Forum: Running Galaxy From Command Line With Bioblend
gravatar for vaskin90
5.1 years ago by
Milan, Italy
vaskin90280 wrote:

I was looking for a script that runs a Galaxy workflow as a simple command line tool: uploads the file, runs a workflow, downloads the file. Descriptions of this process are scattered through different forums and pretty incomplete. So I wrote a simple script with BioBlend that does that. You need to create a galaxy workflow, add the Input dataset element (the Workflow control at the very bottom of the list of the tools), configure the ids and paths in the script.

import sys
import os
from bioblend.galaxy import GalaxyInstance
from bioblend.galaxy.histories import HistoryClient
from import ToolClient
from bioblend.galaxy.workflows import WorkflowClient
from bioblend.galaxy.datasets import DatasetClient

#Execute workflow from the command line.
#Example calls:
#python input output
#python '/Users/pro/Documents/sandbox/data/reads/e_coli_1000.fq' '/Users/pro/Documents/sandbox/data/reads/ecoli.bed'

GALAXY_URL = 'http://localhost:8082/'
API_KEY = '1fbb3a586ff63534e6c4536e598c6bee'
WORKFLOW_ID = 'f2db41e1fa331b3e'
TOOL_ID_IN_GALAXY = 'gears_tool'

def findDatasedIdByExtention(datasetClient, output, ext):
    id = ''
    for datasetId in output['outputs']:
        dataset = datasetClient.show_dataset(datasetId)
        if dataset['file_ext'] == ext:
            id = datasetId
    return id
def downloadDataset(datasetClient, datasetId, outpath):
    if datasetId != '':
        datasetClient.download_dataset(datasetId, outpath, False, True)
        print 'Dataset id %s not found. Fail to download dataset to % s.' % (datasetId, outpath)

def main():
        input_path = sys.argv[1]
        output_path = sys.argv[2]

        galaxyInstance = GalaxyInstance(url = GALAXY_URL, key=API_KEY)
        historyClient = HistoryClient(galaxyInstance)
        toolClient = ToolClient(galaxyInstance)
        workflowClient = WorkflowClient(galaxyInstance)
        datasetClient = DatasetClient(galaxyInstance)

        history = historyClient.create_history('tmp')
        uploadedFile = toolClient.upload_file(input_path, history['id'] )

        workflow = workflowClient.show_workflow(WORKFLOW_ID)
        dataset_map  = {workflow['inputs'].keys()[0]: {'id': uploadedFile['outputs'][0]['id'], 'src': 'hda'}}
        params = {TOOL_ID_IN_GALAXY: {'param': 'reference_genome', 'value': 'hg19'}}
        output = workflowClient.run_workflow(WORKFLOW_ID, dataset_map, params, history['id'])

        downloadDataset(datasetClient, findDatasedIdByExtention(datasetClient, output, 'bed'), output_path)
        #delete history
        #if galaxy instance support dataset purging
        #historyClient.delete_history(history['id'], True)

    except IndexError:
        print 'usage: %s key url workflow_id history step=src=dataset_id' % os.path.basename(sys.argv[0])

if __name__ == '__main__':
forum galaxy • 2.6k views
ADD COMMENTlink written 5.1 years ago by vaskin90280

How do you find the workflow ID?

ADD REPLYlink written 3.0 years ago by alexander.lenail0
from bioblend.galaxy import GalaxyInstance
from bioblend.galaxy.workflows import WorkflowClient
GALAXY_URL = '...'
API_KEY = '...'
galaxyInstance = GalaxyInstance(url=GALAXY_URL, key=API_KEY)
workflowClient = WorkflowClient(galaxyInstance)
print workflowClient.get_workflows()
ADD REPLYlink modified 3.0 years ago • written 3.0 years ago by alexander.lenail0
Please log in to add an answer.


Use of this site constitutes acceptance of our User Agreement and Privacy Policy.
Powered by Biostar version 2.3.0
Traffic: 1164 users visited in the last hour