diff --git a/gga_get_data.py b/gga_get_data.py
index 6ff524b29333ee5470ce146b54976e6e3d448c5a..20ec80d37f1b1449fd216ae616d8f594976e952a 100755
--- a/gga_get_data.py
+++ b/gga_get_data.py
@@ -122,14 +122,14 @@ class GetData(speciesData.SpeciesData):
# Where to store blast results?
# search_excluded_datasets = ["interpro_path", "orthofinder_path", "blastp_path", "blastx_path"]
- # # These datasets will not be searched if missing in the input file
+ # These datasets will not be searched if missing in the input file
# Copy datasets in the organism src_data dir tree correct folder
for k, v in datasets_to_get.items():
if v: # If dataset is not present in input file, skip copy
if k in genome_datasets:
logging.info("Copying {0} ({1}) into {2}".format(k, v, organism_genome_dir))
- genome_fname = "v%s.fasta" % self.genome_version
+ genome_fname = "{0}_v{1}.fasta".format(self.dataset_prefix, self.genome_version)
try:
shutil.copyfile(os.path.abspath(v), os.path.join(organism_genome_dir, genome_fname))
except Exception as exc:
@@ -137,19 +137,19 @@ class GetData(speciesData.SpeciesData):
elif k in annotation_datasets:
dataset_fname = ""
if k == "gff_path":
- dataset_fname = "OGS%s.gff" % self.ogs_version
+ dataset_fname = "{0}_OGS{1}.gff".format(self.dataset_prefix, self.ogs_version)
elif k == "transcripts_path":
- dataset_fname = "OGS%s_transcripts.fasta" % self.ogs_version
+ dataset_fname = "{0}_OGS{1}_transcripts.fasta".format(self.dataset_prefix, self.ogs_version)
elif k == "proteins_path":
- dataset_fname = "OGS%s_proteins.fasta" % self.ogs_version
+ dataset_fname = "{0}_OGS{1}_proteins.fasta".format(self.dataset_prefix, self.ogs_version)
elif k == "orthofinder_path":
- dataset_fname = "OGS%s_orthofinder.tsv" % self.ogs_version
+ dataset_fname = "{0}_OGS{1}_orthofinder.tsv".format(self.dataset_prefix, self.ogs_version)
elif k == "interpro_path":
- dataset_fname = "OGS%s_interproscan.xml" % self.ogs_version
+ dataset_fname = "{0}_OGS{1}_interproscan.xml".format(self.dataset_prefix, self.ogs_version)
elif k == "blastp_path":
- dataset_fname = "OGS%s_blastp.xml" % self.ogs_version
+ dataset_fname = "{0}_OGS{1}_blastp.xml".format(self.dataset_prefix, self.ogs_version)
elif k == "blastx_path":
- dataset_fname = "OGS%s_blastx.xml" % self.ogs_version
+ dataset_fname = "{0}_OGS{1}_blastx.xml".format(self.dataset_prefix, self.ogs_version)
logging.info("Copying {0} ({1}) into {2}".format(k, v, organism_annotation_dir))
try:
shutil.copyfile(os.path.abspath(v), os.path.join(organism_annotation_dir, dataset_fname))
diff --git a/gga_init.py b/gga_init.py
index fbefcebd1c2ce145db1270455cb8518ce3dd47a9..bd1beb4e7ebed69a7945fb0e8ed58a4545bf3483 100755
--- a/gga_init.py
+++ b/gga_init.py
@@ -64,8 +64,9 @@ class DeploySpeciesStack(speciesData.SpeciesData):
if not config["banner_path"] == "" and os.path.isfile(os.path.abspath(config["banner_path"])):
banner_dest_path = os.path.abspath("./banner.png")
logging.info("Custom banner path: %s" % self.config["banner_path"])
- if os.path.samefile(os.path.abspath(config["banner_path"]),banner_dest_path):
- shutil.copy(os.path.abspath(self.config["banner_path"]), banner_dest_path)
+ # if os.path.samefile(os.path.abspath(config["banner_path"]), banner_dest_path):
+ # shutil.copy(os.path.abspath(self.config["banner_path"]), banner_dest_path)
+ shutil.copy(os.path.abspath(self.config["banner_path"]), banner_dest_path)
else:
logging.debug("Using default banner for Tripal pages")
self.config.pop("banner_path", None)
diff --git a/gga_load_data.py b/gga_load_data.py
index 856d0435c2319bd7575b81089da7586159702f73..c4ed5594a9d3d173bd11d4ee4918a1152cd6a5ca 100755
--- a/gga_load_data.py
+++ b/gga_load_data.py
@@ -59,20 +59,18 @@ class LoadData(speciesData.SpeciesData):
"""
Create or set the working history to the current species one
- TODO - move to utilities?
