From 49f5add2f9fb393db5d7436230cc0cf2536f0b57 Mon Sep 17 00:00:00 2001
From: Loraine Gueguen <loraine.gueguen@sb-roscoff.fr>
Date: Fri, 28 May 2021 23:19:47 +0200
Subject: [PATCH] Refactor run_wf (WIP)
---
...constants.py => phaeoexplorer_constants.py | 18 +-
run_workflow_phaeoexplorer.py | 242 +++++++-----------
2 files changed, 112 insertions(+), 148 deletions(-)
rename phaoexplorer_constants.py => phaeoexplorer_constants.py (75%)
diff --git a/phaoexplorer_constants.py b/phaeoexplorer_constants.py
similarity index 75%
rename from phaoexplorer_constants.py
rename to phaeoexplorer_constants.py
index 1cecdb1..2773e2b 100644
--- a/phaoexplorer_constants.py
+++ b/phaeoexplorer_constants.py
@@ -6,11 +6,23 @@ import constants
### Workflows
WORKFLOWS_PATH = "workflows_phaeoexplorer/"
-WORKFLOW_LOAD_FASTA_GFF_JBROWSE = "load_fasta_gff_jbrowse"
-WORKFLOW_LOAD_FASTA_GFF_JBROWSE_FILE_1_ORG = "Galaxy-Workflow-chado_load_tripal_synchronize_jbrowse_1org_v4.ga"
+WF_LOAD_GFF_JB = "load_fasta_gff_jbrowse"
+
+WF_LOAD_GFF_JB_1_ORG_FILE = "Galaxy-Workflow-chado_load_tripal_synchronize_jbrowse_1org_v4.ga"
+WF_LOAD_GFF_JB_1_ORG_INPUT_GENOME = "0"
+WF_LOAD_GFF_JB_1_ORG_INPUT_GFF = "1"
+WF_LOAD_GFF_JB_1_ORG_INPUT_PROTEINS = "2"
+WF_LOAD_GFF_JB_1_ORG_STEP_LOAD_FASTA = "3"
+WF_LOAD_GFF_JB_1_ORG_STEP_JBROWSE = "4"
+WF_LOAD_GFF_JB_1_ORG_STEP_LOAD_GFF = "5"
+WF_LOAD_GFF_JB_1_ORG_STEP_JB_TO_CONTAINER = "6"
+WF_LOAD_GFF_JB_1_ORG_STEP_FEATURE_SYNC = "7"
+WF_LOAD_GFF_JB_1_ORG_STEP_POPULATE_VIEWS = "8"
+WF_LOAD_GFF_JB_1_ORG_STEP_INDEX = "9"
+
WORKFLOW_BLAST = "blast"
WORKFLOW_INTERPRO = "interpro"
-WORKFLOW_VALID_TYPES = [WORKFLOW_LOAD_FASTA_GFF_JBROWSE, WORKFLOW_BLAST, WORKFLOW_INTERPRO]
+WORKFLOW_VALID_TYPES = [WF_LOAD_GFF_JB, WORKFLOW_BLAST, WORKFLOW_INTERPRO]
### Galaxy tools
diff --git a/run_workflow_phaeoexplorer.py b/run_workflow_phaeoexplorer.py
index c03b917..60c0ed3 100755
--- a/run_workflow_phaeoexplorer.py
+++ b/run_workflow_phaeoexplorer.py
@@ -16,7 +16,7 @@ from bioblend import galaxy
import utilities
import speciesData
import constants
-import phaoexplorer_constants
+import phaeoexplorer_constants
"""
gga_init.py
@@ -27,7 +27,7 @@ Usage: $ python3 gga_init.py -i input_example.yml --config [config file] [OPTION
class StrainWorkflowParam:
def __init__(self, genus_species, strain_sex, genus, species, sex, strain, full_name, species_folder_name, org_id,
- genome_analysis_id, ogs_analysis_id, blastp_analysis_id, interpro_analysis_id, hda_ids, history_id,
+ genome_analysis_id, ogs_analysis_id, blastp_analysis_id, interpro_analysis_id, history_id,
instance, instance_url, email, password):
self.genus_species = genus_species
self.strain_sex = strain_sex
@@ -42,7 +42,6 @@ class StrainWorkflowParam:
self.ogs_analysis_id = ogs_analysis_id
self.blastp_analysis_id = blastp_analysis_id
self.interpro_analysis_id = interpro_analysis_id
- self.hda_ids = hda_ids
self.history_id = history_id
self.instance = instance
self.instance_url = instance_url
@@ -58,21 +57,21 @@ class StrainWorkflowParam:
def check_param_for_workflow_load_fasta_gff_jbrowse(self, params):
