def __main__():
parser = argparse.ArgumentParser(description = 'Import workflows from a local directory')
parser.add_argument('-p', '--port', help = 'port number from your docker container that you map to your host machine. The default is 80', default = '80')
parser.add_argument('-k', '--key', help = 'user API key')
args = parser.parse_args()
# port and api key
port = args.port
api_key = args.key
# galaxy client instance
galaxy_home = environ['GALAXY_HOME']
galaxy_client = GalaxyInstance(url = "http://127.0.0.1:" + port, key = api_key)
if galaxy_client:
# workflow client instance
workflow_client = WorkflowClient(galaxy_client)
my_workflows_dir = environ['GALAXY_HOME'] + '/my_workflows'
workflow_files = []
for f in listdir(my_workflows_dir):
if isfile(join(my_workflows_dir, f)):
f_path = join(my_workflows_dir, f)
workflow_client.import_workflow_from_local_path(f_path)
print('Imported workflow: ' + f)
def main():
try:
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
historyClient.delete_history(history['id'])
#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])
sys.exit(1)
def main():
galaxyInstance = GalaxyInstance(url=GALAXY_URL, key=API_KEY)
toolClient = ToolClient(galaxyInstance)
histories = HistoryClient(galaxyInstance)
workflowsClient = WorkflowClient(galaxyInstance)
libraryClient = LibraryClient(galaxyInstance)
brassica_library = libraryClient.get_libraries(
name=' Evolutionary Systems Biology')
files = libraryClient.show_library(brassica_library[0]['id'],
contents=True)
#print(files)
itemp = 0
for f in files:
if f['type'] == 'folder':
continue # do nothing, try next
#initial set
#if itemp == 31:
# break
#print ("Name " + f['name'])
replicate = f['name'].split('_')[-1].split('.')[0]
#print replicate
if replicate == '1':
itemp = itemp + 1
if not (itemp >= 71 and itemp <= 92):
continue
base = f['name'].split('_')[:-1]
#print base
forward_name = f['name']
reverse_name = '_'.join(base) + '_2.fastq.bz2'
forward_id = f['id']
files2 = libraryClient.show_library(brassica_library[0]['id'],
contents=True)
for f2 in files2:
if f2['name'] == reverse_name:
reverse_id = f2['id']
print forward_name
print reverse_name
new_history_name = f['name'].split('_')[7] + "_" + f['name'].split(
'_')[-3] + "_" + f['name'].split('_')[-2]
print new_history_name
hist = histories.create_history(name=new_history_name)
dataset_F = histories.upload_dataset_from_library(
hist['id'], forward_id)
dataset_R = histories.upload_dataset_from_library(
hist['id'], reverse_id)
datamap = {}
datamap['0'] = {'src': 'hda', 'id': dataset_F['id']}
datamap['1'] = {'src': 'hda', 'id': dataset_R['id']}
workflows = workflowsClient.get_workflows(name="Maize HISAT 2.1")
workflow = workflows[0]
try:
w = workflowsClient.run_workflow(workflow['id'],
datamap,
history_id=hist['id'])
except:
print('Next')
def check_galaxy(api_key, galaxy_url):
gi = GalaxyInstance(galaxy_url, key=api_key)
gi.verify = False
wc = WorkflowClient(gi)
try:
wc.get_workflows()
except ConnectionError as e:
raise forms.ValidationError(
'Something is wrong with Galaxy connection, please check')
def main():
try:
gInstance = GalaxyInstance(url = GALAXY_URL, key=API_KEY)
wClient = WorkflowClient(gInstance)
print ':::::::::::::::::::::::::::::::::::::::::::'
print '>>>>>>>>>>>>>>>>> get current workflowlist...'
gInstance = GalaxyInstance(url = GALAXY_URL, key=API_KEY)
wClient = WorkflowClient(gInstance)
dataset = wClient.get_workflows()
wf_namelist = [x['name'] for x in dataset if x['deleted'] == False]
print wf_namelist
print ':::::::::::::::::::::::::::::::::::::::::::'
print '>>>>>>>>>>>>>>>>> clone BiT Workflows from github...'
if not os.path.exists(wf_dname + '/' + repo_name):
makeDir(wf_dname)
os.chdir(wf_dname)
git_url = 'https://github.com/myoshimura080822/' + repo_name + '.git'
Repo.clone_from(git_url, repo_name)
else:
print repo_name + ' already cloned. To update, Please delete, move or rename dir before this script execute.'
return 0
print ':::::::::::::::::::::::::::::::::::::::::::'
print '>>>>>>>>>>>>>>>>> delete and inport workflow files...'
mytoolsdir = wf_dname + '/' + repo_name + '/'
clone_wf_list = [file.replace(mytoolsdir, "") for file in get_all_ga(mytoolsdir)]
print clone_wf_list
delete_itm =[]
[[ delete_itm.append(y) for y in wf_namelist if y.find(x.replace('.ga','')) > -1] for x in clone_wf_list]
print delete_itm
id_list = []
[[id_list.append(x['id']) for x in dataset if x['name'].find(y) > -1] for y in delete_itm]
print id_list
[wClient.delete_workflow(x) for x in id_list]
print wClient.get_workflows()
wf_file_path = get_all_ga(mytoolsdir)
[wClient.import_workflow_from_local_path(file) for file in wf_file_path]
print wClient.get_workflows()
print ':::::::::::::::::::::::::::::::::::::::::::'
print '>>>>>>>>>>>>>>>>> script ended :)'
return 0
except:
info = sys.exc_info()
tbinfo = traceback.format_tb( info[2] )
print 'Error Info...'.ljust( 80, '=' )
for tbi in tbinfo:
print tbi
print ' %s' % str( info[1] )
print '\n'.rjust( 85, '=' )
sys.exit(1)
def main():
galaxyInstance = GalaxyInstance(url=GALAXY_URL, key=API_KEY)
toolClient = ToolClient(galaxyInstance)
histories = HistoryClient(galaxyInstance)
workflowsClient = WorkflowClient(galaxyInstance)
libraryClient = LibraryClient(galaxyInstance)
brassica_library = libraryClient.get_libraries(
name=' Evolutionary Systems Biology')
files = libraryClient.show_library(brassica_library[0]['id'],
contents=True)
#print(files)
for f in files:
if f['type'] == 'folder':
continue # do nothing, try next
#initial set
#if itemp == 31:
# break
#print ("Name " + f['name'])
replicate = f['name'].split('/')[-1][0]
#print replicate
if replicate == 'X':
base = f['name'].split('/')[-1].split('.')[0]
#print base
forward_name = f['name']
forward_id = f['id']
print forward_name
new_history_name = base
print new_history_name
hist = histories.create_history(name=new_history_name)
dataset_F = histories.upload_dataset_from_library(
hist['id'], forward_id)
datamap = {}
datamap['0'] = {'src': 'hda', 'id': dataset_F['id']}
workflows = workflowsClient.get_workflows(
name="Maize Small samples HISAT 2.1")
workflow = workflows[0]
try:
w = workflowsClient.run_workflow(workflow['id'],
datamap,
history_id=hist['id'])
except:
print('Next')
def create_clients(self):
'''
Create bioblend clients for the Galaxy instance.
