[med-svn] [metaphlan2] 02/04: Add debian/ dir
Andreas Tille
tille at debian.org
Tue Sep 13 07:30:36 UTC 2016
This is an automated email from the git hooks/post-receive script.
tille pushed a commit to branch master
in repository metaphlan2.
commit 69abde905af228983c9a83cee67ef15b3fc703f4
Author: Andreas Tille <tille at debian.org>
Date: Tue Sep 13 08:43:54 2016 +0200
Add debian/ dir
---
debian/bin/metaphlan2 | 5 +
debian/bin/strainphlan | 7 +
debian/changelog | 11 +
debian/clean | 2 +
debian/compat | 1 +
debian/control | 43 +++
debian/copyright | 33 +++
debian/docs | 1 +
debian/install | 4 +
debian/manpages | 1 +
debian/metaphlan2.1 | 313 +++++++++++++++++++++
.../patches/mpa_dir-is-usr_share_metaphlan2.patch | 239 ++++++++++++++++
debian/patches/series | 2 +
debian/patches/spelling.patch | 46 +++
debian/rules | 19 ++
debian/source/format | 1 +
debian/strainphlan.1 | 209 ++++++++++++++
debian/upstream/metadata | 11 +
debian/watch | 4 +
19 files changed, 952 insertions(+)
diff --git a/debian/bin/metaphlan2 b/debian/bin/metaphlan2
new file mode 100755
index 0000000..78a4e45
--- /dev/null
+++ b/debian/bin/metaphlan2
@@ -0,0 +1,5 @@
+#!/bin/sh
+
+cmd=`basename "$0" .py`.py
+
+exec "/usr/share/metaphlan2/$cmd" "$@"
diff --git a/debian/bin/strainphlan b/debian/bin/strainphlan
new file mode 100755
index 0000000..2b8fb45
--- /dev/null
+++ b/debian/bin/strainphlan
@@ -0,0 +1,7 @@
+#!/bin/sh
+
+export PYTHONPATH="$PATH:/usr/share/metaphlan2/strainer_src"
+
+cmd=`basename "$0" .py`.py
+
+exec "/usr/share/metaphlan2/$cmd" "$@"
diff --git a/debian/changelog b/debian/changelog
new file mode 100644
index 0000000..e222c01
--- /dev/null
+++ b/debian/changelog
@@ -0,0 +1,11 @@
+metaphlan2 (2.6.0+ds-1) UNRELEASED; urgency=medium
+
+ * Initial release (Closes: #???)
+
+ -- Andreas Tille <tille at debian.org> Thu, 18 Aug 2016 15:33:57 +0200
+
+metaphlan2 (2.5.0-0~ubuntu14.04~ppa1) trusty; urgency=medium
+
+ * Pre-release to Debian Med PPA
+
+ -- Andreas Tille <tille at debian.org> Mon, 23 May 2016 16:09:13 +0200
diff --git a/debian/clean b/debian/clean
new file mode 100644
index 0000000..8d3e111
--- /dev/null
+++ b/debian/clean
@@ -0,0 +1,2 @@
+README.html
+strainphlan_src/*.pyc
diff --git a/debian/compat b/debian/compat
new file mode 100644
index 0000000..ec63514
--- /dev/null
+++ b/debian/compat
@@ -0,0 +1 @@
+9
diff --git a/debian/control b/debian/control
new file mode 100644
index 0000000..2433562
--- /dev/null
+++ b/debian/control
@@ -0,0 +1,43 @@
+Source: metaphlan2
+Maintainer: Debian Med Packaging Team <debian-med-packaging at lists.alioth.debian.org>
+Uploaders: Andreas Tille <tille at debian.org>
+Section: science
+Priority: optional
+Build-Depends: debhelper (>= 9),
+ python-all,
+ dh-python,
+ python-markdown,
+ bowtie2
+Standards-Version: 3.9.8
+Vcs-Browser: https://anonscm.debian.org/cgit/debian-med/metaphlan2.git
+Vcs-Git: https://anonscm.debian.org/git/debian-med/metaphlan2.git
+Homepage: https://bitbucket.org/nsegata/metaphlan2/wiki/Home
+
+Package: metaphlan2
+Architecture: all
+Depends: ${python:Depends},
+ ${misc:Depends},
+ python-biom-format,
+ python-msgpack,
+ python-pandas,
+ bowtie2
+Description: Metagenomic Phylogenetic Analysis
+ MetaPhlAn is a computational tool for profiling the composition of
+ microbial communities (Bacteria, Archaea, Eukaryotes and Viruses) from
+ metagenomic shotgun sequencing data with species level resolution. From
+ version 2.0, MetaPhlAn is also able to identify specific strains (in the
+ not-so-frequent cases in which the sample contains a previously
+ sequenced strains) and to track strains across samples for all species.
+ .
+ MetaPhlAn 2.0 relies on ~1M unique clade-specific marker genes (the
+ marker information file can be found at src/utils/markers_info.txt.bz2
+ or here) identified from ~17,000 reference genomes (~13,500 bacterial
+ and archaeal, ~3,500 viral, and ~110 eukaryotic), allowing:
+ .
+ * unambiguous taxonomic assignments;
+ * accurate estimation of organismal relative abundance;
+ * species-level resolution for bacteria, archaea, eukaryotes and
+ viruses;
+ * strain identification and tracking
+ * orders of magnitude speedups compared to existing methods.
+ * metagenomic strain-level population genomics
diff --git a/debian/copyright b/debian/copyright
new file mode 100644
index 0000000..a6af4b4
--- /dev/null
+++ b/debian/copyright
@@ -0,0 +1,33 @@
+Format: http://www.debian.org/doc/packaging-manuals/copyright-format/1.0/
+Upstream-Name: MetaPhlAn2
+Upstream-Contact: Nicola Segata <nicola.segata at unitn.it>
+Source: https://bitbucket.org/biobakery/metaphlan2/downloads
+Files-Excluded: */*.bt2
+
+Files: *
+Copyright: 2012-2016 Duy Tin Truong, Nicola Segata and Curtis Huttenhower
+License: expat
+
+Files: debian/*
+Copyright: © 2016 Andreas Tille <tille at debian.org>
+License: expat
+
+License: expat
+ Permission is hereby granted, free of charge, to any person obtaining a
+ copy of this software and associated documentation files (the
+ "Software"), to deal in the Software without restriction, including
+ without limitation the rights to use, copy, modify, merge, publish,
+ distribute, sublicense, and/or sell copies of the Software, and to
+ permit persons to whom the Software is furnished to do so, subject to
+ the following conditions:
+ .
+ The above copyright notice and this permission notice shall be included
+ in all copies or substantial portions of the Software.
+ .
