New tool addition: KneadData

tools/kneaddata/.shed.yml

@@ -0,0 +1,15 @@
+name: kneaddata
+owner: iuc
+type: unrestricted
+description: Quality control and contaminant removal for metagenomic data
+long_description: >
+  KneadData is a tool designed to perform quality control on
+  metagenomic and metatranscriptomic sequencing data, especially
+  data from microbiome experiments. It performs adapter trimming,
+  quality filtering, and removal of host contamination using
+  Bowtie2/TRIMMOMATIC/TRF.
+homepage_url: https://github.com/biobakery/kneaddata
+remote_repository_url: https://github.com/galaxyproject/tools-iuc/tree/master/tools/kneaddata
+categories:
+  - Metagenomics
+  - Statistics

tools/kneaddata/kneaddata.xml

@@ -0,0 +1,272 @@
+<tool id="kneaddata" name="KneadData" version="0.12.1+galaxy0" python_template_version="3.5" profile="21.05">
+    <description>Quality control and contaminant removal for metagenomic data</description>
+    <requirements>
+        <requirement type="package" version="0.12.3">kneaddata</requirement>
+        <requirement type="package" version="0.40">trimmomatic</requirement>
+        <requirement type="package" version="2.5.4">bowtie2</requirement>
+        <requirement type="package" version="4.09.1">trf</requirement>
+        <requirement type="package" version="0.12.1">fastqc</requirement>
+    </requirements>
+    <command detect_errors="exit_code"><![CDATA[
+        kneaddata 
+        #if $read_type.select_read_type == "s" 
+            --unpaired "$read_type.single_read" 
+        #else 
+            -i1 "$read_type.forward_read" 
+            -i2 "$read_type.backward_read" 
+        #end if
+        -o "output_dir"
+        #if "$output_prefix"
+            --output-prefix "$output_prefix"
+        #end if
+        --threads "$number_threads"
+        --processes "$number_processes"
+        --quality-scores "$quality_scores"
+        #if $trimmomatic.trimmomatic_options.select_option == "c"
+            --trimmomatic-options "$trimmomatic.trimmomatic_options.custom_settings"
+        #end if
+        #if $trimmomatic.max_memory
+            --max-memory "$trimmomatic.max_memory"
+        #end if
+        #if $trimmomatic.sequencer
+            --sequencer-source "$trimmomatic.sequencer"
+        #end if
+        #if $trf_step.trf_bool == "include"
+            --mismatch "$trf.mismatch"
+            --delta "$trf.indel"
+            --minscore "$trf.minimum_score"
+            --maxperiod "$trf.maximum_period"
+        #else
+            --bypass-trf
+        #end if
+        $trim_repetitive
+        #if $trim_repetitive
+            --fastqc "fastqc"
+        #end if
+
+
+    ]]></command>
+
+    <inputs>
+
+        <conditional name="read_type"> 
+            <param name="select_read_type" type="select" label="Read type"> 
+                <option value="s">Single read</option> 
+                <option value="p">Paired reads</option> 
+            </param> 
+
+            <when value="s"> 
+                <param name="single_read" type="data" format="fastq" label="Single Read"/> 
+            </when> 
+            <when value="p"> 
+                <param name="forward_read" type="data" format="fastq" label="Forward read"/> 
+                <param name="backward_read" type="data" format="fastq" label="Reversed read" /> 
+            </when> 
+        </conditional>
+
+        <param name="trim_repetitive" type="boolean" truevalue="--run-trim-repetitive" falsevalue="" label="Trim repetitive/overrepresented sequences generated by FASTQC reports"/>
+
+        <param name="output_prefix" type="text" label="Custom prefix for all output files" help="Leave empty to keep the input file name."/>
+
+        <param name="number_threads" type="integer" value="1" label="Number of threads"/>
+
+        <param name="number_processes" type="integer" value="1" label="Number of processes"/>
+
+        <param name="quality_scores" type="select" label="Select quality score"> 
+            <option value="phred33" selected="true" >phred33</option> 
+            <option value="phred64">phred64</option> 
+        </param> 
+
+        <section name="trimmomatic" title="Trimmomatic arguments" >
+
+            <param name="max_memory" type="text" value="500m" label="Maximum memory for Trimmomatic"/>
+
+            <conditional name="trimmomatic_options">
+                <param name="select_option" type="select" label="Trimmomatic settings"> 
+                    <option value="d">Default settings</option> 
+                    <option value="c">Customize settings</option> 
+                </param> 
+
+                <when value="c"> 
+                    <param name="custom_settings" type="text" label="Custom Trimmomatic options" help="Manually specifying additional arguments will completely override the defaults."/> 
+                </when> 