'''
# Create first client and check if the API works
self.config_client = ConfigClient(self.instance)
try:
self.config_client.get_version()
self.config_client.get_config()
except:
logger.error("Provided API-key does not work.")
return False
try:
self.user_client = UserClient(self.instance)
self.workflow_client = WorkflowClient(self.instance)
self.tool_client = ToolClient(self.instance)
self.toolshed_client = ToolShedClient(self.instance)
self.library_client = LibraryClient(self.instance)
self.roles_client = RolesClient(self.instance)
self.history_client = HistoryClient(self.instance)
self.dataset_client = DatasetClient(self.instance)
except:
logger.error("Error initializing other bioblend clients.")
return False
return True
def workflow_sync(user):
# get all instances for that user
gits = GalaxyInstanceTracking.objects.filter(
galaxyuser__internal_user=user)
dj_wfs = Workflow.objects.all()
# loop through instances
all_wfs = []
for git in gits:
## loop through workflows for that instance
gi, gu = get_gi_gu(user, git)
wc = WorkflowClient(gi)
wfs = wc.get_workflows()
all_wfs.extend(wfs)
for wf in wfs:
wfd = wc.show_workflow(wf['id'])
### check if id of the workflow already in galaxy
wjson = wc.export_workflow_dict(wf['id'])
dj_wf = dj_wfs.filter(galaxy_id=wfd['id'])
if dj_wf:
if not dj_wf[0].latest_workflow_uuid == wf[
'latest_workflow_uuid']:
dj_wf_update = dj_wf[0]
dj_wf_update.latest_workflow_uuid = wf[
'latest_workflow_uuid']
dj_wf_update.name = wf['name']
dj_wf_update.workflowjson = wjson
dj_wf_update.save()
else:
workflow = Workflow(galaxy_id=wf['id'],
name=wf['name'],
description='added automatically',
galaxyinstancetracking=git,
added_by=user,
workflowjson=wjson)
workflow.save()
all_wfs_gi = [w['id'] for w in all_wfs]
## check if workflow is currently accessible
Workflow.objects.exclude(galaxy_id__in=all_wfs_gi).update(accessible=False)
def run_galaxy_workflow(wid, user, git, pkd, l, history_name, library):
gi, gu = get_gi_gu(user, git)
st = get_time_stamp()
workflow_input_d = get_workflow_inputs(l, pkd, gi, git, history_name,
library)
wc = WorkflowClient(gi)
print(workflow_input_d)
workflow = Workflow.objects.get(id=wid)
wf = wc.get_workflows(workflow_id=workflow.galaxy_id)[0]
wfi = wc.invoke_workflow(wf['id'],
inputs=workflow_input_d,
import_inputs_to_history=True,
history_name='{}_({})'.format(history_name, st))
return wfi
def get_galaxy_workflow_inputs(w, user):
wf = w.workflowfile
git = w.galaxyinstancetracking
wf_name = w.name
api_key = GalaxyUser.objects.get(internal_user=user,
galaxyinstancetracking=git).api_key
galaxy_url = git.url
gi = GalaxyInstance(galaxy_url, key=api_key)
gi.verify = False
wc = WorkflowClient(gi)
wfd = wf.read()
jsonload = json.loads(wfd)
now = datetime.datetime.now()
jsonload['name'] = '{} dj-upload[{} {}]'.format(jsonload['name'], wf_name,
now.strftime("%Y-%m-%d"))
wfimp = wc.import_workflow_json(jsonload)
return check_workflow_data_inputs(wfimp['id'], wc), wfimp['id']
def main():
galaxyInstance = GalaxyInstance(url=GALAXY_URL, key=API_KEY)
toolClient = ToolClient(galaxyInstance)
historyClient = HistoryClient(galaxyInstance)
workflowsClient = WorkflowClient(galaxyInstance)
libraryClient = LibraryClient(galaxyInstance)
datasetClient = DatasetClient(galaxyInstance)
histories = historyClient.get_histories(deleted=False)
for hist in histories:
hist_id = hist['id']
countSecondary = historyClient.show_matching_datasets(
hist_id, name_filter=name_filter)
if len(countSecondary) != 0:
#print(countSecondary)
file_path = dir_name + '/' + hist[
'name'] + '_' + name_filter + '.' + ext
#print(file_path)
#print(countSecondary[0]['dataset_id'])
datasetClient.download_dataset(countSecondary[0]['id'],
file_path=file_path,
use_default_filename=False)
sys.exit()
def get_workflow_status(user):
# go through every galaxy instance
gits = GalaxyInstanceTracking.objects.filter(
galaxyuser__internal_user=user)
dj_wfs = Workflow.objects.all()
# loop through instances
status = []
for git in gits:
## loop through workflows for that instance
gi, gu = get_gi_gu(user, git)
wc = WorkflowClient(gi)
hc = HistoryClient(gi)
wfs = wc.get_workflows()
for wf in wfs:
wfd = wc.show_workflow(wf['id'])
winvoke = wc.get_invocations(wf['id'])
for wi in winvoke:
wid = wc.show_invocation(wf['id'], wi['id'])
h_l = hc.get_histories(wid['history_id'], deleted=True)
if h_l:
h = h_l[0]
else:
continue
sd = get_status_d(wid)
sd['name'] = wfd['name']
hd = hc.show_history(h['id'])
sd['history_name'] = h['name']
datetime_object = datetime.strptime(hd['update_time'],
'%Y-%m-%dT%H:%M:%S.%f')
# sd['history_url'] = '{}{}'.format(git.url, hd['url'])
sd['update_time'] = datetime_object.strftime(
'%Y-%m-%d %H:%M:%S')
sd['update_time_unix'] = unixtime(datetime_object)
sd['galaxy_instance'] = git.name
status.append(sd)
status = sorted(status, key=lambda k: k['update_time_unix'], reverse=True)
return status
def main():
try:
gInstance = GalaxyInstance(url=GALAXY_URL, key=API_KEY)
wClient = WorkflowClient(gInstance)
print ':::::::::::::::::::::::::::::::::::::::::::'
print '>>>>>>>>>>>>>>>>> get current workflowlist...'