-
:return:
"""
try:
- histories = self.instance.histories.get_histories(name=str(self.full_name))
+ histories = self.instance.histories.get_histories(name=str(self.genus_species))
self.history_id = histories[0]["id"]
- logging.info("History for {0}: {1}".format(self.full_name, self.history_id))
+ logging.debug("History ID set for {0} {1}: {2}".format(self.genus, self.species, self.history_id))
except IndexError:
- logging.info("Creating history for %s" % self.full_name)
- self.instance.histories.create_history(name=str(self.full_name))
- histories = self.instance.histories.get_histories(name=str(self.full_name))
+ logging.info("Creating history for {0} {1}".format(self.genus, self.species))
+ self.instance.histories.create_history(name=str(self.genus_species))
+ histories = self.instance.histories.get_histories(name=str(self.genus_species))
self.history_id = histories[0]["id"]
- logging.info("History for {0}: {1}".format(self.full_name, self.history_id))
+ logging.debug("History ID set for {0} {1}: {2}".format(self.genus, self.species, self.history_id))
return self.history_id
@@ -82,9 +80,16 @@ class LoadData(speciesData.SpeciesData):
Will do nothing if H. sapiens isn't in the database
"""
+
+ 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")
+ delete_organism_tool = self.instance.tools.show_tool("toolshed.g2.bx.psu.edu/repos/gga/chado_organism_delete_organisms/organism_delete_organisms/2.3.4+galaxy0")
+
+ get_organism_tool_version = get_organism_tool["version"]
+ delete_organism_tool_version = delete_organism_tool["version"]
+
logging.debug("Getting 'Homo sapiens' ID in instance's chado database")
get_sapiens_id_job = self.instance.tools.run_tool(
- tool_id="toolshed.g2.bx.psu.edu/repos/gga/chado_organism_get_organisms/organism_get_organisms/2.3.4+galaxy0",
+ tool_id="toolshed.g2.bx.psu.edu/repos/gga/chado_organism_get_organisms/organism_get_organisms/%s" % get_organism_tool_version,
history_id=self.history_id,
tool_inputs={"genus": "Homo", "species": "sapiens"})
get_sapiens_id_job_output = get_sapiens_id_job["outputs"][0]["id"]
@@ -95,7 +100,7 @@ class LoadData(speciesData.SpeciesData):
sapiens_id = str(
get_sapiens_id_final_output["organism_id"]) # needs to be str to be recognized by the chado tool
self.instance.tools.run_tool(
- tool_id="toolshed.g2.bx.psu.edu/repos/gga/chado_organism_delete_organisms/organism_delete_organisms/2.3.4+galaxy0",
+ tool_id="toolshed.g2.bx.psu.edu/repos/gga/chado_organism_delete_organisms/organism_delete_organisms/%s" % delete_organism_tool_version,
history_id=self.history_id,
tool_inputs={"organism": str(sapiens_id)})
except bioblend.ConnectionError:
@@ -386,9 +391,9 @@ if __name__ == "__main__":
load_data_for_current_species.connect_to_instance()
# Load the datasets into a galaxy library
- logging.info("Setting up library for %s" % load_data_for_current_species.full_name)
+ logging.info("Setting up library for {0} {1}".format(load_data_for_current_species.genus, load_data_for_current_species.species))
load_data_for_current_species.setup_library()
- logging.info("Successfully set up library in galaxy for %s" % load_data_for_current_species.full_name)
+ logging.info("Successfully set up library in galaxy for {0} {1}".format(load_data_for_current_species.genus, load_data_for_current_species.species))
# Set or get the history for the current organism
load_data_for_current_species.set_get_history()
@@ -402,8 +407,8 @@ if __name__ == "__main__":
# load_data_for_current_species.purge_histories() # Testing purposes
- logging.info("Data successfully loaded and imported for %s" % load_data_for_current_species.full_name)
+ logging.info("Data successfully loaded and imported for {0} {1}".format(load_data_for_current_species.genus, load_data_for_current_species.species))
else:
- logging.critical("The galaxy container for %s is not ready yet!" % load_data_for_current_species.full_name)
+ logging.critical("The galaxy container for {0} {1} is not ready yet".format(load_data_for_current_species.genus, load_data_for_current_species.species))
sys.exit()
diff --git a/run_workflow_phaeoexplorer.py b/run_workflow_phaeoexplorer.py
index 49f3a2a9ba6ccab47bfd5e7118db987fee52d706..2c385d476ca128e949e9b9a1353c0679ed5d6958 100755
--- a/run_workflow_phaeoexplorer.py
+++ b/run_workflow_phaeoexplorer.py
@@ -38,17 +38,18 @@ class RunWorkflow(speciesData.SpeciesData):
"""
Create or set the working history to the current species one
-
:return:
"""
try:
- histories = self.instance.histories.get_histories(name=str(self.full_name))
+ histories = self.instance.histories.get_histories(name=str(self.genus_species))
self.history_id = histories[0]["id"]
+ logging.debug("History ID set for {0}: {1}".format(self.full_name, self.history_id))
except IndexError:
logging.info("Creating history for %s" % self.full_name)
self.instance.histories.create_history(name=str(self.full_name))
- histories = self.instance.histories.get_histories(name=str(self.full_name))
+ histories = self.instance.histories.get_histories(name=str(self.genus_species))
self.history_id = histories[0]["id"]
+ logging.debug("History ID set for {0}: {1}".format(self.full_name, self.history_id))
return self.history_id
@@ -114,7 +115,7 @@ class RunWorkflow(speciesData.SpeciesData):
"""
- logging.info("Connecting to the galaxy instance (%s)" % self.instance_url)
+ logging.debug("Connecting to the galaxy instance (%s)" % self.instance_url)
self.instance = galaxy.GalaxyInstance(url=self.instance_url,
email=self.config["galaxy_default_admin_email"],
password=self.config["galaxy_default_admin_password"]
@@ -127,53 +128,17 @@ class RunWorkflow(speciesData.SpeciesData):
logging.critical("Cannot connect to galaxy instance (%s) " % self.instance_url)
sys.exit()
else:
- logging.info("Successfully connected to galaxy instance (%s) " % self.instance_url)
+ logging.debug("Successfully connected to galaxy instance (%s) " % self.instance_url)
return 1
- def install_changesets_revisions_from_workflow(self, workflow_path):
- """
- Read a .ga file to extract the information about the different tools called.
- Check if every tool is installed via a "show_tool".
- If a tool is not installed (versions don't match), send a warning to the logger and install the required changeset (matching the tool version)
- Doesn't do anything if versions match
-
- :return:
- """
-
- logging.info("Validating that installed tools versions and changesets match workflow versions")
-
- # Load the workflow file (.ga) in a buffer
- with open(workflow_path, 'r') as ga_in_file:
-
- # Then store the decoded json dictionary
- workflow_dict = json.load(ga_in_file)
-
- # Look up every "step_id" looking for tools
- for k, v in workflow_dict["steps"].items():
- if v["tool_id"]:
- # Get the descriptive dictionary of the installed tool (using the tool id in the workflow)
- show_tool = self.instance.tools.show_tool(v["tool_id"])
+ def return_instance(self):
