From df6d5d55b2fc052a2088d16392832a8cef0f36a6 Mon Sep 17 00:00:00 2001
From: Arthur Le Bars <arthur.le-bars@sb-roscoff.fr>
Date: Mon, 10 May 2021 20:29:57 +0200
Subject: [PATCH] Blast workflow added (v1)
---
run_workflow_phaeoexplorer.py | 1295 +++++++++--------
...axy-Workflow-load_blast_results_1org_v1.ga | 271 ++++
...axy-Workflow-load_blast_results_2org_v1.ga | 418 ++++++
3 files changed, 1371 insertions(+), 613 deletions(-)
create mode 100644 workflows_phaeoexplorer/Galaxy-Workflow-load_blast_results_1org_v1.ga
create mode 100644 workflows_phaeoexplorer/Galaxy-Workflow-load_blast_results_2org_v1.ga
diff --git a/run_workflow_phaeoexplorer.py b/run_workflow_phaeoexplorer.py
index 282dcd7..b5f70f0 100755
--- a/run_workflow_phaeoexplorer.py
+++ b/run_workflow_phaeoexplorer.py
@@ -71,41 +71,41 @@ class RunWorkflow(speciesData.SpeciesData):
logging.debug("Library ID: %s" % self.library_id)
instance_source_data_folders = self.instance.libraries.get_folders(library_id=library_id)
- # Access folders via their absolute path
- genome_folder = self.instance.libraries.get_folders(library_id=library_id, name="/genome/" + str(self.species_folder_name) + "/v" + str(self.genome_version))
- annotation_folder = self.instance.libraries.get_folders(library_id=library_id, name="/annotation/" + str(self.species_folder_name) + "/OGS" + str(self.ogs_version))
+ # # Access folders via their absolute path
+ # genome_folder = self.instance.libraries.get_folders(library_id=library_id, name="/genome/" + str(self.species_folder_name) + "/v" + str(self.genome_version))
+ # annotation_folder = self.instance.libraries.get_folders(library_id=library_id, name="/annotation/" + str(self.species_folder_name) + "/OGS" + str(self.ogs_version))
- # Get their IDs
- genome_folder_id = genome_folder[0]["id"]
- annotation_folder_id = annotation_folder[0]["id"]
+ # # Get their IDs
+ # genome_folder_id = genome_folder[0]["id"]
+ # annotation_folder_id = annotation_folder[0]["id"]
- # Get the content of the folders
- genome_folder_content = self.instance.folders.show_folder(folder_id=genome_folder_id, contents=True)
- annotation_folder_content = self.instance.folders.show_folder(folder_id=annotation_folder_id, contents=True)
+ # # Get the content of the folders
+ # genome_folder_content = self.instance.folders.show_folder(folder_id=genome_folder_id, contents=True)
+ # annotation_folder_content = self.instance.folders.show_folder(folder_id=annotation_folder_id, contents=True)
- # Find genome folder datasets
- genome_fasta_ldda_id = genome_folder_content["folder_contents"][0]["ldda_id"]
+ # # Find genome folder datasets
+ # genome_fasta_ldda_id = genome_folder_content["folder_contents"][0]["ldda_id"]
- annotation_gff_ldda_id, annotation_proteins_ldda_id, annotation_transcripts_ldda_id = None, None, None
+ # annotation_gff_ldda_id, annotation_proteins_ldda_id, annotation_transcripts_ldda_id = None, None, None
- # Several dicts in the annotation folder content (one dict = one file)
- for k, v in annotation_folder_content.items():
- if k == "folder_contents":
- for d in v:
- if "proteins" in d["name"]:
- annotation_proteins_ldda_id = d["ldda_id"]
- if "transcripts" in d["name"]:
- annotation_transcripts_ldda_id = d["ldda_id"]
- if ".gff" in d["name"]:
- annotation_gff_ldda_id = d["ldda_id"]
+ # # Several dicts in the annotation folder content (one dict = one file)
+ # for k, v in annotation_folder_content.items():
+ # if k == "folder_contents":
+ # for d in v:
+ # if "proteins" in d["name"]:
+ # annotation_proteins_ldda_id = d["ldda_id"]
+ # if "transcripts" in d["name"]:
+ # annotation_transcripts_ldda_id = d["ldda_id"]
+ # if ".gff" in d["name"]:
+ # annotation_gff_ldda_id = d["ldda_id"]
- # Minimum datasets to populate tripal views --> will not work if these files are not assigned in the input file
- self.datasets["genome_file"] = genome_fasta_ldda_id
- self.datasets["gff_file"] = annotation_gff_ldda_id
- self.datasets["proteins_file"] = annotation_proteins_ldda_id
- self.datasets["transcripts_file"] = annotation_transcripts_ldda_id
+ # # Minimum datasets to populate tripal views --> will not work if these files are not assigned in the input file
+ # self.datasets["genome_file"] = genome_fasta_ldda_id
+ # self.datasets["gff_file"] = annotation_gff_ldda_id
+ # self.datasets["proteins_file"] = annotation_proteins_ldda_id
+ # self.datasets["transcripts_file"] = annotation_transcripts_ldda_id
- return {"history_id": self.history_id, "library_id": library_id, "datasets": self.datasets}
+ return {"history_id": self.history_id, "library_id": library_id}
def connect_to_instance(self):
@@ -357,6 +357,107 @@ class RunWorkflow(speciesData.SpeciesData):
return({"org_id": org_id, "genome_analysis_id": genome_analysis_id, "ogs_analysis_id": ogs_analysis_id})
+ def add_organism_blastp_analysis(self):
+ """
+ Add OGS and genome vX analyses to Chado database
+ Required for Chado Load Tripal Synchronize workflow (which should be ran as the first workflow)
+ Called outside workflow for practical reasons (Chado add doesn't have an input link for analysis or organism)
+
+ :return:
+
+ """
+
+ self.connect_to_instance()
+ self.set_get_history()
+
+ tool_version = "2.3.4+galaxy0"
+
+ get_organism_tool = self.instance.tools.show_tool("toolshed.g2.bx.psu.edu/repos/gga/chado_organism_get_organisms/organism_get_organisms/2.3.4+galaxy0")
+
+ get_organisms = self.instance.tools.run_tool(
+ tool_id="toolshed.g2.bx.psu.edu/repos/gga/chado_organism_get_organisms/organism_get_organisms/%s" % tool_version,
+ history_id=self.history_id,
+ tool_inputs={})
+
+ time.sleep(10) # Ensure the tool has had time to complete
+ org_outputs = get_organisms["outputs"] # Outputs from the get_organism tool
+ org_job_out_id = org_outputs[0]["id"] # ID of the get_organism output dataset (list of dicts)
+ org_json_output = self.instance.datasets.download_dataset(dataset_id=org_job_out_id) # Download the dataset
+ org_output = json.loads(org_json_output) # Turn the dataset into a list for parsing
+
+ org_id = None
+
+ # Look up list of outputs (dictionaries)
+ for organism_output_dict in org_output:
+ if organism_output_dict["genus"] == self.genus and organism_output_dict["species"] == "{0} {1}".format(self.species, self.sex):
+ correct_organism_id = str(organism_output_dict["organism_id"]) # id needs to be a str to be recognized by chado tools
+ org_id = str(correct_organism_id)
+
+
+ if org_id is None:
+ if self.common == "" or self.common is None:
+ add_org_job = self.instance.tools.run_tool(
+ tool_id="toolshed.g2.bx.psu.edu/repos/gga/chado_organism_add_organism/organism_add_organism/%s" % tool_version,
+ history_id=self.history_id,
+ tool_inputs={"abbr": self.abbreviation,
+ "genus": self.genus_uppercase,
+ "species": self.chado_species_name,
+ "common": self.abbreviation})
+ org_job_out_id = add_org_job["outputs"][0]["id"]
+ org_json_output = self.instance.datasets.download_dataset(dataset_id=org_job_out_id)
+ org_output = json.loads(org_json_output)
+ org_id = str(org_output["organism_id"]) # id needs to be a str to be recognized by chado tools
+ else:
+ add_org_job = self.instance.tools.run_tool(
+ tool_id="toolshed.g2.bx.psu.edu/repos/gga/chado_organism_add_organism/organism_add_organism/%s" % tool_version,
+ history_id=self.history_id,
+ tool_inputs={"abbr": self.abbreviation,
+ "genus": self.genus_uppercase,
+ "species": self.chado_species_name,
+ "common": self.common})
+ org_job_out_id = add_org_job["outputs"][0]["id"]
+ org_json_output = self.instance.datasets.download_dataset(dataset_id=org_job_out_id)
+ org_output = json.loads(org_json_output)
+ org_id = str(org_output["organism_id"]) # id needs to be a str to be recognized by chado tools
+
+
+ get_analyses = self.instance.tools.run_tool(
+ tool_id="toolshed.g2.bx.psu.edu/repos/gga/chado_analysis_get_analyses/analysis_get_analyses/%s" % tool_version,
+ history_id=self.history_id,
+ tool_inputs={})
+
+ time.sleep(10)
+ analysis_outputs = get_analyses["outputs"]
+ analysis_job_out_id = analysis_outputs[0]["id"]
+ analysis_json_output = self.instance.datasets.download_dataset(dataset_id=analysis_job_out_id)
+ analysis_output = json.loads(analysis_json_output)
+
+ blastp_analysis_id = None
+
+ # Look up list of outputs (dictionaries)
+ for analysis_output_dict in analysis_output:
+ if analysis_output_dict["name"] == "Diamond on " + self.full_name_lowercase + " OGS" + self.ogs_version:
+ blastp_analysis_id = str(analysis_output_dict["analysis_id"])
+
+
+ if blastp_analysis_id is None:
+ add_blast_analysis_job = self.instance.tools.run_tool(
+ tool_id="toolshed.g2.bx.psu.edu/repos/gga/chado_analysis_add_analysis/analysis_add_analysis/%s" % tool_version,
+ history_id=self.history_id,
+ tool_inputs={"name": "Diamond on " + self.full_name_lowercase + " OGS" + self.ogs_version,
+ "program": "Performed by Genoscope",
+ "programversion": str(self.sex + " OGS" + self.ogs_version),
+ "sourcename": "Genoscope",
+ "date_executed": self.date})
+ analysis_outputs = add_blast_analysis_job["outputs"]
+ analysis_job_out_id = analysis_outputs[0]["id"]
+ analysis_json_output = self.instance.datasets.download_dataset(dataset_id=analysis_job_out_id)
+ analysis_output = json.loads(analysis_json_output)
+ blastp_analysis_id = str(analysis_output["analysis_id"])
+
+ # print({"org_id": org_id, "genome_analysis_id": genome_analysis_id, "ogs_analysis_id": ogs_analysis_id})
+ return({"org_id": org_id, "blastp_analysis_id": blastp_analysis_id})
+
def add_interproscan_analysis(self):
"""
"""
@@ -393,43 +494,6 @@ class RunWorkflow(speciesData.SpeciesData):
return self.interpro_analysis_id
- def add_blastp_diamond_analysis(self):
- """
-
- """
- # Add Blastp (diamond) analysis to chado
- logging.info("Adding Blastp Diamond analysis to the instance's chado database")
- self.instance.tools.run_tool(
- tool_id="toolshed.g2.bx.psu.edu/repos/gga/chado_analysis_add_analysis/analysis_add_analysis/2.3.3",
- history_id=self.history_id,
- tool_inputs={"name": "Diamond on OGS%s" % self.ogs_version,
- "program": "Diamond",
- "programversion": "OGS%s" % self.ogs_version,
- "sourcename": "Genoscope",
- "date_executed": self.date})
-
-
- def get_blastp_diamond_analysis_id(self):
- """
- """
-
- # Get blasp ID
- blast_diamond_analysis = self.instance.tools.run_tool(
- tool_id="toolshed.g2.bx.psu.edu/repos/gga/chado_analysis_get_analyses/analysis_get_analyses/2.3.3",
- history_id=self.history_id,
- tool_inputs={"name": "Diamond on OGS%s" % self.ogs_version})
- blast_diamond_analysis_job_out = blast_diamond_analysis["outputs"][0]["id"]
- blast_diamond_analysis_json_output = self.instance.datasets.download_dataset(dataset_id=blast_diamond_analysis_job_out)
- try:
- blast_diamond_analysis_output = json.loads(blast_diamond_analysis_json_output)[0]
- self.blast_diamond_analysis_id = str(blast_diamond_analysis_output["analysis_id"])
- except IndexError as exc:
- logging.critical("No matching InterproScan analysis exists in the instance's chado database")
- sys.exit(exc)
-
- return self.blast_diamond_analysis_id
-
-
def run_workflow(self, workflow_path, workflow_parameters, workflow_name, datamap):
"""
Run a workflow in galaxy
@@ -560,12 +624,12 @@ class RunWorkflow(speciesData.SpeciesData):
self.datasets["interproscan_file"] = e["ldda_id"]
self.datasets_name["interproscan_file"] = e["name"]
elif "blastp" in e["name"]:
- self.datasets["blast_diamond_file"] = e["ldda_id"]