params = [self.genus_species, self.strain_sex, self.genus, self.species, self.sex, self.strain, self.full_name,
self.species_folder_name, self.org_id,
- self.genome_analysis_id, self.ogs_analysis_id, self.hda_ids, self.history_id,
+ self.genome_analysis_id, self.ogs_analysis_id, self.history_id,
self.instance, self.instance_url, self.email, self.password]
self.check_param(params)
def check_param_for_workflow_blast(self, params):
params = [self.genus_species, self.strain_sex, self.genus, self.species, self.sex, self.strain, self.full_name,
self.species_folder_name, self.org_id,
- self.blastp_analysis_id, self.hda_ids, self.history_id,
+ self.blastp_analysis_id, self.history_id,
self.instance, self.instance_url, self.email, self.password]
self.check_param(params)
def check_param_for_workflow_interpro(self, params):
params = [self.genus_species, self.strain_sex, self.genus, self.species, self.sex, self.strain, self.full_name,
self.species_folder_name, self.org_id,
- self.interpro_analysis_id, self.hda_ids, self.history_id,
+ self.interpro_analysis_id, self.history_id,
self.instance, self.instance_url, self.email, self.password]
self.check_param(params)
@@ -111,6 +110,14 @@ class RunWorkflow(speciesData.SpeciesData):
self.ogs_analysis_programversion = "OGS{0}".format(self.ogs_version)
self.ogs_analysis_sourcename = self.full_name
+ self.genome_hda_id = None
+ self.gff_hda_id = None
+ self.transcripts_hda_id = None
+ self.proteins_hda_id = None
+ self.blastp_hda_id = None
+ self.blastx_hda_id = None
+ self.interproscan_hda_id = None
+
def set_history(self):
"""
Create or set the working history to the current species one
@@ -165,50 +172,50 @@ class RunWorkflow(speciesData.SpeciesData):
# Verify that the add_organism and add_analysis versions are correct in the instance
- add_organism_tool = self.instance.tools.show_tool(phaoexplorer_constants.ADD_ORGANISM_TOOL_ID)
- add_analysis_tool = self.instance.tools.show_tool(phaoexplorer_constants.ADD_ANALYSIS_TOOL_ID)
- get_organisms_tool = self.instance.tools.show_tool(phaoexplorer_constants.GET_ORGANISMS_TOOL_ID)
- get_analyses_tool = self.instance.tools.show_tool(phaoexplorer_constants.GET_ANALYSES_TOOL_ID)
- analysis_sync_tool = self.instance.tools.show_tool(phaoexplorer_constants.ANALYSIS_SYNC_TOOL_ID)
- organism_sync_tool = self.instance.tools.show_tool(phaoexplorer_constants.ORGANISM_SYNC_TOOL_ID)
+ add_organism_tool = self.instance.tools.show_tool(phaeoexplorer_constants.ADD_ORGANISM_TOOL_ID)
+ add_analysis_tool = self.instance.tools.show_tool(phaeoexplorer_constants.ADD_ANALYSIS_TOOL_ID)
+ get_organisms_tool = self.instance.tools.show_tool(phaeoexplorer_constants.GET_ORGANISMS_TOOL_ID)
+ get_analyses_tool = self.instance.tools.show_tool(phaeoexplorer_constants.GET_ANALYSES_TOOL_ID)
+ analysis_sync_tool = self.instance.tools.show_tool(phaeoexplorer_constants.ANALYSIS_SYNC_TOOL_ID)
+ organism_sync_tool = self.instance.tools.show_tool(phaeoexplorer_constants.ORGANISM_SYNC_TOOL_ID)