- # Check if an installed version matches the workflow tool version
- # (If it's not installed, the show_tool version returned will be a default version with the suffix "XXXX+0")
- if show_tool["version"] != v["tool_version"]:
- # If it doesn't match, proceed to install of the correct changeset revision
- print(show_tool)
- # logging.warning("Tool versions don't match for {0} (changeset installed: {1} | changeset required: {2}). Installing changeset revision {3}...".format(v["tool_shed_repository"]["name"], show_tool["changeset_revision"], v["tool_shed_repository"]["changeset_revision"], v["tool_shed_repository"]["changeset_revision"]))
- toolshed = "https://" + v["tool_shed_repository"]["tool_shed"]
- name = v["tool_shed_repository"]["name"]
- owner = v["tool_shed_repository"]["owner"]
- changeset_revision = v["tool_shed_repository"]["changeset_revision"]
- self.instance.toolshed.install_repository_revision(tool_shed_url=toolshed, name=name, owner=owner,
- changeset_revision=changeset_revision,
- install_tool_dependencies=True,
- install_repository_dependencies=False,
- install_resolver_dependencies=True)
+ return self.instance
+
- logging.info("Tools versions and changesets from workflow validated")
def install_changesets_revisions_for_individual_tools(self):
"""
@@ -189,21 +154,22 @@ class RunWorkflow(speciesData.SpeciesData):
logging.info("Validating installed individual tools versions and changesets")
# Verify that the add_organism and add_analysis versions are correct in the toolshed
- add_organism_tool = self.instance.tools.show_tool("toolshed.g2.bx.psu.edu/repos/gga/chado_organism_add_organism/organism_add_organism/2.3.3")
- add_analysis_tool = self.instance.tools.show_tool("toolshed.g2.bx.psu.edu/repos/gga/chado_analysis_add_analysis/analysis_add_analysis/2.3.3")
- get_organism_tool = self.instance.tools.show_tool("toolshed.g2.bx.psu.edu/repos/gga/chado_organism_get_organisms/organism_get_organisms/2.3.3")
- get_analysis_tool = self.instance.tools.show_tool("toolshed.g2.bx.psu.edu/repos/gga/chado_analysis_get_analyses/analysis_get_analyses/2.3.3")
+ add_organism_tool = self.instance.tools.show_tool("toolshed.g2.bx.psu.edu/repos/gga/chado_organism_add_organism/organism_add_organism/2.3.4+galaxy0")
+ add_analysis_tool = self.instance.tools.show_tool("toolshed.g2.bx.psu.edu/repos/gga/chado_analysis_add_analysis/analysis_add_analysis/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_analysis_tool = self.instance.tools.show_tool("toolshed.g2.bx.psu.edu/repos/gga/chado_analysis_get_analyses/analysis_get_analyses/2.3.4+galaxy0")
- # changeset for 2.3.3 has to be manually found because there is no way to get the wanted changeset of a non installed tool via bioblend
+ # changeset for 2.3.4+galaxy0 has to be manually found because there is no way to get the wanted changeset of a non installed tool via bioblend
# except for workflows (.ga) that already contain the changeset revisions inside the steps ids
- if get_organism_tool["version"] != "2.3.3":
- logging.warning("Changeset for %s is not installed" % toolshed_dict["name"])
- changeset_revision = "b07279b5f3bf"
+ if get_organism_tool["version"] != "2.3.4+galaxy0":
toolshed_dict = get_organism_tool["tool_shed_repository"]
+ logging.warning("Changeset for %s is not installed" % toolshed_dict["name"])
+ changeset_revision = "831229e6cda2"
name = toolshed_dict["name"]
owner = toolshed_dict["owner"]
toolshed = "https://" + toolshed_dict["tool_shed"]
+ logging.warning("Installing changeset revision {0} for {1}".format(changeset_revision, name))
self.instance.toolshed.install_repository_revision(tool_shed_url=toolshed, name=name, owner=owner,
changeset_revision=changeset_revision,
@@ -211,13 +177,14 @@ class RunWorkflow(speciesData.SpeciesData):
install_repository_dependencies=False,
install_resolver_dependencies=True)
- if get_analysis_tool["version"] != "2.3.3":
- logging.warning("Changeset for %s is not installed" % toolshed_dict["name"])
- changeset_revision = "c7be2feafd73"
+ if get_analysis_tool["version"] != "2.3.4+galaxy0":
toolshed_dict = changeset_revision["tool_shed_repository"]
+ logging.warning("Changeset for %s is not installed" % toolshed_dict["name"])
+ changeset_revision = "a867923f555e"
name = toolshed_dict["name"]
owner = toolshed_dict["owner"]
toolshed = "https://" + toolshed_dict["tool_shed"]
+ logging.warning("Installing changeset revision {0} for {1}".format(changeset_revision, name))
self.instance.toolshed.install_repository_revision(tool_shed_url=toolshed, name=name, owner=owner,
changeset_revision=changeset_revision,
@@ -225,13 +192,14 @@ class RunWorkflow(speciesData.SpeciesData):
install_repository_dependencies=False,
install_resolver_dependencies=True)
- if add_organism_tool["version"] != "2.3.3":
- logging.warning("Changeset for %s is not installed" % toolshed_dict["name"])
- changeset_revision = "680a1fe3c266"
+ if add_organism_tool["version"] != "2.3.4+galaxy0":
toolshed_dict = add_organism_tool["tool_shed_repository"]
+ logging.warning("Changeset for %s is not installed" % toolshed_dict["name"])
+ changeset_revision = "1f12b9650028"
name = toolshed_dict["name"]
owner = toolshed_dict["owner"]
toolshed = "https://" + toolshed_dict["tool_shed"]
+ logging.warning("Installing changeset revision {0} for {1}".format(changeset_revision, name))
self.instance.toolshed.install_repository_revision(tool_shed_url=toolshed, name=name, owner=owner,
changeset_revision=changeset_revision,
@@ -239,14 +207,15 @@ class RunWorkflow(speciesData.SpeciesData):
install_repository_dependencies=False,
install_resolver_dependencies=True)
- if add_analysis_tool["version"] != "2.3.3":
- logging.warning("Changeset for %s is not installed" % toolshed_dict["name"])
- changeset_revision = "43c36801669f"
+ if add_analysis_tool["version"] != "2.3.4+galaxy0":
toolshed_dict = add_analysis_tool["tool_shed_repository"]
+ logging.warning("Changeset for %s is not installed" % toolshed_dict["name"])
+ changeset_revision = "10b2b1c70e69"
name = toolshed_dict["name"]
owner = toolshed_dict["owner"]
toolshed = "https://" + toolshed_dict["tool_shed"]
- logging.warning("Installing changeset revision %s for add_analysis" % changeset_revision)
+ logging.warning("Installing changeset revision {0} for {1}".format(changeset_revision, name))
+
self.instance.toolshed.install_repository_revision(tool_shed_url=toolshed, name=name, owner=owner,
changeset_revision=changeset_revision,
install_tool_dependencies=True,
@@ -281,120 +250,111 @@ class RunWorkflow(speciesData.SpeciesData):
self.connect_to_instance()
self.set_get_history()
- # We want the tools version default to be 2.3.3 at the moment
- tool_version = "2.3.3"
- # Add organism (species) to chado
- logging.info("Adding organism to the instance's chado database")
- if self.common == "" or self.common is None:
- 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})
- else:
- 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})