- self.datasets_name["blast_diamond_file"] = e["name"]
+ self.datasets["blastp_file"] = e["ldda_id"]
+ self.datasets_name["blastp_file"] = e["name"]
history_datasets_li = self.instance.datasets.get_datasets()
- genome_hda_id, gff_hda_id, transcripts_hda_id, proteins_hda_id, blast_diamond_hda_id, interproscan_hda_id = None, None, None, None, None, None
+ genome_hda_id, gff_hda_id, transcripts_hda_id, proteins_hda_id, blastp_hda_id, interproscan_hda_id = None, None, None, None, None, None
# Finding datasets in history (matching datasets names)
for dataset in history_datasets_li:
@@ -579,8 +643,8 @@ class RunWorkflow(speciesData.SpeciesData):
transcripts_hda_id = dataset_id
if dataset_name == "{0}_OGS{1}_proteins.fasta".format(self.dataset_prefix, self.ogs_version):
proteins_hda_id = dataset_id
- if dataset_name == "{0}_OGS{1}_blastx.xml".format(self.dataset_prefix, self.ogs_version):
- blast_diamond_hda_id = dataset_id
+ if dataset_name == "{0}_OGS{1}_blastp.xml".format(self.dataset_prefix, self.ogs_version):
+ blastp_hda_id = dataset_id
# Import each dataset into history if it is not imported
@@ -604,27 +668,27 @@ class RunWorkflow(speciesData.SpeciesData):
interproscan_hda_id = interproscan_dataset_upload["id"]
except Exception as exc:
logging.debug("Interproscan file not found in library (history: {0})".format(self.history_id))
- if blast_diamond_hda_id is None:
+ if blastp_hda_id is None:
try:
- blast_diamond_dataset_upload = self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=self.datasets["blast_diamond_file"])
- blast_diamond_hda_id = blast_diamond_upload["id"]
+ blastp_dataset_upload = self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=self.datasets["blastp_file"])
+ blastp_hda_id = blastp_dataset_upload["id"]
except Exception as exc:
- logging.debug("Blastp file not found in library (history: {0})".format(self.history_id))
+ logging.debug("blastp file not found in library (history: {0})".format(self.history_id))
- logging.debug("History dataset IDs (hda_id) for %s:" % self.full_name)
- logging.debug({"genome_hda_id": genome_hda_id,
- "gff_hda_id": gff_hda_id,
- "transcripts_hda_id": transcripts_hda_id,
- "proteins_hda_id": proteins_hda_id,
- "blast_diamond_hda_id": blast_diamond_hda_id,
- "interproscan_hda_id": interproscan_hda_id})
+ # logging.debug("History dataset IDs (hda_id) for %s:" % self.full_name)
+ # logging.debug({"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,
+ # "interproscan_hda_id": interproscan_hda_id})
# Return a dict made of the hda ids
return {"genome_hda_id": genome_hda_id,
"gff_hda_id": gff_hda_id,
"transcripts_hda_id": transcripts_hda_id,
"proteins_hda_id": proteins_hda_id,
- "blast_diamond_hda_id": blast_diamond_hda_id,
+ "blastp_hda_id": blastp_hda_id,
"interproscan_hda_id": interproscan_hda_id}
@@ -662,17 +726,16 @@ class RunWorkflow(speciesData.SpeciesData):
if "interproscan_file" in self.datasets_name.keys():
if dataset_dict["name"] == self.datasets_name["interproscan_file"] and dataset_dict["id"] not in imported_datasets_ids:
interproscan_dataset_hda_id = dataset_dict["id"]
-
if "blast_diamond_file" in self.datasets_name.keys():
- if dataset_dict["name"] == self.datasets_name["blast_diamond_file"] and dataset_dict["id"] not in imported_datasets_ids:
- blast_diamond_dataset_hda_id = dataset_dict["id"]
+ if dataset_dict["name"] == self.datasets_name["blastp_file"] and dataset_dict["id"] not in imported_datasets_ids:
+ blastp_dataset_hda_id = dataset_dict["id"]
logging.debug("Genome dataset hda id: %s" % genome_dataset_hda_id)
logging.debug("Proteins dataset hda ID: %s" % proteins_datasets_hda_id)
logging.debug("Transcripts dataset hda ID: %s" % transcripts_dataset_hda_id)
logging.debug("GFF dataset hda ID: %s" % gff_dataset_hda_id)
logging.debug("InterproScan dataset hda ID: %s" % gff_dataset_hda_id)
- logging.debug("Blast Diamond dataset hda ID: %s" % gff_dataset_hda_id)
+ logging.debug("Blastp Diamond dataset hda ID: %s" % blastp_dataset_hda_id)
# Add datasets IDs to already imported IDs (so we don't assign all the wrong IDs to the next organism if there is one)
imported_datasets_ids.append(genome_dataset_hda_id)
@@ -680,13 +743,13 @@ class RunWorkflow(speciesData.SpeciesData):
imported_datasets_ids.append(proteins_datasets_hda_id)
imported_datasets_ids.append(gff_dataset_hda_id)
imported_datasets_ids.append(interproscan_dataset_hda_id)
- imported_datasets_ids.append(blast_diamond_dataset_hda_id)
+ imported_datasets_ids.append(blastp_dataset_hda_id)
# Return a dict made of the hda ids
return {"genome_hda_id": genome_dataset_hda_id, "transcripts_hda_id": transcripts_dataset_hda_id,
"proteins_hda_id": proteins_datasets_hda_id, "gff_hda_id": gff_dataset_hda_id,
"interproscan_hda_id": interproscan_dataset_hda_id,
- "blast_diamond_hda_id": blast_diamond_dataset_hda_id,
+ "blastp_hda_id": blastp_dataset_hda_id,
"imported_datasets_ids": imported_datasets_ids}
@@ -748,7 +811,7 @@ def run_workflow(workflow_path, workflow_parameters, datamap, config, input_spec
-def create_sp_workflow_dict(sp_dict, main_dir, config):
+def create_sp_workflow_dict(sp_dict, main_dir, config, workflow_type):
"""
"""
@@ -778,19 +841,65 @@ def create_sp_workflow_dict(sp_dict, main_dir, config):
run_workflow_for_current_organism.species)
+ if workflow_type == "load_fasta_gff_jbrowse":
+ run_workflow_for_current_organism.connect_to_instance()
+
+ history_id = run_workflow_for_current_organism.set_get_history()
+
+ run_workflow_for_current_organism.install_changesets_revisions_for_individual_tools()
+ ids = run_workflow_for_current_organism.add_organism_ogs_genome_analyses()
+
+ org_id = None
+ genome_analysis_id = None
+ ogs_analysis_id = None
+ org_id = ids["org_id"]
+ genome_analysis_id = ids["genome_analysis_id"]
+ ogs_analysis_id = ids["ogs_analysis_id"]
+ instance_attributes = run_workflow_for_current_organism.get_instance_attributes()
+ hda_ids = run_workflow_for_current_organism.import_datasets_into_history()
+
+ strain_sex = "{0}_{1}".format(run_workflow_for_current_organism.strain, run_workflow_for_current_organism.sex)
+ genus_species = run_workflow_for_current_organism.genus_species
+
+ # Create the dictionary holding all attributes needed to connect to the galaxy instance
+ attributes = {"genus": run_workflow_for_current_organism.genus,
+ "species": run_workflow_for_current_organism.species,
+ "genus_species": run_workflow_for_current_organism.genus_species,
+ "full_name": run_workflow_for_current_organism.full_name,
+ "species_folder_name": run_workflow_for_current_organism.species_folder_name,
+ "sex": run_workflow_for_current_organism.sex,
+ "strain": run_workflow_for_current_organism.strain,
+ "org_id": org_id,
+ "genome_analysis_id": genome_analysis_id,
+ "ogs_analysis_id": ogs_analysis_id,
+ "instance_attributes": instance_attributes,
+ "hda_ids": hda_ids,
+ "history_id": history_id,
+ "instance": run_workflow_for_current_organism.instance,
+ "instance_url": run_workflow_for_current_organism.instance_url,
+ "email": config["galaxy_default_admin_email"],
+ "password": config["galaxy_default_admin_password"]}
+
+ sp_workflow_dict[genus_species] = {strain_sex: attributes}
+
+ else:
+ logging.critical("The galaxy container for %s is not ready yet!" % run_workflow_for_current_organism.full_name)
+ sys.exit()
+
+ return sp_workflow_dict
+
+ if workflow_type == "blast":
run_workflow_for_current_organism.connect_to_instance()
history_id = run_workflow_for_current_organism.set_get_history()
run_workflow_for_current_organism.install_changesets_revisions_for_individual_tools()
- ids = run_workflow_for_current_organism.add_organism_ogs_genome_analyses()
+ ids = run_workflow_for_current_organism.add_organism_blastp_analysis()
org_id = None
- genome_analysis_id = None
- ogs_analysis_id = None
org_id = ids["org_id"]
- genome_analysis_id = ids["genome_analysis_id"]
- ogs_analysis_id = ids["ogs_analysis_id"]
+ blastp_analysis_id = None
+ blastp_analysis_id = ids["blastp_analysis_id"]
instance_attributes = run_workflow_for_current_organism.get_instance_attributes()
hda_ids = run_workflow_for_current_organism.import_datasets_into_history()
@@ -806,8 +915,7 @@ def create_sp_workflow_dict(sp_dict, main_dir, config):
"sex": run_workflow_for_current_organism.sex,
"strain": run_workflow_for_current_organism.strain,
"org_id": org_id,
- "genome_analysis_id": genome_analysis_id,
- "ogs_analysis_id": ogs_analysis_id,
+ "blastp_analysis_id": blastp_analysis_id,
"instance_attributes": instance_attributes,
"hda_ids": hda_ids,
"history_id": history_id,
@@ -823,8 +931,6 @@ def create_sp_workflow_dict(sp_dict, main_dir, config):
sys.exit()
- return sp_workflow_dict
-
def install_changesets_revisions_from_workflow(instance, workflow_path):
"""
@@ -900,7 +1006,7 @@ if __name__ == "__main__":
parser.add_argument("--workflow", "-w",
type=str,
- help="Worfklow to run")
+ help="Worfklow to run. Available options: load_fasta_gff_jbrowse, blast, interpro")
args = parser.parse_args()
@@ -924,44 +1030,452 @@ if __name__ == "__main__":
sp_dict_list = utilities.parse_input(args.input)
- # # Checking if user specified a workflow to run
- # if not args.workflow:
- # logging.critical("No workflow specified, exiting")
- # sys.exit()
- # else:
- # workflow = os.path.abspath(args.workflow)
+ workflow_valid_types = ["load_fasta_gff_jbrowse", "blast", "interpro"]
+
+ workflow_type = None
+ # Checking if user specified a workflow to run
+ if not args.workflow:
+ logging.critical("No workflow type specified, exiting")
+ sys.exit()
+ elif args.workflow in 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]))
config = utilities.parse_config(args.config)
all_sp_workflow_dict = {}
- 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
- current_sp_workflow_dict = create_sp_workflow_dict(sp_dict, main_dir=args.main_directory, config=config)
+ if workflow_type == "load_fasta_gff_jbrowse":
+ for sp_dict in sp_dict_list:
- current_sp_key = list(current_sp_workflow_dict.keys())[0]
- current_sp_value = list(current_sp_workflow_dict.values())[0]
- current_sp_strain_sex_key = list(current_sp_value.keys())[0]
- current_sp_strain_sex_value = list(current_sp_value.values())[0]
+ # Add and retrieve all analyses/organisms for the current input species and add their IDs to the input dictionary
+ current_sp_workflow_dict = create_sp_workflow_dict(sp_dict, main_dir=args.main_directory, config=config, workfow_type="load_fasta_gff_jbrowse")
- # Add the species dictionary to the complete dictionary
- # This dictionary contains every organism present in the input file
- # Its structure is the following:
- # {genus species: {strain1_sex1: {variables_key: variables_values}, strain1_sex2: {variables_key: variables_values}}}
- if not current_sp_key in all_sp_workflow_dict.keys():
- all_sp_workflow_dict[current_sp_key] = current_sp_value
- else:
- all_sp_workflow_dict[current_sp_key][current_sp_strain_sex_key] = current_sp_strain_sex_value
+ current_sp_key = list(current_sp_workflow_dict.keys())[0]
+ current_sp_value = list(current_sp_workflow_dict.values())[0]
+ current_sp_strain_sex_key = list(current_sp_value.keys())[0]
+ current_sp_strain_sex_value = list(current_sp_value.values())[0]
+
+ # Add the species dictionary to the complete dictionary
+ # This dictionary contains every organism present in the input file
+ # Its structure is the following:
+ # {genus species: {strain1_sex1: {variables_key: variables_values}, strain1_sex2: {variables_key: variables_values}}}