# changeset for 2.3.4+galaxy0 has to be manually found because there is no way to get the wanted changeset of a non installed tool via bioblend
# except for workflows (.ga) that already contain the changeset revisions inside the steps ids
utilities.install_repository_revision(current_version=get_organisms_tool["version"],
toolshed_dict=get_organisms_tool["tool_shed_repository"],
- version_to_install=phaoexplorer_constants.GET_ORGANISMS_TOOL_VERSION,
- changeset_revision=phaoexplorer_constants.GET_ORGANISMS_TOOL_CHANGESET_REVISION,
+ version_to_install=phaeoexplorer_constants.GET_ORGANISMS_TOOL_VERSION,
+ changeset_revision=phaeoexplorer_constants.GET_ORGANISMS_TOOL_CHANGESET_REVISION,
instance=self.instance)
utilities.install_repository_revision(current_version=get_analyses_tool["version"],
toolshed_dict=get_analyses_tool["tool_shed_repository"],
- version_to_install=phaoexplorer_constants.GET_ANALYSES_TOOL_VERSION,
- changeset_revision=phaoexplorer_constants.GET_ANALYSES_TOOL_CHANGESET_REVISION,
+ version_to_install=phaeoexplorer_constants.GET_ANALYSES_TOOL_VERSION,
+ changeset_revision=phaeoexplorer_constants.GET_ANALYSES_TOOL_CHANGESET_REVISION,
instance=self.instance)
utilities.install_repository_revision(current_version=add_organism_tool["version"],
toolshed_dict=add_organism_tool["tool_shed_repository"],
- version_to_install=phaoexplorer_constants.ADD_ORGANISM_TOOL_VERSION,
- changeset_revision=phaoexplorer_constants.ADD_ORGANISM_TOOL_CHANGESET_REVISION,
+ version_to_install=phaeoexplorer_constants.ADD_ORGANISM_TOOL_VERSION,
+ changeset_revision=phaeoexplorer_constants.ADD_ORGANISM_TOOL_CHANGESET_REVISION,
instance=self.instance)
utilities.install_repository_revision(current_version=add_analysis_tool["version"],
toolshed_dict=add_analysis_tool["tool_shed_repository"],
- version_to_install=phaoexplorer_constants.ADD_ANALYSIS_TOOL_VERSION,
- changeset_revision=phaoexplorer_constants.ADD_ANALYSIS_TOOL_CHANGESET_REVISION,
+ version_to_install=phaeoexplorer_constants.ADD_ANALYSIS_TOOL_VERSION,
+ changeset_revision=phaeoexplorer_constants.ADD_ANALYSIS_TOOL_CHANGESET_REVISION,
instance=self.instance)
utilities.install_repository_revision(current_version=analysis_sync_tool["version"],
toolshed_dict=analysis_sync_tool["tool_shed_repository"],
- version_to_install=phaoexplorer_constants.ANALYSIS_SYNC_TOOL_VERSION,
- changeset_revision=phaoexplorer_constants.ANALYSIS_SYNC_TOOL_CHANGESET_REVISION,
+ version_to_install=phaeoexplorer_constants.ANALYSIS_SYNC_TOOL_VERSION,
+ changeset_revision=phaeoexplorer_constants.ANALYSIS_SYNC_TOOL_CHANGESET_REVISION,
instance=self.instance)
utilities.install_repository_revision(current_version=organism_sync_tool["version"],
toolshed_dict=organism_sync_tool["tool_shed_repository"],
- version_to_install=phaoexplorer_constants.ORGANISM_SYNC_TOOL_VERSION,
- changeset_revision=phaoexplorer_constants.ORGANISM_SYNC_TOOL_CHANGESET_REVISION,
+ version_to_install=phaeoexplorer_constants.ORGANISM_SYNC_TOOL_VERSION,
+ changeset_revision=phaeoexplorer_constants.ORGANISM_SYNC_TOOL_CHANGESET_REVISION,
instance=self.instance)
logging.info("Success: individual tools versions and changesets validated")
@@ -217,13 +224,13 @@ class RunWorkflow(speciesData.SpeciesData):