+ tool_version = "2.3.4+galaxy0"
- # Add OGS analysis to chado
- logging.info("Adding OGS 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/%s" % tool_version,
- history_id=self.history_id,
- tool_inputs={"name": 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})
+ 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")
- # Add genome analysis to chado
- logging.info("Adding genome 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/%s" % tool_version,
+ 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={"name": self.full_name_lowercase + " genome v" + self.genome_version,
- "program": "Performed by Genoscope",
- "programversion": str(self.sex + "genome v" + self.genome_version),
- "sourcename": "Genoscope",
- "date_executed": self.date})
+ tool_inputs={})
- # # TODO: check output of get_organism --> if empty or wrong --> rerun --> else: go next
- # # Get organism and analyses IDs (runtime inputs for workflow)
- # time.sleep(3)
- # # Get the ID for the current organism in chado
- # org = 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={"abbr": self.abbreviation,
- # "genus": self.genus_uppercase,
- # "species": self.chado_species_name,
- # "common": self.common})
-
- # time.sleep(3)
- # # Run tool again (sometimes the tool doesn't return anything despite the organism already being in the db)
- # org = 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={"abbr": self.abbreviation,
- # "genus": self.genus_uppercase,
- # "species": self.chado_species_name,
- # "common": self.common})
-
- # org_job_out = org["outputs"][0]["id"]
- # org_json_output = self.instance.datasets.download_dataset(dataset_id=org_job_out)
- # try:
- # org_output = json.loads(org_json_output)[0]
- # self.org_id = str(org_output["organism_id"]) # id needs to be a str to be recognized by chado tools
- # except IndexError:
- # logging.critical("No organism matching " + self.full_name + " exists in the instance's chado database")
- # sys.exit()
-
-
- def get_genome_analysis_id(self):
- """
- """
+ 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
- # Get the ID for the genome analysis in chado
- genome_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": self.full_name_lowercase + " genome v" + self.genome_version})
- genome_analysis_job_out = genome_analysis["outputs"][0]["id"]
- genome_analysis_json_output = self.instance.datasets.download_dataset(dataset_id=genome_analysis_job_out)
- try:
- genome_analysis_output = json.loads(genome_analysis_json_output)[0]
- self.genome_analysis_id = str(genome_analysis_output["analysis_id"])
- except IndexError as exc:
- logging.critical("no matching genome analysis exists in the instance's chado database")
- sys.exit(exc)
+ org_id = None
- return self.genome_analysis_id
+ # 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)
- def get_ogs_analysis_id(self):
- """
- """
- # Get the ID for the OGS analysis in chado
- ogs_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",
+ 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={"name": self.full_name_lowercase + " OGS" + self.ogs_version})
- ogs_analysis_job_out = ogs_analysis["outputs"][0]["id"]
- ogs_analysis_json_output = self.instance.datasets.download_dataset(dataset_id=ogs_analysis_job_out)
- try:
- ogs_analysis_output = json.loads(ogs_analysis_json_output)[0]
- self.ogs_analysis_id = str(ogs_analysis_output["analysis_id"])
- except IndexError as exc:
- logging.critical("No matching OGS analysis exists in the instance's chado database")
- sys.exit(exc)
+ 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)
+
+ ogs_analysis_id = None
+ genome_analysis_id = None
+
+ # Look up list of outputs (dictionaries)
+ for analysis_output_dict in analysis_output:
+ if analysis_output_dict["name"] == self.full_name_lowercase + " OGS" + self.ogs_version:
+ ogs_analysis_id = str(analysis_output_dict["analysis_id"])
+ if analysis_output_dict["name"] == self.full_name_lowercase + " genome v" + self.genome_version:
+ genome_analysis_id = str(analysis_output_dict["analysis_id"])
- return self.ogs_analysis_id
+
+ if ogs_analysis_id is None:
+ add_ogs_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": 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_ogs_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)
+ ogs_analysis_id = str(analysis_output["analysis_id"])
+
+ if genome_analysis_id is None:
+ add_genome_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": self.full_name_lowercase + " genome v" + self.genome_version,
+ "program": "Performed by Genoscope",
+ "programversion": str(self.sex + "genome v" + self.genome_version),
+ "sourcename": "Genoscope",
+ "date_executed": self.date})
+ analysis_outputs = add_genome_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)
+ genome_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, "genome_analysis_id": genome_analysis_id, "ogs_analysis_id": ogs_analysis_id})
def add_interproscan_analysis(self):
@@ -404,7 +364,7 @@ class RunWorkflow(speciesData.SpeciesData):
# Add Interpro analysis to chado
logging.info("Adding Interproscan 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",
+ tool_id="toolshed.g2.bx.psu.edu/repos/gga/chado_analysis_add_analysis/analysis_add_analysis/2.3.4+galaxy0",
history_id=self.history_id,
tool_inputs={"name": "InterproScan on OGS%s" % self.ogs_version,
"program": "InterproScan",
@@ -419,7 +379,7 @@ class RunWorkflow(speciesData.SpeciesData):
# Get interpro ID
interpro_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",
+ tool_id="toolshed.g2.bx.psu.edu/repos/gga/chado_analysis_get_analyses/analysis_get_analyses/2.3.4+galaxy0",
history_id=self.history_id,
tool_inputs={"name": "InterproScan on OGS%s" % self.ogs_version})
interpro_analysis_job_out = interpro_analysis["outputs"][0]["id"]
@@ -546,16 +506,6 @@ class RunWorkflow(speciesData.SpeciesData):
return invocation_report
-
-
- def get_datasets_ldda_ids(self):
- """
- Get and return the ldda_ids (and names) for the datasets in the library
- """
-
- return 0
-
-
def import_datasets_into_history(self):
"""
Find datasets in a library, get their ID and import them into the current history if they are not already
@@ -580,19 +530,16 @@ class RunWorkflow(speciesData.SpeciesData):
for i in instance_source_data_folders:
folders_ids[i["name"]] = i["id"]
-
# Iterating over the folders to find datasets and map datasets to their IDs
- logging.debug("Datasets IDs: ")
for k, v in folders_ids.items():
if k == "/genome/{0}/v{1}".format(self.species_folder_name, self.genome_version):
sub_folder_content = self.instance.folders.show_folder(folder_id=v, contents=True)
for k2, v2 in sub_folder_content.items():
for e in v2:
if type(e) == dict:
- if e["name"].endswith(".fa"):
+ if e["name"].endswith(".fasta"):
self.datasets["genome_file"] = e["ldda_id"]
self.datasets_name["genome_file"] = e["name"]
- logging.debug("\tGenome file:\t" + e["name"] + ": " + e["ldda_id"])