+ if not current_sp_key in all_sp_workflow_dict.keys():
+ all_sp_workflow_dict[current_sp_key] = current_sp_value
+ else:
+ all_sp_workflow_dict[current_sp_key][current_sp_strain_sex_key] = current_sp_strain_sex_value
+
+
+ for k, v in all_sp_workflow_dict.items():
+ if len(list(v.keys())) == 1:
+ logging.info("Input organism %s: 1 species detected in input dictionary" % k)
+
+ # Set workflow path (1 organism)
+ workflow_path = os.path.join(os.path.abspath(script_dir), "workflows_phaeoexplorer/Galaxy-Workflow-chado_load_tripal_synchronize_jbrowse_1org_v4.ga")
+
+ # Instance object required variables
+ instance_url, email, password = None, None, None
+
+ # Set the galaxy instance variables
+ for k2, v2 in v.items():
+ instance_url = v2["instance_url"]
+ email = v2["email"]
+ password = v2["password"]
+
+ instance = galaxy.GalaxyInstance(url=instance_url, email=email, password=password)
+
+ # Check if the versions of tools specified in the workflow are installed in galaxy
+ install_changesets_revisions_from_workflow(workflow_path=workflow_path, instance=instance)
+
+ organism_key_name = list(v.keys())
+ org_dict = v[organisms_key_names[0]]
+
+ history_id = org_dict["history_id"]
+
+ # Organism 1 attributes
+ org_genus = org_dict["genus"]
+ org_species = org_dict["species"]
+ org_genus_species = org_dict["genus_species"]
+ org_species_folder_name = org_dict["species_folder_name"]
+ org_full_name = org_dict["full_name"]
+ org_strain = org_dict["sex"]
+ org_sex = org_dict["strain"]
+ org_org_id = org_dict["org_id"]
+ org_genome_analysis_id = org_dict["genome_analysis_id"]
+ org_ogs_analysis_id = org_dict["ogs_analysis_id"]
+ org_genome_hda_id = org_dict["hda_ids"]["genome_hda_id"]
+ org_transcripts_hda_id = org_dict["hda_ids"]["transcripts_hda_id"]
+ org_proteins_hda_id = org_dict["hda_ids"]["proteins_hda_id"]
+ org_gff_hda_id = org_dict["hda_ids"]["gff_hda_id"]
+
+ # Store these values into a dict for parameters logging/validation
+ org_parameters_dict = {
+ "org_genus": org_genus,
+ "org_species": org_species,
+ "org_genus_species": org_genus_species,
+ "org_species_folder_name": org_species_folder_name,
+ "org_full_name": org_full_name,
+ "org_strain": org_strain,
+ "org_sex": org_sex,
+ "org_org_id": org_org_id,
+ "org_genome_analysis_id": org_genome_analysis_id,
+ "org_ogs_analysis_id": org_ogs_analysis_id,
+ "org_genome_hda_id": org_genome_hda_id,
+ "org_transcripts_hda_id": org_transcripts_hda_id,
+ "org_proteins_hda_id": org_proteins_hda_id,
+ "org_gff_hda_id": org_gff_hda_id,
+ }
+
+ # Look for empty parameters values, throw a critical error if a parameter value is invalid
+ for param_name, param_value in org_parameters_dict.items():
+ if param_value is None or param_value == "":
+ logging.critical("Empty parameter value found for organism {0} (parameter: {1}, parameter value: {2})".format(org_full_name, param_name, param_value))
+ sys.exit()
+
+ # 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] = {}
+
+ # 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}
+
+
+ with open(workflow_path, 'r') as ga_in_file:
+ # Store the decoded json dictionary
+ workflow_dict = json.load(ga_in_file)
+ workflow_name = workflow_dict["name"]
+
+ # For the Jbrowse tool, 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)
+ jbrowse_menu_url_org = "https://{hostname}/sp/{genus_sp}/feature/{Genus}/{species}/mRNA/{id}".format(hostname=config["hostname"], genus_sp=org_genus_species, Genus=org_genus[0].upper() + org_genus[1:], species=org_species, id="{id}")
+ if "menu_url" not in config.keys():
+ jbrowse_menu_url_org = "https://{hostname}/sp/{genus_sp}/feature/{Genus}/{species}/mRNA/{id}".format(hostname=config["hostname"], genus_sp=org_genus_species, Genus=org_genus[0].upper() + org_genus[1:], species=org_species, id="{id}")
+ else:
+ jbrowse_menu_url_org = config["menu_url"] + "/sp/{genus_sp}/feature/{Genus}/{species}/mRNA/{id}".format(genus_sp=org_genus_species, Genus=org_genus[0].upper() + org_genus[1:], species=org_species, id="{id}")
+
+ # show_tool_add_organism = instance.tools.show_tool(tool_id="toolshed.g2.bx.psu.edu/repos/gga/chado_organism_add_organism/organism_add_organism/2.3.4+galaxy0", io_details=True)
+ # print(show_tool_add_organism)
+ # show_jbrowse_tool = instance.tools.show_tool(tool_id="toolshed.g2.bx.psu.edu/repos/iuc/jbrowse/jbrowse/1.16.11+galaxy0", io_details=True)
+ # print(show_jbrowse_tool)
+ # show_jbrowse_container_tool = instance.tools.show_tool(tool_id="toolshed.g2.bx.psu.edu/repos/gga/jbrowse_to_container/jbrowse_to_container/0.5.1", io_details=True)
+ # print(show_jbrowse_container_tool)
+
+ # Replace values in the workflow dictionary
+ workflow_dict["steps"]["4"]["tool_state"] = workflow_dict["steps"]["4"]["tool_state"].replace("__MENU_URL_ORG__", jbrowse_menu_url_org)
+ workflow_dict["steps"]["6"]["tool_state"] = workflow_dict["steps"]["6"]["tool_state"].replace("__DISPLAY_NAME_ORG__", org_full_name).replace("__UNIQUE_ID_ORG__", org_species_folder_name)
+
+ # Import the workflow in galaxy as a dict
+ instance.workflows.import_workflow_dict(workflow_dict=workflow_dict)
+
+ # Get its attributes
+ workflow_attributes = 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 = 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 finding workflow %s" % workflow_name)
+
+ # Finally, invoke the workflow alogn with its datamap, parameters and the history in which to invoke it
+ instance.workflows.invoke_workflow(workflow_id=workflow_id, history_id=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, instance_url))
+
+
+ if len(list(v.keys())) == 2:
+
+ logging.info("Input organism %s: 2 species detected in input dictionary" % k)
+
+ # Set workflow path (2 organisms)
+ workflow_path = os.path.join(os.path.abspath(script_dir), "workflows_phaeoexplorer/Galaxy-Workflow-chado_load_tripal_synchronize_jbrowse_2org_v4.ga")
+
+ # Instance object required variables
+ instance_url, email, password = None, None, None
+
+ # Set the galaxy instance variables
+ for k2, v2 in v.items():
+ instance_url = v2["instance_url"]
+ email = v2["email"]
+ password = v2["password"]
+
+ instance = galaxy.GalaxyInstance(url=instance_url, email=email, password=password)
+
+ # Check if the versions of tools specified in the workflow are installed in galaxy
+ install_changesets_revisions_from_workflow(workflow_path=workflow_path, instance=instance)
+
+ # Get key names from the current organism (item 1 = organism 1, item 2 = organism 2)
+ organisms_key_names = list(v.keys())
+ org1_dict = v[organisms_key_names[0]]
+ org2_dict = v[organisms_key_names[1]]
+
+ history_id = org1_dict["history_id"]
+
+ # Organism 1 attributes
+ org1_genus = org1_dict["genus"]
+ org1_species = org1_dict["species"]
+ org1_genus_species = org1_dict["genus_species"]
+ org1_species_folder_name = org1_dict["species_folder_name"]
+ org1_full_name = org1_dict["full_name"]
+ org1_strain = org1_dict["sex"]
+ org1_sex = org1_dict["strain"]
+ org1_org_id = org1_dict["org_id"]
+ org1_genome_analysis_id = org1_dict["genome_analysis_id"]
+ org1_ogs_analysis_id = org1_dict["ogs_analysis_id"]
+ org1_genome_hda_id = org1_dict["hda_ids"]["genome_hda_id"]
+ org1_transcripts_hda_id = org1_dict["hda_ids"]["transcripts_hda_id"]
+ org1_proteins_hda_id = org1_dict["hda_ids"]["proteins_hda_id"]
+ org1_gff_hda_id = org1_dict["hda_ids"]["gff_hda_id"]
+
+ # Store these values into a dict for parameters logging/validation
+ org1_parameters_dict = {
+ "org1_genus": org1_genus,
+ "org1_species": org1_species,
+ "org1_genus_species": org1_genus_species,
+ "org1_species_folder_name": org1_species_folder_name,
+ "org1_full_name": org1_full_name,
+ "org1_strain": org1_strain,
+ "org1_sex": org1_sex,
+ "org1_org_id": org1_org_id,
+ "org1_genome_analysis_id": org1_genome_analysis_id,
+ "org1_ogs_analysis_id": org1_ogs_analysis_id,
+ "org1_genome_hda_id": org1_genome_hda_id,
+ "org1_transcripts_hda_id": org1_transcripts_hda_id,
+ "org1_proteins_hda_id": org1_proteins_hda_id,
+ "org1_gff_hda_id": org1_gff_hda_id,
+ }
+
+ # Look for empty parameters values, throw a critical error if a parameter value is invalid
+ for param_name, param_value in org1_parameters_dict.items():
+ if param_value is None or param_value == "":
+ logging.critical("Empty parameter value found for organism {0} (parameter: {1}, parameter value: {2})".format(org1_full_name, param_name, param_value))
+ sys.exit()
+
+ # Organism 2 attributes
+ org2_genus = org2_dict["genus"]
+ org2_species = org2_dict["species"]
+ org2_genus_species = org2_dict["genus_species"]
+ org2_species_folder_name = org2_dict["species_folder_name"]
+ org2_full_name = org2_dict["full_name"]
+ org2_strain = org2_dict["sex"]
+ org2_sex = org2_dict["strain"]
+ org2_org_id = org2_dict["org_id"]
+ org2_genome_analysis_id = org2_dict["genome_analysis_id"]
+ org2_ogs_analysis_id = org2_dict["ogs_analysis_id"]
+ org2_genome_hda_id = org2_dict["hda_ids"]["genome_hda_id"]
+ org2_transcripts_hda_id = org2_dict["hda_ids"]["transcripts_hda_id"]
+ org2_proteins_hda_id = org2_dict["hda_ids"]["proteins_hda_id"]
+ org2_gff_hda_id = org2_dict["hda_ids"]["gff_hda_id"]
+
+ # Store these values into a dict for parameters logging/validation
+ org2_parameters_dict = {
+ "org2_genus": org2_genus,
+ "org2_species": org2_species,
+ "org2_genus_species": org2_genus_species,
+ "org2_species_folder_name": org2_species_folder_name,
+ "org2_full_name": org2_full_name,
+ "org2_strain": org2_strain,
+ "org2_sex": org2_sex,
+ "org2_org_id": org2_org_id,
+ "org2_genome_analysis_id": org2_genome_analysis_id,
+ "org2_ogs_analysis_id": org2_ogs_analysis_id,
+ "org2_genome_hda_id": org2_genome_hda_id,
+ "org2_transcripts_hda_id": org2_transcripts_hda_id,
+ "org2_proteins_hda_id": org2_proteins_hda_id,
+ "org2_gff_hda_id": org2_gff_hda_id,
+ }
+
+ # Look for empty parameters values, throw a critical error if a parameter value is invalid
+ for param_name, param_value in org2_parameters_dict.items():
+ if param_value is None or param_value == "":
+ logging.critical("Empty parameter value found for organism {0} (parameter: {1}, parameter value: {2})".format(org2_full_name, param_name, param_value))
+ sys.exit()
+
+ # Source files association (ordered by their IDs in the workflow)
+ # WARNING: Be very careful about how the workflow is "organized" (i.e the order of the steps/datasets, check the .ga if there is any error)
+ GFF_FILE_ORG1 = "0"
+ GENOME_FASTA_FILE_ORG1 = "1"
+ PROTEINS_FASTA_FILE_ORG1 = "2"
+
+ GENOME_FASTA_FILE_ORG2 = "3"
+ GFF_FILE_ORG2 = "4"
+ PROTEINS_FASTA_FILE_ORG2 = "5"
+
+ LOAD_FASTA_ORG1 = "6"
+ JBROWSE_ORG1 = "7"
+ JRBOWSE_ORG2 = "8"
+
+ LOAD_GFF_ORG1 = "9"
+ JBROWSE_CONTAINER = "10"
+ SYNC_FEATURES_ORG1 = "11"
+
+ LOAD_FASTA_ORG2 = "12"
+ LOAD_GFF_ORG2 = "13"
+
+ SYNC_FEATURES_ORG2 = "14"
+ POPULATE_MAT_VIEWS = "15"
+ INDEX_TRIPAL_DATA = "16"
+
+ # Set the workflow parameters (individual tools runtime parameters in the workflow)
+ workflow_parameters = {}
+
+ # 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_ORG1] = {}
+ workflow_parameters[GFF_FILE_ORG1] = {}
+ workflow_parameters[PROTEINS_FASTA_FILE_ORG1] = {}
+ workflow_parameters[GENOME_FASTA_FILE_ORG2] = {}
+ workflow_parameters[GFF_FILE_ORG2] = {}
+ workflow_parameters[PROTEINS_FASTA_FILE_ORG2] = {}
+
+ # Organism 1
+ workflow_parameters[LOAD_FASTA_ORG1] = {"organism": org1_org_id,
+ "analysis_id": org1_genome_analysis_id,