gInstance = GalaxyInstance(url=GALAXY_URL, key=API_KEY)
wClient = WorkflowClient(gInstance)
dataset = wClient.get_workflows()
wf_namelist = [x['name'] for x in dataset if x['deleted'] == False]
print wf_namelist
print ':::::::::::::::::::::::::::::::::::::::::::'
print '>>>>>>>>>>>>>>>>> clone BiT Workflows from github...'
if not os.path.exists(wf_dname + '/galaxy-workflow_rnaseq'):
makeDir(wf_dname)
os.chdir(wf_dname)
git_url = 'https://github.com/myoshimura080822/galaxy-workflow_rnaseq.git'
Repo.clone_from(git_url, 'galaxy-workflow_rnaseq')
else:
print 'BiT Workflow already cloned. To update, Please delete, move or rename "/galaxy-workflow_rnaseq" before script execute.'
return 0
print ':::::::::::::::::::::::::::::::::::::::::::'
print '>>>>>>>>>>>>>>>>> delete and inport workflow files...'
mytoolsdir = wf_dname + '/galaxy-workflow_rnaseq/'
clone_wf_list = [
file.replace(mytoolsdir, "") for file in get_all_ga(mytoolsdir)
]
print clone_wf_list
delete_itm = []
[[
delete_itm.append(y) for y in wf_namelist
if y.find(x.replace('.ga', '')) > -1
] for x in clone_wf_list]
print delete_itm
id_list = []
[[id_list.append(x['id']) for x in dataset if x['name'].find(y) > -1]
for y in delete_itm]
print id_list
[wClient.delete_workflow(x) for x in id_list]
print wClient.get_workflows()
[
wClient.import_workflow_from_local_path(file)
for file in get_all_ga(mytoolsdir)
]
print wClient.get_workflows()
print ':::::::::::::::::::::::::::::::::::::::::::'
print '>>>>>>>>>>>>>>>>> script ended :)'
return 0
except:
info = sys.exc_info()
tbinfo = traceback.format_tb(info[2])
print 'Error Info...'.ljust(80, '=')
for tbi in tbinfo:
print tbi
print ' %s' % str(info[1])
print '\n'.rjust(85, '=')
sys.exit(1)
else:
print "You passed %s I need a .ini file" %(sys.argv[1],)
sys.exit(1)
else:
parser.read('configuration.ini')
api_key = get_api_key(parser.get('Globals', 'api_file'))
galaxy_host = parser.get('Globals', 'galaxy_host')
file_name_re = re.compile(parser.get('Globals', 'sample_re'))
galaxyInstance = GalaxyInstance(galaxy_host, key=api_key)
historyClient = HistoryClient(galaxyInstance)
toolClient = ToolClient(galaxyInstance)
workflowClient = WorkflowClient(galaxyInstance)
dataSetClient = DatasetClient(galaxyInstance)
files = get_files(parser.get('Globals','fastq_dir'))
if len(files) == 0:
print "Not able to find any fastq files looked in %s" %(parser.get('Globals', 'fastq_dir'))
else:
print "Found fastq files running workflow for the following files (R2's will be added)"
print ",".join(files)
files_to_keep = {}
for R1 in files:
input_dir_path = os.path.dirname(R1)+"/"
R2 = R1.replace('R1','R2')
if not os.path.exists(R1):
print "%s File Not Found" % (R1, )
raise Exception
parser = SafeConfigParser()
if len(sys.argv) >= 2:
if sys.argv[1].endswith('.ini'):
parser.read(sys.argv[1])
else:
print "You passed %s I need a .ini file" %(sys.argv[1],)
sys.exit(1)
else:
parser.read('configuration.ini')
api_key = get_api_key(parser.get('Globals', 'api_file'))
galaxy_host = parser.get('Globals', 'galaxy_host')
galaxyInstance = GalaxyInstance(galaxy_host, key=api_key)
libraryInstance = LibraryClient(galaxyInstance)
libs = libraryInstance.get_libraries(name=parser.get('Globals','default_lib'))
details = libraryInstance.get_folders(library_id=libs[0]['id'])
folder = libraryInstance.show_library(library_id=libs[0]['id'],contents=True)
for f in folder[1:]:
print "%s:%s" % (f['name'],f['id'])
workflow = WorkflowClient(galaxyInstance)
wf = workflow.get_workflows()
for w in wf:
print w['id']
print w['name']
print w['owner']
def runWorkflow(argDictionary, comparisons,samples):
from bioblend.galaxy import GalaxyInstance
from bioblend.galaxy.histories import HistoryClient
from bioblend.galaxy.tools import ToolClient
