Unfortunately this is one of the most glaring problems with the UI based workflow engine that is Galaxy (That, and no modular workflows)...
You cannot easily pair up more than one set of paired end reads from the UI, you need to use the API to run pairs of FASTQ files like that...

I have written a script that will do this through the API..Excerpt below...
You won't be able to run this as-is, but it gives you some idea what hoops you have to jump through to do this..

The section INPUT FILE DEFINITION is the meat of the script, in that I simply cycle through all the files in a Library and match up the files myself...Ugly but it works....


Thon
<code>

#!/usr/bin/env python
###############################################################################
#
#  MUT190-1.py
#
#  Version 2.0.0
#  Created: 5-Apr-2012
#   By Thon de Boer, GHI
#  Last Update: 23-Apr-2012
#   By Thon de Boer, GHI
#
#  This program will run step MUT190-1; the alignment of FASTQ file with BWA
#  It is based on the generic GALAXY Workflow execution engine,
#  but has hardcoded defaults, seen below
#
# Version 1.0.1: Added get_folder_id
# Version 2.0.0: Made the config file an option (and the only option)
#

"""
Execute a specifc workflow on a specific set of history items.
It is created for running the GATK pipeline on a selected set of paired-end reads
Input to the tool is the name of a History and it will extract all the paired-end FASTQ files from this.
"""

import os, sys, optparse, shutil, subprocess, tempfile, fileinput, psycopg2, ConfigParser
sys.path.insert( 0, os.path.dirname( __file__ ) )
sys.path.insert( 0, "/home/tdeboer/g/scripts/api" )
from common import *
from ThonsModules import *

def main():

    #Parse Command Line
    parser = optparse.OptionParser()
    parser.add_option( '-c', '--config', dest='config', type='string', help='the configuration file containing all the settings for this workflow' )
    parser.add_option( '-t', '--test', action='', dest='test', help='Do not submit, but test the settings', default=False)

    (options, args) = parser.parse_args()
    if not options.config:
        print "Error: No config file proivided. Please provide a configuration file with the -c,--config flag."
        sys.exit(1)

    config = ConfigParser.RawConfigParser()
    try:
        config.read(options.config)
        GALAXY_LIBRARY_FASTQ = config.get('GALAXY', 'GALAXY_LIBRARY_FASTQ').strip('"')
        GALAXY_WORKFLOW_DEFAULT=config.get('GALAXY', 'GALAXY_WORKFLOW_DEFAULT').strip('"')
        GALAXY_OUTHISTORY_DEFAULT=config.get('GALAXY', 'GALAXY_OUTHISTORY_DEFAULT').strip('"')
        galaxyURL=config.get('GALAXY', 'GALAXY_URL').strip('"')
        myKey=config.get('GALAXY', 'MYKEY').strip('"')
    except Exception, e:
        print 'Error: %s' % e
        sys.exit(1)

    data = "">
    #Find the files that go with the history or library
    try:
        historyPrefix = GALAXY_OUTHISTORY_DEFAULT + '-'

        files = {}
        lib_id = get_library(myKey, galaxyURL, GALAXY_LIBRARY_FASTQ)
        files = get_files_from_library(myKey, galaxyURL, GALAXY_LIBRARY_FASTQ, lib_id)
        if files == {}:
            print 'Error: Did not get any files from the library'
            sys.exit(1)
        workflow_id = get_workflow(myKey, galaxyURL, GALAXY_WORKFLOW_DEFAULT)
        data['workflow_id'] = workflow_id
    except Exception, e:
        print 'Error: %s' % e
        sys.exit(1)
        