+                <when value="d">
+                </when> 
+
+            </conditional>
+
+            <param name="sequencer" type="select" label="Available sequencers">
+                <option value="NexteraPE" selected="true">NexteraPE</option>
+                <option value="TruSeq2">TruSeq2</option>
+                <option value="TruSeq3">TruSeq3</option>
+            </param>
+        </section>
+
+
+        <conditional name="trf_step">
+            <param name="trf_bool" type="select" label="Tandem Repeat Finder">
+                <option value="include">Include TRF in KneadData Workflow</option>
+                <option value="skip">Skip TRF</option>
+            </param>
+
+            <when value="include">
+
+                <section name="trf" title="TRF (Tandem Repeats Finder) arguments" >
+
+                    <param name="mismatch" type="select" label="Mismatch penalty">
+                        <option value="3">3 (more permissive)</option> 
+                        <option value="5">5</option>
+                        <option value="7" selected="true">7 (less permissive)</option>  
+                    </param>
+
+                    <param name="indel" type="select" label="Indel penalty (delta)">
+                        <option value="3">3 (more permissive)</option> 
+                        <option value="5">5</option>
+                        <option value="7" selected="true">7 (less permissive)</option>  
+                    </param>
+
+                    <param name="minimum_score" type="integer" value="50" label="Minimum alignment score to report"/>
+                    <param name="maximum_period" type="integer" value="500" min="1" max="2000" label="Maximum period size to report"/>
+
+                </section>
+            </when>
+            <when value="skip">
+
+            </when>
+        </conditional>
+
+    </inputs>
+    <outputs>
+        <data name="single_output" format="fastq" from_work_dir="output_dir/.repeats.removed.fastq" label="KneadData single end results (with TRF)">
+            <filter>read_type["select_read_type"] == "s" and trf_step["trf_bool"] == "include"</filter>
+        </data>
+        <data name="single_output_trimmed" format="fastq" from_work_dir="output_dir/.trimmed.fastq" label="KneadData single end results (without TRF)">
+            <filter>read_type["select_read_type"] == "s" and trf_step["trf_bool"] == "skip"</filter>
+        </data>
+
+        <data name="paired_forward" format="fastq" from_work_dir="output_dir/.repeats.removed.1.fastq" label="KneadData paired end forward reads (with TRF)">
+            <filter>read_type["select_read_type"] == "p" and trf_step["trf_bool"] == "include"</filter>
+        </data>
+        <data name="paired_forward_trimmed" format="fastq" from_work_dir="output_dir/.trimmed.1.fastq" label="KneadData paired end forward reads (without TRF)">
+            <filter>read_type["select_read_type"] == "p" and trf_step["trf_bool"] == "skip"</filter>
+        </data>
+
+        <data name="paired_backward" format="fastq" from_work_dir="output_dir/.repeats.removed.2.fastq" label="KneadData paired end reverse reads (with TRF)">
+            <filter>read_type["select_read_type"] == "p" and trf_step["trf_bool"] == "include"</filter>
+        </data>
+        <data name="paired_backward_trimmed" format="fastq" from_work_dir="output_dir/.trimmed.2.fastq" label="KneadData paired end reverse reads (without TRF)">
+            <filter>read_type["select_read_type"] == "p" and trf_step["trf_bool"] == "skip"</filter>
+        </data>
+    </outputs>
+    <tests>
+        <test expect_num_outputs="1">
+            <param name="number_threads" value="1"/>
+            <param name="number_processes" value="1"/>
+            <param name="quality_scores" value="phred33"/>
+            <section name="trimmomatic">
+                <param name="max_memory" value="500m"/>
+                <param name="sequencer" value="NexteraPE"/>
+                <section name="trimmomatic_options">
+                    <param name="select_option" value="d"/>
+                </section>
+            </section>
+            <section name="read_type">
+                <param name="select_read_type" value="s"/>
+                <param name="single_read" value="28C.single.fastq"/>
+            </section>
+            <output name="single_output" file="single_output.fastq"/>
+        </test>
+        <test expect_num_outputs="2">
+            <param name="number_threads" value="2"/>
+            <param name="number_processes" value="2"/>
+            <param name="quality_scores" value="phred33"/>
+            <section name="trimmomatic">
+                <param name="max_memory" value="500m"/>
+                <param name="sequencer" value="NexteraPE"/>
+                <section name="trimmomatic_options">