+ "do_update": "true"}
+ # workflow_parameters[JBROWSE_ORG1] = {"menu_url": jbrowse_menu_url_org1}
+ workflow_parameters[JBROWSE_ORG1] = {}
+ workflow_parameters[LOAD_GFF_ORG1] = {"organism": org1_org_id, "analysis_id": org1_ogs_analysis_id}
+ workflow_parameters[SYNC_FEATURES_ORG1] = {"organism_id": org1_org_id}
+ # workflow_parameters[JBROWSE_CONTAINER] = {"organisms": [{"name": org1_full_name, "unique_id": org1_species_folder_name, }, {"name": org2_full_name, "unique_id": org2_species_folder_name}]}
+ workflow_parameters[JBROWSE_CONTAINER] = {}
+
+ # Organism 2
+ workflow_parameters[LOAD_FASTA_ORG2] = {"organism": org2_org_id,
+ "analysis_id": org2_genome_analysis_id,
+ "do_update": "true"}
+ workflow_parameters[LOAD_GFF_ORG2] = {"organism": org2_org_id, "analysis_id": org2_ogs_analysis_id}
+ # workflow_parameters[JRBOWSE_ORG2] = {"menu_url": jbrowse_menu_url_org2}
+ workflow_parameters[JRBOWSE_ORG2] = {}
+ workflow_parameters[SYNC_FEATURES_ORG2] = {"organism_id": org2_org_id}
+
+
+ # POPULATE + INDEX DATA
+ workflow_parameters[POPULATE_MAT_VIEWS] = {}
+ workflow_parameters[INDEX_TRIPAL_DATA] = {}
+
+
+ # Set datamap (mapping of input files in the workflow)
+ datamap = {}
+
+ # Organism 1
+ datamap[GENOME_FASTA_FILE_ORG1] = {"src": "hda", "id": org1_genome_hda_id}
+ datamap[GFF_FILE_ORG1] = {"src": "hda", "id": org1_gff_hda_id}
+ datamap[PROTEINS_FASTA_FILE_ORG1] = {"src": "hda", "id": org1_proteins_hda_id}
+
+ # Organism 2
+ datamap[GENOME_FASTA_FILE_ORG2] = {"src": "hda", "id": org2_genome_hda_id}
+ datamap[GFF_FILE_ORG2] = {"src": "hda", "id": org2_gff_hda_id}
+ datamap[PROTEINS_FASTA_FILE_ORG2] = {"src": "hda", "id": org2_proteins_hda_id}
+
+ with open(workflow_path, 'r') as ga_in_file:
+
+ # Store the decoded json dictionary
+ workflow_dict = json.load(ga_in_file)
+ workflow_name = workflow_dict["name"]
+
+ # For the Jbrowse tool, 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)
+ jbrowse_menu_url_org1 = "https://{hostname}/sp/{genus_sp}/feature/{Genus}/{species}/mRNA/{id}".format(hostname=config["hostname"], genus_sp=org1_genus_species, Genus=org1_genus[0].upper() + org1_genus[1:], species=org1_species, id="{id}")
+ jbrowse_menu_url_org2 = "https://{hostname}/sp/{genus_sp}/feature/{Genus}/{species}/mRNA/{id}".format(hostname=config["hostname"], genus_sp=org2_genus_species, Genus=org2_genus[0].upper() + org2_genus[1:], species=org2_species, id="{id}")
+ if "menu_url" not in config.keys():
+ jbrowse_menu_url_org1 = "https://{hostname}/sp/{genus_sp}/feature/{Genus}/{species}/mRNA/{id}".format(hostname=config["hostname"], genus_sp=org1_genus_species, Genus=org1_genus[0].upper() + org1_genus[1:], species=org1_species, id="{id}")
+ jbrowse_menu_url_org2 = "https://{hostname}/sp/{genus_sp}/feature/{Genus}/{species}/mRNA/{id}".format(hostname=config["hostname"], genus_sp=org2_genus_species, Genus=org2_genus[0].upper() + org2_genus[1:], species=org2_species, id="{id}")
+ else:
+ jbrowse_menu_url_org1 = config["menu_url"] + "/sp/{genus_sp}/feature/{Genus}/{species}/mRNA/{id}".format(genus_sp=org1_genus_species, Genus=org1_genus[0].upper() + org1_genus[1:], species=org1_species, id="{id}")
+ jbrowse_menu_url_org2 = config["menu_url"] + "/sp/{genus_sp}/feature/{Genus}/{species}/mRNA/{id}".format(genus_sp=org2_genus_species, Genus=org2_genus[0].upper() + org2_genus[1:], species=org2_species, id="{id}")
+
+ # show_tool_add_organism = instance.tools.show_tool(tool_id="toolshed.g2.bx.psu.edu/repos/gga/chado_organism_add_organism/organism_add_organism/2.3.4+galaxy0", io_details=True)
+ # print(show_tool_add_organism)
+ # show_jbrowse_tool = instance.tools.show_tool(tool_id="toolshed.g2.bx.psu.edu/repos/iuc/jbrowse/jbrowse/1.16.11+galaxy0", io_details=True)
+ # print(show_jbrowse_tool)
+ # show_jbrowse_container_tool = instance.tools.show_tool(tool_id="toolshed.g2.bx.psu.edu/repos/gga/jbrowse_to_container/jbrowse_to_container/0.5.1", io_details=True)
+ # print(show_jbrowse_container_tool)
+
+ # Replace values in the workflow dictionary
+ workflow_dict["steps"]["7"]["tool_state"] = workflow_dict["steps"]["7"]["tool_state"].replace("__MENU_URL_ORG1__", jbrowse_menu_url_org1)
+ workflow_dict["steps"]["8"]["tool_state"] = workflow_dict["steps"]["8"]["tool_state"].replace("__MENU_URL_ORG2__", jbrowse_menu_url_org2)
+ # 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"]["10"]["tool_state"] = workflow_dict["steps"]["10"]["tool_state"].replace("__DISPLAY_NAME_ORG1__", org1_full_name).replace("__UNIQUE_ID_ORG1__", org1_species_folder_name)
+ workflow_dict["steps"]["10"]["tool_state"] = workflow_dict["steps"]["10"]["tool_state"].replace("__DISPLAY_NAME_ORG2__", org2_full_name).replace("__UNIQUE_ID_ORG2__", org2_species_folder_name)
+
+ # Import the workflow in galaxy as a dict
+ instance.workflows.import_workflow_dict(workflow_dict=workflow_dict)
+
+ # Get its attributes
+ workflow_attributes = 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 = 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 finding workflow %s" % workflow_name)
+
+ # Finally, invoke the workflow alogn with its datamap, parameters and the history in which to invoke it
+ instance.workflows.invoke_workflow(workflow_id=workflow_id, history_id=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, instance_url))
+
+ if workflow_type == "blast":
+ 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
+ current_sp_workflow_dict = create_sp_workflow_dict(sp_dict, main_dir=args.main_directory, config=config, workfow_type="blast")
+
+ current_sp_key = list(current_sp_workflow_dict.keys())[0]
+ current_sp_value = list(current_sp_workflow_dict.values())[0]
+ current_sp_strain_sex_key = list(current_sp_value.keys())[0]
+ current_sp_strain_sex_value = list(current_sp_value.values())[0]
+
+ # Add the species dictionary to the complete dictionary
+ # This dictionary contains every organism present in the input file
+ # Its structure is the following:
+ # {genus species: {strain1_sex1: {variables_key: variables_values}, strain1_sex2: {variables_key: variables_values}}}
+ if not current_sp_key in all_sp_workflow_dict.keys():
+ all_sp_workflow_dict[current_sp_key] = current_sp_value
+ else:
+ all_sp_workflow_dict[current_sp_key][current_sp_strain_sex_key] = current_sp_strain_sex_value
- for k, v in all_sp_workflow_dict.items():
if len(list(v.keys())) == 1:
logging.info("Input organism %s: 1 species detected in input dictionary" % k)
# Set workflow path (1 organism)
- workflow_path = os.path.join(os.path.abspath(script_dir), "workflows_phaeoexplorer/Galaxy-Workflow-chado_load_tripal_synchronize_jbrowse_1org_v4.ga")
+ workflow_path = os.path.join(os.path.abspath(script_dir), "workflows_phaeoexplorer/Galaxy-Workflow-load_blast_results_1org_v1.ga")
# Instance object required variables
instance_url, email, password = None, None, None
@@ -982,7 +1496,7 @@ if __name__ == "__main__":
history_id = org_dict["history_id"]
- # Organism 1 attributes
+ # Organism attributes
org_genus = org_dict["genus"]
org_species = org_dict["species"]
org_genus_species = org_dict["genus_species"]
@@ -991,12 +1505,8 @@ if __name__ == "__main__":
org_strain = org_dict["sex"]
org_sex = org_dict["strain"]
org_org_id = org_dict["org_id"]
- org_genome_analysis_id = org_dict["genome_analysis_id"]
- org_ogs_analysis_id = org_dict["ogs_analysis_id"]
- org_genome_hda_id = org_dict["hda_ids"]["genome_hda_id"]
- org_transcripts_hda_id = org_dict["hda_ids"]["transcripts_hda_id"]
- org_proteins_hda_id = org_dict["hda_ids"]["proteins_hda_id"]
- org_gff_hda_id = org_dict["hda_ids"]["gff_hda_id"]
+ org_blastp_analysis_id = org_dict["blastp_analysis_id"]
+ org_blastp_hda_id = org_dict["hda_ids"]["blastp_hda_id"]
# Store these values into a dict for parameters logging/validation
org_parameters_dict = {
@@ -1008,12 +1518,8 @@ if __name__ == "__main__":
"org_strain": org_strain,
"org_sex": org_sex,
"org_org_id": org_org_id,
- "org_genome_analysis_id": org_genome_analysis_id,
- "org_ogs_analysis_id": org_ogs_analysis_id,
- "org_genome_hda_id": org_genome_hda_id,
- "org_transcripts_hda_id": org_transcripts_hda_id,
- "org_proteins_hda_id": org_proteins_hda_id,
- "org_gff_hda_id": org_gff_hda_id,
+ "org_blast_analysis_id": org_blastp_analysis_id,
+ "org_blastp_hda_id": org_blastp_hda_id,
}
# Look for empty parameters values, throw a critical error if a parameter value is invalid
@@ -1022,71 +1528,30 @@ if __name__ == "__main__":
logging.critical("Empty parameter value found for organism {0} (parameter: {1}, parameter value: {2})".format(org_full_name, param_name, param_value))
sys.exit()
+ BLASTP_FILE = "0"
+ LOAD_BLASTP_FILE = "1"
+ SYNC_BLASTP_ANALYSIS = "2"
+ POPULATE_MAT_VIEWS = "3"
+ INDEX_TRIPAL_DATA = "4"
+
# 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[BLASTP_FILE] = {}
+ workflow_parameters[LOAD_BLASTP_FILE] = {"analysis_id": org_blastp_analysis_id, "organism_id": org_org_id}
+ workflow_parameters[SYNC_BLASTP_ANALYSIS] = {"analysis_id": org_blastp_analysis_id}
workflow_parameters[POPULATE_MAT_VIEWS] = {}
workflow_parameters[INDEX_TRIPAL_DATA] = {}
- # 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[BLASTP_FILE] = {"src": "hda", "id": org_blastp_hda_id}
with open(workflow_path, 'r') as ga_in_file:
-
# Store the decoded json dictionary
workflow_dict = json.load(ga_in_file)
workflow_name = workflow_dict["name"]
- # For the Jbrowse tool, 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)
- jbrowse_menu_url_org = "https://{hostname}/sp/{genus_sp}/feature/{Genus}/{species}/mRNA/{id}".format(hostname=config["hostname"], genus_sp=org_genus_species, Genus=org_genus[0].upper() + org_genus[1:], species=org_species, id="{id}")
- if "menu_url" not in config.keys():
- jbrowse_menu_url_org = "https://{hostname}/sp/{genus_sp}/feature/{Genus}/{species}/mRNA/{id}".format(hostname=config["hostname"], genus_sp=org_genus_species, Genus=org_genus[0].upper() + org_genus[1:], species=org_species, id="{id}")
- else:
- jbrowse_menu_url_org = config["menu_url"] + "/sp/{genus_sp}/feature/{Genus}/{species}/mRNA/{id}".format(genus_sp=org_genus_species, Genus=org_genus[0].upper() + org_genus[1:], species=org_species, id="{id}")
-
- # show_tool_add_organism = instance.tools.show_tool(tool_id="toolshed.g2.bx.psu.edu/repos/gga/chado_organism_add_organism/organism_add_organism/2.3.4+galaxy0", io_details=True)
- # print(show_tool_add_organism)
- # show_jbrowse_tool = instance.tools.show_tool(tool_id="toolshed.g2.bx.psu.edu/repos/iuc/jbrowse/jbrowse/1.16.11+galaxy0", io_details=True)
- # print(show_jbrowse_tool)
- # show_jbrowse_container_tool = instance.tools.show_tool(tool_id="toolshed.g2.bx.psu.edu/repos/gga/jbrowse_to_container/jbrowse_to_container/0.5.1", io_details=True)
- # print(show_jbrowse_container_tool)
-
- # Replace values in the workflow dictionary
- workflow_dict["steps"]["4"]["tool_state"] = workflow_dict["steps"]["4"]["tool_state"].replace("__MENU_URL_ORG__", jbrowse_menu_url_org)
- workflow_dict["steps"]["6"]["tool_state"] = workflow_dict["steps"]["6"]["tool_state"].replace("__DISPLAY_NAME_ORG__", org_full_name).replace("__UNIQUE_ID_ORG__", org_species_folder_name)
-
# Import the workflow in galaxy as a dict
instance.workflows.import_workflow_dict(workflow_dict=workflow_dict)
-
# Get its attributes
workflow_attributes = instance.workflows.get_workflows(name=workflow_name)
# Then get its ID (required to invoke the workflow)
@@ -1106,11 +1571,11 @@ if __name__ == "__main__":