    data['ds_map'] ={}
    #Define the standard library datasets
    try:
        ###########################################################################
        #
        # WORKFLOW STEP DEFINITION
        #
        ###########################################################################
        #Format for these lines should be followed...Only change the 'BAITS' and 'MUT190/Baits and Targets/SS_Mut_v2_baits190.bed' text
        data['ds_map'][get_workflow_step(myKey, galaxyURL, workflow_id, 'BAITS')] = get_library_file(myKey, galaxyURL, 'MUT190/Baits and Targets/SS_Mut_v2_baitsMUT190.bed')
        data['ds_map'][get_workflow_step(myKey, galaxyURL, workflow_id, 'TARGETS')] = get_library_file(myKey, galaxyURL, 'MUT190/Baits and Targets/SS_Mut_v2_targetsMUT190_PLUS60.interval')
        data['ds_map'][get_workflow_step(myKey, galaxyURL, workflow_id, 'TARGETS (GATK)')] = get_library_file(myKey, galaxyURL, 'MUT190/Baits and Targets/SS_Mut_v2_targetsMUT190_PLUS400.gatk-interval')
        data['ds_map'][get_workflow_step(myKey, galaxyURL, workflow_id, 'dbSNP VCF File')] = get_library_file(myKey, galaxyURL, 'Annotations/Annotations used in GATK-1.5/dbsnp_135.b37.vcf')
        data['ds_map'][get_workflow_step(myKey, galaxyURL, workflow_id, 'Mills_and_1000G_gold_standard')] = get_library_file(myKey, galaxyURL, 'Annotations/Annotations used in GATK-1.5/Mills_and_1000G_gold_standard.indels.b37.sites.vcf')
    except Exception, e:
        print "Error: Problem with finding all the input steps for this workflow: %s" % e
        sys.exit(1)

    ###########################################################################
    #
    # INPUT FILE DEFINITION
    # These are the files that are cycled over
    #
    ###########################################################################
    for f in files:
        if '_R1.fastq' in f:
            f2 = f.replace('_R1.fastq','_R2.fastq')
            data['ds_map'][get_workflow_step(myKey, galaxyURL, workflow_id, 'FASTQ Input (#1)')] = {'src':'ldda', 'id':files[f] }
            data['ds_map'][get_workflow_step(myKey, galaxyURL, workflow_id, 'FASTQ Input (#2)')] = {'src':'ldda', 'id':files[f2] }
            
            #History will be using PREFIX-FILENAME format
            data['history'] = "%s%s" % ( historyPrefix,f.split('/')[-1] )

            print '-------------------------------------------------------------------'
            print "Preparing workflow for :\n%s\n" % f
            if options.test:
                print data
            else:
                url = "" % galaxyURL
                submit( myKey, url, data )

if __name__ == '__main__':
    main()

</code>

On May 25, 2012, at 06:15 AM, Geert Vandeweyer <geert.vandewey...@ua.ac.be> wrote:

I'm looking for a workflow of :

Forward reads.fastq =>
> QC => map => etc
Reverse reads.fastq =>

and would like to specify pairs of files (from MiSeq) in the batch
workflow interface. I'm currently looking into interlacing the files
outside of galaxy before uploading. Then I can de-interlace as the first
step, but this is redundant, as we get seperate files to start.

