├── smalt
    ├── reads.fastq
    ├── reference.fasta
    ├── Dockerfile
    ├── instructions.sh
    ├── README.md
    └── smalt_wrapper.xml
├── catDocker.xml
└── README.md


/smalt/reads.fastq:
--------------------------------------------------------------------------------
1 | @1
2 | AAAA
3 | +
4 | IIII
5 | @2
6 | AAAA
7 | +
8 | IIII
9 | 


--------------------------------------------------------------------------------
/smalt/reference.fasta:
--------------------------------------------------------------------------------
1 | >a
2 | AAAAGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGGG
3 | 


--------------------------------------------------------------------------------
/catDocker.xml:
--------------------------------------------------------------------------------
 1 | <tool id="catdc" name="Concatenate datasets (in docker)">
 2 |     <description>tail-to-head</description>
 3 |     <requirements>
 4 |       <container type="docker">busybox:ubuntu-12.04</container>
 5 |     </requirements>
 6 |     <command>
 7 |       echo "Galaxy slots passed through contain as \$GALAXY_SLOTS";
 8 |       cat $input1
 9 |       #for $q in $queries
10 |             ${q.input2}
11 |       #end for
12 |       &gt; $out_file1;
13 |       echo "Work dir output" &gt; working_file
14 | 
15 |     </command>
16 |     <inputs>
17 |         <param name="input1" type="data" label="Concatenate Dataset"/>
18 |         <repeat name="queries" title="Dataset">
19 |             <param name="input2" type="data" label="Select" />
20 |         </repeat>
21 |     </inputs>
22 |     <outputs>
23 |         <data name="out_file1" format="input" metadata_source="input1"/>
24 |         <data name="out_file2" format="txt" from_work_dir="working_file" />
25 |     </outputs>
26 |     <help>
27 |     </help>
28 | </tool>
29 | 


--------------------------------------------------------------------------------
/smalt/Dockerfile:
--------------------------------------------------------------------------------
 1 | # Galaxy - SMALT
 2 | # From https://toolshed.g2.bx.psu.edu/repository/view_repository?sort=Repository.name&operation=view_or_manage_repository&changeset_revision=54855bd8d107&id=ec70d959cc6d865d
 3 | 
 4 | FROM debian:wheezy
 5 | 
 6 | MAINTAINER Aaron Petkau, aaron.petkau@gmail.com
 7 | 
 8 | # make sure the package repository is up to date
 9 | RUN DEBIAN_FRONTEND=noninteractive apt-get -qq update
10 | 
11 | RUN DEBIAN_FRONTEND=noninteractive apt-get install -y python
12 | RUN DEBIAN_FRONTEND=noninteractive apt-get install -y wget
13 | RUN DEBIAN_FRONTEND=noninteractive apt-get install -y mercurial
14 | 
15 | RUN mkdir /tmp/smalt
16 | WORKDIR /tmp/smalt
17 | 
18 | RUN wget ftp://ftp.sanger.ac.uk/pub4/resources/software/smalt/smalt-0.7.3.tgz
19 | RUN tar -xvvzf smalt-0.7.3.tgz
20 | RUN cp smalt-0.7.3/smalt_x86_64 /usr/bin/smalt_unknown
21 | 
22 | RUN hg clone https://toolshed.g2.bx.psu.edu/repos/cjav/smalt smalt_deps
23 | RUN cp smalt_deps/smalt_wrapper.py /usr/bin/smalt_wrapper.py
24 | RUN chmod a+x /usr/bin/smalt_wrapper.py
25 | 
26 | RUN apt-get clean && rm -rf /tmp/smalt && rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/*
27 | 


--------------------------------------------------------------------------------
/smalt/instructions.sh:
--------------------------------------------------------------------------------
 1 | # Run docker image 'debian/wheezy' in interactive mode
 2 | sudo docker run -i -t debian:wheezy
 3 | 
 4 | # Run the below in this image
 5 | 
 6 | apt-get update
 7 | apt-get install python
 8 | apt-get install wget
 9 | apt-get install mercurial
10 | 
11 | mkdir tool
12 | cd tool
13 | 
14 | wget ftp://ftp.sanger.ac.uk/pub4/resources/software/smalt/smalt-0.7.3.tgz
15 | tar -xvvzf smalt-0.7.3.tgz
16 | 
17 | # because the smalt_wrapper.py finds the binary name based on `uname -i` which is unknown in docker
18 | mv smalt-0.7.3/smalt_x86_64 smalt_unknown
19 | 
20 | hg clone https://toolshed.g2.bx.psu.edu/repos/cjav/smalt smalt_deps
21 | cp smalt_deps/smalt_wrapper.py .