from bioblend.galaxy.workflows import WorkflowClient
from bioblend.galaxy.libraries import LibraryClient
import tempfile
import time
api_key = ''
galaxy_host = ''
gi = GalaxyInstance(url=galaxy_host, key=api_key)
history_client = HistoryClient(gi)
tool_client = ToolClient(gi)
workflow_client = WorkflowClient(gi)
library_client = LibraryClient(gi)
history = history_client.create_history(argDictionary['accessionNumber'])
comparisonsTable = tool_client.upload_file(comparisons, history['id'], file_type='txt')
sampleTable = tool_client.upload_file(samples, history['id'], file_type='tabular')
if argDictionary['site'] == "ENA":
#fastqs available on ENA
tool_inputs = {
"accessionNumber":argDictionary["ENA"],"sampleTable":{'id': sampleTable['outputs'][0]['id'], 'src': 'hda'}
}
#run the tool to get the data from ENA
tool_client.run_tool(history['id'],'getRNASeqExpressionData', tool_inputs)
#we want to wait until we have all datasets
while getNumberNotComplete(history['id'], history_client) > 0:
time.sleep(10)
#sleep until all the fastq files are findable
time.sleep(120)
dirpath = tempfile.mkdtemp()
fileList = getDatasetsByApproxName("files.tabular", history,history_client)[0]
fileList = history_client.download_dataset(history["id"],fileList["id"],dirpath)
num_lines = sum(1 for line in open(fileList)) -1
datasets=list()
while len(datasets)!=num_lines:
time.sleep(10)
datasets = getDatasetsByApproxName("fastq",history,history_client )
else: #for SRA
if argDictionary['single'] == "TRUE":
with open(samples) as tsvfile:
reader = csv.DictReader(tsvfile, delimiter='\t')
for sample in reader:
print (sample)
fileNames=str.split(sample["File"],"|")
for fileName in fileNames:
tool_inputs = {
"input|input_select":"accession_number",
"outputformat":"fastqsanger.gz",
"input|accession":fileName
}
#run the tool to get the single data from SRA
tool_client.run_tool(history['id'],'toolshed.g2.bx.psu.edu/repos/iuc/sra_tools/fastq_dump/2.8.1.3', tool_inputs)
else:
with open(samples) as tsvfile:
reader = csv.DictReader(tsvfile, delimiter='\t')
for sample in reader:
tool_inputs = {
"accession_number":sample["File"]
}
#run the tool to get the paired data from SRA
tool_client.run_tool(history['id'],'toolshed.g2.bx.psu.edu/repos/mandorodriguez/fastqdump_paired/fastq_dump_paired/1.1.4', tool_inputs)
while getNumberNotComplete(history['id'], history_client) > 0:
time.sleep(10)
datasets = getDatasetsByApproxName("fastq",history,history_client )
#get the fastQC tool
for fastq in datasets:
try:
tool_inputs = {'input_file' : {'id': fastq['id'], 'src': 'hda'}}
tool_client.run_tool(history['id'],'toolshed.g2.bx.psu.edu/repos/devteam/fastqc/fastqc/0.69', tool_inputs)
except Exception:
pass
#wait till complete
while getNumberNotComplete(history['id'], history_client) > 0:
time.sleep(10)
#make dataset collections for quantification using the fastq files
collections=list()
with open(samples) as tsvfile:
reader = csv.DictReader(tsvfile, delimiter='\t')
for row in reader:
datasets=list()
fileNames=str.split(row["File"],"|")
for fileName in fileNames:
datasets= datasets + getDatasetsByApproxName(fileName,history,history_client )
#make list of datasets
collections.append(makeDataSetCollection(datasets,row["Sample"],history,history_client))
#get the correct kallisto index
species = argDictionary['species'].lower()
index = getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name=species +"IndexFile")
index = {'id': index, 'src': 'hda'}
#run kallisto for every dataset collection
for collection in collections:
#set up the tool_inputs
tool_inputs = {'index' : index,'inputs' : {'id': collection['id'], 'src': 'hdca'} ,"single":argDictionary["single"],"stranded":argDictionary["stranded"]}
#often encounter connection broken error - possible problem with Certus server?