add_analysis_tool_dataset = utilities.run_tool_and_download_single_output_dataset(
instance=self.instance,
- tool_id=phaoexplorer_constants.ADD_ANALYSIS_TOOL_ID,
+ tool_id=phaeoexplorer_constants.ADD_ANALYSIS_TOOL_ID,
history_id=self.history_id,
tool_inputs={"name": name,
- "program": phaoexplorer_constants.ADD_ANALYSIS_TOOL_PARAM_PROGRAM,
+ "program": phaeoexplorer_constants.ADD_ANALYSIS_TOOL_PARAM_PROGRAM,
"programversion": programversion,
"sourcename": sourcename,
- "date_executed": phaoexplorer_constants.ADD_ANALYSIS_TOOL_PARAM_DATE})
+ "date_executed": phaeoexplorer_constants.ADD_ANALYSIS_TOOL_PARAM_DATE})
analysis_dict = json.loads(add_analysis_tool_dataset)
analysis_id = str(analysis_dict["analysis_id"])
@@ -234,7 +241,7 @@ class RunWorkflow(speciesData.SpeciesData):
time.sleep(60)
utilities.run_tool(
instance=self.instance,
- tool_id=phaoexplorer_constants.ANALYSIS_SYNC_TOOL_ID,
+ tool_id=phaeoexplorer_constants.ANALYSIS_SYNC_TOOL_ID,
history_id=self.history_id,
tool_inputs={"analysis_id": analysis_id})
@@ -242,7 +249,7 @@ class RunWorkflow(speciesData.SpeciesData):
get_organisms_tool_dataset = utilities.run_tool_and_download_single_output_dataset(
instance=self.instance,
- tool_id=phaoexplorer_constants.GET_ORGANISMS_TOOL_ID,
+ tool_id=phaeoexplorer_constants.GET_ORGANISMS_TOOL_ID,
history_id=self.history_id,
tool_inputs={},
time_sleep=10
@@ -259,7 +266,7 @@ class RunWorkflow(speciesData.SpeciesData):
if org_id is None:
add_organism_tool_dataset = utilities.run_tool_and_download_single_output_dataset(
instance=self.instance,
- tool_id=phaoexplorer_constants.ADD_ORGANISM_TOOL_ID,
+ tool_id=phaeoexplorer_constants.ADD_ORGANISM_TOOL_ID,
history_id=self.history_id,
tool_inputs={"abbr": self.abbreviation,
"genus": self.genus_uppercase,
@@ -273,7 +280,7 @@ class RunWorkflow(speciesData.SpeciesData):
time.sleep(60)
utilities.run_tool(
instance=self.instance,
- tool_id=phaoexplorer_constants.ORGANISM_SYNC_TOOL_ID,
+ tool_id=phaeoexplorer_constants.ORGANISM_SYNC_TOOL_ID,
history_id=self.history_id,
tool_inputs={"organism_id": org_id})
@@ -283,7 +290,7 @@ class RunWorkflow(speciesData.SpeciesData):
get_analyses_tool_dataset = utilities.run_tool_and_download_single_output_dataset(
instance=self.instance,
- tool_id=phaoexplorer_constants.GET_ANALYSES_TOOL_ID,
+ tool_id=phaeoexplorer_constants.GET_ANALYSES_TOOL_ID,
history_id=self.history_id,
tool_inputs={},
time_sleep=10
@@ -672,77 +679,13 @@ class RunWorkflow(speciesData.SpeciesData):
except Exception as exc:
logging.debug("blastp file not found in library (history: {0})".format(self.history_id))
- hda_ids = {"genome_hda_id": genome_hda_id,
- "gff_hda_id": gff_hda_id,
- "transcripts_hda_id": transcripts_hda_id,
- "proteins_hda_id": proteins_hda_id,
- "blastp_hda_id": blastp_hda_id,
- "blastx_hda_id": blastx_hda_id,
- "interproscan_hda_id": interproscan_hda_id}
-
- # logging.debug("History dataset IDs (hda_id) for %s:" % self.full_name)
- # logging.debug(hda_ids)
-
- # Return a dict made of the hda ids
- return hda_ids
-
-def run_workflow(workflow_path, workflow_parameters, datamap, config, input_species_number):
- """