22 | 
23 | # add smalt tools to PATH (probably different ways to do this)
24 | ln -s /tool/smalt_unknown /usr/bin 
25 | ln -s /tool/smalt_wrapper.py /usr/bin
26 | 
27 | # make smalt_wrapper executable
28 | chmod a+x /tool/smalt_wrapper.py
29 | 
30 | # exit out of docker image and run the below to commit to new container.  replace the number '07b...' with container id for the above docker container.
31 | sudo docker commit -m "make smalt_wrapper executable" -a "Aaron Petkau" 07b937918961 apetkau/smalt:v3
32 | 
33 | # push to dockerhub
34 | # please see instructions at http://docs.docker.com/userguide/dockerimages/#push-an-image-to-docker-hub
35 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | Integrating Docker-based tools within Galaxy
 2 | ============================================
 3 | 
 4 | This document describes a method for integrating [Docker](http://www.docker.com/) based tools within [Galaxy](http://galaxyproject.org/).  Docker is a method for wrapping up a tool along with all of it's dependencies into a single container which can be distrubted with the help of [Dockerhub](https://hub.docker.com/).  A method to run docker based tools was added to Galaxy in https://bitbucket.org/galaxy/galaxy-central/pull-request/401/allow-tools-and-deployers-to-specify/diff.
 5 | 
 6 | Initial Galaxy and Docker Setup
 7 | -------------------------------
 8 | 
 9 | ### Setup Latest Galaxy
10 | 
11 | Please download and setup the latest Galaxy from galaxy-central.  More detailed instructions are found at https://wiki.galaxyproject.org/Admin/GetGalaxy but the two main commands you need to run are:
12 | 
13 | ```bash
14 | $ hg clone https://bitbucket.org/galaxy/galaxy-central
15 | $ cd galaxy-central
16 | $ sh run.sh
17 | ```
18 | 
19 | ### Setup Docker Test Tool
20 | 
21 | A test tool configuration file `catDocker.xml` is included with Galaxy (or at [catDocker.xml](catDocker.xml)).  This can be setup with the following commands (run within `galaxy-central` directory).
22 | 
23 | 1. Setup `catDocker.xml` tool
24 |    
25 |    ```bash
26 |    $ mkdir tools/docker
27 |    $ cp test/functional/tools/catDocker.xml tools/docker/
28 |    ```
29 |    
30 |    Now, in the `tool_conf.xml` file please add a new section for this tool:
31 |    
32 |    ```xml
33 |      <section>
34 |        <tool file="docker/catDocker.xml"/>
35 |      </section>
36 |    ```
37 | 
38 | 2. Construct a `job_conf.xml` which instructs Galaxy to run tools docker-based tools using docker.
39 |    
40 |    Construct a basic `job_conf.xml` with the following command.
41 |    
42 |    ```bash
43 |    cp job_conf.xml.sample_basic job_conf.xml
44 |    ```
45 |    
46 |    Add a docker destination in `job_conf.xml` to enable running through docker:
47 |    
48 |    ```xml
49 |        <destinations default="docker_local">
50 |           <destination id="local" runner="local"/>
51 |           <destination id="docker_local" runner="local">
52 |             <param id="docker_enabled">true</param>
53 |           </destination>
54 |        </destinations>
55 |    ```
56 |    
57 |    More information can be found in the `job_conf.xml.sample_advanced` file that comes with Galaxy.
58 | 
59 | 3. Enable docker to run using sudo without a password.
