July 2015" "fastq-clipper 1.1.2" "User Commands" +.SH NAME +fastq-clipper \- ea-utils: removes one or more adapter sequences from the fastq file +.SH DESCRIPTION +usage: fastq\-clipper [options] <fastq\-file> <adapters> +.PP +Removes one or more adapter sequences from the fastq file. +Adapter sequences are colon\-delimited. +Stats go to stderr, unless \fB\-o\fR is specified. +.SH OPTIONS +.TP +\fB\-h\fR +This help +.TP +\fB\-o\fR FIL +Output file (stats to stdout) +.TP +\fB\-p\fR N +Maximum difference percentage (10) +.TP +\fB\-m\fR N +Minimum clip length (1) +.TP +\fB\-l\fR N +Minimum remaining sequence length (15) +.TP +\fB\-x\fR [N] +Extra match length past adapter length, +.IP +N =\-1 : search all +N = 0 : search only up to adapter length +.TP +\fB\-e\fR +End\-of\-line (default) +.TP +\fB\-b\fR +Beginning\-of\-line (not supported yet) diff --git a/debian/man/fastq-join.1 b/debian/man/fastq-join.1 new file mode 100644 index 0000000..b311344 --- /dev/null +++ b/debian/man/fastq-join.1 @@ -0,0 +1,34 @@ +.\" DO NOT MODIFY THIS FILE! It was generated by help2man 1.47.1. +.TH FASTQ-JOIN "1" "July 2015" "fastq-join 1.1.2" "User Commands" +.SH NAME +fastq-join \- ea-utils: join two paired-end reads on the overlapping ends +.SH SYNOPSIS +.B fastq-join +[\fI\,options\/\fR] \fI\,<read1.fq> <read2.fq> \/\fR[\fI\,mate.fq\/\fR] \fI\,-o <read.%.fq>\/\fR +.SH DESCRIPTION +fastq\-join: invalid option \fB\-\-\fR 'h' +Unknown option `\-h'. +.PP +Joins two paired\-end reads on the overlapping ends. +.SH OPTIONS +\fB\-o\fR FIL See 'Output' below +\fB\-v\fR C Verifies that the 2 files probe id's match up to char C +.IP +use ' ' (space) for Illumina reads +.PP +\fB\-p\fR N N\-percent maximum difference (8) +\fB\-m\fR N N\-minimum overlap (6) +\fB\-r\fR FIL Verbose stitch length report +\fB\-R\fR No reverse complement +\fB\-x\fR Allow insert < read length +.PP +Output: +.IP +You can supply 3 \fB\-o\fR arguments, for un1, un2, join files, or one +.PP +argument as a file name template. The suffix 'un1, un2, or join' is +appended to the file, or they replace a %\-character if present. +.IP +If a 'mate' input file is present (barcode read), then the files +.PP +\&'un3' and 'join2' are also created. diff --git a/debian/man/fastq-mcf.1 b/debian/man/fastq-mcf.1 new file mode 100644 index 0000000..ea04561 --- /dev/null +++ b/debian/man/fastq-mcf.1 @@ -0,0 +1,148 @@ +.\" DO NOT MODIFY THIS FILE! It was generated by help2man 1.47.1. +.TH FASTQ-MCF "1" "July 2015" "fastq-mcf 1.1.2" "User Commands" +.SH NAME +fastq-mcf \- ea-utils: detect levels of adapter presence, compute likelihoods and locations of the adapters +.SH SYNOPSIS +.B fastq-mcf +[\fI\,options\/\fR] \fI\,<adapters.fa> <reads.fq> \/\fR[\fI\,mates1.fq \/\fR...] +.SH DESCRIPTION +Version: 1.04.676 +.PP +Detects levels of adapter presence, computes likelihoods and +locations (start, end) of the adapters. Removes the adapter +sequences from the fastq file(s). +.PP +Stats go to stderr, unless \fB\-o\fR is specified. +.PP +Specify \fB\-0\fR to turn off all default settings +.PP +If you specify multiple 