#bypass by ignoring the exception
tool_client.run_tool(history['id'],'kallistoQuant', tool_inputs)
# we want to wait until we have all datasets
while getNumberNotComplete(history['id'], history_client) > 0:
time.sleep(10)
# Run multiqc on kallisto logs and fastqc files
datasets = getDatasetsByApproxName("RawData",history,history_client )
kallistoLogs = getDatasetsByApproxName(".log", history, history_client)
tool_inputs = {}
for i, dataset in enumerate(datasets+kallistoLogs):
if not dataset["deleted"]:
if dataset in datasets:
software = 'fastqc'
else:
software = 'kallisto'
params = {'id' : dataset['id'], 'src': 'hda', 'name': dataset['name']}
tool_inputs.update({'results_%s|software_cond|software' % i: software, 'results_%s|input_file' % i: params})
# #summarise with the multiQC tool
tool_client.run_tool(history['id'],'multiqc', tool_inputs)
multiQc = getDatasetsByApproxName("multiqc",history,history_client)[0]
#get all the abundance files to convert to gene level counts matrix
datasets = getDatasetsByApproxName(".abundance",history,history_client )
#make a dataset collection for to make a countsMatrix
collection = makeDataSetCollection(datasets,"abundances",history,history_client)
#set up the tool_inputs
tool_inputs = {'inputs' : {'id': collection['id'], 'src': 'hdca'} ,"species":argDictionary['species']}
#convert abundances to gene level counts matrix
tool_client.run_tool(history['id'],'KallistoAbundancestoGeneCountMatrix', tool_inputs)
# A diry hack, we want to wait until we have all datasets
while getNumberNotComplete(history['id'], history_client) > 0:
time.sleep(10)
txi = getDatasetsByApproxName("txi",history,history_client)
#set up the tool_inputs for PCA
tool_inputs = {'txiData' : {'id': txi[0]['id'], 'src': 'hda'} ,'sampleTable' : {'id': sampleTable['outputs'][0]['id'], 'src': 'hda'} ,"species":argDictionary['species'],'technicalReplicates':argDictionary['technicalReplicates'],'batchCorrect':argDictionary['batchCorrect']}
#run deseq2
tool_client.run_tool(history['id'],'PCARNASeq', tool_inputs)
pca = getDatasetsByApproxName("PCA",history,history_client)[0]
#set up the tool_inputs for DESeq2
tool_inputs = {'txiData' : {'id': txi[0]['id'], 'src': 'hda'} ,'sampleTable' : {'id': sampleTable['outputs'][0]['id'], 'src': 'hda'} ,
'comparisonsTable' : {'id': comparisonsTable['outputs'][0]['id'], 'src': 'hda'} ,"foldChangeOnly":argDictionary['foldChangeOnly'],"species":argDictionary['species'],'technicalReplicates':argDictionary['technicalReplicates'],'batchCorrect':argDictionary['batchCorrect']}
#run deseq2
tool_client.run_tool(history['id'],'DESeq2FoldChange', tool_inputs)
#run chrdir
tool_client.run_tool(history['id'],'characteristicDirectionRNASeq', tool_inputs)
#we want to wait until we have all datasets
while getNumberNotComplete(history['id'], history_client) > 0:
time.sleep(10)
#get the foldchange data, cut and run pathway workflow
dataset_id = getFoldChangeData(history, history_client)['id']
return_collection = [{'accessionNo':argDictionary['accessionNumber'], 'foldChange': getUrl(dataset_id), 'PCA': getUrl(pca["id"]),'chrDirTable': getUrl(getMostRecentDatasetByName('chrDirTable.tabular', history, history_client)['id'])}]
number_of_comparisons = -1
for line in open(comparisons):
if not line.isspace():
number_of_comparisons += 1
for comparison in range(0, int(number_of_comparisons)):
tool_inputs = {
'foldChangeTable' : {'id': dataset_id, 'src': 'hda'},
'comparisonNumber' : comparison + 1
}
tool_client.run_tool(history['id'], 'cutFoldChangeTable', tool_inputs)
while getNumberNotComplete(history['id'], history_client) > 0:
time.sleep(10)
if argDictionary['species'] in ["Rat","Cow","Horse","Pig","Zebrafish"]:
pathwayAnalysisWorkflow = workflow_client.show_workflow('c9468fdb6dc5c5f1')
params = dict()
for key in pathwayAnalysisWorkflow['steps'].keys():
params[key] = argDictionary
if argDictionary['species'] == "Rat":
network=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="ratStringNetwork")
geneLengths=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="ratGeneLengths")
homology=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="HOM_AllOrganism.rpt")
if argDictionary['species'] == "Cow":
network=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="cowStringNetwork")
geneLengths=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="cowGeneLengths")
homology=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="HOM_AllOrganism.rpt")
if argDictionary['species'] == "Horse":
network=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="horseStringNetwork")
geneLengths=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="horseGeneLengths")
homology=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="Homology.horse.txt")
if argDictionary['species'] == "Pig":
network=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="pigStringNetwork.txt")
geneLengths=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="pigGeneLengths.tabular")
homology=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="Homology.pig.txt")
if argDictionary['species'] == "Zebrafish":
network=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="zebrafishStringNetwork")
geneLengths=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="zebrafishGeneLengths")
homology=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="HOM_AllOrganism.rpt")
pathwayDatamap = {'3' : {'id': homology, 'src': 'hda'},'2' : {'id': network, 'src': 'hda'},'1' : {'id': geneLengths, 'src': 'hda'}}
diffExpDataCollection = getDatasetsByName('cutTable.tabular', history, history_client)
for index, diffExpData in enumerate(diffExpDataCollection):
numCompleted = getNumberComplete(history['id'], history_client) + 10
print(numCompleted)
pathwayDatamap["0"] = {'id': diffExpData['id'], 'src': 'hda'}
workflow_client.invoke_workflow(pathwayAnalysisWorkflow['id'],
inputs = pathwayDatamap,
history_id = history['id'],
params = params)
comparisonDict = getRowFromCsv(comparisons, index)
if 'Factor1' in comparisonDict.keys():
comparisonDict['Factor'] = comparisonDict['Factor1'] + "." + comparisonDict['Factor2']
return_dict = {'accessionNo':argDictionary['accessionNumber'],
'factor':comparisonDict['Factor'],
'comparisonNum':comparisonDict['Numerator'],
'comparisonDenom':comparisonDict['Denominator'],
'foldChange': getUrl(diffExpData['id']),
'interactome': pathwayDatamap['0']['id'],
'exonLength': pathwayDatamap['2']['id']}
while getNumberComplete(history['id'], history_client) < numCompleted:
time.sleep(10)
return_dict['moduleNodes'] = getUrl(getMostRecentDatasetByName('moduleNodes.text',
history, history_client)['id'])
return_dict['modulePlots'] = getUrl(getMostRecentDatasetByName('modulePlots.pdf',
history, history_client)['id'])
return_dict['slimEnrichPathways'] = getUrl(getMostRecentDatasetByName('slimEnrichmentPathways.tabular',
history, history_client)['id'])