if k == "/annotation/{0}/OGS{1}".format(self.species_folder_name, self.ogs_version):
sub_folder_content = self.instance.folders.show_folder(folder_id=v, contents=True)
@@ -600,56 +547,85 @@ class RunWorkflow(speciesData.SpeciesData):
for e in v2:
if type(e) == dict:
if "transcripts" in e["name"]:
+ # the attributes datasets is set in the function get_instance_attributes()
self.datasets["transcripts_file"] = e["ldda_id"]
self.datasets_name["transcripts_file"] = e["name"]
- logging.debug("\tTranscripts file:\t" + e["name"] + ": " + e["ldda_id"])
elif "proteins" in e["name"]:
self.datasets["proteins_file"] = e["ldda_id"]
self.datasets_name["proteins_file"] = e["name"]
- logging.debug("\tProteins file:\t" + e["name"] + ": " + e["ldda_id"])
elif "gff" in e["name"]:
self.datasets["gff_file"] = e["ldda_id"]
self.datasets_name["gff_file"] = e["name"]
- logging.debug("\tGFF file:\t" + e["name"] + ": " + e["ldda_id"])
elif "interpro" in e["name"]:
self.datasets["interproscan_file"] = e["ldda_id"]
self.datasets_name["interproscan_file"] = e["name"]
- logging.debug("\tInterproscan file:\t" + e["name"] + ": " + e["ldda_id"])
elif "blastp" in e["name"]:
self.datasets["blast_diamond_file"] = e["ldda_id"]
self.datasets_name["blast_diamond_file"] = e["name"]
- logging.debug("\tBlastp diamond file:\t" + e["name"] + ": " + e["ldda_id"])
- logging.debug("Uploading datasets into history %s" % self.history_id)
+
+ 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
+
+ # Finding datasets in history (matching datasets names)
+ for dataset in history_datasets_li:
+ dataset_name = dataset["name"]
+ dataset_id = dataset["id"]
+ if dataset_name == "{0}_v{1}.fasta".format(self.dataset_prefix, self.genome_version):
+ genome_hda_id = dataset_id
+ if dataset_name == "{0}_OGS{1}.gff".format(self.dataset_prefix, self.ogs_version):
+ gff_hda_id = dataset_id
+ if dataset_name == "{0}_OGS{1}_transcripts.fasta".format(self.dataset_prefix, self.ogs_version):
+ 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
+
+
# Import each dataset into history if it is not imported
+ logging.debug("Uploading datasets into history %s" % self.history_id)
- first_hda_ids = self.get_datasets_hda_ids()
-
- if first_hda_ids["genome_hda_id"] is None:
- self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=self.datasets["genome_file"])
- if first_hda_ids["gff_hda_id"] is None:
- self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=self.datasets["gff_file"])
- if first_hda_ids["transcripts_hda_id"] is None:
- self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=self.datasets["transcripts_file"])
- if first_hda_ids["proteins_hda_id"] is None:
- self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=self.datasets["proteins_file"])
- if first_hda_ids["interproscan_hda_id"] is None:
+ if genome_hda_id is None:
+ genome_dataset_upload = self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=self.datasets["genome_file"])
+ genome_hda_id = genome_dataset_upload["id"]
+ if gff_hda_id is None:
+ gff_dataset_upload = self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=self.datasets["gff_file"])
+ gff_hda_id = gff_dataset_upload["id"]
+ if transcripts_hda_id is None:
+ transcripts_dataset_upload = self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=self.datasets["transcripts_file"])
+ transcripts_hda_id = transcripts_dataset_upload["id"]
+ if proteins_hda_id is None:
+ proteins_dataset_upload = self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=self.datasets["proteins_file"])
+ proteins_hda_id = proteins_dataset_upload["id"]
+ if interproscan_hda_id is None:
try:
- self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=self.datasets["interproscan_file"])
+ interproscan_dataset_upload = self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=self.datasets["interproscan_file"])
+ 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 first_hda_ids["blast_diamond_hda_id"] is None:
+ if blast_diamond_hda_id is None:
try:
- self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=self.datasets["blast_diamond_file"])
+ 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"]
except Exception as exc:
logging.debug("Blastp file not found in library (history: {0})".format(self.history_id))
- # _datasets = self.instance.datasets.get_datasets()
- # with open(os.path.join(self.main_dir, "datasets_ids.json"), "w") as datasets_ids_outfile:
- # datasets_ids_outfile.write(str(_datasets))
+ 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})
# Return a dict made of the hda ids
- return self.get_datasets_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,
+ "interproscan_hda_id": interproscan_hda_id}
def get_datasets_hda_ids(self):
@@ -675,107 +651,229 @@ class RunWorkflow(speciesData.SpeciesData):
# Match files imported in history names vs library datasets names to assign their respective hda_id
for dataset_dict in history_datasets_li:
if dataset_dict["history_id"] == self.history_id:
- if dataset_dict["name"] == self.datasets_name["genome_file"]:
+ if dataset_dict["name"] == self.datasets_name["genome_file"] and dataset_dict["id"] not in imported_datasets_ids:
genome_dataset_hda_id = dataset_dict["id"]
- logging.debug("Genome dataset hda id: %s" % genome_dataset_hda_id)
- elif dataset_dict["name"] == self.datasets_name["proteins_file"]:
+ elif dataset_dict["name"] == self.datasets_name["proteins_file"] and dataset_dict["id"] not in imported_datasets_ids:
proteins_datasets_hda_id = dataset_dict["id"]
- logging.debug("Proteins dataset hda ID: %s" % proteins_datasets_hda_id)
- elif dataset_dict["name"] == self.datasets_name["transcripts_file"]:
+ elif dataset_dict["name"] == self.datasets_name["transcripts_file"] and dataset_dict["id"] not in imported_datasets_ids:
transcripts_dataset_hda_id = dataset_dict["id"]
- logging.debug("Transcripts dataset hda ID: %s" % transcripts_dataset_hda_id)
- elif dataset_dict["name"] == self.datasets_name["gff_file"]:
+ elif dataset_dict["name"] == self.datasets_name["gff_file"] and dataset_dict["id"] not in imported_datasets_ids:
gff_dataset_hda_id = dataset_dict["id"]
- logging.debug("GFF dataset hda ID: %s" % gff_dataset_hda_id)
-
if "interproscan_file" in self.datasets_name.keys():
- if dataset_dict["name"] == self.datasets_name["interproscan_file"]:
+ 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"]
- logging.debug("InterproScan dataset hda ID: %s" % gff_dataset_hda_id)
+
if "blast_diamond_file" in self.datasets_name.keys():
- if dataset_dict["name"] == self.datasets_name["blast_diamond_file"]:
+ 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"]
- logging.debug("Blast Diamond dataset hda ID: %s" % gff_dataset_hda_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)
+
+ # 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)
+ imported_datasets_ids.append(transcripts_dataset_hda_id)
+ 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)
# 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}
+ "blast_diamond_hda_id": blast_diamond_dataset_hda_id,