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+ OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+ IN NO EV ENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
+ CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
+ TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
+ SOFTWARE OR TH E USE OR OTHER DEALINGS IN THE SOFTWARE.
diff --git a/debian/docs b/debian/docs
new file mode 100644
index 0000000..daa30a3
--- /dev/null
+++ b/debian/docs
@@ -0,0 +1 @@
+README.html
diff --git a/debian/install b/debian/install
new file mode 100644
index 0000000..680f4da
--- /dev/null
+++ b/debian/install
@@ -0,0 +1,4 @@
+*.py usr/share/metaphlan2
+utils usr/share/metaphlan2
+debian/bin usr
+db_v20 usr/share/metaphlan2
diff --git a/debian/manpages b/debian/manpages
new file mode 100644
index 0000000..0f65186
--- /dev/null
+++ b/debian/manpages
@@ -0,0 +1 @@
+debian/*.1
diff --git a/debian/metaphlan2.1 b/debian/metaphlan2.1
new file mode 100644
index 0000000..3c10635
--- /dev/null
+++ b/debian/metaphlan2.1
@@ -0,0 +1,313 @@
+.TH METAPHLAN2 "1" "July 2016" "metaphlan2 2.5.0" "User Commands"
+.SH NAME
+metaphlan2 \- METAgenomic PHyLogenetic ANalysis for metagenomic taxonomic profiling
+.SH SYNOPSIS
+.B metaphlan2
+ \fB\-\-input_type\fR
+{fastq,fasta,multifasta,multifastq,bowtie2out,sam}
+[\-\-mpa_pkl MPA_PKL] [\-\-bowtie2db METAPHLAN_BOWTIE2_DB]
+[\-\-bt2_ps BowTie2 presets] [\-\-bowtie2_exe BOWTIE2_EXE]
+[\-\-bowtie2out FILE_NAME] [\-\-no_map] [\-\-tmp_dir]
+[\-\-tax_lev TAXONOMIC_LEVEL] [\-\-min_cu_len]
+[\-\-min_alignment_len] [\-\-ignore_viruses]
+[\-\-ignore_eukaryotes] [\-\-ignore_bacteria] [\-\-ignore_archaea]
+[\-\-stat_q] [\-\-ignore_markers IGNORE_MARKERS] [\-\-avoid_disqm]
+[\-\-stat] [\-t ANALYSIS TYPE] [\-\-nreads NUMBER_OF_READS]
+[\-\-pres_th PRESENCE_THRESHOLD] [\-\-clade] [\-\-min_ab] [\-h]
+[\-o output file] [\-\-sample_id_key name] [\-\-sample_id value]
+[\-s sam_output_file] [\-\-biom biom_output] [\-\-mdelim mdelim]
+[\-\-nproc N] [\-v]
+[INPUT_FILE] [OUTPUT_FILE]
+.SH DESCRIPTION
+.SS MetaPhlAn 2 clade\-abundance estimation
+.PP
+The basic usage of MetaPhlAn 2 consists in the identification of the clades (from phyla to species and
+strains in particular cases) present in the metagenome obtained from a microbiome sample and their
+relative abundance. This correspond to the default analysis type (\fB\-\-analysis_type\fR rel_ab).
+.IP *
+Profiling a metagenome from raw reads:
+.IP
+metaphlan2 metagenome.fastq \fB\-\-input_type\fR fastq
+.IP *
+You can take advantage of multiple CPUs and save the intermediate BowTie2 output for re\-running
+.IP
+MetaPhlAn extremely quickly:
+.br
+metaphlan2 metagenome.fastq \fB\-\-bowtie2out\fR metagenome.bowtie2.bz2 \fB\-\-nproc\fR 5 \fB\-\-input_type\fR fastq
+.IP *
+If you already mapped your metagenome against the marker DB (using a previous MetaPhlAn run), you
+can obtain the results in few seconds by using the previously saved \fB\-\-bowtie2out\fR file and
+specifying the input (\fB\-\-input_type\fR bowtie2out):
+.IP
+metaphlan2 metagenome.bowtie2.bz2 \fB\-\-nproc\fR 5 \fB\-\-input_type\fR bowtie2out
+.IP *
+You can also provide an externally BowTie2\-mapped SAM if you specify this format with
+\fB\-\-input_type\fR. Two steps: first apply BowTie2 and then feed MetaPhlAn2 with the obtained sam:
+.IP
+bowtie2 \fB\-\-sam\-no\-hd\fR \fB\-\-sam\-no\-sq\fR \fB\-\-no\-unal\fR \fB\-\-very\-sensitive\fR \fB\-S\fR metagenome.sam \fB\-x\fR /usr/share/metaphlan2/db_v20/mpa_v20_m200 \fB\-U\fR metagenome.fastq
+metaphlan2 metagenome.sam \fB\-\-input_type\fR sam > profiled_metagenome.txt
+.IP *
+Multiple alternative ways to pass the input are also available:
+.IP
+cat metagenome.fastq | metaphlan2 \fB\-\-input_type\fR fastq
+.br
+tar xjf metagenome.tar.bz2 \fB\-\-to\-stdout\fR | metaphlan2 \fB\-\-input_type\fR fastq
+.br
+metaphlan2 \fB\-\-input_type\fR fastq < metagenome.fastq
+.br
+metaphlan2 \fB\-\-input_type\fR fastq <(bzcat metagenome.fastq.bz2)
+.br
+metaphlan2 \fB\-\-input_type\fR fastq <(zcat metagenome_1.fastq.gz metagenome_2.fastq.gz)
+.IP *
+We can also natively handle paired\-end metagenomes, and, more generally, metagenomes stored in
+multiple files (but you need to specify the \fB\-\-bowtie2out\fR parameter):
+.IP
+metaphlan2 metagenome_1.fastq,metagenome_2.fastq \fB\-\-bowtie2out\fR metagenome.bowtie2.bz2 \fB\-\-nproc\fR 5 \fB\-\-input_type\fR fastq
+.SS MetaPhlAn 2 strain tracking
+.PP
+MetaPhlAn 2 introduces the capability of charachterizing organisms at the strain level using non
+aggregated marker information. Such capability comes with several slightly different flavours and
+are a way to perform strain tracking and comparison across multiple samples.
+Usually, MetaPhlAn 2 is first ran with the default \fB\-\-analysis_type\fR to profile the species present in
+the community, and then a strain\-level profiling can be performed to zoom\-in into specific species
+of interest. This operation can be performed quickly as it exploits the \fB\-\-bowtie2out\fR intermediate
+file saved during the execution of the default analysis type.
+.IP *
+The following command will output the abundance of each marker with a RPK (reads per kil\-base)
+higher 0.0. (we are assuming that metagenome_outfmt.bz2 has been generated before as
+shown above).
+.IP
+metaphlan2 \fB\-t\fR marker_ab_table metagenome_outfmt.bz2 \fB\-\-input_type\fR bowtie2out > marker_abundance_table.txt
+.IP
+The obtained RPK can be optionally normalized by the total number of reads in the metagenome
+to guarantee fair comparisons of abundances across samples. The number of reads in the metagenome
+needs to be passed with the '\-\-nreads' argument
+.IP *
+The list of markers present in the sample can be obtained with '\-t marker_pres_table'
+.IP
+metaphlan2 \fB\-t\fR marker_pres_table metagenome_outfmt.bz2 \fB\-\-input_type\fR bowtie2out > marker_abundance_table.txt
+.IP
+The \fB\-\-pres_th\fR argument (default 1.0) set the minimum RPK value to consider a marker present
+.IP *
+The list '\-t clade_profiles' analysis type reports the same information of '\-t marker_ab_table'
+but the markers are reported on a clade\-by\-clade basis.