if len(list(v.keys())) == 2:
-
+
logging.info("Input organism %s: 2 species detected in input dictionary" % k)
# Set workflow path (2 organisms)
- workflow_path = os.path.join(os.path.abspath(script_dir), "workflows_phaeoexplorer/Galaxy-Workflow-chado_load_tripal_synchronize_jbrowse_2org_v4.ga")
+ workflow_path = os.path.join(os.path.abspath(script_dir), "workflows_phaeoexplorer/Galaxy-Workflow-load_blast_results_2org_v1.ga")
# Instance object required variables
instance_url, email, password = None, None, None
@@ -1126,7 +1591,6 @@ if __name__ == "__main__":
# Check if the versions of tools specified in the workflow are installed in galaxy
install_changesets_revisions_from_workflow(workflow_path=workflow_path, instance=instance)
- # Get key names from the current organism (item 1 = organism 1, item 2 = organism 2)
organisms_key_names = list(v.keys())
org1_dict = v[organisms_key_names[0]]
org2_dict = v[organisms_key_names[1]]
@@ -1142,12 +1606,8 @@ if __name__ == "__main__":
org1_strain = org1_dict["sex"]
org1_sex = org1_dict["strain"]
org1_org_id = org1_dict["org_id"]
- org1_genome_analysis_id = org1_dict["genome_analysis_id"]
- org1_ogs_analysis_id = org1_dict["ogs_analysis_id"]
- org1_genome_hda_id = org1_dict["hda_ids"]["genome_hda_id"]
- org1_transcripts_hda_id = org1_dict["hda_ids"]["transcripts_hda_id"]
- org1_proteins_hda_id = org1_dict["hda_ids"]["proteins_hda_id"]
- org1_gff_hda_id = org1_dict["hda_ids"]["gff_hda_id"]
+ org1_blastp_analysis_id = org1_dict["blastp_analysis_id"]
+ org1_blastp_hda_id = org1_dict["hda_ids"]["blastp_hda_id"]
# Store these values into a dict for parameters logging/validation
org1_parameters_dict = {
@@ -1159,14 +1619,11 @@ if __name__ == "__main__":
"org1_strain": org1_strain,
"org1_sex": org1_sex,
"org1_org_id": org1_org_id,
- "org1_genome_analysis_id": org1_genome_analysis_id,
- "org1_ogs_analysis_id": org1_ogs_analysis_id,
- "org1_genome_hda_id": org1_genome_hda_id,
- "org1_transcripts_hda_id": org1_transcripts_hda_id,
- "org1_proteins_hda_id": org1_proteins_hda_id,
- "org1_gff_hda_id": org1_gff_hda_id,
+ "org1_blast_analysis_id": org1_blastp_analysis_id,
+ "org1_blastp_hda_id": org1_blastp_hda_id,
}
+
# Look for empty parameters values, throw a critical error if a parameter value is invalid
for param_name, param_value in org1_parameters_dict.items():
if param_value is None or param_value == "":
@@ -1182,30 +1639,23 @@ if __name__ == "__main__":
org2_strain = org2_dict["sex"]
org2_sex = org2_dict["strain"]
org2_org_id = org2_dict["org_id"]
- org2_genome_analysis_id = org2_dict["genome_analysis_id"]
- org2_ogs_analysis_id = org2_dict["ogs_analysis_id"]
- org2_genome_hda_id = org2_dict["hda_ids"]["genome_hda_id"]
- org2_transcripts_hda_id = org2_dict["hda_ids"]["transcripts_hda_id"]
- org2_proteins_hda_id = org2_dict["hda_ids"]["proteins_hda_id"]
- org2_gff_hda_id = org2_dict["hda_ids"]["gff_hda_id"]
+ org2_blastp_analysis_id = org2_dict["blastp_analysis_id"]
+ org2_blastp_hda_id = org2_dict["hda_ids"]["blastp_hda_id"]
# Store these values into a dict for parameters logging/validation
org2_parameters_dict = {
"org2_genus": org2_genus,
"org2_species": org2_species,
"org2_genus_species": org2_genus_species,
- "org2_species_folder_name": org2_species_folder_name,
+ "org2_species_folder_name": orgé_species_folder_name,
"org2_full_name": org2_full_name,
"org2_strain": org2_strain,
"org2_sex": org2_sex,
"org2_org_id": org2_org_id,
- "org2_genome_analysis_id": org2_genome_analysis_id,
- "org2_ogs_analysis_id": org2_ogs_analysis_id,
- "org2_genome_hda_id": org2_genome_hda_id,
- "org2_transcripts_hda_id": org2_transcripts_hda_id,
- "org2_proteins_hda_id": org2_proteins_hda_id,
- "org2_gff_hda_id": org2_gff_hda_id,
+ "org2_blast_analysis_id": org2_blastp_analysis_id,
+ "org2_blastp_hda_id": org2_blastp_hda_id,
}
+
# Look for empty parameters values, throw a critical error if a parameter value is invalid
for param_name, param_value in org2_parameters_dict.items():
@@ -1215,115 +1665,51 @@ if __name__ == "__main__":
# Source files association (ordered by their IDs in the workflow)
# WARNING: Be very careful about how the workflow is "organized" (i.e the order of the steps/datasets, check the .ga if there is any error)
- GFF_FILE_ORG1 = "0"
- GENOME_FASTA_FILE_ORG1 = "1"
- PROTEINS_FASTA_FILE_ORG1 = "2"
-
- GENOME_FASTA_FILE_ORG2 = "3"
- GFF_FILE_ORG2 = "4"
- PROTEINS_FASTA_FILE_ORG2 = "5"
-
- LOAD_FASTA_ORG1 = "6"
- JBROWSE_ORG1 = "7"
- JRBOWSE_ORG2 = "8"
-
- LOAD_GFF_ORG1 = "9"
- JBROWSE_CONTAINER = "10"
- SYNC_FEATURES_ORG1 = "11"
-
- LOAD_FASTA_ORG2 = "12"
- LOAD_GFF_ORG2 = "13"
-
- SYNC_FEATURES_ORG2 = "14"
- POPULATE_MAT_VIEWS = "15"
- INDEX_TRIPAL_DATA = "16"
+ BLASTP_FILE_ORG1 = "0"
+ BLASTP_FILE_ORG2 = "1"
+ LOAD_BLASTP_FILE_ORG1 = "2"
+ LOAD_BLASTP_FILE_ORG1 = "3"
+ SYNC_BLASTP_ANALYSIS_ORG1 = "4"
+ SYNC_BLASTP_ANALYSIS_ORG2 = "5"
+ POPULATE_MAT_VIEWS = "6"
+ INDEX_TRIPAL_DATA = "7"
# Set the workflow parameters (individual tools runtime parameters in the workflow)
workflow_parameters = {}
# 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_ORG1] = {}
- workflow_parameters[GFF_FILE_ORG1] = {}
- workflow_parameters[PROTEINS_FASTA_FILE_ORG1] = {}
- workflow_parameters[GENOME_FASTA_FILE_ORG2] = {}
- workflow_parameters[GFF_FILE_ORG2] = {}
- workflow_parameters[PROTEINS_FASTA_FILE_ORG2] = {}
+ workflow_parameters[BLASTP_FILE_ORG1] = {}
+ workflow_parameters[BLASTP_FILE_ORG2] = {}
# Organism 1
- workflow_parameters[LOAD_FASTA_ORG1] = {"organism": org1_org_id,
- "analysis_id": org1_genome_analysis_id,
- "do_update": "true"}
- # workflow_parameters[JBROWSE_ORG1] = {"menu_url": jbrowse_menu_url_org1}
- workflow_parameters[JBROWSE_ORG1] = {}
- workflow_parameters[LOAD_GFF_ORG1] = {"organism": org1_org_id, "analysis_id": org1_ogs_analysis_id}
- workflow_parameters[SYNC_FEATURES_ORG1] = {"organism_id": org1_org_id}
- # workflow_parameters[JBROWSE_CONTAINER] = {"organisms": [{"name": org1_full_name, "unique_id": org1_species_folder_name, }, {"name": org2_full_name, "unique_id": org2_species_folder_name}]}
- workflow_parameters[JBROWSE_CONTAINER] = {}
+ workflow_parameters[LOAD_BLASTP_FILE_ORG1] = {"organism_id": org1_org_id,
+ "analysis_id": org1_blastp_analysis_id}
+ workflow_parameters[SYNC_BLASTP_ANALYSIS_ORG1] = {"analysis_id": org1_blastp_analysis_id}
# Organism 2
- workflow_parameters[LOAD_FASTA_ORG2] = {"organism": org2_org_id,
- "analysis_id": org2_genome_analysis_id,
- "do_update": "true"}
- workflow_parameters[LOAD_GFF_ORG2] = {"organism": org2_org_id, "analysis_id": org2_ogs_analysis_id}
- # workflow_parameters[JRBOWSE_ORG2] = {"menu_url": jbrowse_menu_url_org2}
- workflow_parameters[JRBOWSE_ORG2] = {}
- workflow_parameters[SYNC_FEATURES_ORG2] = {"organism_id": org2_org_id}
-
+ workflow_parameters[LOAD_BLASTP_FILE_ORG2] = {"organism_id": org2_org_id,
+ "analysis_id": org2_blastp_analysis_id}
+ workflow_parameters[SYNC_BLASTP_ANALYSIS_ORG2] = {"analysis_id": org2_blastp_analysis_id}
- # POPULATE + INDEX DATA
workflow_parameters[POPULATE_MAT_VIEWS] = {}
workflow_parameters[INDEX_TRIPAL_DATA] = {}
-
# Set datamap (mapping of input files in the workflow)
datamap = {}
# Organism 1
- datamap[GENOME_FASTA_FILE_ORG1] = {"src": "hda", "id": org1_genome_hda_id}
- datamap[GFF_FILE_ORG1] = {"src": "hda", "id": org1_gff_hda_id}
- datamap[PROTEINS_FASTA_FILE_ORG1] = {"src": "hda", "id": org1_proteins_hda_id}
+ datamap[BLASTP_FILE_ORG1] = {"src": "hda", "id": org1_blastp_hda_id}
# Organism 2
- datamap[GENOME_FASTA_FILE_ORG2] = {"src": "hda", "id": org2_genome_hda_id}
- datamap[GFF_FILE_ORG2] = {"src": "hda", "id": org2_gff_hda_id}
- datamap[PROTEINS_FASTA_FILE_ORG2] = {"src": "hda", "id": org2_proteins_hda_id}
+ datamap[BLASTP_FILE_ORG2] = {"src": "hda", "id": org2_blastp_hda_id}
with open(workflow_path, 'r') as ga_in_file:
-
# Store the decoded json dictionary
workflow_dict = json.load(ga_in_file)
workflow_name = workflow_dict["name"]
- # For the Jbrowse tool, 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)
- jbrowse_menu_url_org1 = "https://{hostname}/sp/{genus_sp}/feature/{Genus}/{species}/mRNA/{id}".format(hostname=config["hostname"], genus_sp=org1_genus_species, Genus=org1_genus[0].upper() + org1_genus[1:], species=org1_species, id="{id}")
- jbrowse_menu_url_org2 = "https://{hostname}/sp/{genus_sp}/feature/{Genus}/{species}/mRNA/{id}".format(hostname=config["hostname"], genus_sp=org2_genus_species, Genus=org2_genus[0].upper() + org2_genus[1:], species=org2_species, id="{id}")
- if "menu_url" not in config.keys():
- jbrowse_menu_url_org1 = "https://{hostname}/sp/{genus_sp}/feature/{Genus}/{species}/mRNA/{id}".format(hostname=config["hostname"], genus_sp=org1_genus_species, Genus=org1_genus[0].upper() + org1_genus[1:], species=org1_species, id="{id}")
- jbrowse_menu_url_org2 = "https://{hostname}/sp/{genus_sp}/feature/{Genus}/{species}/mRNA/{id}".format(hostname=config["hostname"], genus_sp=org2_genus_species, Genus=org2_genus[0].upper() + org2_genus[1:], species=org2_species, id="{id}")
- else:
- jbrowse_menu_url_org1 = config["menu_url"] + "/sp/{genus_sp}/feature/{Genus}/{species}/mRNA/{id}".format(genus_sp=org1_genus_species, Genus=org1_genus[0].upper() + org1_genus[1:], species=org1_species, id="{id}")
- jbrowse_menu_url_org2 = config["menu_url"] + "/sp/{genus_sp}/feature/{Genus}/{species}/mRNA/{id}".format(genus_sp=org2_genus_species, Genus=org2_genus[0].upper() + org2_genus[1:], species=org2_species, id="{id}")
-
- # show_tool_add_organism = instance.tools.show_tool(tool_id="toolshed.g2.bx.psu.edu/repos/gga/chado_organism_add_organism/organism_add_organism/2.3.4+galaxy0", io_details=True)
- # print(show_tool_add_organism)
- # show_jbrowse_tool = instance.tools.show_tool(tool_id="toolshed.g2.bx.psu.edu/repos/iuc/jbrowse/jbrowse/1.16.11+galaxy0", io_details=True)
- # print(show_jbrowse_tool)
- # show_jbrowse_container_tool = instance.tools.show_tool(tool_id="toolshed.g2.bx.psu.edu/repos/gga/jbrowse_to_container/jbrowse_to_container/0.5.1", io_details=True)
- # print(show_jbrowse_container_tool)
-
- # Replace values in the workflow dictionary
- workflow_dict["steps"]["7"]["tool_state"] = workflow_dict["steps"]["7"]["tool_state"].replace("__MENU_URL_ORG1__", jbrowse_menu_url_org1)
- workflow_dict["steps"]["8"]["tool_state"] = workflow_dict["steps"]["8"]["tool_state"].replace("__MENU_URL_ORG2__", jbrowse_menu_url_org2)
- # 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"]["10"]["tool_state"] = workflow_dict["steps"]["10"]["tool_state"].replace("__DISPLAY_NAME_ORG1__", org1_full_name).replace("__UNIQUE_ID_ORG1__", org1_species_folder_name)
- workflow_dict["steps"]["10"]["tool_state"] = workflow_dict["steps"]["10"]["tool_state"].replace("__DISPLAY_NAME_ORG2__", org2_full_name).replace("__UNIQUE_ID_ORG2__", org2_species_folder_name)
-
# Import the workflow in galaxy as a dict
instance.workflows.import_workflow_dict(workflow_dict=workflow_dict)
-
# Get its attributes
workflow_attributes = instance.workflows.get_workflows(name=workflow_name)
# Then get its ID (required to invoke the workflow)
@@ -1340,320 +1726,3 @@ if __name__ == "__main__":
logging.info("Successfully imported and invoked workflow {0}, check the galaxy instance ({1}) for the jobs state".format(workflow_name, instance_url))
-
-
-
-
-
-
-
- # Get the instance attribute from the object for future connections
- # This is the GalaxyInstance object from bioblend (not the url!)