'paired\-end' inputs, then a \fB\-o\fR option is +required for each. IE: \fB\-o\fR read1.clip.q \fB\-o\fR read2.clip.fq +.SH OPTIONS +.TP +\fB\-h\fR +This help +.TP +\fB\-o\fR FIL +Output file (stats to stdout) +.TP +\fB\-s\fR N.N +Log scale for adapter minimum\-length\-match (2.2) +.TP +\fB\-t\fR N +% occurance threshold before adapter clipping (0.25) +.TP +\fB\-m\fR N +Minimum clip length, overrides scaled auto (1) +.TP +\fB\-p\fR N +Maximum adapter difference percentage (10) +.TP +\fB\-l\fR N +Minimum remaining sequence length (19) +.TP +\fB\-L\fR N +Maximum remaining sequence length (none) +.TP +\fB\-D\fR N +Remove duplicate reads : Read_1 has an identical N bases (0) +.TP +\fB\-k\fR N +sKew percentage\-less\-than causing cycle removal (2) +.TP +\fB\-x\fR N +\&'N' (Bad read) percentage causing cycle removal (20) +.TP +\fB\-q\fR N +quality threshold causing base removal (10) +.TP +\fB\-w\fR N +window\-size for quality trimming (1) +.TP +\fB\-H\fR +remove >95% homopolymer reads (no) +.TP +\fB\-X\fR +remove low complexity reads (no) +.TP +\fB\-0\fR +Set all default parameters to zero/do nothing +.TP +\fB\-U\fR|u +Force disable/enable Illumina PF filtering (auto) +.TP +\fB\-P\fR N +Phred\-scale (auto) +.TP +\fB\-R\fR +Don't remove N's from the fronts/ends of reads +.TP +\fB\-n\fR +Don't clip, just output what would be done +.TP +\fB\-C\fR N +Number of reads to use for subsampling (300k) +.TP +\fB\-S\fR +Save all discarded reads to '.skip' files +.TP +\fB\-d\fR +Output lots of random debugging stuff +.SS "Quality adjustment options:" +.TP +\fB\-\-cycle\-adjust\fR +CYC,AMT Adjust cycle CYC (negative = offset from end) by amount AMT +.TP +\fB\-\-phred\-adjust\fR +SCORE,AMT Adjust score SCORE by amount AMT +.TP +\fB\-\-phred\-adjust\-max\fR +SCORE Adjust scores > SCORE to SCOTE +.SS "Filtering options*:" +.TP +\fB\-\-[mate\-]qual\-mean\fR +NUM Minimum mean quality score +.TP +\fB\-\-[mate\-]qual\-gt\fR +NUM,THR At least NUM quals > THR +.TP +\fB\-\-[mate\-]max\-ns\fR +NUM Maxmium N\-calls in a read (can be a %) +.TP +\fB\-\-[mate\-]min\-len\fR +NUM Minimum remaining length (same as \fB\-l\fR) +.TP +\fB\-\-homopolymer\-pct\fR +PCT Homopolymer filter percent (95) +.TP +\fB\-\-lowcomplex\-pct\fR +PCT Complexity filter percent (95) +.PP +If mate\- prefix is used, then applies to second non\-barcode read only +.PP +Adapter files are 'fasta' formatted: +.PP +Specify n/a to turn off adapter clipping, and just use filters +.PP +Increasing the scale makes recognition\-lengths longer, a scale +of 100 will force full\-length recognition of adapters. +.PP +Adapter sequences with _5p in their label will match 'end's, +and sequences with _3p in their label will match 'start's, +otherwise the 'end' is auto\-determined. +.PP +Skew is when one cycle is poor, 'skewed' toward a particular base. +If any nucleotide is less than the skew percentage, then the +whole cycle is removed. Disable for methyl\-seq, etc. +.PP +Set the skew (\fB\-k\fR) or N\-pct (\fB\-x\fR) to 0 to turn it off (should be done +for miRNA, amplicon and other low\-complexity situations!) +.PP +Duplicate read filtering is appropriate for assembly tasks, and +never when read length < expected coverage. \fB\-D\fR 50 will use +4.5GB RAM on 100m DNA reads \- be careful. Great for RNA assembly. +.PP +*Quality filters are evaluated after clipping/trimming +.PP +Homopolymer filtering is a subset of low\-complexity, but will not +be separately tracked unless both are turned on. diff --git a/debian/man/fastq-multx.1 b/debian/man/fastq-multx.1 new file mode 100644 index 0000000..04a12e7 --- /dev/null +++ b/debian/man/fastq-multx.1 @@ -0,0 +1,50 @@ +.\" DO NOT MODIFY THIS FILE! It was generated by help2man 1.47.1. +.TH FASTQ-MULTX "1" "July 2015" "fastq-multx 1.1.2" "User Commands" +.SH NAME +fastq-multx \- ea-utils: replace % with the barcode id in the barcodes file +.SH SYNOPSIS +.B fastq-multx +[\fI\,-g|-l|-B\/\fR] \fI\,<barcodes.fil> <read1.fq> -o r1.%.fq \/\fR[\fI\,mate.fq -o r2.%.fq\/\fR] ... +.SH DESCRIPTION +fastq\-multx: invalid option \fB\-\-\fR 'h' +Unknown option `\-h'. +.PP +Version: 1.02.684 +.PP +Output files must contain a '%' sign which is replaced with the barcode id in the barcodes file. +Output file can be n/a to discard the corresponding data (use this for the barcode read) +.PP +Barcodes file (\fB\-B\fR) looks like this: +.PP +<id1> <sequence1> +<id2> <sequence2> ... +.PP +Default is to guess the \fB\-bol\fR or \fB\-eol\fR based on clear stats. +.PP +If \fB\-g\fR is used, then it's parameter is an index lane, and frequently occuring sequences are used. +.PP +If \fB\-l\fR is used then all barcodes in the file are tried, and the *group* with the *most* matches is chosen. +.PP +Grouped barcodes file (\fB\-l\fR or \fB\-L\fR) looks like this: +.PP +<id1> <sequence1> <group1> +<id1> <sequence1> <group1> +<id2> <sequence2> <group2>... +.PP +Mated reads, if supplied, are kept in\-sync +.SH OPTIONS +\fB\-o\fR FIL1 Output files (one per input, required) +\fB\-g\fR SEQFIL Determine barcodes from indexed read SEQFIL +\fB\-l\fR BCFIL Determine barcodes from any read, using BCFIL as a master list +\fB\-L\fR BCFIL Determine barcodes from <read1.fq>, using BCFIL as a master list +\fB\-B\fR BCFIL Use barcodes from the specified file, don't run a determination step +\fB\-b\fR Force beginning of line (5') for barcode matching +\fB\-e\fR Force end of line (3') for batcode matching +\fB\-t\fR NUM Divide threshold for auto\-determine by factor NUM (1), > 1 = more sensitive +\fB\-G\fR NAME Use group(s) matching NAME only +\fB\-x\fR Don't trim barcodes off before writing out destination +\fB\-n\fR Don't execute, just print likely barcode list +\fB\-v\fR C Verify that mated id's match up to character C (Use ' ' for illumina) +\fB\-m\fR N Allow up to N mismatches, as long as they are unique (1) +\fB\-d\fR N Require a minimum distance of N between the best and next best (2) +\fB\-q\fR N Require a minimum phred quality of N to accept a barcode base (0) diff --git a/debian/man/fastq-stats.1 b/debian/man/fastq-stats.1 new file mode 100644 index 0000000..9836370 --- /dev/null +++ b/debian/man/fastq-stats.1 @@ -0,0 +1,66 @@ +.