+.IP
+metaphlan2 \fB\-t\fR clade_profiles metagenome_outfmt.bz2 \fB\-\-input_type\fR bowtie2out > marker_abundance_table.txt
+.IP *
+Finally, to obtain all markers present for a specific clade and all its subclades, the
+\&'\-t clade_specific_strain_tracker' should be used. For example, the following command
+is reporting the presence/absence of the markers for the B. fragulis species and its strains
+the optional argument \fB\-\-min_ab\fR specifies the minimum clade abundance for reporting the markers
+.IP
+$ metaphlan2 \fB\-t\fR clade_specific_strain_tracker \fB\-\-clade\fR s__Bacteroides_fragilis metagenome_outfmt.bz2 \fB\-\-input_type\fR bowtie2out > marker_abundance_table.txt
+.PP
+.SH OPTIONS
+.SS positional arguments
+.TP
+INPUT_FILE
+the input file can be:
+.IP *
+a fastq file containing metagenomic reads
+.IP
+OR
+.IP *
+a BowTie2 produced SAM file.
+.IP
+OR
+.IP *
+an intermediary mapping file of the metagenome generated by a previous MetaPhlAn run
+.IP
+If the input file is missing, the script assumes that the input is provided using the standard
+input, or named pipes.
+IMPORTANT: the type of input needs to be specified with \fB\-\-input_type\fR
+.TP
+OUTPUT_FILE
+the tab\-separated output file of the predicted taxon relative abundances
+[stdout if not present]
+.SS Required arguments
+.TP
+\fB\-\-input_type\fR {fastq,fasta,multifasta,multifastq,bowtie2out,sam}
+set whether the input is the multifasta file of metagenomic reads or
+the SAM file of the mapping of the reads against the MetaPhlAn db.
+[default 'automatic', i.e. the script will try to guess the input format]
+.SS "Mapping arguments:"
+.TP
+\fB\-\-mpa_pkl\fR MPA_PKL
+the metadata pickled MetaPhlAn file
+.TP
+\fB\-\-bowtie2db\fR METAPHLAN_BOWTIE2_DB
+The BowTie2 database file of the MetaPhlAn database.
+Used if \fB\-\-input_type\fR is fastq, fasta, multifasta, or multifastq
+.TP
+\fB\-\-bt2_ps\fR BowTie2 presets
+presets options for BowTie2 (applied only when a multifasta file is provided)
+The choices enabled in MetaPhlAn are:
+.IP *
+sensitive
+.IP *
+very\-sensitive
+.IP *
+sensitive\-local
+.IP *
+very\-sensitive\-local
+.IP
+[default very\-sensitive]
+.TP
+\fB\-\-bowtie2_exe\fR BOWTIE2_EXE
+Full path and name of the BowTie2 executable. This option allows
+MetaPhlAn to reach the executable even when it is not in the system
+PATH or the system PATH is unreachable
+.TP
+\fB\-\-bowtie2out\fR FILE_NAME
+The file for saving the output of BowTie2
+.TP
+\fB\-\-no_map\fR
+Avoid storing the \fB\-\-bowtie2out\fR map file
+.TP
+\fB\-\-tmp_dir\fR
+the folder used to store temporary files
+[default is the OS dependent tmp dir]
+.SS Post-mapping arguments
+.TP
+\fB\-\-tax_lev\fR TAXONOMIC_LEVEL
+The taxonomic level for the relative abundance output:
+.br
+\&'a' : all taxonomic levels
+.br
+\&'k' : kingdoms
+.br
+\&'p' : phyla only
+.br
+\&'c' : classes only
+.br
+\&'o' : orders only
+.br
+\&'f' : families only
+.br
+\&'g' : genera only
+.br
+\&'s' : species only
+.br
+[default 'a']
+.TP
+\fB\-\-min_cu_len\fR
+minimum total nucleotide length for the markers in a clade for
+estimating the abundance without considering sub\-clade abundances
+[default 2000]
+.TP
+\fB\-\-min_alignment_len\fR
+The sam records for aligned reads with the longest subalignment
+length smaller than this threshold will be discarded.
+[default None]
+.TP
+\fB\-\-ignore_viruses\fR
+Do not profile viral organisms
+.TP
+\fB\-\-ignore_eukaryotes\fR
+Do not profile eukaryotic organisms
+.TP
+\fB\-\-ignore_bacteria\fR
+Do not profile bacterial organisms
+.TP
+\fB\-\-ignore_archaea\fR
+Do not profile archeal organisms
+.TP
+\fB\-\-stat_q\fR
+Quantile value for the robust average
+[default 0.1]
+.TP
+\fB\-\-ignore_markers\fR IGNORE_MARKERS
+File containing a list of markers to ignore.
+.TP
+\fB\-\-avoid_disqm\fR
+Deactivate the procedure of disambiguating the quasi\-markers based on the
+marker abundance pattern found in the sample. It is generally recommended
+too keep the disambiguation procedure in order to minimize false positives
+.TP
+\fB\-\-stat\fR
+EXPERIMENTAL! Statistical approach for converting marker abundances into clade abundances
+.br
+\&'avg_g' : clade global (i.e. normalizing all markers together) average
+.br
+\&'avg_l' : average of length\-normalized marker counts
+.br
+\&'tavg_g' : truncated clade global average at \fB\-\-stat_q\fR quantile
+.br
+\&'tavg_l' : trunated average of length\-normalized marker counts (at \fB\-\-stat_q\fR)
+.br
+\&'wavg_g' : winsorized clade global average (at \fB\-\-stat_q\fR)
+.br
+\&'wavg_l' : winsorized average of length\-normalized marker counts (at \fB\-\-stat_q\fR)
+.br
+\&'med' : median of length\-normalized marker counts
+.br
+[default tavg_g]
+.SS Additional analysis types and arguments
+.TP
+\fB\-t\fR ANALYSIS TYPE
+Type of analysis to perform:
+.IP *
+rel_ab: profiling a metagenomes in terms of relative abundances
+.IP *
+rel_ab_w_read_stats: profiling a metagenomes in terms of relative abundances and estimate the number of reads coming from each clade.
+.IP *
+reads_map: mapping from reads to clades (only reads hitting a marker)
+.IP *
+clade_profiles: normalized marker counts for clades with at least a non\-null marker
+.IP *
+marker_ab_table: normalized marker counts (only when > 0.0 and normalized by metagenome size if \fB\-\-nreads\fR is specified)
+.IP *
+marker_counts: non\-normalized marker counts [use with extreme caution]
+.IP *
+marker_pres_table: list of markers present in the sample (threshold at 1.0 if not differently specified with \fB\-\-pres_th\fR
+.IP
+[default 'rel_ab']
+.TP
+\fB\-\-nreads\fR NUMBER_OF_READS
+The total number of reads in the original metagenome. It is used only when
+\fB\-t\fR marker_table is specified for normalizing the length\-normalized counts
+with the metagenome size as well. No normalization applied if \fB\-\-nreads\fR is not
+specified
+.TP
+\fB\-\-pres_th\fR PRESENCE_THRESHOLD
+Threshold for calling a marker present by the \fB\-t\fR marker_pres_table option
+.TP
+\fB\-\-clade\fR
+The clade for clade_specific_strain_tracker analysis
+.TP
+\fB\-\-min_ab\fR
+The minimum percentage abundace for the clade in the clade_specific_strain_tracker analysis
+.TP
+\fB\-h\fR, \fB\-\-help\fR
+show this help message and exit
+.SS Output arguments
+.TP
+\fB\-o\fR output file, \fB\-\-output_file\fR output file
+The output file (if not specified as positional argument)
+.TP
+\fB\-\-sample_id_key\fR name
+Specify the sample ID key for this analysis. Defaults to '#SampleID'.