60 | 
61 |    Add docker runner to sudoers file (replace `galaxy` with the username you are running galaxy under):
62 | 
63 |    ```
64 |    galaxy  ALL = (root) NOPASSWD: SETENV: /usr/bin/docker
65 |    ```
66 | 
67 | 4. Start up Galaxy
68 | 
69 |    ```bash
70 |    $ sh run.sh
71 |    ```
72 | 
73 | 5. Test
74 | 
75 |    Run test tool **Concatenate datasets (in docker)**
76 | 
77 |    Check log file.  If the tool ran you should see entries with `docker` like:
78 | 
79 |    ```
80 |     command is: sudo docker run -e "GALAXY_SLOTS=$GALAXY_SLOTS" -v /home/aaron/Projects/galaxy-central:/home/aaron/Proje
81 |    cts/galaxy-central:ro -v /home/aaron/Projects/galaxy-central/tools/docker:/home/aaron/Projects/galaxy-central/tools/docker:ro -v /home/aaron/Projects/galaxy-central/datab
82 |    ase/job_working_directory/000/6:/home/aaron/Projects/galaxy-central/database/job_working_directory/000/6:rw -v /home/aaron/Projects/galaxy-central/database/files:/home/aa
83 |    ron/Projects/galaxy-central/database/files:rw -w /home/aaron/Projects/galaxy-central/database/job_working_directory/000/6 --net none busybox:ubuntu-14.04 /home/aaron/Projects/galaxy-central/database/job_working_directory/000/6/container.sh; return_code=$?; if [ -f /home/aaron/Projects/galaxy-central/database/job_working_directory/000/6/wo
84 |    rking_file ] ; then cp /home/aaron/Projects/galaxy-central/database/job_working_directory/000/6/working_file /home/aaron/Projects/galaxy-central/database/files/000/dataset_10.dat ; fi; sh -c "exit $return_code"
85 |    ```
86 | 
87 | Integrating SMALT with Docker
88 | -----------------------------
89 | 
90 | This contains information on how to integrated a more complicated tool (SMALT) with Docker.  Please see documentation at [SMALT+Docker](smalt/).
91 | 


--------------------------------------------------------------------------------
/smalt/README.md:
--------------------------------------------------------------------------------
  1 | Integration of SMALT into Galaxy and Docker
  2 | ===========================================
  3 | 
  4 | This describes a way to construct a docker image and modify a tool within Galaxy to work with Docker.  The tool I use is SMALT from https://toolshed.g2.bx.psu.edu/repository/find_tools?sort=Repository.name&operation=view_or_manage_repository&id=61631a13f8a13237.
  5 | 
  6 | 1. Building a Docker Image
  7 | ==========================
  8 | 
  9 | There are two different methods to construct a docker image for a tool:
 10 | 
 11 | 1. Interactively
 12 | 2. Using a `Dockerfile`
 13 | 
 14 | 1. Building a Docker Image Interactively
 15 | ----------------------------------------
 16 | 
 17 | The interactive method of constructing a docker image is a good method for installing all the dependencies for a tool if you're not quite sure exactly what commands you need to run to get the tool working.  This method involves starting up a docker container, and running commands within this container to get your tool working.  Then, you can **commit** this container to an image and save to dockerhub for re-use.
 18 | 
 19 | ### Step 1: Starting up a Docker base Image
 20 | 
 21 | To build a docker image we need a starting point.  The base image we will use is **debian/wheezy** since it contains `apt-get` for installing more software.  To start up this image in an interactive mode please run:
 22 | 
 23 | ```bash
 24 | $ sudo docker run -i -t debian:wheezy
 25 | ```
 26 | 
 27 | This should bring up a prompt that looks like:
 28 | 
 29 | ```
 30 | root@2c1077a38bce:/#
 31 | ```
 32 | 
 33 | Note that the id `2c1077a38bce` can be used later for saving this container to an image.
 34 | 
 35 | ### Step 2: Installing Basic Dependencies
 36 | 
 37 | A few dependencies are required to install SMALT.  These can be installed with:
 38 | 
 39 | ```bash
 40 | $ apt-get update
 41 | $ apt-get install python
 42 | $ apt-get install wget
 43 | $ apt-get install mercurial
 44 | ```
 45 | 
 46 | ### Step 3: Installing SMALT
 47 | 
 48 | We will install SMALT by downloading the necessary software and copying to `/usr/bin`.  This can be accomplished with:
 49 | 
 50 | ```bash
 51 | $ mkdir tool
 52 | $ cd tool
 53 | 
 54 | $ wget ftp://ftp.sanger.ac.uk/pub4/resources/software/smalt/smalt-0.7.3.tgz
 55 | $ tar -xvvzf smalt-0.7.3.tgz
 56 | 
 57 | # because the smalt_wrapper.py finds the binary name based on `uname -i` which is unknown in docker
 58 | $ mv smalt-0.7.3/smalt_x86_64 smalt_unknown
 59 | 
 60 | $ hg clone https://toolshed.g2.bx.psu.edu/repos/cjav/smalt smalt_deps
 61 | $ cp smalt_deps/smalt_wrapper.py .