+ "imported_datasets_ids": imported_datasets_ids}
- def get_organism_id(self):
- """
- Retrieve current organism ID
- Will try to add it to Chado if the organism ID can't be found
- :return:
- """
+def run_workflow(workflow_path, workflow_parameters, datamap, config, input_species_number):
+ """
+ Run a workflow in galaxy
+ Requires the .ga file to be loaded as a dictionary (optionally could be uploaded as a raw file)
- tool_version = "2.3.3"
- time.sleep(3)
+ :param workflow_name:
+ :param workflow_parameters:
+ :param datamap:
+ :return:
+ """
- # # Get the ID for the current organism in chado
- # org = self.instance.tools.run_tool(
- # tool_id="toolshed.g2.bx.psu.edu/repos/gga/chado_organism_get_organisms/organism_get_organisms/2.3.3",
- # history_id=self.history_id,
- # tool_inputs={"abbr": self.abbreviation,
- # "genus": self.genus_uppercase,
- # "species": self.chado_species_name,
- # "common": self.common})
+ logging.info("Importing workflow %s" % str(workflow_path))
- # time.sleep(3)
+ # Load the workflow file (.ga) in a buffer
+ with open(workflow_path, 'r') as ga_in_file:
- # Run tool again (sometimes the tool doesn't return anything despite the organism already being in the db)
- org = self.instance.tools.run_tool(
- tool_id="toolshed.g2.bx.psu.edu/repos/gga/chado_organism_get_organisms/organism_get_organisms/2.3.3",
- history_id=self.history_id,
- tool_inputs={"abbr": self.abbreviation,
- "genus": self.genus_uppercase,
- "species": self.chado_species_name,
- "common": self.common})
+ # Then store the decoded json dictionary
+ workflow_dict = json.load(ga_in_file)
+
+ # In case of the Jbrowse workflow, we unfortunately have to manually edit the parameters instead of setting them
+ # as runtime values, using runtime parameters makes the tool throw an internal critical error ("replace not found" error)
+ # Scratchgmod test: need "http" (or "https"), the hostname (+ port)
+ if "menu_url" not in config.keys():
+ jbrowse_menu_url = "https://{hostname}/sp/{genus_sp}/feature/{Genus}/{species}/mRNA/{id}".format(hostname=self.config["hostname"], genus_sp=self.genus_species, Genus=self.genus_uppercase, species=self.species, id="{id}")
+ else:
+ jbrowse_menu_url = config["menu_url"]
+ if workflow_name == "Jbrowse":
+ workflow_dict["steps"]["2"]["tool_state"] = workflow_dict["steps"]["2"]["tool_state"].replace("__MENU_URL__", jbrowse_menu_url)
+ # The UNIQUE_ID is specific to a combination genus_species_strain_sex so every combination should have its unique workflow
+ # in galaxy --> define a naming method for these workflows
+ workflow_dict["steps"]["3"]["tool_state"] = workflow_dict["steps"]["3"]["tool_state"].replace("__FULL_NAME__", self.full_name).replace("__UNIQUE_ID__", self.species_folder_name)
+
+ # Import the workflow in galaxy as a dict
+ self.instance.workflows.import_workflow_dict(workflow_dict=workflow_dict)
- org_job_out = org["outputs"][0]["id"]
- org_json_output = self.instance.datasets.download_dataset(dataset_id=org_job_out)
+ # Get its attributes
+ workflow_attributes = self.instance.workflows.get_workflows(name=workflow_name)
+ # Then get its ID (required to invoke the workflow)
+ workflow_id = workflow_attributes[0]["id"] # Index 0 is the most recently imported workflow (the one we want)
+ show_workflow = self.instance.workflows.show_workflow(workflow_id=workflow_id)
+ # Check if the workflow is found
try:
- org_output = json.loads(org_json_output)[0]
- self.org_id = str(org_output["organism_id"]) # id needs to be a str to be recognized by chado tools
- except IndexError:
- logging.warning("No organism matching " + self.full_name + " exists in the instance's chado database, adding it")
- if self.common == "" or self.common is None:
- 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})
- else:
- 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})
- # Run tool again (sometimes the tool doesn't return anything despite the organism already being in the db)
- org = self.instance.tools.run_tool(
- tool_id="toolshed.g2.bx.psu.edu/repos/gga/chado_organism_get_organisms/organism_get_organisms/2.3.3",
- history_id=self.history_id,
- tool_inputs={"abbr": self.abbreviation,
- "genus": self.genus_uppercase,
- "species": self.chado_species_name,
- "common": self.common})
+ logging.debug("Workflow ID: %s" % workflow_id)
+ except bioblend.ConnectionError:
+ logging.warning("Error retrieving workflow attributes for workflow %s" % workflow_name)
- org_job_out = org["outputs"][0]["id"]
- org_json_output = self.instance.datasets.download_dataset(dataset_id=org_job_out)
- try:
- org_output = json.loads(org_json_output)[0]
- self.org_id = str(org_output["organism_id"]) # id needs to be a str to be recognized by chado tools
- except IndexError:
- logging.critical("Cannot add {0} as an organism in Chado, please check the galaxy instance {1}".format(self.full_name, self.instance_url))
- sys.exit()
+ # Finally, invoke the workflow alogn with its datamap, parameters and the history in which to invoke it
+ self.instance.workflows.invoke_workflow(workflow_id=workflow_id,
+ history_id=self.history_id,
+ params=workflow_parameters,
+ inputs=datamap,
+ allow_tool_state_corrections=True)
+
+ logging.info("Successfully imported and invoked workflow {0}, check the galaxy instance ({1}) for the jobs state".format(workflow_name, self.instance_url))
+
+
+
+
+def create_sp_workflow_dict(sp_dict, main_dir, config):
+ """
+ """
- return self.org_id
+ sp_workflow_dict = {}
+ run_workflow_for_current_organism = RunWorkflow(parameters_dictionary=sp_dict)
+
+ # Verifying the galaxy container is running
+ if utilities.check_galaxy_state(genus_lowercase=run_workflow_for_current_organism.genus_lowercase,
+ species=run_workflow_for_current_organism.species,
+ script_dir=run_workflow_for_current_organism.script_dir):
+
+ # Starting
+ logging.info("run_workflow.py called for %s" % run_workflow_for_current_organism.full_name)
+
+ # Setting some of the instance attributes
+ run_workflow_for_current_organism.main_dir = main_dir
+ run_workflow_for_current_organism.species_dir = os.path.join(run_workflow_for_current_organism.main_dir,
+ run_workflow_for_current_organism.genus_species +
+ "/")
+
+ # Parse the config yaml file
+ run_workflow_for_current_organism.config = config
+ # Set the instance url attribute --> TODO: the localhost rule in the docker-compose still doesn't work on scratchgmodv1
+ run_workflow_for_current_organism.instance_url = "http://localhost:{0}/sp/{1}_{2}/galaxy/".format(
+ run_workflow_for_current_organism.config["http_port"],
+ run_workflow_for_current_organism.genus_lowercase,
+ run_workflow_for_current_organism.species)
+
+
+ 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
+
+
+def install_changesets_revisions_from_workflow(instance, workflow_path):
+ """
+ Read a .ga file to extract the information about the different tools called.