+                    <param name="select_option" value="d"/>
+                </section>
+            </section>
+            <section name="read_type">
+                <param name="select_read_type" value="p"/>
+                <param name="forward_read" value="28C.R1.fastq"/>
+                <param name="backward_read" value="28C.R2.fastq"/>
+            </section>
+            <output name="paired_forward" file="paired_forward.fastq"/>
+            <output name="paired_backward" file="paired_backward.fastq"/>
+        </test>
+    </tests>
+
+    <help><![CDATA[
+    usage: kneaddata [-h] [--version] [-v] [-i1 INPUT1] [-i2 INPUT2]
+                 [-un UNPAIRED]  -o OUTPUT_DIR
+                 [-db REFERENCE_DB] [--bypass-trim] [--run-trim-repetitive]
+                 [--output-prefix OUTPUT_PREFIX] [-t &lt;1&gt;] [-p &lt;1&gt;]
+                 [-q {phred33,phred64}] [--run-bmtagger]
+                 [--run-fastqc-start] [--run-fastqc-end] [--store-temp-output]
+                 [--cat-final-output]
+                 [--log-level {DEBUG,INFO,WARNING,ERROR,CRITICAL}] [--log LOG]
+                 [--trimmomatic TRIMMOMATIC_PATH] [--max-memory MAX_MEMORY]
+                 [--trimmomatic-options TRIMMOMATIC_OPTIONS]
+                 [--bowtie2 BOWTIE2_PATH] [--bowtie2-options BOWTIE2_OPTIONS]
+                 [--bmtagger BMTAGGER_PATH] [--trf TRF_PATH] [--match MATCH]
+                 [--mismatch MISMATCH] [--delta DELTA] [--pm PM] [--pi PI]
+                 [--minscore MINSCORE] [--maxperiod MAXPERIOD]
+                 [--fastqc FASTQC_PATH]
+
+    KneadData
+
+    options:
+
+
+    -h, --help  show this help message and exit
+    -v, --verbose  additional output is printed
+    --version  show program's version number and exit
+    -i INPUT, --input INPUT  input FASTQ file (add a second argument instance to run with paired input files)
+    -o OUTPUT_DIR, --output OUTPUT_DIR  directory to write output files
+    --db REFERENCE_DB, --reference-db REFERENCE_DB  location of reference database
+    --run-trim-repetitive  Option to trim repetitive/overrepresented sequences generated by FASTQC reports 
+    --bypass-trim  bypass the trim step
+    --output-prefix OUTPUT_PREFIX  prefix for all output files  [ DEFAULT : $SAMPLE_kneaddata ]
+    -t <1>, --threads <1>  number of threads  [ Default : 1 ]
+    -p <1>, --processes <1>  number of processes  [ Default : 1 ]
+    -q <quality>, --quality-scores <quality>  quality scores [phred33|phred64] [DEFAULT: phred33]
+    --run-bmtagger  run BMTagger instead of Bowtie2 to identify contaminant reads
+    --bypass-trf  option to bypass the removal of tandem repeats
+    --run-fastqc-start  run fastqc at the beginning of the workflow
+    --run-fastqc-end  run fastqc at the end of the workflow
+    --store-temp-output  store temp output files [ DEFAULT : temp output files are removed ]
+    --cat-final-output  concatenate all final output files [ DEFAULT : final output is not concatenated ]
+    --log-level <DEBUG|INFO|WARNING|ERROR|CRITICAL>  level of log messages [DEFAULT: DEBUG]
+    --log LOG  log file [ DEFAULT : $OUTPUT_DIR/$SAMPLE_kneaddata.log ]
+    --trimmomatic TRIMMOMATIC_PATH  path to trimmomatic [ DEFAULT : $PATH ]
+    --max-memory MAX_MEMORY  max amount of memory [ DEFAULT : 500m ]
+    --trimmomatic-options TRIMMOMATIC_OPTIONS  options for trimmomatic [ DEFAULT : SLIDINGWINDOW:4:20 MINLEN:50 ]
+      MINLEN is set to 50 percent of total input read length. The user can alternatively specify a length (in bases) for MINLEN.
+    --sequencer-source  options for sequencer-source [ DEFAULT: NexteraPE]  Available sequencers: ["NexteraPE","TruSeq2","TruSeq3"]
+    --bowtie2 BOWTIE2_PATH  path to bowtie2 [ DEFAULT : $PATH ]
+    --bowtie2-options BOWTIE2_OPTIONS  options for bowtie2 [ DEFAULT : --very-sensitive ]
+    --bmtagger BMTAGGER_PATH  path to BMTagger  [ DEFAULT : $PATH ]
+    --bypass-trf  bypass the TRF step
+    --trf TRF_PATH  path to TRF [ DEFAULT : $PATH ]
+    --mismatch MISMATCH  mismatching penalty  [ DEFAULT : 7 ]
+    --delta DELTA  indel penalty  [ DEFAULT : 7 ]
+    --pm PM  match probability  [ DEFAULT : 80 ]
+    --pi PI  indel probability  [ DEFAULT : 10 ]
+    --minscore MINSCORE  minimum alignment score to report  [ DEFAULT : 50 ]
+    --maxperiod MAXPERIOD  maximum period size to report  [ DEFAULT : 500 ]
+    --fastqc FASTQC_PATH  path to fastqc [ DEFAULT : $PATH ]
+
+    ]]></help>
+    <citations>
+        <citation type="bibtex">
+        @software{kneaddata,
+        title = {KneadData},
+        author = {Harvard School of Public Health},
+        year = {2015},
+        url = {https://github.com/biobakery/kneaddata},
+        license = {MIT},
+        note = {Quality control and contaminant removal tool for metagenomic sequencing data}
+        }</citation>
+    </citations>
+</tool>