+.TP
+\fB\-\-sample_id\fR value
+Specify the sample ID for this analysis. Defaults to 'Metaphlan2_Analysis'.
+.TP
+\fB\-s\fR sam_output_file, \fB\-\-samout\fR sam_output_file
+The sam output file
+.TP
+\fB\-\-biom\fR biom_output, \fB\-\-biom_output_file\fR biom_output
+If requesting biom file output: The name of the output file in biom format
+.TP
+\fB\-\-mdelim\fR mdelim, \fB\-\-metadata_delimiter_char\fR mdelim
+Delimiter for bug metadata: \- defaults to pipe. e.g. the pipe in k__Bacteria|p__Proteobacteria
+.SS Other arguments
+.TP
+\fB\-\-nproc\fR N
+The number of CPUs to use for parallelizing the mapping
+[default 1, i.e. no parallelism]
+.TP
+\fB\-v\fR, \fB\-\-version\fR
+Prints the current MetaPhlAn version and exit
+.SH AUTHOR
+The code of MetaPhlAn was rwitten by Nicola Segata (nicola.segata at unitn.it), Duy Tin Truong (duytin.truong at unitn.it).
+.P
+This manpage was written by Andreas Tille for the Debian distribution and can be used for any other usage of the program.
diff --git a/debian/patches/mpa_dir-is-usr_share_metaphlan2.patch b/debian/patches/mpa_dir-is-usr_share_metaphlan2.patch
new file mode 100644
index 0000000..bd8690e
--- /dev/null
+++ b/debian/patches/mpa_dir-is-usr_share_metaphlan2.patch
@@ -0,0 +1,239 @@
+Author: Andreas Tille <tille at debian.org>
+Last-Update: Mon, 23 May 2016 16:09:13 +0200
+Description: Instead of setting mpa_dir bash variable the path to the
+ database files in /usr/share/metaphlan2 is set explicitly.
+ .
+ The doc is also adapted to this change.
+
+--- a/metaphlan2.py
++++ b/metaphlan2.py
+@@ -385,7 +385,7 @@ def read_params(args):
+
+ "* You can also provide an externally BowTie2-mapped SAM if you specify this format with \n"
+ " --input_type. Two steps: first apply BowTie2 and then feed MetaPhlAn2 with the obtained sam:\n"
+- "$ bowtie2 --sam-no-hd --sam-no-sq --no-unal --very-sensitive -S metagenome.sam -x ${mpa_dir}/db_v20/mpa_v20_m200 -U metagenome.fastq\n"
++ "$ bowtie2 --sam-no-hd --sam-no-sq --no-unal --very-sensitive -S metagenome.sam -x /usr/share/metaphlan2/db_v20/mpa_v20_m200 -U metagenome.fastq\n"
+ "$ metaphlan2.py metagenome.sam --input_type sam > profiled_metagenome.txt\n\n"
+
+ "* Multiple alternative ways to pass the input are also available:\n"
+@@ -1107,7 +1107,7 @@ if __name__ == '__main__':
+ # check for the mpa_pkl file
+ if not os.path.isfile(pars['mpa_pkl']):
+ sys.stderr.write("Error: Unable to find the mpa_pkl file at: " + pars['mpa_pkl'] +
+- "\nExpecting location ${mpa_dir}/db_v20/map_v20_m200.pkl "
++ "\nExpecting location /usr/share/metaphlan2/db_v20/mpa_v20_m200.pkl "
+ "\nSelect the file location with the option --mpa_pkl.\n"
+ "Exiting...\n\n")
+ sys.exit(1)
+@@ -1155,7 +1155,7 @@ if __name__ == '__main__':
+ sys.stderr.write( "No MetaPhlAn BowTie2 database found "
+ "[--bowtie2db option]! "
+ "(or wrong path provided)."
+- "\nExpecting location ${mpa_dir}/db_v20/map_v20_m200 "
++ "\nExpecting location /usr/share/metaphlan2/db_v20/mpa_v20_m200 "
+ "\nExiting... " )
+ sys.exit(1)
+
+--- a/README.md
++++ b/README.md
+@@ -60,32 +60,27 @@ Cloning the repository via the following
+
+ This section presents some basic usages of MetaPhlAn2, for more advanced usages, please see at [its wiki](https://bitbucket.org/biobakery/biobakery/wiki/metaphlan2).
+
+-We assume here that ``metaphlan2.py`` is in the system path and that ``mpa_dir`` bash variable contains the main MetaPhlAn folder. You can set this two variables moving to your MetaPhlAn2 local folder and type:
+-```
+-#!cmd
+-$ export PATH=`pwd`:$PATH
+-$ export mpa_dir=`pwd`
+-```
++We assume here that ``metaphlan2`` is in the system path.
+
+ Here is the basic example to profile a metagenome from raw reads (requires BowTie2 in the system path with execution and read permissions, Perl installed).