- # instance = run_workflow_for_current_organism.instance
-
- # if "2org" in str(workflow):
- # logging.info("Executing workflow %s" % workflow)
-
-
- # run_workflow_for_current_organism.connect_to_instance()
- # run_workflow_for_current_organism.set_get_history()
-
- # # TODO: only do this once per instance (not at each iteration!)
- # run_workflow_for_current_organism.install_changesets_revisions_for_individual_tools()
- # run_workflow_for_current_organism.install_changesets_revisions_from_workflow(workflow_path=workflow)
- # run_workflow_for_current_organism.add_organism_ogs_genome_analyses()
- # org_id = run_workflow_for_current_organism.get_organism_id()
- # genome_analysis_id = run_workflow_for_current_organism.get_genome_analysis_id()
- # ogs_analysis_id = run_workflow_for_current_organism.get_ogs_analysis_id()
- # instance_attributes = run_workflow_for_current_organism.get_instance_attributes()
-
-
- # # Import datasets into history and retrieve their hda IDs
- # # TODO: can be simplified with direct access to the folder contents via the full path (no loop required)
-
- # hda_ids = run_workflow_for_current_organism.import_datasets_into_history()
- # hda_ids_list.append(hda_ids)
-
-
- # # TODO: Exlcude the workflow invocation from the loop
- # # Extract instance url from one, attributes from both in lists ?
-
-
- # # Source files association (ordered by their IDs in the workflow)
- # GENOME_FASTA_FILE_ORG1 = "0"
- # GFF_FILE_ORG1 = "1"
- # PROTEINS_FASTA_FILE_ORG1 = "2"
- # GENOME_FASTA_FILE_ORG2 = "3"
- # GFF_FILE_ORG2 = "4"
- # PROTEINS_FASTA_FILE_ORG2 = "5"
-
- # LOAD_FASTA_ORG1 = "6"
- # JBROWSE_ORG1 = "7"
- # JRBOWSE_ORG2 = "8"
-
- # LOAD_GFF_ORG1 = "9"
- # JBROWSE_CONTAINER = "10"
- # SYNC_FEATURES_ORG1 = "11"
-
- # LOAD_FASTA_ORG2 = "12"
- # LOAD_GFF_ORG2 = "13"
-
- # SYNC_FEATURES_ORG2 = "14"
- # POPULATE_MAT_VIEWS = "15"
- # INDEX_TRIPAL_DATA = "16"
-
- # workflow_parameters = {}
-
- # workflow_parameters[GENOME_FASTA_FILE_ORG1] = {}
- # workflow_parameters[GFF_FILE_ORG1] = {}
- # workflow_parameters[PROTEINS_FASTA_FILE_ORG1] = {}
- # workflow_parameters[GENOME_FASTA_FILE_ORG2] = {}
- # workflow_parameters[GFF_FILE_ORG2] = {}
- # workflow_parameters[PROTEINS_FASTA_FILE_ORG2] = {}
-
-
- # # ORGANISM 1
- # workflow_parameters[LOAD_FASTA_ORG1] = {"organism": org_ids[0],
- # "analysis_id": genome_analysis_ids[0],
- # "do_update": "true"}
- # # Change "do_update": "true" to "do_update": "false" in above parameters to prevent appending/updates to the fasta file in chado
- # # WARNING: It is safer to never update it and just change the genome/ogs versions in the config
- # workflow_parameters[JBROWSE_ORG1] = {}
- # workflow_parameters[LOAD_GFF_ORG1] = {"organism": org_ids[0], "analysis_id": ogs_analysis_ids[0]}
- # workflow_parameters[SYNC_FEATURES_ORG1] = {"organism_id": org_ids[0]}
- # workflow_parameters[JBROWSE_CONTAINER] = {}
-
-
- # # ORGANISM 2
- # workflow_parameters[LOAD_FASTA_ORG2] = {"organism": org_ids[1],
- # "analysis_id": genome_analysis_ids[1],
- # "do_update": "true"}
- # # Change "do_update": "true" to "do_update": "false" in above parameters to prevent appending/updates to the fasta file in chado
- # # WARNING: It is safer to never update it and just change the genome/ogs versions in the config
- # workflow_parameters[LOAD_GFF_ORG2] = {"organism": org_ids[1], "analysis_id": ogs_analysis_ids[1]}
- # workflow_parameters[JRBOWSE_ORG2] = {}
- # workflow_parameters[SYNC_FEATURES_ORG2] = {"organism_id": org_ids[1]}
-
- # workflow_parameters[SYNC_GENOME_ANALYSIS_INTO_TRIPAL] = {"analysis_id": ogs_analysis_ids[0]}
- # workflow_parameters[SYNC_OGS_ANALYSIS_INTO_TRIPAL] = {"analysis_id": genome_analysis_ids[0]}
- # workflow_parameters[SYNC_FEATURES_INTO_TRIPAL] = {"organism_id": org_ids[0]}
-
- # # POPULATE + INDEX DATA
- # workflow_parameters[POPULATE_MAT_VIEWS] = {}
- # workflow_parameters[INDEX_TRIPAL_DATA] = {}
-
- # # Datamap for input datasets - dataset source (type): ldda (LibraryDatasetDatasetAssociation)
- # run_workflow_for_current_organism.datamap = {}
-
- # run_workflow_for_current_organism.datamap[GENOME_FASTA_FILE_ORG1] = {"src": "hda", "id": hda_ids_list[0]["genome_hda_id"]}
- # run_workflow_for_current_organism.datamap[GFF_FILE_ORG1] = {"src": "hda", "id": hda_ids_list[0]["gff_hda_id"]}
- # run_workflow_for_current_organism.datamap[PROTEINS_FASTA_FILE_ORG1] = {"src": "hda", "id": hda_ids_list[0]["proteins_hda_id"]}
-
- # run_workflow_for_current_organism.datamap[GENOME_FASTA_FILE_ORG2] = {"src": "hda", "id": hda_ids_list[1]["genome_hda_id"]}
- # run_workflow_for_current_organism.datamap[GFF_FILE_ORG2] = {"src": "hda", "id": hda_ids_list[1]["gff_hda_id"]}
- # run_workflow_for_current_organism.datamap[GFF_FILE_ORG2] = {"src": "hda", "id": hda_ids_list[1]["proteins_hda_id"]}
-
-
-
- # logging.info("OK: Workflow invoked")
-
-
-
- # # If input workflow is Chado_load_Tripal_synchronize.ga
- # if "Chado_load_Tripal_synchronize" in str(workflow):
-
- # logging.info("Executing workflow 'Chado_load_Tripal_synchronize'")
-
- # run_workflow_for_current_organism.connect_to_instance()
- # run_workflow_for_current_organism.set_get_history()
- # # run_workflow_for_current_organism.get_species_history_id()
-
- # run_workflow_for_current_organism.install_changesets_revisions_for_individual_tools()
- # run_workflow_for_current_organism.install_changesets_revisions_from_workflow(workflow_path=workflow)
- # run_workflow_for_current_organism.add_organism_ogs_genome_analyses()
- # run_workflow_for_current_organism.get_organism_id()
- # run_workflow_for_current_organism.get_genome_analysis_id()
- # run_workflow_for_current_organism.get_ogs_analysis_id()
-
- # # run_workflow_for_current_organism.tripal_synchronize_organism_analyses()
-
- # # Get the attributes of the instance and project data files
- # run_workflow_for_current_organism.get_instance_attributes()
-
- # # Import datasets into history and retrieve their hda IDs
- # # TODO: can be simplified with direct access to the folder contents via the full path (no loop required)
- # hda_ids = run_workflow_for_current_organism.import_datasets_into_history()
-
- # # DEBUG
- # # run_workflow_for_current_organism.get_invocation_report(workflow_name="Chado load Tripal synchronize")
-
- # # Explicit workflow parameter names
- # GENOME_FASTA_FILE = "0"
- # GFF_FILE = "1"
- # PROTEINS_FASTA_FILE = "2"
- # TRANSCRIPTS_FASTA_FILE = "3"
-
- # LOAD_FASTA_IN_CHADO = "4"
- # LOAD_GFF_IN_CHADO = "5"
- # SYNC_ORGANISM_INTO_TRIPAL = "6"
- # SYNC_GENOME_ANALYSIS_INTO_TRIPAL = "7"
- # SYNC_OGS_ANALYSIS_INTO_TRIPAL = "8"
- # SYNC_FEATURES_INTO_TRIPAL = "9"
-
- # workflow_parameters = {}
-
- # workflow_parameters[GENOME_FASTA_FILE] = {}
- # workflow_parameters[GFF_FILE] = {}
- # workflow_parameters[PROTEINS_FASTA_FILE] = {}
- # workflow_parameters[TRANSCRIPTS_FASTA_FILE] = {}
-
- # workflow_parameters[LOAD_FASTA_IN_CHADO] = {"organism": run_workflow_for_current_organism.org_id,
- # "analysis_id": run_workflow_for_current_organism.genome_analysis_id,
- # "do_update": "true"}
- # # Change "do_update": "true" to "do_update": "false" in above parameters to prevent appending/updates to the fasta file in chado
- # # WARNING: It is safer to never update it and just change the genome/ogs versions in the config
- # workflow_parameters[LOAD_GFF_IN_CHADO] = {"organism": run_workflow_for_current_organism.org_id,
- # "analysis_id": run_workflow_for_current_organism.ogs_analysis_id}
- # workflow_parameters[SYNC_ORGANISM_INTO_TRIPAL] = {"organism_id": run_workflow_for_current_organism.org_id}
- # workflow_parameters[SYNC_GENOME_ANALYSIS_INTO_TRIPAL] = {"analysis_id": run_workflow_for_current_organism.ogs_analysis_id}
- # workflow_parameters[SYNC_OGS_ANALYSIS_INTO_TRIPAL] = {"analysis_id": run_workflow_for_current_organism.genome_analysis_id}
- # workflow_parameters[SYNC_FEATURES_INTO_TRIPAL] = {"organism_id": run_workflow_for_current_organism.org_id}
-
- # # Datamap for input datasets - dataset source (type): ldda (LibraryDatasetDatasetAssociation)
- # run_workflow_for_current_organism.datamap = {}
- # run_workflow_for_current_organism.datamap[GENOME_FASTA_FILE] = {"src": "hda", "id": hda_ids["genome_hda_id"]}
- # run_workflow_for_current_organism.datamap[GFF_FILE] = {"src": "hda", "id": hda_ids["gff_hda_id"]}
- # run_workflow_for_current_organism.datamap[PROTEINS_FASTA_FILE] = {"src": "hda", "id": hda_ids["proteins_hda_id"]}
- # run_workflow_for_current_organism.datamap[TRANSCRIPTS_FASTA_FILE] = {"src": "hda", "id": hda_ids["transcripts_hda_id"]}
-
- # # run_workflow_for_current_organism.datamap = {}
- # # run_workflow_for_current_organism.datamap[GENOME_FASTA_FILE] = {"src": "hda", "id":
- # # run_workflow_for_current_organism.datasets["genome_file"]}
- # # run_workflow_for_current_organism.datamap[GFF_FILE] = {"src": "hda",
- # # "id": hda_ids["gff_hda_id"]}
-
- # # Ensures galaxy has had time to retrieve datasets
- # time.sleep(60)
- # # Run the Chado load Tripal sync workflow with the parameters set above
- # run_workflow_for_current_organism.run_workflow(workflow_path=workflow,
- # workflow_parameters=workflow_parameters,
- # datamap=run_workflow_for_current_organism.datamap,
- # workflow_name="Chado load Tripal synchronize")
-
- # # Jbrowse creation workflow
- # elif "Jbrowse" in str(workflow):
-
- # logging.info("Executing workflow 'Jbrowse'")
-
- # run_workflow_for_current_organism.connect_to_instance()
- # run_workflow_for_current_organism.set_get_history()
- # run_workflow_for_current_organism.install_changesets_revisions_from_workflow(workflow_path=workflow)
- # run_workflow_for_current_organism.get_organism_id()
- # # Import datasets into history and get their hda IDs
- # run_workflow_for_current_organism.import_datasets_into_history()
- # hda_ids = run_workflow_for_current_organism.get_datasets_hda_ids() # Note: only call this function AFTER calling "import_datasets_into_history()"
-
- # # Debugging
- # # run_workflow_for_current_organism.get_invocation_report(workflow_name="Jbrowse")
-
- # GENOME_FASTA_FILE = "0"
- # GFF_FILE = "1"
- # ADD_JBROWSE = "2"
- # ADD_ORGANISM_TO_JBROWSE = "3"
-
- # workflow_parameters = {}
- # workflow_parameters[GENOME_FASTA_FILE] = {}
- # workflow_parameters[GFF_FILE] = {}
- # workflow_parameters[ADD_JBROWSE] = {}
- # workflow_parameters[ADD_ORGANISM_TO_JBROWSE] = {}
-
- # run_workflow_for_current_organism.datamap = {}
- # run_workflow_for_current_organism.datamap[GENOME_FASTA_FILE] = {"src": "hda", "id": hda_ids["genome_hda_id"]}