 62 | 
 63 | # add smalt tools to /usr/bin so they're on the PATH
 64 | $ ln -s /tool/smalt_unknown /usr/bin
 65 | $ ln -s /tool/smalt_wrapper.py /usr/bin
 66 | 
 67 | # make smalt_wrapper executable
 68 | $ chmod a+x /tool/smalt_wrapper.py
 69 | ```
 70 | 
 71 | You can test out SMALT by trying to run `smalt_unknown` and `smalt_wrapper.py` in the docker container.
 72 | 
 73 | ### Step 4: Building an Image
 74 | 
 75 | To build the docker image from the container, please exit the container and run the following:
 76 | 
 77 | ```bash
 78 | $ sudo docker commit -m "make smalt image" -a "Aaron Petkau" 2c1077a38bce apetkau/smalt-galaxy
 79 | ```
 80 | 
 81 | Please fill in the appropriate information for your image.  In particular, make sure the container id `2c1077a38bce` is correct.
 82 | 
 83 | To push this image to dockerhub you can run:
 84 | 
 85 | ```bash
 86 | $ sudo docker push apetkau/smalt-galaxy
 87 | ```
 88 | 
 89 | 2. Building an image using a `Dockerfile`
 90 | -----------------------------------------
 91 | 
 92 | Alternatively, instead of building an image interactively, you can build an image with a `Dockerfile`.  An example Dockerfile can be found in this repository at [Dockerfile](Dockerfile).  To build an image please run:
 93 | 
 94 | ```bash
 95 | $ sudo docker build -t apetkau/smalt-galaxy .
 96 | ```
 97 | 
 98 | More information on Dockerfiles can be found at https://docs.docker.com/reference/builder/.
 99 | 
100 | 2. Installing Tool configuration
101 | ================================
102 | 
103 | ### Installing Example file
104 | 
105 | Once a Docker image has been built, it can be integrated into a tool by modifying the tool configuration XML file.  For SMALT, the configuration file is [smalt_wrapper.xml](smalt_wrapper.xml).  This is based on https://toolshed.g2.bx.psu.edu/repos/cjav/smalt/file/54855bd8d107/smalt_wrapper.xml.  And can be installed by running:
106 | 
107 | ```bash
108 | $ cp smalt_wrapper.xml galaxy-central/tools/docker/smalt_wrapper.xml
109 | ```
110 | 
111 | Then, please add this tool to the `tool_conf.xml` by adding:
112 | 
113 | ```xml
114 |  <tool file="docker/smalt_wrapper.xml"/>
115 | ```
116 | 
117 | ### List of Changes
118 | 
119 | The exact changes you I needed to make are:
120 | 
121 | 1. I added the specific docker image name to the requirements by changing:
122 | 
123 |    ```xml
124 |      <requirements>
125 |        <requirement type="package" version="0.7.3">smalt</requirement>
126 |      </requirements>
127 |    ```
128 |    
129 |    To
130 |    
131 |    ```xml
132 |      <requirements>
133 |            <container type="docker">apetkau/smalt-galaxy</container>
134 |      </requirements>
135 |    ```
136 | 
137 | 2. I had to remove `interpreter` from the command attribute by changing
138 | 
139 |    ```xml
140 |      <command interpreter="python">
141 |        smalt_wrapper.py
142 |    ```
143 |    
144 |    To
145 |    
146 |    ```xml
147 |      <command>
148 |        smalt_wrapper.py
149 |    ```
150 | 
151 | 3. Running Galaxy
152 | =================
153 | 
154 | Once the tool is installed, please run Galaxy.  And test out the tool.  Some example files (reference.fasta and reads.fastq) are included.  To make sure it's running in docker you can look for the following `sudo docker run` in the logs:
155 | 
156 | ```
157 | galaxy.jobs.runners DEBUG 2014-06-28 16:50:00,930 (18) command is: sudo docker run -e "GALAXY_SLOTS=$GALAXY_SLOTS" -v /home/aaron/Projects/galaxy-central:/home/aaron/Proj
158 | ects/galaxy-central:ro -v /home/aaron/Projects/galaxy-central/tools/docker:/home/aaron/Projects/galaxy-central/tools/docker:ro -v /home/aaron/Projects/galaxy-central/data
159 | base/job_working_directory/000/18:/home/aaron/Projects/galaxy-central/database/job_working_directory/000/18:rw -v /home/aaron/Projects/galaxy-central/database/files:/home
160 | /aaron/Projects/galaxy-central/database/files:rw -w /home/aaron/Projects/galaxy-central/database/job_working_directory/000/18 --net none apetkau/smalt:v3 /home/aaron/Proj
161 | ects/galaxy-central/database/job_working_directory/000/18/container.sh
162 | ```
163 | 


--------------------------------------------------------------------------------