+
+ ```
+ #!cmd
+-$ metaphlan2.py metagenome.fastq --input_type fastq > profiled_metagenome.txt
++$ metaphlan2 metagenome.fastq --input_type fastq > profiled_metagenome.txt
+ ```
+
+ It is highly recommended to save the intermediate BowTie2 output for re-running MetaPhlAn extremely quickly (--bowtie2out), and use multiple CPUs (--nproc) if available:
+
+ ```
+ #!cmd
+-$ metaphlan2.py metagenome.fastq --bowtie2out metagenome.bowtie2.bz2 --nproc 5 --input_type fastq > profiled_metagenome.txt
++$ metaphlan2 metagenome.fastq --bowtie2out metagenome.bowtie2.bz2 --nproc 5 --input_type fastq > profiled_metagenome.txt
+ ```
+
+ If you already mapped your metagenome against the marker DB (using a previous MetaPhlAn run), you can obtain the results in few seconds by using the previously saved --bowtie2out file and specifying the input (--input_type bowtie2out):
+
+ ```
+ #!cmd
+-$ metaphlan2.py metagenome.bowtie2.bz2 --nproc 5 --input_type bowtie2out > profiled_metagenome.txt
++$ metaphlan2 metagenome.bowtie2.bz2 --nproc 5 --input_type bowtie2out > profiled_metagenome.txt
+ ```
+
+ You can also provide an externally BowTie2-mapped SAM if you specify this format with --input_type. Two steps here: first map your metagenome with BowTie2 and then feed MetaPhlAn2 with the obtained sam:
+@@ -93,41 +88,41 @@ You can also provide an externally BowTi
+ ```
+ #!cmd
+ $ bowtie2 --sam-no-hd --sam-no-sq --no-unal --very-sensitive -S metagenome.sam -x ${mpa_dir}/db_v20/mpa_v20_m200 -U metagenome.fastq
+-$ metaphlan2.py metagenome.sam --input_type sam > profiled_metagenome.txt
++$ metaphlan2 metagenome.sam --input_type sam > profiled_metagenome.txt
+ ```
+
+ In order to make MetaPhlAn 2 easily compatible with complex metagenomic pipeline, there are now multiple alternative ways to pass the input:
+
+ ```
+ #!cmd
+-$ cat metagenome.fastq | metaphlan2.py --input_type fastq > profiled_metagenome.txt
++$ cat metagenome.fastq | metaphlan2 --input_type fastq > profiled_metagenome.txt
+ ```
+
+ ```
+ #!cmd
+-$ tar xjf metagenome.tar.bz2 --to-stdout | metaphlan2.py --input_type fastq --bowtie2db ${mpa_dir}/db_v20/mpa_v20_m200 > profiled_metagenome.txt
++$ tar xjf metagenome.tar.bz2 --to-stdout | metaphlan2 --input_type fastq --bowtie2db ${mpa_dir}/db_v20/mpa_v20_m200 > profiled_metagenome.txt
+ ```
+
+ ```
+ #!cmd
+-$ metaphlan2.py --input_type fastq < metagenome.fastq > profiled_metagenome.txt
++$ metaphlan2 --input_type fastq < metagenome.fastq > profiled_metagenome.txt
+ ```
+
+ ```
+ #!cmd
+-$ metaphlan2.py --input_type fastq <(bzcat metagenome.fastq.bz2) > profiled_metagenome.txt
++$ metaphlan2 --input_type fastq <(bzcat metagenome.fastq.bz2) > profiled_metagenome.txt
+ ```
+
+ ```
+ #!cmd
+-$ metaphlan2.py --input_type fastq <(zcat metagenome_1.fastq.gz metagenome_2.fastq.gz) > profiled_metagenome.txt
++$ metaphlan2 --input_type fastq <(zcat metagenome_1.fastq.gz metagenome_2.fastq.gz) > profiled_metagenome.txt
+ ```
+
+ MetaPhlAn 2 can also natively **handle paired-end metagenomes** (but does not use the paired-end information), and, more generally, metagenomes stored in multiple files (but you need to specify the --bowtie2out parameter):
+
+ ```
+ #!cmd
+-$ metaphlan2.py metagenome_1.fastq,metagenome_2.fastq --bowtie2out metagenome.bowtie2.bz2 --nproc 5 --input_type fastq > profiled_metagenome.txt
++$ metaphlan2 metagenome_1.fastq,metagenome_2.fastq --bowtie2out metagenome.bowtie2.bz2 --nproc 5 --input_type fastq > profiled_metagenome.txt
+ ```
+
+ For advanced options and other analysis types (such as strain tracking) please refer to the full command-line options.
+@@ -136,7 +131,7 @@ For advanced options and other analysis
+
+
+ ```
+-usage: metaphlan2.py --input_type
++usage: metaphlan2 --input_type
+ {fastq,fasta,multifasta,multifastq,bowtie2out,sam}
+ [--mpa_pkl MPA_PKL] [--bowtie2db METAPHLAN_BOWTIE2_DB]
+ [--bt2_ps BowTie2 presets] [--bowtie2_exe BOWTIE2_EXE]
+@@ -161,7 +156,7 @@ AUTHORS: Nicola Segata (nicola.segata at un
+
+ COMMON COMMANDS
+
+- We assume here that metaphlan2.py is in the system path and that mpa_dir bash variable contains the
++ We assume here that metaphlan2 is in the system path and that mpa_dir bash variable contains the
+ main MetaPhlAn folder. Also BowTie2 should be in the system path with execution and read
+ permissions, and Perl should be installed.
+
+@@ -172,32 +167,32 @@ strains in particular cases) present in
+ relative abundance. This correspond to the default analysis type (--analysis_type rel_ab).
+
+ * Profiling a metagenome from raw reads:
+-$ metaphlan2.py metagenome.fastq --input_type fastq
++$ metaphlan2 metagenome.fastq --input_type fastq
+
+ * You can take advantage of multiple CPUs and save the intermediate BowTie2 output for re-running
+ MetaPhlAn extremely quickly:
+-$ metaphlan2.py metagenome.fastq --bowtie2out metagenome.bowtie2.bz2 --nproc 5 --input_type fastq
++$ metaphlan2 metagenome.fastq --bowtie2out metagenome.bowtie2.bz2 --nproc 5 --input_type fastq
+
+ * If you already mapped your metagenome against the marker DB (using a previous MetaPhlAn run), you
+ can obtain the results in few seconds by using the previously saved --bowtie2out file and
+ specifying the input (--input_type bowtie2out):
+-$ metaphlan2.py metagenome.bowtie2.bz2 --nproc 5 --input_type bowtie2out
++$ metaphlan2 metagenome.bowtie2.bz2 --nproc 5 --input_type bowtie2out
+
+ * You can also provide an externally BowTie2-mapped SAM if you specify this format with
+ --input_type. Two steps: first apply BowTie2 and then feed MetaPhlAn2 with the obtained sam:
+-$ bowtie2 --sam-no-hd --sam-no-sq --no-unal --very-sensitive -S metagenome.sam -x ${mpa_dir}/db_v20/mpa_v20_m200 -U metagenome.fastq
+-$ metaphlan2.py metagenome.sam --input_type sam > profiled_metagenome.txt
++$ bowtie2 --sam-no-hd --sam-no-sq --no-unal --very-sensitive -S metagenome.sam -x /usr/share/metaphlan2/db_v20/mpa_v20_m200 -U metagenome.fastq
++$ metaphlan2 metagenome.sam --input_type sam > profiled_metagenome.txt
+
+ * Multiple alternative ways to pass the input are also available:
+-$ cat metagenome.fastq | metaphlan2.py --input_type fastq
+-$ tar xjf metagenome.tar.bz2 --to-stdout | metaphlan2.py --input_type fastq
+-$ metaphlan2.py --input_type fastq < metagenome.fastq
+-$ metaphlan2.py --input_type fastq <(bzcat metagenome.fastq.bz2)
+-$ metaphlan2.py --input_type fastq <(zcat metagenome_1.fastq.gz metagenome_2.fastq.gz)
++$ cat metagenome.fastq | metaphlan2 --input_type fastq
++$ tar xjf metagenome.tar.bz2 --to-stdout | metaphlan2 --input_type fastq
++$ metaphlan2 --input_type fastq < metagenome.fastq
++$ metaphlan2 --input_type fastq <(bzcat metagenome.fastq.bz2)
++$ metaphlan2 --input_type fastq <(zcat metagenome_1.fastq.gz metagenome_2.fastq.gz)
+
+ * We can also natively handle paired-end metagenomes, and, more generally, metagenomes stored in
+ multiple files (but you need to specify the --bowtie2out parameter):
+-$ metaphlan2.py metagenome_1.fastq,metagenome_2.fastq --bowtie2out metagenome.bowtie2.bz2 --nproc 5 --input_type fastq
++$ metaphlan2 metagenome_1.fastq,metagenome_2.fastq --bowtie2out metagenome.bowtie2.bz2 --nproc 5 --input_type fastq
+
+ -------------------------------------------------------------------
+
+@@ -215,23 +210,23 @@ file saved during the execution of the d
+ * The following command will output the abundance of each marker with a RPK (reads per kil-base)
+ higher 0.0. (we are assuming that metagenome_outfmt.bz2 has been generated before as
+ shown above).