- # run_workflow_for_current_organism.datamap[GFF_FILE] = {"src": "hda", "id": hda_ids["gff_hda_id"]}
-
- # # Run the jbrowse creation workflow
- # run_workflow_for_current_organism.run_workflow(workflow_path=workflow,
- # workflow_parameters=workflow_parameters,
- # datamap=run_workflow_for_current_organism.datamap,
- # workflow_name="Jbrowse")
-
- # elif "Interpro" in str(workflow):
-
- # logging.info("Executing workflow 'Interproscan")
-
- # run_workflow_for_current_organism.connect_to_instance()
- # run_workflow_for_current_organism.set_get_history()
- # run_workflow_for_current_organism.install_changesets_revisions_from_workflow(workflow_path=workflow)
- # # run_workflow_for_current_organism.get_species_history_id()
-
- # # Get the attributes of the instance and project data files
- # run_workflow_for_current_organism.get_instance_attributes()
- # run_workflow.add_interproscan_analysis()
- # run_workflow_for_current_organism.get_interpro_analysis_id()
-
- # # Import datasets into history and retrieve their hda IDs
- # run_workflow_for_current_organism.import_datasets_into_history()
- # hda_ids = run_workflow_for_current_organism.get_datasets_hda_ids()
-
- # INTERPRO_FILE = "0"
- # LOAD_INTERPRO_IN_CHADO = "1"
- # SYNC_INTERPRO_ANALYSIS_INTO_TRIPAL = "2"
- # SYNC_FEATURES_INTO_TRIPAL = "3"
- # POPULATE_MAT_VIEWS = "4"
- # INDEX_TRIPAL_DATA = "5"
-
- # workflow_parameters = {}
- # workflow_parameters[INTERPRO_FILE] = {}
- # workflow_parameters[LOAD_INTERPRO_IN_CHADO] = {"organism": run_workflow_for_current_organism.org_id,
- # "analysis_id": run_workflow_for_current_organism.interpro_analysis_id}
- # workflow_parameters[SYNC_INTERPRO_ANALYSIS_INTO_TRIPAL] = {"analysis_id": run_workflow_for_current_organism.interpro_analysis_id}
-
-
- # run_workflow_for_current_organism.datamap = {}
- # run_workflow_for_current_organism.datamap[INTERPRO_FILE] = {"src": "hda", "id": run_workflow_for_current_organism.hda_ids["interproscan_hda_id"]}
-
- # # Run Interproscan workflow
- # run_workflow_for_current_organism.run_workflow(workflow_path=workflow,
- # workflow_parameters=workflow_parameters,
- # datamap=run_workflow_for_current_organism.datamap,
- # workflow_name="Interproscan")
-
- # elif "Blast" in str(workflow):
-
- # logging.info("Executing workflow 'Blast_Diamond")
-
- # run_workflow_for_current_organism.connect_to_instance()
- # run_workflow_for_current_organism.set_get_history()
- # run_workflow_for_current_organism.install_changesets_revisions_from_workflow(workflow_path=workflow)
- # # run_workflow_for_current_organism.get_species_history_id()
-
- # # Get the attributes of the instance and project data files
- # run_workflow_for_current_organism.get_instance_attributes()
- # run_workflow_for_current_organism.add_blastp_diamond_analysis()
- # run_workflow_for_current_organism.get_blastp_diamond_analysis_id()
-
- # # Import datasets into history and retrieve their hda IDs
- # run_workflow_for_current_organism.import_datasets_into_history()
- # hda_ids = run_workflow_for_current_organism.get_datasets_hda_ids()
-
- # BLAST_FILE = "0"
- # LOAD_BLAST_IN_CHADO = "1"
- # SYNC_BLAST_ANALYSIS_INTO_TRIPAL = "2"
- # SYNC_FEATURES_INTO_TRIPAL = "3"
- # POPULATE_MAT_VIEWS = "4"
- # INDEX_TRIPAL_DATA = "5"
-
- # workflow_parameters = {}
- # workflow_parameters[INTERPRO_FILE] = {}
- # workflow_parameters[LOAD_BLAST_IN_CHADO] = {"organism": run_workflow_for_current_organism.org_id,
- # "analysis_id": run_workflow_for_current_organism.blast_diamond_analysis_id}
- # workflow_parameters[SYNC_BLAST_ANALYSIS_INTO_TRIPAL] = {"analysis_id": run_workflow_for_current_organism.blast_diamond_analysis_id}
-
- # run_workflow_for_current_organism.datamap = {}
- # run_workflow_for_current_organism.datamap[INTERPRO_FILE] = {"src": "hda", "id": hda_ids["interproscan_hda_id"]}
-
- # # Run Interproscan workflow
- # run_workflow_for_current_organism.run_workflow(workflow_path=workflow,
- # workflow_parameters=workflow_parameters,
- # datamap=run_workflow_for_current_organism.datamap,
- # workflow_name="Interproscan")
diff --git a/workflows_phaeoexplorer/Galaxy-Workflow-load_blast_results_1org_v1.ga b/workflows_phaeoexplorer/Galaxy-Workflow-load_blast_results_1org_v1.ga
new file mode 100644
index 0000000..db4e953
--- /dev/null
+++ b/workflows_phaeoexplorer/Galaxy-Workflow-load_blast_results_1org_v1.ga
@@ -0,0 +1,271 @@
+{
+ "a_galaxy_workflow": "true",
+ "annotation": "",
+ "format-version": "0.1",
+ "name": "load_blast_results_1org_v1",
+ "steps": {
+ "0": {
+ "annotation": "",
+ "content_id": null,
+ "errors": null,
+ "id": 0,
+ "input_connections": {},
+ "inputs": [
+ {
+ "description": "",
+ "name": "blast file xml org1"
+ }
+ ],
+ "label": "blast file xml org1",
+ "name": "Input dataset",
+ "outputs": [],
+ "position": {
+ "bottom": 416.1999969482422,
+ "height": 82.19999694824219,
+ "left": 410,
+ "right": 610,
+ "top": 334,
+ "width": 200,
+ "x": 410,
+ "y": 334
+ },
+ "tool_id": null,
+ "tool_state": "{\"optional\": false}",
+ "tool_version": null,
+ "type": "data_input",
+ "uuid": "b1c63d94-61a7-4bf1-8b5d-e08fb34c0357",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "output",
+ "uuid": "f602d234-8cea-4db9-ab77-678cdc0d2101"
+ }
+ ]
+ },
+ "1": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_load_blast/load_blast/2.3.4+galaxy0",
+ "errors": null,
+ "id": 1,
+ "input_connections": {
+ "input": {
+ "id": 0,
+ "output_name": "output"
+ }
+ },
+ "inputs": [
+ {
+ "description": "runtime parameter for tool Chado load Blast results",
+ "name": "analysis_id"
+ },
+ {
+ "description": "runtime parameter for tool Chado load Blast results",
+ "name": "input"
+ },
+ {
+ "description": "runtime parameter for tool Chado load Blast results",
+ "name": "organism_id"
+ },
+ {
+ "description": "runtime parameter for tool Chado load Blast results",
+ "name": "wait_for"
+ }
+ ],
+ "label": "load blast results org1",
+ "name": "Chado load Blast results",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "json"
+ }
+ ],
+ "position": {
+ "bottom": 457.3999938964844,
+ "height": 164.39999389648438,
+ "left": 711,
+ "right": 911,
+ "top": 293,
+ "width": 200,
+ "x": 711,
+ "y": 293
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_load_blast/load_blast/2.3.4+galaxy0",
+ "tool_shed_repository": {
+ "changeset_revision": "08ae8b27b193",
+ "name": "chado_load_blast",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"analysis_id\": {\"__class__\": \"RuntimeValue\"}, \"blastdb_id\": \"21\", \"input\": {\"__class__\": \"RuntimeValue\"}, \"match_on_name\": \"false\", \"organism_id\": {\"__class__\": \"RuntimeValue\"}, \"psql_target\": {\"method\": \"remote\", \"__current_case__\": 0}, \"query_type\": \"polypeptide\", \"re_name\": \"\", \"skip_missing\": \"false\", \"wait_for\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": "2.3.4+galaxy0",
+ "type": "tool",
+ "uuid": "10144cf8-f121-45f3-ba64-9f4d66bf1e56",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "results",
+ "uuid": "95708895-8439-4257-bff6-96e4c51a0725"
+ }
+ ]
+ },
+ "2": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_analysis_sync/analysis_sync/3.2.1.0",
+ "errors": null,
+ "id": 2,
+ "input_connections": {
+ "wait_for": {
+ "id": 1,
+ "output_name": "results"
+ }
+ },
+ "inputs": [
+ {
+ "description": "runtime parameter for tool Synchronize an analysis",
+ "name": "analysis_id"
+ }
+ ],
+ "label": "sync blast analysis org1",
+ "name": "Synchronize an analysis",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "json"
+ }
+ ],
+ "position": {
+ "bottom": 451.3999938964844,
+ "height": 154.39999389648438,
+ "left": 1010,
+ "right": 1210,
+ "top": 297,
+ "width": 200,
+ "x": 1010,
+ "y": 297
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_analysis_sync/analysis_sync/3.2.1.0",
+ "tool_shed_repository": {
+ "changeset_revision": "f487ff676088",
+ "name": "tripal_analysis_sync",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"analysis_id\": {\"__class__\": \"RuntimeValue\"}, \"wait_for\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": "3.2.1.0",
+ "type": "tool",
+ "uuid": "99e7496d-ac32-467d-8c09-2efd48d0231a",
+ "workflow_outputs": [
+ {
+ "label": "Synchronize Analysis into Tripal",
+ "output_name": "results",
+ "uuid": "1fb6db92-90a2-4e33-beec-f2f974e369e9"
+ }
+ ]
+ },
+ "3": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_db_populate_mviews/db_populate_mviews/3.2.1.0",
+ "errors": null,
+ "id": 3,
+ "input_connections": {
+ "wait_for": {
+ "id": 2,
+ "output_name": "results"
+ }
+ },
+ "inputs": [],
+ "label": "populate mat views",
+ "name": "Populate materialized views",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "txt"
+ }
+ ],
+ "position": {
+ "bottom": 452.3999938964844,
+ "height": 154.39999389648438,
+ "left": 1295,
+ "right": 1495,
+ "top": 298,
+ "width": 200,
+ "x": 1295,
+ "y": 298
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_db_populate_mviews/db_populate_mviews/3.2.1.0",
+ "tool_shed_repository": {
+ "changeset_revision": "3c08f32a3dc1",
+ "name": "tripal_db_populate_mviews",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"mview\": \"\", \"wait_for\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": "3.2.1.0",
+ "type": "tool",
+ "uuid": "5c947dd5-89df-4146-9ab8-9e1d6de42360",
+ "workflow_outputs": [
+ {
+ "label": "Populate Tripal materialized view(s)",
+ "output_name": "results",
+ "uuid": "0a0c9fa7-3a3c-459d-b5c7-b7a5a11459f3"
+ }
+ ]
+ },
+ "4": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_db_index/db_index/3.2.1.1",
+ "errors": null,
+ "id": 4,
+ "input_connections": {
+ "wait_for": {
+ "id": 3,
+ "output_name": "results"
+ }
+ },
+ "inputs": [],
+ "label": "index tripal data",
+ "name": "Index Tripal data",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "txt"
+ }
+ ],
+ "position": {
+ "bottom": 433.6000061035156,
+ "height": 113.60000610351562,
+ "left": 1570,
+ "right": 1770,
+ "top": 320,
+ "width": 200,
+ "x": 1570,
+ "y": 320
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_db_index/db_index/3.2.1.1",
+ "tool_shed_repository": {
+ "changeset_revision": "d55a39f12dda",
+ "name": "tripal_db_index",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"expose\": {\"do_expose\": \"no\", \"__current_case__\": 0}, \"queues\": \"10\", \"table\": {\"mode\": \"website\", \"__current_case__\": 0}, \"tokenizer\": \"standard\", \"wait_for\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": "3.2.1.1",