/smalt/smalt_wrapper.xml:
--------------------------------------------------------------------------------
  1 | <tool id="smalt_wrapper (docker)" name="SMALT" version="0.0.3">
  2 |   <requirements>
  3 | 	<container type="docker">apetkau/smalt-galaxy</container>
  4 |   </requirements>
  5 |   <description>maps query reads onto the reference sequences</description>
  6 |   <command>
  7 |     smalt_wrapper.py 
  8 |       --threads="4"
  9 | 
 10 |       ## reference source
 11 |       --fileSource=$genomeSource.refGenomeSource
 12 |       #if $genomeSource.refGenomeSource == "history":
 13 |         ##build index on the fly
 14 |         --ref="${genomeSource.ownFile}"
 15 |         --dbkey=$dbkey
 16 |       #else:
 17 |         ##use precomputed indexes
 18 |         --ref="${genomeSource.indices.fields.path}"
 19 |         --do_not_build_index
 20 |       #end if
 21 | 
 22 |       ## input file(s)
 23 |       --input1=$paired.input1
 24 |       #if $paired.sPaired == "paired":
 25 |         --input2=$paired.input2
 26 |       #end if
 27 | 
 28 |       ## output file
 29 |       --output=$output
 30 | 
 31 |       ## run parameters
 32 |       --genAlignType=$paired.sPaired
 33 |       --params=$params.source_select
 34 |       #if $params.source_select != "pre_set":
 35 |         --scorDiff=$params.scorDiff
 36 |         #if $paired.sPaired == "paired":
 37 |           --insertMax=$params.insertMax
 38 |           --insertMin=$params.insertMin
 39 |           --pairTyp=$params.pairTyp
 40 |         #end if
 41 |         --minScor=$params.minScor
 42 |         --partialAlignments=$params.partialAlignments
 43 |         --minBasq=$params.minBasq
 44 |         --seed=$params.seed
 45 |         --complexityWeighted=$params.complexityWeighted
 46 |         --exhaustiveSearch=$params.cExhaustiveSearch.exhaustiveSearch
 47 |         #if $params.cExhaustiveSearch.exhaustiveSearch == "true"
 48 |           --minCover=$params.cExhaustiveSearch.minCover
 49 |         #end if
 50 |         --minId=$params.minId
 51 |       #end if
 52 | 
 53 |       ## suppress output SAM header
 54 |       --suppressHeader=$suppressHeader
 55 |   </command>
 56 |   <inputs>
 57 |     <conditional name="genomeSource">
 58 |       <param name="refGenomeSource" type="select" label="Will you select a reference genome from your history or use a built-in index?">
 59 |         <option value="indexed">Use a built-in index</option>
 60 |         <option value="history">Use one from the history</option>
 61 |       </param>
 62 |       <when value="indexed">
 63 |         <param name="indices" type="select" label="Select a reference genome">
 64 |           <options from_data_table="smalt_indexes">
 65 |             <filter type="sort_by" column="2" />
 66 |             <validator type="no_options" message="No indexes are available" />
 67 |           </options>
 68 |         </param>
 69 |       </when>
 70 |       <when value="history">
 71 |         <param name="ownFile" type="data" format="fasta" metadata_name="dbkey" label="Select a reference from history" />
 72 |       </when>
 73 |     </conditional>
 74 |     <conditional name="paired">
 75 |       <param name="sPaired" type="select" label="Is this library mate-paired?">
 76 |         <option value="single">Single-end</option>
 77 |         <option value="paired">Paired-end</option>
 78 |       </param>
 79 |       <when value="single">
 80 |         <param name="input1" type="data" format="fastqsanger" label="FASTQ file" help="FASTQ with Sanger-scaled quality values (fastqsanger)" />
 81 |       </when>
 82 |       <when value="paired">
 83 |         <param name="input1" type="data" format="fastqsanger" label="Forward FASTQ file" help="FASTQ with Sanger-scaled quality values (fastqsanger)" />
 84 |         <param name="input2" type="data" format="fastqsanger" label="Reverse FASTQ file" help="FASTQ with Sanger-scaled quality values (fastqsanger)" />
 85 |       </when>
 86 |     </conditional>
 87 |     <conditional name="params">
 88 |       <param name="source_select" type="select" label="Smalt settings to use" help="For most mapping needs use Commonly Used settings. If you want full control use Full Parameter List">