+ Check if every tool is installed via a "show_tool".
+ If a tool is not installed (versions don't match), send a warning to the logger and install the required changeset (matching the tool version)
+ Doesn't do anything if versions match
+
+ :return:
+ """
+
+ logging.info("Validating that installed tools versions and changesets match workflow versions")
+
+ # Load the workflow file (.ga) in a buffer
+ with open(workflow_path, 'r') as ga_in_file:
+
+ # Then store the decoded json dictionary
+ workflow_dict = json.load(ga_in_file)
+
+ # Look up every "step_id" looking for tools
+ for k, v in workflow_dict["steps"].items():
+ if v["tool_id"]:
+ # Get the descriptive dictionary of the installed tool (using the tool id in the workflow)
+ show_tool = instance.tools.show_tool(v["tool_id"])
+ # Check if an installed version matches the workflow tool version
+ # (If it's not installed, the show_tool version returned will be a default version with the suffix "XXXX+0")
+ if show_tool["version"] != v["tool_version"]:
+ # If it doesn't match, proceed to install of the correct changeset revision
+ toolshed = "https://" + v["tool_shed_repository"]["tool_shed"]
+ name = v["tool_shed_repository"]["name"]
+ owner = v["tool_shed_repository"]["owner"]
+ changeset_revision = v["tool_shed_repository"]["changeset_revision"]
+
+ logging.warning("Installed tool versions for tool {0} do not match the version required by the specified workflow, installing changeset {1}".format(name, changeset_revision))
+
+ # Install changeset
+ instance.toolshed.install_repository_revision(tool_shed_url=toolshed, name=name, owner=owner,
+ changeset_revision=changeset_revision,
+ install_tool_dependencies=True,
+ install_repository_dependencies=False,
+ install_resolver_dependencies=True)
+ else:
+ toolshed = "https://" + v["tool_shed_repository"]["tool_shed"]
+ name = v["tool_shed_repository"]["name"]
+ owner = v["tool_shed_repository"]["owner"]
+ changeset_revision = v["tool_shed_repository"]["changeset_revision"]
+ logging.debug("Installed tool versions for tool {0} match the version in the specified workflow (changeset {1})".format(name, changeset_revision))
+
+ logging.info("Tools versions and changesets from workflow validated")
if __name__ == "__main__":
@@ -826,242 +924,624 @@ 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)
+
+
+ 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:
- # Creating an instance of the RunWorkflow object for the current organism
- run_workflow_for_current_organism = RunWorkflow(parameters_dictionary=sp_dict)
+ # 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)
- # Checking if user specified a workflow to run
- if not args.workflow:
- logging.critical("No workflow specified, exiting")
- sys.exit()
+ 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:
- workflow = os.path.abspath(args.workflow)
-
- # Verifying the galaxy container is running
- if utilities.check_galaxy_state(genus_lowercase=run_workflow_for_current_organism.genus_lowercase,
- species=run_workflow_for_current_organism.species,
- script_dir=run_workflow_for_current_organism.script_dir):
-
- # Starting
- logging.info("run_workflow.py called for %s" % run_workflow_for_current_organism.full_name)
-
- # Setting some of the instance attributes
- run_workflow_for_current_organism.main_dir = args.main_directory
- run_workflow_for_current_organism.species_dir = os.path.join(run_workflow_for_current_organism.main_dir,
- run_workflow_for_current_organism.genus_species +
- "/")
-
- # Parse the config yaml file
- run_workflow_for_current_organism.config = utilities.parse_config(args.config)
- # Set the instance url attribute --> TODO: the localhost rule in the docker-compose still doesn't work on scratchgmodv1
- run_workflow_for_current_organism.instance_url = "http://localhost:{0}/sp/{1}_{2}/galaxy/".format(
- run_workflow_for_current_organism.config["http_port"],
- run_workflow_for_current_organism.genus_lowercase,
- run_workflow_for_current_organism.species)
-
-
-
- # 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")
+ 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_v2.ga")
+
+ # 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)
+
+ # Set datamap (mapping of input files in the workflow)
+ datamap = {}
+
+
+ # Set the workflow parameters (individual tools runtime parameters in the workflow)
+ workflow_parameters = {}
+
+ 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()
+
+
+ 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"]
+ 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\}")
+
+
+ # 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)
- else:
- logging.critical("The galaxy container for %s is not ready yet!" % run_workflow_for_current_organism.full_name)
- sys.exit()
+ # 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))
+
+
+
+
+
+
+
+
+ # 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/speciesData.py b/speciesData.py
index 5d9ffc2a51abf5d4211232c9e6db09226729e286..a8637b01484de65a257f12eec6e5afacc406d014 100755
--- a/speciesData.py
+++ b/speciesData.py
@@ -39,11 +39,11 @@ class SpeciesData:
if parameters_dictionary["data"]["genome_version"] == "":
self.genome_version = "1.0"
else:
- self.genome_version = parameters_dictionary["data"]["genome_version"]
+ self.genome_version = str(parameters_dictionary["data"]["genome_version"])
if parameters_dictionary["data"]["ogs_version"] == "":
self.ogs_version = "1.0"
else:
- self.ogs_version = parameters_dictionary["data"]["ogs_version"]
+ self.ogs_version = str(parameters_dictionary["data"]["ogs_version"])
# TODO: catch blocks if key is absent in input
self.genome_path = parameters_dictionary["data"]["genome_path"]
@@ -66,18 +66,27 @@ class SpeciesData:
self.full_name_lowercase = self.full_name.lower()