+ "type": "tool",
+ "uuid": "5ecc30b0-07ab-4f9b-81f0-31310358c221",
+ "workflow_outputs": [
+ {
+ "label": "Index Tripal data",
+ "output_name": "results",
+ "uuid": "5c0f0431-acb0-4e40-a7e4-8a562933fd97"
+ }
+ ]
+ }
+ },
+ "tags": [],
+ "uuid": "80e32784-e39e-48ce-a6e3-7627de734ca6",
+ "version": 4
+}
\ No newline at end of file
diff --git a/workflows_phaeoexplorer/Galaxy-Workflow-load_blast_results_2org_v1.ga b/workflows_phaeoexplorer/Galaxy-Workflow-load_blast_results_2org_v1.ga
new file mode 100644
index 0000000..67d62db
--- /dev/null
+++ b/workflows_phaeoexplorer/Galaxy-Workflow-load_blast_results_2org_v1.ga
@@ -0,0 +1,418 @@
+{
+ "a_galaxy_workflow": "true",
+ "annotation": "",
+ "format-version": "0.1",
+ "name": "load_blast_results_2org_v1",
+ "steps": {
+ "0": {
+ "annotation": "",
+ "content_id": null,
+ "errors": null,
+ "id": 0,
+ "input_connections": {},
+ "inputs": [
+ {
+ "description": "",
+ "name": "blast file xml org1"
+ }
+ ],
+ "label": "blast file xml org1",
+ "name": "Input dataset",
+ "outputs": [],
+ "position": {
+ "bottom": 356.1999969482422,
+ "height": 82.19999694824219,
+ "left": 168,
+ "right": 368,
+ "top": 274,
+ "width": 200,
+ "x": 168,
+ "y": 274
+ },
+ "tool_id": null,
+ "tool_state": "{\"optional\": false}",
+ "tool_version": null,
+ "type": "data_input",
+ "uuid": "b1c63d94-61a7-4bf1-8b5d-e08fb34c0357",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "output",
+ "uuid": "8c6e3cd8-d0a0-403f-a882-f5206c8627f9"
+ }
+ ]
+ },
+ "1": {
+ "annotation": "",
+ "content_id": null,
+ "errors": null,
+ "id": 1,
+ "input_connections": {},
+ "inputs": [
+ {
+ "description": "",
+ "name": "blast file xml org2"
+ }
+ ],
+ "label": "blast file xml org2",
+ "name": "Input dataset",
+ "outputs": [],
+ "position": {
+ "bottom": 467.1999969482422,
+ "height": 82.19999694824219,
+ "left": 200,
+ "right": 400,
+ "top": 385,
+ "width": 200,
+ "x": 200,
+ "y": 385
+ },
+ "tool_id": null,
+ "tool_state": "{\"optional\": false}",
+ "tool_version": null,
+ "type": "data_input",
+ "uuid": "9de2716c-eecd-48fc-8a71-b3d1f5daef85",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "output",
+ "uuid": "8d7cef33-5fdc-481b-a0fd-542c42c6d032"
+ }
+ ]
+ },
+ "2": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_load_blast/load_blast/2.3.4+galaxy0",
+ "errors": null,
+ "id": 2,
+ "input_connections": {
+ "input": {
+ "id": 0,
+ "output_name": "output"
+ }
+ },
+ "inputs": [
+ {
+ "description": "runtime parameter for tool Chado load Blast results",
+ "name": "analysis_id"
+ },
+ {
+ "description": "runtime parameter for tool Chado load Blast results",
+ "name": "input"
+ },
+ {
+ "description": "runtime parameter for tool Chado load Blast results",
+ "name": "organism_id"
+ },
+ {
+ "description": "runtime parameter for tool Chado load Blast results",
+ "name": "wait_for"
+ }
+ ],
+ "label": "load blast results org1",
+ "name": "Chado load Blast results",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "json"
+ }
+ ],
+ "position": {
+ "bottom": 361.3999938964844,
+ "height": 164.39999389648438,
+ "left": 528,
+ "right": 728,
+ "top": 197,
+ "width": 200,
+ "x": 528,
+ "y": 197
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_load_blast/load_blast/2.3.4+galaxy0",
+ "tool_shed_repository": {
+ "changeset_revision": "08ae8b27b193",
+ "name": "chado_load_blast",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"analysis_id\": {\"__class__\": \"RuntimeValue\"}, \"blastdb_id\": \"21\", \"input\": {\"__class__\": \"RuntimeValue\"}, \"match_on_name\": \"false\", \"organism_id\": {\"__class__\": \"RuntimeValue\"}, \"psql_target\": {\"method\": \"remote\", \"__current_case__\": 0}, \"query_type\": \"polypeptide\", \"re_name\": \"\", \"skip_missing\": \"false\", \"wait_for\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": "2.3.4+galaxy0",
+ "type": "tool",
+ "uuid": "595f6e1f-955a-42be-b03b-1269d1f7d189",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "results",
+ "uuid": "c0ad63b8-045e-4a7c-97ba-8bc45862550b"
+ }
+ ]
+ },
+ "3": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_load_blast/load_blast/2.3.4+galaxy0",
+ "errors": null,
+ "id": 3,
+ "input_connections": {
+ "input": {
+ "id": 1,
+ "output_name": "output"
+ }
+ },
+ "inputs": [
+ {
+ "description": "runtime parameter for tool Chado load Blast results",
+ "name": "input"
+ },
+ {
+ "description": "runtime parameter for tool Chado load Blast results",
+ "name": "wait_for"
+ }
+ ],
+ "label": "load blast results org2",
+ "name": "Chado load Blast results",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "json"
+ }
+ ],
+ "position": {
+ "bottom": 545.3999938964844,
+ "height": 164.39999389648438,
+ "left": 591,
+ "right": 791,
+ "top": 381,
+ "width": 200,
+ "x": 591,
+ "y": 381
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_load_blast/load_blast/2.3.4+galaxy0",
+ "tool_shed_repository": {
+ "changeset_revision": "08ae8b27b193",
+ "name": "chado_load_blast",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"analysis_id\": \"1\", \"blastdb_id\": \"1\", \"input\": {\"__class__\": \"RuntimeValue\"}, \"match_on_name\": \"false\", \"organism_id\": \"2\", \"psql_target\": {\"method\": \"remote\", \"__current_case__\": 0}, \"query_type\": \"polypeptide\", \"re_name\": \"\", \"skip_missing\": \"false\", \"wait_for\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": "2.3.4+galaxy0",
+ "type": "tool",
+ "uuid": "5d08ed84-681b-431c-92c9-3b2fd5f32176",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "results",
+ "uuid": "6ed0a7c4-5b78-4016-8c21-0aaa992acd11"
+ }
+ ]
+ },
+ "4": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_analysis_sync/analysis_sync/3.2.1.0",
+ "errors": null,
+ "id": 4,
+ "input_connections": {
+ "wait_for": {
+ "id": 2,
+ "output_name": "results"
+ }
+ },
+ "inputs": [
+ {
+ "description": "runtime parameter for tool Synchronize an analysis",
+ "name": "analysis_id"
+ }
+ ],
+ "label": "sync blast analysis org1",
+ "name": "Synchronize an analysis",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "json"
+ }
+ ],
+ "position": {
+ "bottom": 360.3999938964844,
+ "height": 154.39999389648438,
+ "left": 858,
+ "right": 1058,
+ "top": 206,
+ "width": 200,
+ "x": 858,
+ "y": 206
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_analysis_sync/analysis_sync/3.2.1.0",
+ "tool_shed_repository": {
+ "changeset_revision": "f487ff676088",
+ "name": "tripal_analysis_sync",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"analysis_id\": {\"__class__\": \"RuntimeValue\"}, \"wait_for\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": "3.2.1.0",
+ "type": "tool",
+ "uuid": "99e7496d-ac32-467d-8c09-2efd48d0231a",
+ "workflow_outputs": [
+ {
+ "label": "Synchronize Analysis into Tripal",
+ "output_name": "results",
+ "uuid": "9792ea7a-0b4d-4355-9ce6-db2ba1ed36e9"
+ }
+ ]
+ },
+ "5": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_analysis_sync/analysis_sync/3.2.1.0",
+ "errors": null,
+ "id": 5,
+ "input_connections": {
+ "wait_for": {
+ "id": 3,
+ "output_name": "results"
+ }
+ },
+ "inputs": [],
+ "label": "sync blast analysis org2",
+ "name": "Synchronize an analysis",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "json"
+ }
+ ],
+ "position": {
+ "bottom": 545.3999938964844,
+ "height": 154.39999389648438,
+ "left": 899,
+ "right": 1099,
+ "top": 391,
+ "width": 200,
+ "x": 899,
+ "y": 391
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_analysis_sync/analysis_sync/3.2.1.0",
+ "tool_shed_repository": {
+ "changeset_revision": "f487ff676088",
+ "name": "tripal_analysis_sync",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"analysis_id\": \"1\", \"wait_for\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": "3.2.1.0",
+ "type": "tool",
+ "uuid": "99f68436-37c7-409a-bcf0-70bde40a9a8e",
+ "workflow_outputs": [
+ {
+ "label": "Synchronize Analysis into Tripal",
+ "output_name": "results",
+ "uuid": "ce2c98b7-17f2-4646-a3bf-784af0103f4e"
+ }
+ ]
+ },
+ "6": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_db_populate_mviews/db_populate_mviews/3.2.1.0",
+ "errors": null,
+ "id": 6,
+ "input_connections": {
+ "wait_for": {
+ "id": 5,
+ "output_name": "results"
+ }
+ },
+ "inputs": [],
+ "label": "populate mat views",
+ "name": "Populate materialized views",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "txt"
+ }
+ ],
+ "position": {
+ "bottom": 474.3999938964844,
+ "height": 154.39999389648438,
+ "left": 1174,
+ "right": 1374,
+ "top": 320,
+ "width": 200,
+ "x": 1174,
+ "y": 320
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_db_populate_mviews/db_populate_mviews/3.2.1.0",
+ "tool_shed_repository": {
+ "changeset_revision": "3c08f32a3dc1",
+ "name": "tripal_db_populate_mviews",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"mview\": \"\", \"wait_for\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": "3.2.1.0",
+ "type": "tool",
+ "uuid": "5c947dd5-89df-4146-9ab8-9e1d6de42360",
+ "workflow_outputs": [
+ {
+ "label": "Populate Tripal materialized view(s)",
+ "output_name": "results",
+ "uuid": "31970b1e-e567-4994-b05e-31d3406ebdf3"
+ }
+ ]
+ },
+ "7": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_db_index/db_index/3.2.1.1",
+ "errors": null,
+ "id": 7,
+ "input_connections": {
+ "wait_for": {
+ "id": 6,
+ "output_name": "results"
+ }
+ },
+ "inputs": [],
+ "label": "index tripal data",
+ "name": "Index Tripal data",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "txt"
+ }
+ ],
+ "position": {
+ "bottom": 454.6000061035156,
+ "height": 113.60000610351562,
+ "left": 1444,
+ "right": 1644,
+ "top": 341,
+ "width": 200,
+ "x": 1444,
+ "y": 341
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_db_index/db_index/3.2.1.1",
+ "tool_shed_repository": {
+ "changeset_revision": "d55a39f12dda",
+ "name": "tripal_db_index",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"expose\": {\"do_expose\": \"no\", \"__current_case__\": 0}, \"queues\": \"10\", \"table\": {\"mode\": \"website\", \"__current_case__\": 0}, \"tokenizer\": \"standard\", \"wait_for\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": "3.2.1.1",
+ "type": "tool",
+ "uuid": "5ecc30b0-07ab-4f9b-81f0-31310358c221",
+ "workflow_outputs": [
+ {
+ "label": "Index Tripal data",
+ "output_name": "results",
+ "uuid": "c4398cf0-10ca-45c7-ab62-9854b7519ecb"
+ }
+ ]
+ }
+ },
+ "tags": [],
+ "uuid": "1219fcfa-e57c-437e-ac5e-4d803e3dafd9",
+ "version": 5
+}
\ No newline at end of file
--
GitLab