 89 |         <option value="pre_set">Commonly Used</option>
 90 |         <option value="full">Full Parameter List</option>
 91 |       </param>
 92 |       <when value="pre_set" />
 93 |       <when value="full">
 94 |         <conditional name="cExhaustiveSearch">
 95 |             <param name="exhaustiveSearch" type="boolean" truevalue="true" falsevalue="false" checked="no" label="Do exhaustive search? (map -x)" help="This flag triggers a more exhaustive search for alignments at the cost of decreased speed." />
 96 |           <when value="true">
 97 |               <param name="minCover" type="float" value="0" label="Minimum cover (map -c)" help="Only consider mappings where the k-mer word seeds cover the query read to a minimum extent." />
 98 |           </when>
 99 |           <when value="no" />
100 |         </conditional>
101 |         <param name="scorDiff" type="integer" value="0" label="Score diff (map -d)" help="Set a threshold of the Smith-Waterman alignment score relative to the maximum score." />
102 |         <param name="insertMax" type="integer" value="500" label="Maximum insert size (map -i)" help="Only in paired-end mode." />
103 |         <param name="insertMin" type="integer" value="0" label="Minimum insert size (map -j)" help="Only in paired-end mode." />
104 |         <param name="pairTyp" type="text" size="2" value="pe" label="Type of read pair library (map -l)" help="Can be either 'pe', 'mp' or 'pp'." />
105 |         <param name="minScor" type="integer" value="0" label="Minimum score (map -m)" help="Sets an absolute threshold of the Smith-Waterman scores." />
106 |         <param name="partialAlignments" type="boolean" truevalue="true" falsevalue="false" checked="no" label="Partial alignments (map -p)" help="Report partial alignments if they are complementary on the read (split reads)." />
107 |         <param name="minBasq" type="integer" value="0" label="Base quality threshold (map -q)" help="Sets a base quality threshold (0 &lt;= minbasq &lt;= 10, default 0)." />
108 |         <param name="seed" type="integer" value="0" label="Seed (map -r)" help="See below." />
109 |         <param name="complexityWeighted" type="boolean" truevalue="true" falsevalue="false" checked="no" label="Complexity weighted (map -w)" help="Smith-Waterman scores are complexity weighted." />
110 |         <param name="minId" type="float" value="0" label="Identity threshold (map -y)" help="Sets an identity threshold for a mapping to be reported." />
111 |       </when>
112 |     </conditional>
113 |     <param name="suppressHeader" type="boolean" truevalue="true" falsevalue="false" checked="False" label="Suppress the header in the output SAM file" help="Smalt produces SAM with several lines of header information" />
114 |   </inputs>
115 |   <outputs>
116 |     <data format="sam" name="output" label="${tool.name} on ${on_string}: mapped reads">
117 |       <actions>
118 |         <conditional name="genomeSource.refGenomeSource">
119 |           <when value="indexed">
120 |             <action type="metadata" name="dbkey">
121 |               <option type="from_data_table" name="smalt_indexes" column="1">
122 |                 <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/>
123 |                 <filter type="param_value" ref="genomeSource.indices" column="0"/>
124 |               </option>
125 |             </action>
126 |           </when>
127 |           <when value="history">
128 |             <action type="metadata" name="dbkey">
129 |               <option type="from_param" name="genomeSource.ownFile" param_attribute="dbkey" />
130 |             </action>
131 |           </when>
132 |         </conditional>
133 |       </actions>
134 |     </data>
135 |   </outputs>
136 |   <help>
137 | 
138 | **What it does**
139 | 
140 | SMALT is a pairwise sequence alignment program for the experimentingcient mapping of DNA sequencing reads onto genomic reference sequences. It uses a combination of short-word hashing and dynamic programming. Most types of sequencing platforms are supported including paired-end sequencing reads.