+-$ metaphlan2.py -t marker_ab_table metagenome_outfmt.bz2 --input_type bowtie2out > marker_abundance_table.txt
++$ metaphlan2 -t marker_ab_table metagenome_outfmt.bz2 --input_type bowtie2out > marker_abundance_table.txt
+ The obtained RPK can be optionally normalized by the total number of reads in the metagenome
+ to guarantee fair comparisons of abundances across samples. The number of reads in the metagenome
+ needs to be passed with the '--nreads' argument
+
+ * The list of markers present in the sample can be obtained with '-t marker_pres_table'
+-$ metaphlan2.py -t marker_pres_table metagenome_outfmt.bz2 --input_type bowtie2out > marker_abundance_table.txt
++$ metaphlan2 -t marker_pres_table metagenome_outfmt.bz2 --input_type bowtie2out > marker_abundance_table.txt
+ The --pres_th argument (default 1.0) set the minimum RPK value to consider a marker present
+
+ * The list '-t clade_profiles' analysis type reports the same information of '-t marker_ab_table'
+ but the markers are reported on a clade-by-clade basis.
+-$ metaphlan2.py -t clade_profiles metagenome_outfmt.bz2 --input_type bowtie2out > marker_abundance_table.txt
++$ metaphlan2 -t clade_profiles metagenome_outfmt.bz2 --input_type bowtie2out > marker_abundance_table.txt
+
+ * Finally, to obtain all markers present for a specific clade and all its subclades, the
+ '-t clade_specific_strain_tracker' should be used. For example, the following command
+ is reporting the presence/absence of the markers for the B. fragulis species and its strains
+-$ metaphlan2.py -t clade_specific_strain_tracker --clade s__Bacteroides_fragilis metagenome_outfmt.bz2 db_v20/mpa_v20_m200.pkl --input_type bowtie2out > marker_abundance_table.txt
++$ metaphlan2 -t clade_specific_strain_tracker --clade s__Bacteroides_fragilis metagenome_outfmt.bz2 db_v20/mpa_v20_m200.pkl --input_type bowtie2out > marker_abundance_table.txt
+ the optional argument --min_ab specifies the minimum clade abundance for reporting the markers
+
+ -------------------------------------------------------------------
+@@ -536,7 +531,7 @@ pickle.dump(db, ofile, pickle.HIGHEST_PR
+ ofile.close()
+ ```
+
+-* To use the new database, switch to metaphlan2/db_v21 instead of metaphlan2/db_v20 when running metaphlan2.py with option "--mpa_pkl".
++* To use the new database, switch to metaphlan2/db_v21 instead of metaphlan2/db_v20 when running metaphlan2 with option "--mpa_pkl".
+
+
+ ##**Metagenomic strain-level population genomics**##
+@@ -614,7 +609,7 @@ for f in $(ls fastqs/*.bz2)
+ do
+ echo "Running metaphlan2 on ${f}"
+ bn=$(basename ${f} | cut -d . -f 1)
+- tar xjfO ${f} | ../metaphlan2.py --bowtie2db ../db_v20/mpa_v20_m200 --mpa_pkl ../db_v20/mpa_v20_m200.pkl --input_type multifastq --nproc 10 -s sams/${bn}.sam.bz2 --bowtie2out sams/${bn}.bowtie2_out.bz2 -o sams/${bn}.profile
++ tar xjfO ${f} | metaphlan2 --bowtie2db /usr/share/metaphlan2/db_v20/mpa_v20_m200 --mpa_pkl /usr/share/metaphlan2/db_v20/mpa_v20_m200.pkl --input_type multifastq --nproc 10 -s sams/${bn}.sam.bz2 --bowtie2out sams/${bn}.bowtie2_out.bz2 -o sams/${bn}.profile
+ done
+ ```
+
+@@ -761,4 +756,4 @@ In the output folder, you can find the f
+ 1. clade_name.fasta: the alignment file of all metagenomic strains.
+ 3. *.marker_pos: this file shows the starting position of each marker in the strains.
+ 3. *.info: this file shows the general information like the total length of the concatenated markers (full sequence length), number of used markers, etc.
+-4. *.polymorphic: this file shows the statistics on the polymorphic site, where "sample" is the sample name, "percentage_of_polymorphic_sites" is the percentage of sites that are suspected to be polymorphic, "avg_freq" is the average frequency of the dominant alleles on all polymorphic sites, "avg_coverage" is the average coverage at all polymorphic sites.
+\ No newline at end of file
++4. *.polymorphic: this file shows the statistics on the polymorphic site, where "sample" is the sample name, "percentage_of_polymorphic_sites" is the percentage of sites that are suspected to be polymorphic, "avg_freq" is the average frequency of the dominant alleles on all polymorphic sites, "avg_coverage" is the average coverage at all polymorphic sites.
diff --git a/debian/patches/series b/debian/patches/series
new file mode 100644
index 0000000..bd078ce
--- /dev/null
+++ b/debian/patches/series
@@ -0,0 +1,2 @@
+mpa_dir-is-usr_share_metaphlan2.patch
+spelling.patch
diff --git a/debian/patches/spelling.patch b/debian/patches/spelling.patch
new file mode 100644
index 0000000..8142807
--- /dev/null
+++ b/debian/patches/spelling.patch
@@ -0,0 +1,46 @@
+Author: Andreas Tille <tille at debian.org>
+Last-Update: Mon, 23 May 2016 16:09:13 +0200
+Description: Spelling
+
+--- a/README.md
++++ b/README.md
+@@ -315,7 +315,7 @@ Post-mapping arguments:
+ Additional analysis types and arguments:
+ -t ANALYSIS TYPE Type of analysis to perform:
+ * rel_ab: profiling a metagenomes in terms of relative abundances
+- * rel_ab_w_read_stats: profiling a metagenomes in terms of relative abundances and estimate the number of reads comming from each clade.
++ * rel_ab_w_read_stats: profiling a metagenomes in terms of relative abundances and estimate the number of reads coming from each clade.
+ * reads_map: mapping from reads to clades (only reads hitting a marker)
+ * clade_profiles: normalized marker counts for clades with at least a non-null marker
+ * marker_ab_table: normalized marker counts (only when > 0.0 and normalized by metagenome size if --nreads is specified)
+@@ -744,7 +744,7 @@ python ../strainphlan.py -h
+ The default setting can be stringent for some cases where you have very few samples left in the phylogenetic tree. You can relax some parameters to add more samples back:
+
+ 1. *marker_in_clade*: In each sample, the clades with the percentage of present markers less than this threshold are removed. Default "0.8". You can set this parameter to "0.5" to add some more samples.
+-2. *sample_in_marker*: If the percentage of samples that a marker present in is less than this threhold, that marker is removed. Default "0.8". You can set this parameter to "0.5" to add some more samples.
++2. *sample_in_marker*: If the percentage of samples that a marker present in is less than this threshold, that marker is removed. Default "0.8". You can set this parameter to "0.5" to add some more samples.
