diff kraken.xml @ 0:0f17a8816b28 draft

planemo upload for repository https://github.com/galaxyproject/tools-devteam/blob/master/tool_collections/kraken/kraken/ commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/kraken.xml	Thu Jul 23 10:55:44 2015 -0400
@@ -0,0 +1,113 @@
+<?xml version="1.0"?>
+<tool id="kraken" name="Kraken" version="1.1.0">
+    <description>
+        assign taxonomic labels to sequencing reads
+    </description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <command>
+        <![CDATA[
+        @SET_DATABASE_PATH@ &&
+        kraken --threads \${GALAXY_SLOTS:-1} @INPUT_DATABASE@ 
+        
+        #if $input_sequences.is_of_type( 'fastq' ):
+            --fastq-input
+        #else:
+            --fasta-input
+        #end if
+
+        ${only_classified_output}
+
+        #if str( $quick_operation.quick ) == "yes":
+            --quick
+            --min-hits ${quick_operation.min_hits}
+
+        #end if
+
+        "$input_sequences"
+
+        #if $split_reads:
+            --classified-out "${classified_out}" --unclassified-out "${unclassified_out}"
+        #end if
+        --output "${output}"
+        ##kraken-translate --db ${kraken_database.fields.name} "${output}" > "${translated}"
+        ]]>
+    </command>
+    <inputs>
+        <param format="fasta,fastq" label="Input sequences" name="input_sequences" type="data" help="FASTA or FASTQ datasets"/>
+        <param label="Output classified and unclassified reads?" name="split_reads" type="boolean" help="Sets --unclassified-out and --classified-out"/>
+  
+        <conditional name="quick_operation">
+            <param name="quick" type="select" label="Enable quick operation?" help="--quick; Rather than searching all k-mers in a sequence, stop classification after a specified number of database hit">
+                <option value="yes">Yes</option>
+                <option selected="True" value="no">No</option>
+            </param>
+            <when value="yes">
+                <param name="min_hits" type="integer" value="1" label="Number of hits required for classification" help="--min-hits; min-hits will allow you to require multiple hits before declaring a sequence classified, which can be especially useful with custom databases when testing to see if sequences either do or do not belong to a particular genome; default=1"/>
+            </when>
+            <when value="no">
+                <!-- Do absolutely nothing -->
+            </when>
+        </conditional>
+
+        <param name="only_classified_output" type="boolean" checked="False" truevalue="--only-classified-output" falsevalue="" label="Print no Kraken output for unclassified sequences" help="--only-classified-output"/>
+
+        <expand macro="input_database" />
+    </inputs>
+    <outputs>
+        <data format="tabular" label="${tool.name} on ${on_string}: Classified reads" name="classified_out">
+            <filter>(split_reads)</filter>
+        </data>
+        <data format="tabular" label="${tool.name} on ${on_string}: Unclassified reads" name="unclassified_out">
+            <filter>(split_reads)</filter>
+        </data>
+        <data format="tabular" label="${tool.name} on ${on_string}: Classification" name="output" />
+        <!--<data format="tabular" label="${tool.name} on ${on_string}: Translated classification" name="translated" />-->
+    </outputs>
+    <help>
+        <![CDATA[
+**What it does**
+
+Kraken is a taxonomic sequence classifier that assigns taxonomic labels to short DNA reads. It does this by examining the k-mers within a read and querying a database with those k-mers. This database contains a mapping of every k-mer in Kraken's genomic library to the lowest common ancestor (LCA) in a taxonomic tree of all genomes that contain that k-mer. The set of LCA taxa that correspond to the k-mers in a read are then analyzed to create a single taxonomic label for the read; this label can be any of the nodes in the taxonomic tree. Kraken is designed to be rapid, sensitive, and highly precise.
+
+-----
+
+**Kraken options**
+
+The Galaxy version of Kraken implements the following options::
+
+        
+  --fasta-input             Input is FASTA format
+  --fastq-input             Input is FASTQ format
+  --quick                   Quick operation (use first hit or hits)
+  --min-hits NUM            In quick op., number of hits req'd for classification
+                            NOTE: this is ignored if --quick is not specified
+  --unclassified-out        Print unclassified sequences to filename
+  --classified-out          Print classified sequences to filename
+
+  --only-classified-output  Print no Kraken output for unclassified sequences
+                          
+------
+
+**Output Format**
+
+Each sequence classified by Kraken results in a single line of output. Output lines contain five tab-delimited fields; from left to right, they are::
+
+    1. "C"/"U": one letter code indicating that the sequence was either classified or unclassified.
+    2. The sequence ID, obtained from the FASTA/FASTQ header.
+    3. The taxonomy ID Kraken used to label the sequence; this is 0 if the sequence is unclassified.
+    4. The length of the sequence in bp.
+    5. A space-delimited list indicating the LCA mapping of each k-mer in the sequence. For example, "562:13 561:4 A:31 0:1 562:3" would indicate that:
+            a) the first 13 k-mers mapped to taxonomy ID #562
+            b) the next 4 k-mers mapped to taxonomy ID #561
+            c) the next 31 k-mers contained an ambiguous nucleotide
+            d) the next k-mer was not in the database
+            e) the last 3 k-mers mapped to taxonomy ID #562
+        ]]>
+    </help>
+    <expand macro="requirements" />
+    <expand macro="stdio" />
+    <expand macro="version_command" />
+    <expand macro="citations" />
+</tool>