debian/changelog

-scoary (1.6.16-1) UNRELEASED; urgency=medium
+scoary (1.6.16-1) unstable; urgency=medium
 
-  * Initial release (Closes: #nnnn)
+  * Initial release (Closes: #920857)
 
- -- Andreas Tille <tille@debian.org>  Tue, 29 Jan 2019 18:26:15 +0100
+ -- Andreas Tille <tille@debian.org>  Tue, 29 Jan 2019 22:07:27 +0100

debian/createmanpages

+#!/bin/sh
+MANDIR=debian
+mkdir -p $MANDIR
+
+VERSION=`dpkg-parsechangelog | awk '/^Version:/ {print $2}' | sed -e 's/^[0-9]*://' -e 's/-.*//' -e 's/[+~]dfsg$//'`
+NAME=`grep "^Description:" debian/control | sed 's/^Description: *//' | head -n1`
+PROGNAME=`grep "^Package:" debian/control | sed 's/^Package: *//' | head -n1`
+
+AUTHOR=".SH AUTHOR\nThis manpage was written by $DEBFULLNAME for the Debian distribution and
+can be used for any other usage of the program.
+"
+
+# If program name is different from package name or title should be
+# different from package short description change this here
+progname=${PROGNAME}
+help2man --no-info --no-discard-stderr \
+         --name="$NAME" \
+            --version-string="$VERSION" ${progname} > $MANDIR/${progname}.1
+echo $AUTHOR >> $MANDIR/${progname}.1
+
+progname=vcf2scoary
+help2man --no-info --no-discard-stderr  \
+         --name="takes in vcf files and creates a presence/absence matrix of mutations in the Roary/Scoary format" \
+            --version-string="$VERSION" ${progname} > $MANDIR/${progname}.1
+echo $AUTHOR >> $MANDIR/${progname}.1
+
+echo "$MANDIR/*.1" > debian/manpages
+
+cat <<EOT
+Please enhance the help2man output.
+The following web page might be helpful in doing so:
+    http://liw.fi/manpages/
+EOT

debian/manpages

-debian/scoary.1
+debian/*.1

debian/rules

@@ -5,3 +5,8 @@ export LC_ALL = C.UTF-8
 
 %:
 	dh $@ --with python2 --buildsystem=pybuild
+
+override_dh_auto_test:
+ifeq (,$(filter nocheck,$(DEB_BUILD_OPTIONS)))
+	echo "Test data are missing so we can not test"
+endif