141 | 
142 | ------
143 | 
144 | Please cite the website "http://www.sanger.ac.uk/resources/software/smalt/".
145 | 
146 | ------
147 | 
148 | **Know what you are doing**
149 | 
150 | .. class:: warningmark
151 | 
152 | There is no such thing (yet) as an automated gearshift in short read mapping. It is all like stick-shift driving in San Francisco. In other words = running this tool with default parameters will probably not give you meaningful results. A way to deal with this is to **understand** the parameters by carefully reading the `documentation`__ and experimenting. Fortunately, Galaxy makes experimenting easy.
153 | 
154 |  .. __: http://www.sanger.ac.uk/resources/software/smalt/
155 | 
156 | ------
157 | 
158 | **Input formats**
159 | 
160 | SMALT accepts files in Sanger FASTQ format (galaxy type *fastqsanger*). Use the FASTQ Groomer to prepare your files.
161 | 
162 | ------
163 | 
164 | **A Note on Built-in Reference Genomes**
165 | 
166 | The default variant for all genomes is "Full", defined as all primary chromosomes (or scaffolds/contigs) including mitochondrial plus associated unmapped, plasmid, and other segments. When only one version of a genome is available in this tool, it represents the default "Full" variant. Some genomes will have more than one variant available. The "Canonical Male" or sometimes simply "Canonical" variant contains the primary chromosomes for a genome. For example a human "Canonical" variant contains chr1-chr22, chrX, chrY, and chrM. The "Canonical Female" variant contains the primary chromosomes excluding chrY.
167 | 
168 | ------
169 | 
170 | **Outputs**
171 | 
172 | The output is in SAM format.
173 | 
174 | -------
175 | 
176 | **SMALT parameter list**
177 | 
178 | This is an exhaustive list of SMALT options:
179 | 
180 | For **map**::
181 | 
182 |   -a
183 |      Output explicit alignments along with the mappings.
184 | 
185 |   -c &lt;mincover&gt;
186 |      Only consider mappings where the k-mer word seeds cover the query read to
187 |      a minimum extent. If &lt;mincover&gt; is an integer or floating point &gt; 1.0, at
188 |      least this many bases of the read must be covered by k-mer word seeds. If
189 |      &lt;mincover&gt; is a floating point &lt;= 1.0, it specifies the fraction of the
190 |      query read length that must be covered by k-mer word seeds. This option
191 |      is only valid in conjunction with the '-x' flag.
192 | 
193 |   -d &lt;scordiff&gt;
194 |      Set a threshold of the Smith-Waterman alignment score relative to the
195 |      maximum score. When mapping single reads, all alignments are reported
196 |      that have Smith-Waterman scores within &lt;scorediff&gt; of the maximum.
197 |      Mappings with lower scores are skipped. If &lt;scorediff&gt; is set to to a
198 |      value &lt; 0, all alignments are printed that have scores above the
199 |      threshold specified with the '-m &lt;minscor&gt;' option.
200 |      For paired reads, only a value of 0 is supported. With the option '-d 0'
201 |      all aligments (pairings) with the best score are output. By default
202 |      (without the option '-d 0') single reads/mates with multiple best mappings
203 |      are reported as 'not mapped'.