return_dict['enrichedDrugsReverse'] = getUrl(getMostRecentDatasetByName('enrichedDrugsReverse.tabular',
history, history_client)['id'])
return_dict['enrichedDrugsMimic'] = getUrl(getMostRecentDatasetByName('enrichedDrugsMimic.tabular',
history, history_client)['id'])
return_dict['enrichedTerms'] = getUrl(getMostRecentDatasetByName('enrichedTerms.tabular',
history, history_client)['id'])
return_dict['enrichedTerms.reduced'] = getUrl(getMostRecentDatasetByName('enrichedTerms.reduced.tabular',
history, history_client)['id'])
return_dict['GO.MDS'] = getUrl(getMostRecentDatasetByName('GO.MDS.html',
history, history_client)['id'])
return_collection.append(return_dict)
# Hard code keys to define the order
keys = ['accessionNo','multiQC','factor','PCA','chrDirTable','comparisonNum','comparisonDenom','foldChange',
'interactome','exonLength','moduleNodes','modulePlots',
'slimEnrichPathways','secretedProteins','enrichedDrugsReverse','enrichedDrugsMimic','enrichedTerms','enrichedTerms.reduced','GO.MDS']
outFileName = 'output/' + argDictionary['accessionNumber'] + '-workflowOutput.tsv'
with open(outFileName, 'wb') as csvFile:
# Get headers from last dictionary in collection as first doesn't contain all keys
csvOutput = csv.DictWriter(csvFile, keys, delimiter = "\t")
csvOutput.writeheader()
csvOutput.writerows(return_collection)
#tool_client.upload_file(outFileName, history['id'], file_type='tsv')
return return_collection
else:
pathwayAnalysisWorkflow = workflow_client.show_workflow('e85a3be143d5905b')
params = dict()
for key in pathwayAnalysisWorkflow['steps'].keys():
params[key] = argDictionary
if argDictionary['species'] == "Mouse":
network=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="mouseStringNetwork")
geneLengths=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="MouseGeneLengths.tab")
homology=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="Homology.mouse.txt")
secretedReference=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="uniprot-secreted-mouse.txt")
pathwayDatamap = {'4' : {'id': secretedReference, 'src': 'hda'},'3' : {'id': homology, 'src': 'hda'},'2' : {'id': network, 'src': 'hda'},'1' : {'id': geneLengths, 'src': 'hda'}}
else:
network=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="humanStringNetwork")
geneLengths=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="geneLengths")
homology=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="Homology.mouse.txt")
secretedReference=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="uniprot-secreted-human.txt")
pathwayDatamap = {'4' : {'id': secretedReference, 'src': 'hda'},'3' : {'id': homology, 'src': 'hda'},'2' : {'id': network, 'src': 'hda'},'1' : {'id': geneLengths, 'src': 'hda'}}
diffExpDataCollection = getDatasetsByName('cutTable.tabular', history, history_client)
for index, diffExpData in enumerate(diffExpDataCollection):
numCompleted = getNumberComplete(history['id'], history_client) + 14
print(numCompleted)
pathwayDatamap["0"] = {'id': diffExpData['id'], 'src': 'hda'}
#pathwayDatamap['1'] = {'id': diffExpData['id'], 'src': 'hda'}
workflow_client.invoke_workflow(pathwayAnalysisWorkflow['id'],
inputs = pathwayDatamap,
history_id = history['id'],
params = params)
comparisonDict = getRowFromCsv(comparisons, index)
if 'Factor1' in comparisonDict.keys():
comparisonDict['Factor'] = comparisonDict['Factor1'] + "." + comparisonDict['Factor2']
return_dict = {'accessionNo':argDictionary['accessionNumber'],
'factor':comparisonDict['Factor'],
'comparisonNum':comparisonDict['Numerator'],
'comparisonDenom':comparisonDict['Denominator'],
'foldChange': getUrl(diffExpData['id']),
'interactome': pathwayDatamap['0']['id'],
'exonLength': pathwayDatamap['2']['id']}
while getNumberComplete(history['id'], history_client) < numCompleted:
time.sleep(10)
return_dict['moduleNodes'] = getUrl(getMostRecentDatasetByName('moduleNodes.text',
history, history_client)['id'])
return_dict['modulePlots'] = getUrl(getMostRecentDatasetByName('modulePlots.pdf',
history, history_client)['id'])
return_dict['pathways'] = getUrl(getMostRecentDatasetByName('pathways.tabular',
history, history_client)['id'])
return_dict['enrichPlot'] = getUrl(getMostRecentDatasetByName('enrichmentPlot.png',
history, history_client)['id'])
return_dict['enrichmentTable'] = getUrl(getMostRecentDatasetByName('TF_EnrichmentTable.tabular',
history, history_client)['id'])
return_dict['slimEnrichPathways'] = getUrl(getMostRecentDatasetByName('slimEnrichmentPathways.tabular',
history, history_client)['id'])
return_dict['secretedProteins'] = getUrl(getMostRecentDatasetByName('secretedProteins.tabular',
history, history_client)['id'])
return_dict['enrichedDrugsReverse'] = getUrl(getMostRecentDatasetByName('enrichedDrugsReverse.tabular',
history, history_client)['id'])
return_dict['enrichedDrugsMimic'] = getUrl(getMostRecentDatasetByName('enrichedDrugsMimic.tabular',
history, history_client)['id'])
return_dict['enrichedTerms'] = getUrl(getMostRecentDatasetByName('enrichedTerms.tabular',
history, history_client)['id'])
return_dict['enrichedTerms.reduced'] = getUrl(getMostRecentDatasetByName('enrichedTerms.reduced.tabular',
history, history_client)['id'])
return_dict['GO.MDS'] = getUrl(getMostRecentDatasetByName('GO.MDS.html',
history, history_client)['id'])
return_collection.append(return_dict)
# Hard code keys to define the order
keys = ['accessionNo','multiQC','factor','PCA','chrDirTable','comparisonNum','comparisonDenom','foldChange',
'interactome','exonLength','moduleNodes','modulePlots','pathways','enrichPlot', 'enrichmentTable',
'slimEnrichPathways','secretedProteins','enrichedDrugsReverse','enrichedDrugsMimic','enrichedTerms','enrichedTerms.reduced','GO.MDS']
outFileName = 'output/' + argDictionary['accessionNumber'] + '-workflowOutput.tsv'
with open(outFileName, 'wb') as csvFile:
# Get headers from last dictionary in collection as first doesn't contain all keys
csvOutput = csv.DictWriter(csvFile, keys, delimiter = "\t")
csvOutput.writeheader()
csvOutput.writerows(return_collection)
return return_collection
def runWorkflow(argDictionary, comparisons):
from bioblend.galaxy import GalaxyInstance
from bioblend.galaxy.histories import HistoryClient
from bioblend.galaxy.tools import ToolClient
from bioblend.galaxy.workflows import WorkflowClient
from bioblend.galaxy.libraries import LibraryClient
import time
api_key = ''
galaxy_host = 'http://localhost:8080/'
gi = GalaxyInstance(url=galaxy_host, key=api_key)
history_client = HistoryClient(gi)
tool_client = ToolClient(gi)
workflow_client = WorkflowClient(gi)
library_client = LibraryClient(gi)
history = history_client.create_history(row['accessionNumber'])
# Import the galaxy workflow
workflow = workflow_client.show_workflow('a799d38679e985db')
input_file = tool_client.upload_file(comparisons, history['id'], file_type='txt')