- Run a workflow in galaxy
- Requires the .ga file to be loaded as a dictionary (optionally could be uploaded as a raw file)
-
- :param workflow_name:
- :param workflow_parameters:
- :param datamap:
- :return:
- """
-
- logging.info("Importing workflow %s" % str(workflow_path))
-
- # Load the workflow file (.ga) in a buffer
- with open(workflow_path, 'r') as ga_in_file:
-
- # Then store the decoded json dictionary
- workflow_dict = json.load(ga_in_file)
-
- # In case of the Jbrowse workflow, we unfortunately have to manually edit the parameters instead of setting them
- # as runtime values, using runtime parameters makes the tool throw an internal critical error ("replace not found" error)
- # Scratchgmod test: need "http" (or "https"), the hostname (+ port)
- if "jbrowse_menu_url" not in config.keys():
- jbrowse_menu_url = "https://{hostname}/sp/{genus_sp}/feature/{Genus}/{species}/mRNA/{id}".format(hostname=self.config["hostname"], genus_sp=self.genus_species, Genus=self.genus_uppercase, species=self.species, id="{id}")
- else:
- jbrowse_menu_url = config["jbrowse_menu_url"]
- if workflow_name == "Jbrowse":
- workflow_dict["steps"]["2"]["tool_state"] = workflow_dict["steps"]["2"]["tool_state"].replace("__MENU_URL__", jbrowse_menu_url)
- # The UNIQUE_ID is specific to a combination genus_species_strain_sex so every combination should have its unique workflow
- # in galaxy --> define a naming method for these workflows
- workflow_dict["steps"]["3"]["tool_state"] = workflow_dict["steps"]["3"]["tool_state"].replace("__FULL_NAME__", self.full_name).replace("__UNIQUE_ID__", self.species_folder_name)
-
- # Import the workflow in galaxy as a dict
- self.instance.workflows.import_workflow_dict(workflow_dict=workflow_dict)
-
- # Get its attributes
- workflow_attributes = self.instance.workflows.get_workflows(name=workflow_name)
- # Then get its ID (required to invoke the workflow)
- workflow_id = workflow_attributes[0]["id"] # Index 0 is the most recently imported workflow (the one we want)
- show_workflow = self.instance.workflows.show_workflow(workflow_id=workflow_id)
- # Check if the workflow is found
- try:
- logging.debug("Workflow ID: %s" % workflow_id)
- except bioblend.ConnectionError:
- logging.warning("Error retrieving workflow attributes for workflow %s" % workflow_name)
-
- # Finally, invoke the workflow alogn with its datamap, parameters and the history in which to invoke it
- self.instance.workflows.invoke_workflow(workflow_id=workflow_id,
- history_id=self.history_id,
- params=workflow_parameters,
- inputs=datamap,
- allow_tool_state_corrections=True)
-
- logging.info("Successfully imported and invoked workflow {0}, check the galaxy instance ({1}) for the jobs state".format(workflow_name, self.instance_url))
-
-
-
+ self.genome_hda_id = genome_hda_id
+ self.gff_hda_id = gff_hda_id
+ self.transcripts_hda_id = transcripts_hda_id
+ self.proteins_hda_id = proteins_hda_id
+ self.blastp_hda_id = blastp_hda_id
+ self.blastx_hda_id = blastx_hda_id
+ self.interproscan_hda_id = interproscan_hda_id
def get_sp_workflow_param(sp_dict, main_dir, config, workflow_type):