debian/scoary.1

-.TH SCOARY 1 "January 2017"
+.\" DO NOT MODIFY THIS FILE!  It was generated by help2man 1.47.8.
+.TH SCOARY "1" "January 2019" "scoary 1.6.16" "User Commands"
 .SH NAME
-scoary \- pangenome\-wide association studies
+scoary \- pangenome-wide association studies
 .SH SYNOPSIS
-.B scoary
-.RI [ options ] " files" ...
-.SH DESCRIPTION
-\fBscoary\fP is designed to take the gene_presence_absence.csv file from
-.BR roary (1)
-as well as a traits file created by the user and calculate the assocations between all genes in the accessory genome and the traits.
-It reports a list of genes sorted by strength of association per trait.
+scoary [\-h] [\-t TRAITS] [\-g GENES] [\-n NEWICKTREE] [\-s START_COL]
+[\-\-delimiter DELIMITER] [\-r RESTRICT_TO] [\-o OUTDIR] [\-u]
+[\-p P_VALUE_CUTOFF [P_VALUE_CUTOFF ...]]
+[\-c [{I,B,BH,PW,EPW,P} [{I,B,BH,PW,EPW,P} ...]]] [\-m MAX_HITS]
+[\-\-include_input_columns GRABCOLS] [\-w] [\-\-no\-time] [\-e PERMUTE]
+[\-\-no_pairwise] [\-\-collapse] [\-\-threads THREADS] [\-\-test]
+[\-\-citation] [\-\-version]
 .SH OPTIONS
-For a complete usage description, see the help menu.
-.TP
-.B \-h, \-\-help
-Show summary of options.
-.SH SEE ALSO
-.BR roary (1)
-.br
-/usr/share/doc/scoary/README.md.gz
+.SS "optional arguments:"
+.TP
+\fB\-h\fR, \fB\-\-help\fR
+show this help message and exit
+.SS "Input options:"
+.TP
+\fB\-t\fR TRAITS, \fB\-\-traits\fR TRAITS
+Input trait table (comma\-separated\-values). Trait
+presence is indicated by 1, trait absence by 0.
+Assumes strain names in the first column and trait
+names in the first row
+.TP
+\fB\-g\fR GENES, \fB\-\-genes\fR GENES
+Input gene presence/absence table (comma\-separatedvalues) from ROARY. Strain names must be equal to
+those in the trait table
+.TP
+\fB\-n\fR NEWICKTREE, \fB\-\-newicktree\fR NEWICKTREE
+Supply a custom tree (Newick format) for phylogenetic
+analyses instead instead of calculating it internally.
+.TP
+\fB\-s\fR START_COL, \fB\-\-start_col\fR START_COL
+On which column in the gene presence/absence file do
+individual strain info start. Default=15. (1\-based
+indexing)
+.TP
+\fB\-\-delimiter\fR DELIMITER
+The delimiter between cells in the gene
+presence/absence and trait files, as well as the
+output file.
+.TP
+\fB\-r\fR RESTRICT_TO, \fB\-\-restrict_to\fR RESTRICT_TO
+Use if you only want to analyze a subset of your
+strains. Scoary will read the provided comma\-separated
+table of strains and restrict analyzes to these.
+.SS "Output options:"
+.TP
+\fB\-o\fR OUTDIR, \fB\-\-outdir\fR OUTDIR
+Directory to place output files. Default = .
+.TP
+\fB\-u\fR, \fB\-\-upgma_tree\fR
+This flag will cause Scoary to write the calculated
+UPGMA tree to a newick file
+.TP
+\fB\-p\fR P_VALUE_CUTOFF [P_VALUE_CUTOFF ...], \fB\-\-p_value_cutoff\fR P_VALUE_CUTOFF [P_VALUE_CUTOFF ...]
+P\-value cut\-off / alpha level. For Fishers,
+Bonferronis, and Benjamini\-Hochbergs tests, SCOARY
+will not report genes with higher p\-values than this.
+For empirical p\-values, this is treated as an alpha
+level instead. I.e. 0.02 will filter all genes except
+the lower and upper percentile from this test. Run
+with "\-p 1.0" to report all genes. Accepts standard
+form (e.g. 1E\-8). Provide a single value (applied to
+all) or exactly as many values as correction criteria
+and in corresponding order. (See example under
+correction). Default = 0.05
+.TP
+\fB\-c\fR [{I,B,BH,PW,EPW,P} [{I,B,BH,PW,EPW,P} ...]], \fB\-\-correction\fR [{I,B,BH,PW,EPW,P} [{I,B,BH,PW,EPW,P} ...]]
+Apply the indicated filtration measure. Allowed values
+are I, B, BH, PW, EPW, P. I=Individual (naive)
+p\-value. B=Bonferroni adjusted p\-value. BH=BenjaminiHochberg adjusted p. PW=Best (lowest) pairwise
+comparison. EPW=Entire range of pairwise comparison
+p\-values. P=Empirical p\-value from permutations. You
+can enter as many correction criteria as you would
+like. These will be associated with the
+p_value_cutoffs you enter. For example "\-c I EPW \fB\-p\fR
+0.1 0.05" will apply the following cutoffs: Naive
+p\-value must be lower than 0.1 AND the entire range of
+pairwise comparison values are below 0.05 for this
+gene. Note that the empirical p\-values should be
+interpreted at both tails. Therefore, running "\-c P \fB\-p\fR
+0.05" will apply an alpha of 0.05 to the empirical
+(permuted) p\-values, i.e. it will filter everything
+except the upper and lower 2.5 percent of the
+distribution. Default = Individual p\-value. (I)
+.TP
+\fB\-m\fR MAX_HITS, \fB\-\-max_hits\fR MAX_HITS
+Maximum number of hits to report. SCOARY will only
+report the top max_hits results per trait
+.TP
+\fB\-\-include_input_columns\fR GRABCOLS
+Grab columns from the input Roary file. and puts them
+in the output. Handles comma and ranges, e.g.
+\fB\-\-include_input_columns\fR 4,6,8,16\-23. The special
+keyword ALL will include all relevant input columns in
+the output
+.TP
+\fB\-w\fR, \fB\-\-write_reduced\fR
+Use with \fB\-r\fR if you want Scoary to create a new gene
+presence absence file from your reduced set of
+isolates. Note: Columns 1\-14 (No. sequences, Avg group
+size nuc etc) in this file do not reflect the reduced
+dataset. These are taken from the full dataset.
+.TP
+\fB\-\-no\-time\fR
+Output file in the form TRAIT.results.csv, instead of
+TRAIT_TIMESTAMP.csv. When used with the \fB\-w\fR argument
+will output a reduced gene matrix in the form
+gene_presence_absence_reduced.csv rather than
+gene_presence_absence_reduced_TIMESTAMP.csv
+.SS "Analysis options:"
+.TP
+\fB\-e\fR PERMUTE, \fB\-\-permute\fR PERMUTE
+Perform N number of permutations of the significant
+results post\-analysis. Each permutation will do a
+label switching of the phenotype and a new p\-value is
+calculated according to this new dataset. After all N
+permutations are completed, the results are ordered in
+ascending order, and the percentile of the original
+result in the permuted p\-value distribution is
+reported.
+.TP
+\fB\-\-no_pairwise\fR
+Do not perform pairwise comparisons. Inthis mode,
+Scoary will perform population structure\-naive
+calculations only. (Fishers test, ORs etc). Useful for
+summary operations and exploring sets. (Genes unique
+in groups, intersections etc) but not causal analyses.
+.TP
+\fB\-\-collapse\fR
+Add this to collapse correlated genes (genes that have
+identical distribution patterns in the sample) into
+merged units.
+.SS "Misc options:"
+.TP
+\fB\-\-threads\fR THREADS
+Number of threads to use. Default = 1
+.TP
+\fB\-\-test\fR
+Run Scoary on the test set in exampledata, overriding
+all other parameters.
+.TP
+\fB\-\-citation\fR
+Show citation information, and exit.
+.TP
+\fB\-\-version\fR
+Display Scoary version, and exit.
+.PP
+by Ola Brynildsrud (olbb@fhi.no)
+.SH AUTHOR
+This manpage was written by Andreas Tille for the Debian distribution and can be used for any other usage of the program.