Best regards,

Geert


On 05/25/2012 02:12 PM, Dannon Baker wrote:
> Batch mode is currently only allowed for a single input dataset step, so the others are intentionally disabled upon toggling the first one on. We do, however, plan to eventually expand this to allow for pairwise/etc input sets. Out of curiosity, which behavior is it that you're looking for?
>
> -Dannon
>
> On May 25, 2012, at 8:03 AM, Geert Vandeweyer wrote:
>
>> Is it possible to use multiple 'input dataset' steps in a single workflow in batch? If I have two, I can only select batch input on one of them. If one is open, the other toggle button does not respond.
>>
>> Thanks,
>>
>> Geert
>>
>> On 02/14/2012 09:55 PM, Petit III, Robert A. wrote:
>>> Thats it! Consider this resolved, and total operator error. I tried using the 'Input Dataset' step, and am no longer having issues.
>>>
>>> Thanks for the help Dannon.
>>>
>>> ________________________________________
>>> From: Petit III, Robert A.
>>> Sent: Tuesday, February 14, 2012 3:49 PM
>>> To: galaxy-dev@lists.bx.psu.edu
>>> Subject: RE: [galaxy-dev] Batch limit on Wokflows
>>>
>>> Workflow is beginning directly with a tool.
>>>
>>> An example test workflow I've been trying is, I have 20 fasta files, and the workflow has only the FASTA-to-Tabular tool.
>>>
>>> Thanks,
>>> Robert
>>> ________________________________________
>>> From: Dannon Baker [dannonba...@me.com]
>>> Sent: Tuesday, February 14, 2012 3:33 PM
>>> To: Petit III, Robert A.
>>> Cc: galaxy-dev@lists.bx.psu.edu
>>> Subject: Re: [galaxy-dev] Batch limit on Wokflows
>>>
>>> I hadn't had a chance to follow up again yet, but in your workflow, are you using an Input Dataset step, or do you have the workflow beginning directly with a tool?
>>>
>>> -Dannon
>>>
>>> On Feb 14, 2012, at 3:26 PM, Petit III, Robert A. wrote:
>>>
>>>> Here's the latest. I have tested this on Chrome, Firefox, and IE.
>>>>
>>>> I've tried the latest revisions of galaxy-central (71031bf3105c) and galaxy-dist (26920e20157f) straight out of the box (hg clone, sh run.sh, go to localhost:8080). I am still running into same issue. All is well with 19 or less datasets in the history, but as soon as I add a 20th I can no longer run a workflow on multiple datasets.
>>>>
>>>> Are there any known issues running galaxy on Ubuntu 10.04?
>>>>
>>>> ________________________________
>>>>
>>>> This e-mail message (including any attachments) is for the sole use of
>>>> the intended recipient(s) and may contain confidential and privileged
>>>> information. If the reader of this message is not the intended
>>>> recipient, you are hereby notified that any dissemination, distribution
>>>> or copying of this message (including any attachments) is strictly
>>>> prohibited.
>>>>
>>>> If you have received this message in error, please contact
>>>> the sender by reply e-mail message and destroy all copies of the
>>>> original message (including attachments).
>>>>
>>>> ___________________________________________________________
>>>> Please keep all replies on the list by using "reply all"
>>>> in your mail client. To manage your subscriptions to this
>>>> and other Galaxy lists, please use the interface at:
>>>>
>>>> http://lists.bx.psu.edu/
>>> ___________________________________________________________
>>> Please keep all replies on the list by using "reply all"
>>> in your mail client. To manage your subscriptions to this
>>> and other Galaxy lists, please use the interface at:
>>>
>>> http://lists.bx.psu.edu/
>>
>> --
>>
>> Geert Vandeweyer, Ph.D.
>> Department of Medical Genetics
>> University of Antwerp
>> Prins Boudewijnlaan 43
>> 2650 Edegem
>> Belgium
>> Tel: +32 (0)3 275 97 56
>> E-mail: geert.vandewe...@ua.ac.be
>> http://ua.ac.be/cognitivegenetics
>> http://www.linkedin.com/pub/geert-vandeweyer/26/457/726
>>
>> ___________________________________________________________
>> Please keep all replies on the list by using "reply all"
>> in your mail client. To manage your subscriptions to this
>> and other Galaxy lists, please use the interface at:
>>
>> http://lists.bx.psu.edu/


--

Geert Vandeweyer, Ph.D.
Department of Medical Genetics
University of Antwerp
Prins Boudewijnlaan 43
2650 Edegem
Belgium
Tel: +32 (0)3 275 97 56
E-mail: geert.vandewe...@ua.ac.be
http://ua.ac.be/cognitivegenetics
http://www.linkedin.com/pub/geert-vandeweyer/26/457/726

___________________________________________________________
Please keep all replies on the list by using "reply all"
in your mail client. To manage your subscriptions to this
and other Galaxy lists, please use the interface at:

http://lists.bx.psu.edu/
___________________________________________________________
Please keep all replies on the list by using "reply all"
in your mail client.  To manage your subscriptions to this
and other Galaxy lists, please use the interface at:

  http://lists.bx.psu.edu/

Reply via email to