"""
@@ -775,7 +718,7 @@ def get_sp_workflow_param(sp_dict, main_dir, config, workflow_type):
history_id = run_workflow_for_current_organism.set_history()
run_workflow_for_current_organism.install_changesets_revisions_for_individual_tools()
- if workflow_type == phaoexplorer_constants.WORKFLOW_LOAD_FASTA_GFF_JBROWSE:
+ if workflow_type == phaeoexplorer_constants.WF_LOAD_GFF_JB:
analyses_dict_list = run_workflow_for_current_organism.get_analyses()
@@ -793,7 +736,7 @@ def get_sp_workflow_param(sp_dict, main_dir, config, workflow_type):
analysis_sourcename=run_workflow_for_current_organism.ogs_analysis_sourcename
)
- hda_ids = run_workflow_for_current_organism.import_datasets_into_history()
+ run_workflow_for_current_organism.import_datasets_into_history()
# Create the StrainWorkflowParam object holding all attributes needed for the workflow
sp_wf_param = StrainWorkflowParam(
@@ -808,7 +751,13 @@ def get_sp_workflow_param(sp_dict, main_dir, config, workflow_type):
org_id=org_id,
genome_analysis_id=genome_analysis_id,
ogs_analysis_id=ogs_analysis_id,
- hda_ids=hda_ids,
+ genome_hda_id=run_workflow_for_current_organism.genome_hda_id,
+ gff_hda_id=run_workflow_for_current_organism.gff_hda_id,
+ transcripts_hda_id=run_workflow_for_current_organism.transcripts_hda_id,
+ proteins_hda_id=run_workflow_for_current_organism.proteins_hda_id,
+ blastp_hda_id=run_workflow_for_current_organism.blastp_hda_id,
+ blastx_hda_id=run_workflow_for_current_organism.blastx_hda_id,
+ interproscan_hda_id=run_workflow_for_current_organism.interproscan_hda_id,
history_id=history_id,
instance=run_workflow_for_current_organism.instance,
instance_url=run_workflow_for_current_organism.instance_url,
@@ -823,7 +772,7 @@ def get_sp_workflow_param(sp_dict, main_dir, config, workflow_type):
org_id = ids["org_id"]
blastp_analysis_id = ids["blastp_analysis_id"]
- hda_ids = run_workflow_for_current_organism.import_datasets_into_history()
+ run_workflow_for_current_organism.import_datasets_into_history()
# Create the StrainWorkflowParam object holding all attributes needed for the workflow
sp_wf_param = StrainWorkflowParam(
@@ -837,7 +786,13 @@ def get_sp_workflow_param(sp_dict, main_dir, config, workflow_type):
strain=run_workflow_for_current_organism.strain,
org_id=org_id,
blastp_analysis_id=genome_analysis_id,
- hda_ids=hda_ids,
+ genome_hda_id=run_workflow_for_current_organism.genome_hda_id,
+ gff_hda_id=run_workflow_for_current_organism.gff_hda_id,
+ transcripts_hda_id=run_workflow_for_current_organism.transcripts_hda_id,
+ proteins_hda_id=run_workflow_for_current_organism.proteins_hda_id,
+ blastp_hda_id=run_workflow_for_current_organism.blastp_hda_id,
+ blastx_hda_id=run_workflow_for_current_organism.blastx_hda_id,
+ interproscan_hda_id=run_workflow_for_current_organism.interproscan_hda_id,
history_id=history_id,
instance=run_workflow_for_current_organism.instance,
instance_url=run_workflow_for_current_organism.instance_url,
@@ -852,7 +807,7 @@ def get_sp_workflow_param(sp_dict, main_dir, config, workflow_type):
org_id = ids["org_id"]
interpro_analysis_id = ids["interpro_analysis_id"]