tools/kneaddata/test-data/bowtie2_indices.loc

@@ -0,0 +1,38 @@
+# bowtie2_indices.loc.sample
+# This is a *.loc.sample file distributed with Galaxy that enables tools
+# to use a directory of indexed data files. This one is for Bowtie2 and Tophat2.
+# See the wiki: http://wiki.galaxyproject.org/Admin/NGS%20Local%20Setup
+# First create these data files and save them in your own data directory structure.
+# Then, create a bowtie_indices.loc file to use those indexes with tools.
+# Copy this file, save it with the same name (minus the .sample), 
+# follow the format examples, and store the result in this directory.
+# The file should include an one line entry for each index set.
+# The path points to the "basename" for the set, not a specific file.
+# It has four text columns seperated by TABS.
+#
+# <unique_build_id>	<dbkey>	<display_name>	<file_base_path>
+#
+# So, for example, if you had hg18 indexes stored in:
+#
+#    /depot/data2/galaxy/hg19/bowtie2/
+#
+# containing hg19 genome and hg19.*.bt2 files, such as:
+#    -rw-rw-r-- 1 james   james   914M Feb 10 18:56 hg19canon.fa
+#    -rw-rw-r-- 1 james   james   914M Feb 10 18:56 hg19canon.1.bt2
+#    -rw-rw-r-- 1 james   james   683M Feb 10 18:56 hg19canon.2.bt2
+#    -rw-rw-r-- 1 james   james   3.3K Feb 10 16:54 hg19canon.3.bt2
+#    -rw-rw-r-- 1 james   james   683M Feb 10 16:54 hg19canon.4.bt2
+#    -rw-rw-r-- 1 james   james   914M Feb 10 20:45 hg19canon.rev.1.bt2
+#    -rw-rw-r-- 1 james   james   683M Feb 10 20:45 hg19canon.rev.2.bt2
+#
+# then the bowtie2_indices.loc entry could look like this:
+#
+#hg19	hg19	Human (hg19)	/depot/data2/galaxy/hg19/bowtie2/hg19canon
+#
+#More examples:
+#
+#mm10	mm10	Mouse (mm10)	/depot/data2/galaxy/mm10/bowtie2/mm10
+#dm3	dm3		D. melanogaster (dm3)	/depot/data2/galaxy/mm10/bowtie2/dm3
+#
+#
+test_value	test_dbkey	test_name	${__HERE__}/bowtie2-ref