# Run workflow on csv data to create a new history.
params = dict()
for key in workflow['steps'].keys():
params[key] = argDictionary
datamap = {'1' : {'id': input_file['outputs'][0]['id'], 'src': 'hda'}}
workflow_client.invoke_workflow(workflow['id'], inputs = datamap, history_id = history['id'], params = params)
# A diry hack, we want to wait until we have all datasets
while getNumberNotComplete(history['id'], history_client) > 0:
time.sleep(10)
dataset_id = getFoldChangeData(history, history_client)['id']
return_collection = [{'accessionNo':argDictionary['accessionNumber'], 'foldChange': getUrl(dataset_id),
'PCA': getUrl(getMostRecentDatasetByName('PCAplot.png', history, history_client)['id']),'chrDirTable': getUrl(getMostRecentDatasetByName('chrDirTable.tabular', history, history_client)['id'])}]
number_of_comparisons = -1
for line in open(comparisons):
if not line.isspace():
number_of_comparisons += 1
for comparison in range(0, int(number_of_comparisons)):
tool_inputs = {
'foldChangeTable' : {'id': dataset_id, 'src': 'hda'},
'comparisonNumber' : comparison + 1
}
tool_client.run_tool(history['id'], 'cutFoldChangeTable', tool_inputs)
while getNumberNotComplete(history['id'], history_client) > 0:
time.sleep(10)
if argDictionary['species'] in ["Rat","Cow","Horse","Pig","Zebrafish"]:
pathwayAnalysisWorkflow = workflow_client.show_workflow('c9468fdb6dc5c5f1')
params = dict()
for key in pathwayAnalysisWorkflow['steps'].keys():
params[key] = argDictionary
if argDictionary['species'] == "Rat":
network=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="ratStringNetwork")
geneLengths=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="ratGeneLengths")
homology=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="Homology.rat.txt")
if argDictionary['species'] == "Cow":
network=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="cowStringNetwork")
geneLengths=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="cowGeneLengths")
homology=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="Homology.cow.txt")
if argDictionary['species'] == "Horse":
network=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="horseStringNetwork")
geneLengths=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="horseGeneLengths")
homology=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="Homology.horse.txt")
if argDictionary['species'] == "Pig":
network=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="pigStringNetwork.txt")
geneLengths=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="pigGeneLengths.tabular")
homology=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="Homology.pig.txt")
if argDictionary['species'] == "Zebrafish":
network=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="zebrafishStringNetwork")
geneLengths=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="zebrafishGeneLengths")
homology=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="HOM_AllOrganism.rpt")
pathwayDatamap = {'3' : {'id': homology, 'src': 'hda'},'2' : {'id': network, 'src': 'hda'},'1' : {'id': geneLengths, 'src': 'hda'}}
diffExpDataCollection = getDatasetsByName('cutTable.tabular', history, history_client)
for index, diffExpData in enumerate(diffExpDataCollection):
numCompleted = getNumberComplete(history['id'], history_client) + 10
print(numCompleted)
pathwayDatamap["0"] = {'id': diffExpData['id'], 'src': 'hda'}
workflow_client.invoke_workflow(pathwayAnalysisWorkflow['id'],
inputs = pathwayDatamap,
history_id = history['id'],
params = params)
comparisonDict = getRowFromCsv(comparisons, index)
if 'Factor1' in comparisonDict.keys():
comparisonDict['Factor'] = comparisonDict['Factor1'] + "." + comparisonDict['Factor2']
if 'Paired1' in comparisonDict.keys():
comparisonDict['Factor'] = comparisonDict['Paired1']
return_dict = {'accessionNo':argDictionary['accessionNumber'],
'factor':comparisonDict['Factor'],
'comparisonNum':comparisonDict['Numerator'],
'comparisonDenom':comparisonDict['Denominator'],
'foldChange': getUrl(diffExpData['id']),
'interactome': pathwayDatamap['0']['id'],
'exonLength': pathwayDatamap['2']['id']}
while getNumberComplete(history['id'], history_client) < numCompleted:
time.sleep(10)
return_dict['moduleNodes'] = getUrl(getMostRecentDatasetByName('moduleNodes.text',
history, history_client)['id'])
return_dict['modulePlots'] = getUrl(getMostRecentDatasetByName('modulePlots.pdf',
history, history_client)['id'])
return_dict['slimEnrichmentPathways'] = getUrl(getMostRecentDatasetByName('slimEnrichmentPathways.tabular',
history, history_client)['id'])
return_dict['slimEnrichmentPlot'] = getUrl(getMostRecentDatasetByName('slimEnrichmentPlot.png',
history, history_client)['id'])
return_collection.append(return_dict)
# Hard code keys to define the order
keys = ['accessionNo','factor','comparisonNum','comparisonDenom','PCA','chrDirTable','foldChange',
'interactome','exonLength','moduleNodes','modulePlots','enrichmentTable','slimEnrichmentPathways','slimEnrichmentPlot']
with open('output/' + argDictionary['accessionNumber'] + '-workflowOutput.csv', 'wb') as csvFile:
# Get headers from last dictionary in collection as first doesn't contain all keys
csvOutput = csv.DictWriter(csvFile, keys)
csvOutput.writeheader()