- hda_ids = run_workflow_for_current_organism.import_datasets_into_history()
+ run_workflow_for_current_organism.import_datasets_into_history()
# Create the StrainWorkflowParam object holding all attributes needed for the workflow
sp_wf_param = StrainWorkflowParam(
@@ -866,7 +821,13 @@ def get_sp_workflow_param(sp_dict, main_dir, config, workflow_type):
strain=run_workflow_for_current_organism.strain,
org_id=org_id,
interpro_analysis_id=interpro_analysis_id,
- hda_ids=hda_ids,
+ genome_hda_id=run_workflow_for_current_organism.genome_hda_id,
+ gff_hda_id=run_workflow_for_current_organism.gff_hda_id,
+ transcripts_hda_id=run_workflow_for_current_organism.transcripts_hda_id,
+ proteins_hda_id=run_workflow_for_current_organism.proteins_hda_id,
+ blastp_hda_id=run_workflow_for_current_organism.blastp_hda_id,
+ blastx_hda_id=run_workflow_for_current_organism.blastx_hda_id,
+ interproscan_hda_id=run_workflow_for_current_organism.interproscan_hda_id,
history_id=history_id,
instance=run_workflow_for_current_organism.instance,
instance_url=run_workflow_for_current_organism.instance_url,
@@ -981,14 +942,14 @@ if __name__ == "__main__":
if not args.workflow:
logging.critical("No workflow type specified, exiting")
sys.exit()
- elif args.workflow in phaoexplorer_constants.WORKFLOW_VALID_TYPES:
+ elif args.workflow in phaeoexplorer_constants.WORKFLOW_VALID_TYPES:
workflow_type = args.workflow
logging.info("Workflow type set to '%s'" % workflow_type)
script_dir = os.path.dirname(os.path.realpath(sys.argv[0]))
all_sp_workflow_dict = {}
- if workflow_type == phaoexplorer_constants.WORKFLOW_LOAD_FASTA_GFF_JBROWSE:
+ if workflow_type == phaeoexplorer_constants.WF_LOAD_GFF_JB:
for sp_dict in sp_dict_list:
# Add and retrieve all analyses/organisms for the current input species and add their IDs to the input dictionary
@@ -996,7 +957,7 @@ if __name__ == "__main__":
sp_dict,
main_dir=main_dir,
config=config,
- workflow_type=phaoexplorer_constants.WORKFLOW_LOAD_FASTA_GFF_JBROWSE)
+ workflow_type=phaeoexplorer_constants.WF_LOAD_GFF_JB)
current_sp_genus_species = sp_workflow_param.genus_species
current_sp_strain_sex = sp_workflow_param.strain_sex
@@ -1021,7 +982,7 @@ if __name__ == "__main__":
sp_workflow_param = strains[strain_sex]
# Set workflow path (1 organism)
- workflow_path = os.path.join(os.path.abspath(script_dir), phaoexplorer_constants.WORKFLOWS_PATH, phaoexplorer_constants.WORKFLOW_LOAD_FASTA_GFF_JBROWSE_FILE_1_ORG)
+ workflow_path = os.path.join(os.path.abspath(script_dir), phaeoexplorer_constants.WORKFLOWS_PATH, phaeoexplorer_constants.WF_LOAD_GFF_JB_1_ORG_FILE)
# Check if the versions of tools specified in the workflow are installed in galaxy
install_changesets_revisions_from_workflow(workflow_path=workflow_path, instance=sp_workflow_param.instance)
@@ -1039,46 +1000,37 @@ if __name__ == "__main__":
org_org_id = sp_workflow_param.org_id
org_genome_analysis_id = sp_workflow_param.genome_analysis_id
org_ogs_analysis_id = sp_workflow_param.ogs_analysis_id
- org_genome_hda_id = sp_workflow_param.hda_ids["genome_hda_id"]
- org_transcripts_hda_id = sp_workflow_param.hda_ids["transcripts_hda_id"]