+ 3. *N_in_marker*: The consensus markers with the percentage of N nucleotides greater than this threshold are removed. Default "0.2". You can set this parameter to "0.5" to add some more samples.
+ 4. *gap_in_sample*: The samples with full sequences concatenated from all markers and having the percentage of gaps greater than this threshold will be removed. Default 0.2. You can set this parameter to "0.5" to add some more samples.
+ 5. *relaxed_parameters*: use this option to automatically set the above parameters to add some more samples by accepting some more gaps, Ns, etc. This option is equivalent to set: marker_in_clade=0.5, sample_in_marker=0.5, N_in_marker=0.5, gap_in_sample=0.5. Default "False".
+--- a/strainphlan.py
++++ b/strainphlan.py
+@@ -328,7 +328,7 @@ def read_params():
+ required=False,
+ default=['all'],
+ type=str,
+- help='The clades (space seperated) for which the script will compute '\
++ help='The clades (space separated) for which the script will compute '\
+ 'the marker alignments in fasta format and the phylogenetic '\
+ 'trees. If a file name is specified, the clade list in that '\
+ 'file where each clade name is on a line will be read.'
+--- a/metaphlan2.py
++++ b/metaphlan2.py
+@@ -555,7 +555,7 @@ def read_params(args):
+ default='rel_ab', help =
+ "Type of analysis to perform: \n"
+ " * rel_ab: profiling a metagenomes in terms of relative abundances\n"
+- " * rel_ab_w_read_stats: profiling a metagenomes in terms of relative abundances and estimate the number of reads comming from each clade.\n"
++ " * rel_ab_w_read_stats: profiling a metagenomes in terms of relative abundances and estimate the number of reads coming from each clade.\n"
+ " * reads_map: mapping from reads to clades (only reads hitting a marker)\n"
+ " * clade_profiles: normalized marker counts for clades with at least a non-null marker\n"
+ " * marker_ab_table: normalized marker counts (only when > 0.0 and normalized by metagenome size if --nreads is specified)\n"
diff --git a/debian/rules b/debian/rules
new file mode 100755
index 0000000..58cbf32
--- /dev/null
+++ b/debian/rules
@@ -0,0 +1,19 @@
+#!/usr/bin/make -f
+
+# DH_VERBOSE := 1
+export LC_ALL=C.UTF-8
+
+%:
+ dh $@ --with python2
+
+override_dh_auto_build:
+ dh_auto_build
+ markdown_py -f README.html README.md
+
+override_dh_installchangelogs:
+ dh_installchangelogs changeset.txt
+
+#override_dh_fixperms:
+# dh_fixperms
+# chmod +x debian/*/usr/share/metaphlan2/strainer_tutorial/*.sh
+# chmod -x debian/*/usr/share/metaphlan2/strainer_src/*.ini
diff --git a/debian/source/format b/debian/source/format
new file mode 100644
index 0000000..163aaf8
--- /dev/null
+++ b/debian/source/format
@@ -0,0 +1 @@
+3.0 (quilt)
diff --git a/debian/strainphlan.1 b/debian/strainphlan.1
new file mode 100644
index 0000000..583742b
--- /dev/null
+++ b/debian/strainphlan.1
@@ -0,0 +1,209 @@
+.TH METAPHLAN2_STRAINER "1" "July 2016" "metaphlan2_strainer 2.5.0" "User Commands"
+.SH NAME
+metaphlan2_strainer \- METAgenomic PHyLogenetic ANalysis for metagenomic taxonomic profiling (strainer)
+.SH SYNOPSIS
+.B metaphlan2_strainer.py
+[\-h] \fB\-\-ifn_samples\fR IFN_SAMPLES [IFN_SAMPLES ...]
+\fB\-\-mpa_pkl\fR MPA_PKL \fB\-\-output_dir\fR OUTPUT_DIR
+[\-\-ifn_markers IFN_MARKERS]
+[\-\-nprocs_main NPROCS_MAIN]
+[\-\-nprocs_load_samples NPROCS_LOAD_SAMPLES]
+[\-\-nprocs_align_clean NPROCS_ALIGN_CLEAN]
+[\-\-nprocs_raxml NPROCS_RAXML]
+[\-\-bootstrap_raxml BOOTSTRAP_RAXML]
+[\-\-ifn_ref_genomes IFN_REF_GENOMES [IFN_REF_GENOMES ...]]
+[\-\-N_in_marker N_IN_MARKER]
+[\-\-marker_strip_length MARKER_STRIP_LENGTH]
+[\-\-marker_in_clade MARKER_IN_CLADE]
+[\-\-sample_in_clade SAMPLE_IN_CLADE]
+[\-\-sample_in_marker SAMPLE_IN_MARKER]
+[\-\-gap_in_trailing_col GAP_IN_TRAILING_COL]
+[\-\-gap_trailing_col_limit GAP_TRAILING_COL_LIMIT]
+[\-\-gap_in_internal_col GAP_IN_INTERNAL_COL]
+[\-\-gap_in_sample GAP_IN_SAMPLE] [\-\-N_col N_COL]
+[\-\-N_count N_COUNT]
+[\-\-long_gap_length LONG_GAP_LENGTH]
+[\-\-long_gap_percentage LONG_GAP_PERCENTAGE]
+[\-\-p_value P_VALUE]
+[\-\-clades CLADES [CLADES ...]]
+[\-\-marker_list_fn MARKER_LIST_FN]
+[\-\-print_clades_only]
+[\-\-alignment_program {muscle,mafft}]
+[\-\-relaxed_parameters] [\-\-relaxed_parameters2]
+[\-\-keep_alignment_files]
+[\-\-keep_full_alignment_files]
+[\-\-save_sample2fullfreq] [\-\-use_threads]
+.SH DESCRIPTION
+Metaphlan2_strainer is a computational tool for tracking individual strains
+across large set of samples. The input of metaphlan2_strainer is a set of
+metagenomic samples and the output is a set of phylogenetic.
+.
+For each sample, metaphlan2_strainer extracts the strain of a specific species
+by merging and concatenating all reads mapped against that species markers in
+the MetaPhlAn2 database.
+.SH OPTIONS
+.SS optional arguments
+.TP
+\fB\-h\fR, \fB\-\-help\fR
+show this help message and exit
+.TP
+\fB\-\-ifn_samples\fR IFN_SAMPLES [IFN_SAMPLES ...]
+The list of sample files (space separated).The
+wildcard can also be used.
+.TP
+\fB\-\-mpa_pkl\fR MPA_PKL
+The database of metaphlan3.py.
+.TP
+\fB\-\-output_dir\fR OUTPUT_DIR
+The output directory.
+.TP
+\fB\-\-ifn_markers\fR IFN_MARKERS
+The marker file in fasta format.
+.TP
+\fB\-\-nprocs_main\fR NPROCS_MAIN
+The number of processors are used for the main
+threads. Default 1.
+.TP
+\fB\-\-nprocs_load_samples\fR NPROCS_LOAD_SAMPLES
+The number of processors are used for loading samples.
+Default nprocs_main.