debian/vcf2scoary.1

+.\" DO NOT MODIFY THIS FILE!  It was generated by help2man 1.47.8.
+.TH VCF2SCOARY "1" "January 2019" "vcf2scoary 1.6.16" "User Commands"
+.SH NAME
+vcf2scoary \- takes in vcf files and creates a presence/absence matrix of mutations in the Roary/Scoary format
+.SH SYNOPSIS
+vcf2scoary [\-h] [\-\-out OUT] [\-\-types TYPES] [\-\-version] [\-\-force]
+<VCF_file>
+.SH OPTIONS
+.SS "positional arguments:"
+.TP
+<VCF_file>
+The VCF file to convert to Roary/Scoary format
+.SS "optional arguments:"
+.TP
+\fB\-h\fR, \fB\-\-help\fR
+show this help message and exit
+.TP
+\fB\-\-out\fR OUT
+The path to the output file
+.TP
+\fB\-\-types\fR TYPES
+The types of variants to include in the output. NOTE: This
+works if TYPE=XX can be found in the INFO column of the vcf
+file. The special keyword ALL includes all types. This is the
+default setting. Common types are snp, mnp, ins, del and
+complex. Give as comma\-separated list. Example: \fB\-\-types\fR
+snp,ins,del
+.TP
+\fB\-\-version\fR
+show program's version number and exit
+.TP
+\fB\-\-force\fR
+Force overwriting of output file. (If it already exists)
+.PP
+by Ola Brynildsrud (olbb@fhi.no)
+.SH AUTHOR
+This manpage was written by Andreas Tille for the Debian distribution and can be used for any other usage of the program.