csvOutput.writerows(return_collection)
return return_collection
else:
pathwayAnalysisWorkflow = workflow_client.show_workflow('e85a3be143d5905b')
params = dict()
for key in pathwayAnalysisWorkflow['steps'].keys():
params[key] = argDictionary
# MouseGeneLengths.tab has id 457f69dd7016f307 - step 2 of workflow
# Mouse interactome has id 073be90ac6c3bce5 - step 0 of workflow
if argDictionary['species'] == "Mouse":
network=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="mouseStringNetwork")
geneLengths=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="MouseGeneLengths.tab")
homology=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="Homology.mouse.txt")
secretedReference=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="uniprot-secreted-mouse.txt")
pathwayDatamap = {'4' : {'id': secretedReference, 'src': 'hda'},'3' : {'id': homology, 'src': 'hda'},'2' : {'id': network, 'src': 'hda'},'1' : {'id': geneLengths, 'src': 'hda'}}
else:
network=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="humanStringNetwork")
geneLengths=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="geneLengths")
homology=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="Homology.mouse.txt")
secretedReference=getLibraryToolDataID(history=history,history_client=history_client,library_client=library_client,name="uniprot-secreted-human.txt")
pathwayDatamap = {'4' : {'id': secretedReference, 'src': 'hda'},'3' : {'id': homology, 'src': 'hda'},'2' : {'id': network, 'src': 'hda'},'1' : {'id': geneLengths, 'src': 'hda'}}
diffExpDataCollection = getDatasetsByName('cutTable.tabular', history, history_client)
for index, diffExpData in enumerate(diffExpDataCollection):
numCompleted = getNumberComplete(history['id'], history_client) + 14
print(numCompleted)
pathwayDatamap["0"] = {'id': diffExpData['id'], 'src': 'hda'}
workflow_client.invoke_workflow(pathwayAnalysisWorkflow['id'],
inputs = pathwayDatamap,
history_id = history['id'],
params = params)
comparisonDict = getRowFromCsv(comparisons, index)
if 'Factor1' in comparisonDict.keys():
comparisonDict['Factor'] = comparisonDict['Factor1'] + "." + comparisonDict['Factor2']
if 'Paired1' in comparisonDict.keys():
comparisonDict['Factor'] = comparisonDict['Paired1']
return_dict = {'accessionNo':argDictionary['accessionNumber'],
'factor':comparisonDict['Factor'],
'comparisonNum':comparisonDict['Numerator'],
'comparisonDenom':comparisonDict['Denominator'],
'foldChange': getUrl(diffExpData['id']),
'interactome': pathwayDatamap['0']['id'],
'exonLength': pathwayDatamap['2']['id']}
while getNumberComplete(history['id'], history_client) < numCompleted:
time.sleep(10)
return_dict['moduleNodes'] = getUrl(getMostRecentDatasetByName('moduleNodes.text',
history, history_client)['id'])
return_dict['modulePlots'] = getUrl(getMostRecentDatasetByName('modulePlots.pdf',
history, history_client)['id'])
return_dict['pathways'] = getUrl(getMostRecentDatasetByName('pathways.tabular',
history, history_client)['id'])
return_dict['enrichPlot'] = getUrl(getMostRecentDatasetByName('enrichmentPlot.png',
history, history_client)['id'])
return_dict['enrichmentTable'] = getUrl(getMostRecentDatasetByName('TF_EnrichmentTable.tabular',
history, history_client)['id'])
return_dict['slimEnrichmentPathways'] = getUrl(getMostRecentDatasetByName('slimEnrichmentPathways.tabular',
history, history_client)['id'])
return_dict['slimEnrichmentPlot'] = getUrl(getMostRecentDatasetByName('slimEnrichmentPlot.png',
history, history_client)['id'])
return_collection.append(return_dict)
# Hard code keys to define the order
keys = ['accessionNo','factor','comparisonNum','comparisonDenom','PCA','chrDirTable','foldChange',
'interactome','exonLength','moduleNodes','modulePlots','pathways','enrichPlot','enrichmentTable','slimEnrichmentPathways','slimEnrichmentPlot']
with open('output/' + argDictionary['accessionNumber'] + '-workflowOutput.csv', 'wb') as csvFile:
# Get headers from last dictionary in collection as first doesn't contain all keys
csvOutput = csv.DictWriter(csvFile, keys)
csvOutput.writeheader()
csvOutput.writerows(return_collection)
return return_collection
__version__ = '0.1.0'
#import logging
#logging.basicConfig(level=logging.DEBUG)
upload_history_name = 'Uploaded data'
upload_history_tag = 'user_data'
workflow_tag = 'islandcompare'
workflow_owner = 'brinkmanlab'
application_tag = 'IslandCompare'
ext_to_datatype = {
"genbank": "genbank", "gbk": "genbank", "embl": "embl", "gbff": "genbank", "newick": "newick", "nwk": "newick"
}
WorkflowClient.set_max_get_retries(5)
HistoryClient.set_max_get_retries(5)
DatasetClient.set_max_get_retries(5)
JobsClient.set_max_get_retries(5)
InvocationClient.set_max_get_retries(5)
# ======== Patched bioblend functions ===========
# TODO Remove after upgrading to v0.16.0
def get_invocations(self, workflow_id, history_id=None, user_id=None, include_terminal=True, limit=None, view='collection', step_details=False):
url = self._invocations_url(workflow_id)
params = {'include_terminal': include_terminal, 'view': view, 'step_details': step_details}
if history_id: params['history_id'] = history_id
if user_id: params['user_id'] = user_id
if limit: params['limit'] = limit
return self._get(url=url, params=params)