+.TP
+\fB\-\-nprocs_align_clean\fR NPROCS_ALIGN_CLEAN
+The number of processors are used for aligning and
+cleaning markers. Default nprocs_main.
+.TP
+\fB\-\-nprocs_raxml\fR NPROCS_RAXML
+The number of processors are used for running raxml.
+Default nprocs_main.
+.TP
+\fB\-\-bootstrap_raxml\fR BOOTSTRAP_RAXML
+The number of runs for bootstraping when building the
+tree. Default 0.
+.TP
+\fB\-\-ifn_ref_genomes\fR IFN_REF_GENOMES [IFN_REF_GENOMES ...]
+The reference genome file names. They are separated by
+spaces.
+.TP
+\fB\-\-N_in_marker\fR N_IN_MARKER
+The consensus markers with the rate of N nucleotides
+greater than this threshold are removed. Default 0.2.
+.TP
+\fB\-\-marker_strip_length\fR MARKER_STRIP_LENGTH
+The number of nucleotides will be deleted from each of
+two ends of a marker. Default 50.
+.TP
+\fB\-\-marker_in_clade\fR MARKER_IN_CLADE
+In each sample, the clades with the rate of present
+markers less than this threshold are removed. Default
+0.8.
+.TP
+\fB\-\-sample_in_clade\fR SAMPLE_IN_CLADE
+Only clades present in at least sample_in_clade
+samples are kept. Default 2.
+.TP
+\fB\-\-sample_in_marker\fR SAMPLE_IN_MARKER
+If the percentage of samples that a marker present in
+is less than this threshold, that marker is removed.
+Default 0.8.
+.TP
+\fB\-\-gap_in_trailing_col\fR GAP_IN_TRAILING_COL
+If the number of the trailing nucleotide columns in
+aligned markers with the percentage of gaps greater
+than gap_in_trailing_col is less than
+gap_trailing_col_limit, these columns will be removed.
+Default 0.2.
+.TP
+\fB\-\-gap_trailing_col_limit\fR GAP_TRAILING_COL_LIMIT
+If the number of the trailing nucleotide columns in
+aligned markers with the percentage of gaps greater
+than gap_in_trailing_col is less than
+gap_trailing_col_limit, these columns will be removed.
+Default 101.
+.TP
+\fB\-\-gap_in_internal_col\fR GAP_IN_INTERNAL_COL
+The internal nucleotide columns in aligned markers
+with the percentage of gaps greater than
+gap_in_internal_col will be removed. Default 0.3.
+.TP
+\fB\-\-gap_in_sample\fR GAP_IN_SAMPLE
+The samples with full sequences from all markers and
+having the percentage of gaps greater than this
+threshold will be removed. Default 0.2.
+.TP
+\fB\-\-N_col\fR N_COL
+In aligned markers, if the percentage of nucleotide
+columns containing more than N_count Ns less than this
+threshold, these columns will be removed. Default 0.8.
+.TP
+\fB\-\-N_count\fR N_COUNT
+In aligned markers, if the percentage of nucleotide
+columns containing more than N_count Ns less than
+N_col threshold, these columns will be removed.
+Default 0.
+.TP
+\fB\-\-long_gap_length\fR LONG_GAP_LENGTH
+In each concatenated sequence of a sample, sequential
+gap positions is a gap group. A gap group with length
+greater than this threshold is considered as a long
+gap group. If the ratio between the number of unique
+positions in all long gap groups and the concatenated
+sequence length is less than long_gap_percentage,
+these positions will be removed from all concatenated
+sequences. Default 2.
+.TP
+\fB\-\-long_gap_percentage\fR LONG_GAP_PERCENTAGE
+Combining this threshold with long_gap_length to
+removed long gaps. Default 0.8.
+.TP
+\fB\-\-p_value\fR P_VALUE
+The p_value to reject a non\-polymorphic site.Default
+0.05.
+.TP
+\fB\-\-clades\fR CLADES [CLADES ...]
+The clades (space separated) for which the script will
+compute the marker alignments in fasta format and the
+phylogenetic trees. If a file name is specified, the
+clade list in that file where each clade name is on a
+line will be read.Default "automatically identify all
+clades".
+.TP
+\fB\-\-marker_list_fn\fR MARKER_LIST_FN
+The file name containing the list of considered
+markers. The other markers will be discarded. Default
+"None".
+.TP
+\fB\-\-print_clades_only\fR
+Only print the potential clades and stop without
+building any tree. This option is useful when you want
+to check quickly all possible clades and rerun only
+for some specific ones. Default "False".
+.TP
+\fB\-\-alignment_program\fR {muscle,mafft}
+The alignment program. Default "muscle".
+.TP
+\fB\-\-relaxed_parameters\fR
+Set marker_in_clade=0.5, sample_in_marker=0.5,
+N_in_marker=0.5, gap_in_sample=0.5. Default "False".
+.TP
+\fB\-\-relaxed_parameters2\fR
+Set marker_in_clade=0.2, sample_in_marker=0.2,
+N_in_marker=0.8, gap_in_sample=0.8. Default "False".
+.TP
+\fB\-\-keep_alignment_files\fR
+Keep the alignment files of all markers before
+cleaning step.
+.TP
+\fB\-\-keep_full_alignment_files\fR
+Keep the alignment files of all markers before
+truncating the starting and ending parts, and cleaning
+step. This is equivalent to \fB\-\-keep_alignment_files\fR
+\fB\-\-marker_strip_length\fR 0
+.TP
+\fB\-\-save_sample2fullfreq\fR
+Save sample2fullfreq to a msgpack file
+sample2fullfreq.msgpack.
+.TP
+\fB\-\-use_threads\fR
+Use multithreading. Default "Use multiprocessing".
+.SH AUTHOR
+This manpage was written by Andreas Tille for the Debian distribution and can be used for any other usage of the program.
diff --git a/debian/upstream/metadata b/debian/upstream/metadata
new file mode 100644
index 0000000..eaef81b
--- /dev/null
+++ b/debian/upstream/metadata
@@ -0,0 +1,11 @@
+Reference:
+ Author: Duy Tin Truong and Eric A Franzosa and Timothy L Tickle and Matthias Scholz and George Weingart and Edoardo Pasolli and Adrian Tett and Curtis Huttenhower and Nicola Segata
+ Title: "MetaPhlAn2 for enhanced metagenomic taxonomic profiling"
+ Journal: Nature Methods
+ Year: 2015
+ Volume: 12
+ Number: 10
+ Pages: 902–903
+ DOI: 10.1038/nmeth.3589
+ PMID: 26418763
+ URL: http://www.nature.com/nmeth/journal/v12/n10/full/nmeth.3589.html
diff --git a/debian/watch b/debian/watch
new file mode 100644
index 0000000..9d57c0f
--- /dev/null
+++ b/debian/watch
@@ -0,0 +1,4 @@
+version=3
+
+opts="repacksuffix=+ds,dversionmangle=s/\+ds//g,repack,compression=xz" \
+ https://bitbucket.org/biobakery/metaphlan2/downloads?tab=tags .*/(\d[\d.]+)\.tar\.bz2
--
Alioth's /usr/local/bin/git-commit-notice on /srv/git.debian.org/git/debian-med/metaphlan2.git
More information about the debian-med-commit
mailing list