tools/kneaddata/test-data/test_paired_1.fastq

@@ -0,0 +1,4 @@
+@test1
+ACGTACGT
++
+IIIIIIII

tools/kneaddata/test-data/test_paired_2.fastq

@@ -0,0 +1,4 @@
+@test1
+TGCTAGCT
++
+IIIIIIII

tools/kneaddata/test-data/test_single.fastq

@@ -0,0 +1,8 @@
+@test1
+ACGTACGT
++
+IIIIIIII
+@test2
+TGCTAGCT
++
+IIIIIIII

tools/kneaddata/tool-data/bowtie2_indices.loc.sample

@@ -0,0 +1,35 @@
+# bowtie2_indices.loc.sample
+# This is a *.loc.sample file distributed with Galaxy that enables tools
+# to use a directory of indexed data files. This one is for Bowtie2 and Tophat2.
+# See the wiki: http://wiki.galaxyproject.org/Admin/NGS%20Local%20Setup
+# First create these data files and save them in your own data directory structure.
+# Then, create a bowtie_indices.loc file to use those indexes with tools.
+# Copy this file, save it with the same name (minus the .sample), 
+# follow the format examples, and store the result in this directory.
+# The file should include an one line entry for each index set.
+# The path points to the "basename" for the set, not a specific file.
+# It has four text columns seperated by TABS.
+#
+# <unique_build_id>	<dbkey>	<display_name>	<file_base_path>
+#
+# So, for example, if you had hg18 indexes stored in:
+#
+#    /depot/data2/galaxy/hg19/bowtie2/
+#
+# containing hg19 genome and hg19.*.bt2 files, such as:
+#    -rw-rw-r-- 1 james   james   914M Feb 10 18:56 hg19canon.fa
+#    -rw-rw-r-- 1 james   james   914M Feb 10 18:56 hg19canon.1.bt2
+#    -rw-rw-r-- 1 james   james   683M Feb 10 18:56 hg19canon.2.bt2
+#    -rw-rw-r-- 1 james   james   3.3K Feb 10 16:54 hg19canon.3.bt2
+#    -rw-rw-r-- 1 james   james   683M Feb 10 16:54 hg19canon.4.bt2
+#    -rw-rw-r-- 1 james   james   914M Feb 10 20:45 hg19canon.rev.1.bt2
+#    -rw-rw-r-- 1 james   james   683M Feb 10 20:45 hg19canon.rev.2.bt2
+#
+# then the bowtie2_indices.loc entry could look like this:
+#
+#hg19	hg19	Human (hg19)	/depot/data2/galaxy/hg19/bowtie2/hg19canon
+#
+#More examples:
+#
+#mm10	mm10	Mouse (mm10)	/depot/data2/galaxy/mm10/bowtie2/mm10
+#dm3	dm3		D. melanogaster (dm3)	/depot/data2/galaxy/mm10/bowtie2/dm3

tools/kneaddata/tool_data_table_conf.xml.sample

@@ -0,0 +1,8 @@
+<!-- Use the file tool_data_table_conf.xml.oldlocstyle if you don't want to update your loc files as changed in revision 4550:535d276c92bc-->
+<tables>
+    <!-- Locations of indexes in the Bowtie2 mapper format -->
+    <table name="bowtie2_indexes" comment_char="#">
+        <columns>value, dbkey, name, path</columns>
+        <file path="tool-data/bowtie2_indices.loc" />
+    </table>
+</tables>