- org_proteins_hda_id = sp_workflow_param.hda_ids["proteins_hda_id"]
- org_gff_hda_id = sp_workflow_param.hda_ids["gff_hda_id"]
+ org_genome_hda_id = sp_workflow_param.genome_hda_id
+ org_transcripts_hda_id = sp_workflow_param.transcripts_hda_id
+ org_proteins_hda_id = sp_workflow_param.proteins_hda_id
+ org_gff_hda_id = sp_workflow_param.gff_hda_id
# Set the workflow parameters (individual tools runtime parameters in the workflow)
workflow_parameters = {}
- GENOME_FASTA_FILE_ORG = "0"
- GFF_FILE_ORG = "1"
- PROTEINS_FASTA_FILE_ORG = "2"
- LOAD_FASTA_ORG = "3"
- JBROWSE_ORG = "4"
- LOAD_GFF_ORG = "5"
- JBROWSE_CONTAINER = "6"
- SYNC_FEATURES_ORG = "7"
- POPULATE_MAT_VIEWS = "8"
- INDEX_TRIPAL_DATA = "9"
-
# Input files have no parameters (they are set via assigning the hda IDs in the datamap parameter of the bioblend method)
- workflow_parameters[GENOME_FASTA_FILE_ORG] = {}
- workflow_parameters[GFF_FILE_ORG] = {}
- workflow_parameters[PROTEINS_FASTA_FILE_ORG] = {}
- workflow_parameters[LOAD_FASTA_ORG] = {"organism": org_org_id,
- "analysis_id": org_genome_analysis_id,
- "do_update": "true"}
- workflow_parameters[JBROWSE_ORG] = {}
- workflow_parameters[LOAD_GFF_ORG] = {"organism": org_org_id, "analysis_id": org_ogs_analysis_id}
- workflow_parameters[SYNC_FEATURES_ORG] = {"organism_id": org_org_id}
- # POPULATE + INDEX DATA
- workflow_parameters[POPULATE_MAT_VIEWS] = {}
- workflow_parameters[INDEX_TRIPAL_DATA] = {}
+ workflow_parameters[phaeoexplorer_constants.WF_LOAD_GFF_JB_1_ORG_INPUT_GENOME] = {}
+ workflow_parameters[phaeoexplorer_constants.WF_LOAD_GFF_JB_1_ORG_INPUT_GFF] = {}
+ workflow_parameters[phaeoexplorer_constants.WF_LOAD_GFF_JB_1_ORG_INPUT_PROTEINS] = {}
+ workflow_parameters[phaeoexplorer_constants.WF_LOAD_GFF_JB_1_ORG_STEP_LOAD_FASTA] = {
+ "organism": org_org_id,
+ "analysis_id": org_genome_analysis_id,
+ "do_update": "true"}
+ workflow_parameters[phaeoexplorer_constants.WF_LOAD_GFF_JB_1_ORG_STEP_JBROWSE] = {}
+ workflow_parameters[phaeoexplorer_constants.WF_LOAD_GFF_JB_1_ORG_STEP_LOAD_GFF] = {
+ "organism": org_org_id,
+ "analysis_id": org_ogs_analysis_id}
+ workflow_parameters[phaeoexplorer_constants.WF_LOAD_GFF_JB_1_ORG_STEP_FEATURE_SYNC] = {
+ "organism_id": org_org_id}
+ workflow_parameters[phaeoexplorer_constants.WF_LOAD_GFF_JB_1_ORG_STEP_POPULATE_VIEWS] = {}
+ workflow_parameters[phaeoexplorer_constants.WF_LOAD_GFF_JB_1_ORG_STEP_INDEX] = {}
# Set datamap (mapping of input files in the workflow)
datamap = {}
- datamap[GENOME_FASTA_FILE_ORG] = {"src": "hda", "id": org_genome_hda_id}
- datamap[GFF_FILE_ORG] = {"src": "hda", "id": org_gff_hda_id}
- datamap[PROTEINS_FASTA_FILE_ORG] = {"src": "hda", "id": org_proteins_hda_id}
-
+ datamap[phaeoexplorer_constants.WF_LOAD_GFF_JB_1_ORG_INPUT_GENOME] = {"src": "hda", "id": org_genome_hda_id}
+ datamap[phaeoexplorer_constants.WF_LOAD_GFF_JB_1_ORG_INPUT_GFF] = {"src": "hda", "id": org_gff_hda_id}
+ datamap[phaeoexplorer_constants.WF_LOAD_GFF_JB_1_ORG_INPUT_PROTEINS] = {"src": "hda", "id": org_proteins_hda_id}
with open(workflow_path, 'r') as ga_in_file:
--
GitLab