204 | 
205 |   -f &lt;format&gt;
206 |      Specifies the output format. &lt;format&gt; can be either 'bam', 'cigar', 'gff',
207 |      'sam' (default), 'samsoft' or 'ssaha'. Optional extension 'sam:nohead,clip'
208 |      (see manual)
209 | 
210 |   -F &lt;inform&gt;
211 |      Specifies the input format. &lt;inform&gt; can be either 'fastq' (default),
212 |      'sam' or 'bam' (see: samtools.sourceforge.net). SAM and BAM formats
213 |      require additional libraries to be installed.
214 | 
215 |   -g &lt;insfil&gt;
216 |      Use the distribution of insert sizes stored in the file &lt;insfil&gt;. This
217 |      file is in ASCII format and can be generated using the 'sample' task see
218 |      'smalt sample -H' for help).
219 | 
220 |   -H
221 |      Print these instructions.
222 | 
223 |   -i &lt;insertmax&gt;
224 |      Maximum insert size (only in paired-end mode). The default is 500.
225 | 
226 |   -j &lt;insertmin&gt;
227 |      Minimum insert size (only in paired-end mode). The default is 0.
228 | 
229 |   -l &lt;pairtyp&gt;
230 |      Type of read pair library. &lt;pairtyp&gt; can be either 'pe', i.e. for
231 |      the Illumina paired-end library for short inserts (|--&gt; &lt;--|). 'mp'
232 |      for the Illumina mate-pair library for long inserts (&lt;--| |--&gt;) or
233 |      'pp' for mates sequenced on the same strand (|--&gt; |--&gt;). 'pe' is the
234 |      default.
235 | 
236 |   -m &lt;minscor&gt;
237 |      Sets an absolute threshold of the Smith-Waterman scores. Mappings with
238 |      scores below that threshold will not be reported. The default is
239 |      &lt;minscor&gt; = &lt;wordlen&gt; + &lt;stepsiz&gt; - 1
240 | 
241 |   -n &lt;nthreads&gt;
242 |      Run smalt using mutiple threads. &lt;nthread&gt; is the number of additional
243 |      threads forked from the main thread. The order of the reads in the
244 |      input files is not preserved for the output unless '-O' is also specified.
245 | 
246 |   -o &lt;oufilnam&gt;
247 |      Write mapping output (e.g. SAM lines) to a separate file. If this option
248 |      is not specified, mappings are written to standard output together with
249 |      other messages.
250 | 
251 |   -O
252 |      Output mappings in the order of the reads in the input files when using
253 |      multiple threads (option '-n &lt;nthreads&gt;').
254 | 
255 |   -p
256 |      Report partial alignments if they are complementary on the read (split
257 |      reads).
258 | 
259 |   -q &lt;minbasq&gt;
260 |      Sets a base quality threshold (0 &lt;= minbasq &lt;= 10, default 0).
261 |      K-mer words of the read with nucleotides that have a base quality below
262 |      this threshold are not looked up in the hash index.
263 | 
264 |   -r &lt;seed&gt;
265 |      If &lt;seed&gt; &gt;= 0 report an alignment selected at random where there are
266 |      multiple mappings with the same best alignment score. With &lt;seed&gt; = 0
267 |      (default) a seed is derived from the current calendar time. If &lt;seed&gt;
268 |      &lt; 0 reads with multiple best mappings are reported as 'not mapped'.
269 | 
270 |   -T &lt;tmp_dir&gt;
271 |      Write temporary files to directory &lt;tmp_dir&gt; (used with input files in
272 |      SAM/BAM format).
273 | 
274 |   -w
275 |      Smith-Waterman scores are complexity weighted.
276 | 
277 |   -x
278 |      This flag triggers a more exhaustive search for alignments at the cost
279 |      of decreased speed. In paired-end mode each mate is mapped independently.
280 |      (By default the mate with fewer hits in the hash index is mapped first
281 |      and the vicinity is searched for mappings of its mate.)
282 | 
283 |   -y &lt;minid&gt;
284 |      Sets an identity threshold for a mapping to be reported (default: 0).
285 |      &lt;minid&gt; specifies the number of exactly matching nucleotides either as
286 |      a positive integer or as a fraction of the read length (&lt;= 1.0).
287 | 
288 |   </help>
289 | </tool>
290 | 
291 | 
292 | 


--------------------------------------------------------------------------------