\" DO NOT MODIFY THIS FILE! It was generated by help2man 1.47.1. +.TH FASTQ-STATS "1" "July 2015" "fastq-stats 1.1.2" "User Commands" +.SH NAME +fastq-stats \- ea-utils: produce lots of easily digested statistics +.SH SYNOPSIS +.B fastq-stats +[\fI\,options\/\fR] \fI\,<fastq-file>\/\fR +.SH DESCRIPTION +Version: 1.01 $Id: fastq\-stats.cpp 652 2013\-09\-17 17:40:32Z earonesty $ +.PP +Produces lots of easily digested statistics for the files listed +.PP +Options +.PP +\fB\-c\fR cyclemax: max cycles for which following quality stats are produced [35] +\fB\-w\fR INT window: max window size for generating duplicate read statistics [2000000] +\fB\-d\fR debug: prints out debug statements +\fB\-D\fR don't do duplicate read statistics +\fB\-s\fR INT number of top duplicate reads to display +\fB\-x\fR FIL output fastx statistics (requires an output filename) +\fB\-b\fR FIL output base breakdown by per phred quality at every cycle. +.IP +It sets cylemax to longest read length +.PP +\fB\-L\fR FIL Output length counts +.PP +The following data are printed to stdout: +.TP +reads +: #reads in the fastq file +.TP +len +: read length. mean and stdev are provided for variable read lengths +.TP +phred +: phred scale used +.TP +window\-size +: Number of reads used to generate duplicate read statistics +.TP +cycle\-max +: Number of bases to assess for duplicity +.TP +dups +: Number of reads that are duplicates +.TP +%dup +: Pct reads that are duplcate +.TP +unique\-dup seq +: Number sequences that are duplicated +.TP +min dup count +: Smallest duplicate tally for any duplicate sequence +.TP +dup seq <rank> <count> <sequence> +: Lists top 10 most frequent duplicate reads along with count mean and stdev +.TP +qual +: Base Quality min, max and mean +.TP +%A,%T,%C,%G +: base percentages +.TP +total bases +: total number of bases diff --git a/debian/man/fastx-graph.1 b/debian/man/fastx-graph.1 new file mode 100644 index 0000000..117cd19 --- /dev/null +++ b/debian/man/fastx-graph.1 @@ -0,0 +1,23 @@ +.\" DO NOT MODIFY THIS FILE! It was generated by help2man 1.47.1. +.TH FASTX-GRAPH "1" "July 2015" "fastx-graph 1.1.2" "User Commands" +.SH NAME +fastx-graph \- ea-utils: R script to process fastq-stats output +.SH SYNOPSIS +.B fastx-graph +[\fI\,-\/\fR[\fI\,-input|i\/\fR] \fI\,<character>\/\fR] [\fI\,-\/\fR[\fI\,-gc|G\/\fR] \fI\,<character>\/\fR] [\fI\,-\/\fR[\fI\,-out|o\/\fR] \fI\,<character>\/\fR] [\fI\,-\/\fR[\fI\,-help|h\/\fR]] +.SH DESCRIPTION +.PP +.PP +.IP +.TP +\fB\-i\fR|\-\-input +file from fastq\-stats \fB\-x\fR (required) +.TP +\fB\-G\fR|\-\-gc +input gc content file (optional) +.TP +\fB\-o\fR|\-\-out +output filename (optional) +.TP +\fB\-h\fR|\-\-help +this help diff --git a/debian/manpages b/debian/manpages new file mode 100644 index 0000000..13cdaf4 --- /dev/null +++ b/debian/manpages @@ -0,0 +1 @@ +debian/man/*.1 -- Alioth's /usr/local/bin/git-commit-notice on /srv/git.debian.org/git/debian-med/ea-utils.git _______________________________________________ debian-med-commit mailing list [email protected] http://lists.alioth.debian.org/cgi-bin/mailman/listinfo/debian-med-commit
