# HG changeset patch
# User dannon
# Date 1333006331 14400
# Node ID 4f3fe44edb3f6a0821e86569f169c2a775faabfb

Initial upload.  Still needs tests.

diff -r 000000000000 -r 4f3fe44edb3f metaphlan.xml
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/metaphlan.xml	Thu Mar 29 03:32:11 2012 -0400
@@ -0,0 +1,121 @@
+<tool id="metaphlan" name="MetaPhlAn" version="1.0">
+<requirements>
+<requirement type="package">metaphlan</requirement>
+<requirement type="package" version="2.2.25+">blast</requirement>
+</requirements>
+  <description>Metagenomic Phylogenetic Analysis</description>
+  <command>
+      metaphlan.py
+      #if str($source.type) == "fasta":
+          ${source.fasta_input}
+      #else:
+          ${source.blast_input}
+      #end if
+      ${metaphlan_out}
+      --nproc 4
+      #if str($source.type) == "fasta":
+      --blastout metagenome.outfmt6.txt
+      --evalue ${source.evalue}
+      #end if
+      --lib_dir ${GALAXY_DATA_INDEX_DIR}/shared/metaphlan
+      --min_cu_len ${min_cu_len}
+      --min_nreads ${min_nreads}
+  </command>
+  <inputs>
+
+    <conditional name="source">
+        <param name="type" type="select" label="Input Type">
+            <option value="fasta">multi-fasta file containing metagenomic reads</option>
+            <option value="blast">NCBI BLAST output file</option>
+        </param>
+      <when value="fasta">
+        <param format="fasta" name="fasta_input" type="data" label="from"/>
+        <param name="evalue" type="float" size="15" value="0.00001" label="evalue threshold for the blasting" />
+      </when>
+      <when value="blast">
+        <param format="tabular" name="blast_input" type="data" label="from"/>
+      </when>
+    </conditional>
+
+    <param name="tax_lev" type="select" label="Taxonomic Level" help="The taxonomic level for the relative abundance output">
+        <option value="a">All taxonomic levels</option>
+        <option value="k">Kingdoms (Bacteria and Archaea) only</option>
+        <option value="p">Phyla only</option>
+        <option value="c">Classes only</option>
+        <option value="o">Orders only</option>
+        <option value="f">Families only</option>
+        <option value="g">Genera only</option>
+        <option value="s">Species only</option>
+    </param>
+    <param name="min_cu_len" type="integer" value="10000" help="min_cu_len" label="Minimum total nucleotide length for the unique markers for estimating the abundance without considering children clade abundances" />
+    <param name="min_nreads" type="integer" value="5" help="min_nreads" label="minimum total reads assigned to a clade for estimating the abundance without considering children clade abundances" />
+  </inputs>
+  <outputs>
+    <data format="tabular" name="metaphlan_out" label="MetaPhlAn on ${on_string}" />
+    <data format="tabular" name="blast_out" from_work_dir="metagenome.outfmt6.txt" label="MetaPhlAn BLAST on ${on_string}">
+        <filter>source['type'] == "fasta"</filter>
+    </data>
+  </outputs>
+  <tests>
+  </tests>
+  <help>
+
+**What it does**
+MetaPhlAn is a computational tool for profiling the composition of microbial communities from metagenomic shotgun sequencing data. MetaPhlAn relies on unique clade-specific marker genes identified from reference genomes, allowing orders of magnitude speedups and unambiguous taxonomic assignments.
+
+MetaPhlAn main features are:
+
+More than 100x computational speedup compared to Blast-based approaches or other available methods with species level resolution
+Higher accuracy in estimating the true composition of microbial communities in terms of organismal relative abundance
+Unambiguous read-to-taxa assignments as conserved inter-clade sequences are removed from the reference sequence data
+
+---------
+
+**Inputs**
+
+The input file can be a multi-fasta file containing metagenomic reads OR a NCBI BLAST output file (-outfmt 6 format) of the metagenomic read fasta file against the metaflan database.
+
+**outputs**
+
+The output is a tab-separated output file of the predicted taxon relative abundances.
+If the input is a multi-fasta file then the output from the BLAST operation is also provided as an additional output.
+
+---------
+
+**Settings**::
+
+  --tax_lev TAXONOMIC_LEVEL
+                        The taxonomic level for the relative abundance 
+                        output:
+                        'a' : all taxonomic levels
+                        'k' : kingdoms (Bacteria and Archaea) only
+                        'p' : phyla only
+                        'c' : classes only
+                        'o' : orders only
+                        'f' : families only
+                        'g' : genera only
+                        's' : species only
+                        [default 'a']
+  --evalue              evalue threshold for the blasting
+                        [default 1e-6]
+  --min_cu_len          minimum total nucleotide lenght for the unique
+                        markers for estimating the abundance without
+                        considering children clade abundances
+                        [default 10000]
+  --min_nreads          minimum total reads assigned to a clade for
+                        estimating the abundance without considering
+                        children clade abundances
+                        [default 5]
+
+-----
+
+**Citation**
+
+If you find MetaPhlAn useful in your research, please cite our paper:
+Nicola Segata, Levi Waldron, Annalisa Ballarini, Vagheesh Narasimhan, Olivier Jousson, Curtis Huttenhower.
+"Fast and accurate metagenomic profiling of microbial community composition using unique clade-specific marker genes"
+***in review***
+
+    </help>
+</tool>
+