self.abbreviation = "_".join(utilities.filter_empty_not_empty_items([self.genus_lowercase[0], self.species, self.strain, self.sex])["not_empty"])
- self.genus_species = self.genus_lowercase + "_" + self.species
+ self.genus_species = "{0}_{1}".format(self.genus.lower(), self.species.lower())
+ self.dataset_prefix = None
+ if self.sex is not None or self.sex != "":
+ self.dataset_prefix = self.genus[0].lower() + "_" + self.species.lower() + "_" + self.sex[0].lower()
+ else:
+ self.dataset_prefix = self.genus[0].lower() + "_" + self.species.lower()
+
+ # Bioblend/Chado IDs for an organism analyses/organisms/datasets/history/library
+ self.org_id = None
+ self.genome_analysis_id = None
+ self.ogs_analysis_id = None
self.instance_url = None
self.instance = None
self.history_id = None
self.library = None
self.library_id = None
+
self.script_dir = os.path.dirname(os.path.realpath(sys.argv[0]))
self.main_dir = None
self.species_dir = None
- self.org_id = None
- self.genome_analysis_id = None
- self.ogs_analysis_id = None
+
self.tool_panel = None
self.datasets = dict()
self.datasets_name = dict()
@@ -88,7 +97,9 @@ class SpeciesData:
self.datasets = dict()
self.config = None # Custom config used to set environment variables inside containers
self.species_folder_name = "_".join(utilities.filter_empty_not_empty_items([self.genus_lowercase.lower(), self.species.lower(), self.strain.lower(), self.sex.lower()])["not_empty"])
- self.species_folder_name = self.species_folder_name .replace("-", "_")
+ self.species_folder_name = self.species_folder_name .replace("-", "_").replace('__', '_').replace("(", "_").replace(")", "_")
+ if self.species_folder_name.endswith("_"):
+ self.species_folder_name = self.species_folder_name[0:-2]
self.existing_folders_cache = {}
self.bam_metadata_cache = {}
diff --git a/workflows_phaeoexplorer/Galaxy-Workflow-chado_load_tripal_synchronize_jbrowse_2org_v3.ga b/workflows_phaeoexplorer/Galaxy-Workflow-chado_load_tripal_synchronize_jbrowse_2org_v3.ga
new file mode 100644
index 0000000000000000000000000000000000000000..aa88764d3aba81740d81e0415838e148da4a372c
--- /dev/null
+++ b/workflows_phaeoexplorer/Galaxy-Workflow-chado_load_tripal_synchronize_jbrowse_2org_v3.ga
@@ -0,0 +1,907 @@
+{
+ "a_galaxy_workflow": "true",
+ "annotation": "",
+ "format-version": "0.1",
+ "name": "chado_load_tripal_synchronize_jbrowse_2org_v2",
+ "steps": {
+ "0": {
+ "annotation": "",
+ "content_id": null,
+ "errors": null,
+ "id": 0,
+ "input_connections": {},
+ "inputs": [
+ {
+ "description": "",
+ "name": "genome org1"
+ }
+ ],
+ "label": "genome org1",
+ "name": "Input dataset",
+ "outputs": [],
+ "position": {
+ "bottom": 204.8000030517578,
+ "height": 61.80000305175781,
+ "left": 215,
+ "right": 415,
+ "top": 143,
+ "width": 200,
+ "x": 215,
+ "y": 143
+ },
+ "tool_id": null,
+ "tool_state": "{\"optional\": false}",
+ "tool_version": null,
+ "type": "data_input",
+ "uuid": "59f823c8-fd7c-441c-84b6-21c367ba12f6",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "output",
+ "uuid": "95cc9784-0f9c-46df-9f62-4c342f6695e7"
+ }
+ ]
+ },
+ "1": {
+ "annotation": "",
+ "content_id": null,
+ "errors": null,
+ "id": 1,
+ "input_connections": {},
+ "inputs": [
+ {
+ "description": "",
+ "name": "annotations org1"
+ }
+ ],
+ "label": "annotations org1",
+ "name": "Input dataset",
+ "outputs": [],
+ "position": {
+ "bottom": 294.8000030517578,
+ "height": 61.80000305175781,
+ "left": 214,
+ "right": 414,
+ "top": 233,
+ "width": 200,
+ "x": 214,
+ "y": 233
+ },
+ "tool_id": null,
+ "tool_state": "{\"optional\": false}",
+ "tool_version": null,
+ "type": "data_input",
+ "uuid": "c82b756f-2ef5-41d5-9e14-eb9a7ef942c7",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "output",
+ "uuid": "b67afacf-2d88-49f6-af15-02500f0ddc90"
+ }
+ ]
+ },
+ "2": {
+ "annotation": "",
+ "content_id": null,
+ "errors": null,
+ "id": 2,
+ "input_connections": {},
+ "inputs": [
+ {
+ "description": "",
+ "name": "proteins org1"
+ }
+ ],
+ "label": "proteins org1",
+ "name": "Input dataset",
+ "outputs": [],
+ "position": {
+ "bottom": 389.8000030517578,
+ "height": 61.80000305175781,
+ "left": 215,
+ "right": 415,
+ "top": 328,
+ "width": 200,
+ "x": 215,
+ "y": 328
+ },
+ "tool_id": null,
+ "tool_state": "{\"optional\": false}",
+ "tool_version": null,
+ "type": "data_input",
+ "uuid": "0a0ac416-68b8-4c48-980e-04c6230c721e",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "output",
+ "uuid": "cc50348e-1372-406e-9b3e-d2cacfea81b2"
+ }
+ ]
+ },
+ "3": {
+ "annotation": "",
+ "content_id": null,
+ "errors": null,
+ "id": 3,
+ "input_connections": {},
+ "inputs": [
+ {
+ "description": "",
+ "name": "genome org2"
+ }
+ ],
+ "label": "genome org2",
+ "name": "Input dataset",
+ "outputs": [],
+ "position": {
+ "bottom": 479.8000030517578,
+ "height": 61.80000305175781,
+ "left": 214,
+ "right": 414,
+ "top": 418,
+ "width": 200,
+ "x": 214,
+ "y": 418
+ },
+ "tool_id": null,
+ "tool_state": "{\"optional\": false}",
+ "tool_version": null,
+ "type": "data_input",
+ "uuid": "ddd5f0f8-9e14-42f0-a866-2971d02e5435",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "output",
+ "uuid": "0f63af8f-7c12-4c7a-a491-4f55f65fff4e"
+ }
+ ]
+ },
+ "4": {
+ "annotation": "",
+ "content_id": null,
+ "errors": null,
+ "id": 4,
+ "input_connections": {},
+ "inputs": [
+ {
+ "description": "",
+ "name": "annotations org2"
+ }
+ ],
+ "label": "annotations org2",
+ "name": "Input dataset",
+ "outputs": [],
+ "position": {
+ "bottom": 573.8000030517578,
+ "height": 61.80000305175781,
+ "left": 216,
+ "right": 416,
+ "top": 512,
+ "width": 200,
+ "x": 216,
+ "y": 512
+ },
+ "tool_id": null,
+ "tool_state": "{\"optional\": false}",
+ "tool_version": null,
+ "type": "data_input",
+ "uuid": "c7f3b553-5cd2-46e6-a792-e864ab0d2459",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "output",
+ "uuid": "e5ec0e3f-c56a-4c4c-b905-26b7e85808d3"
+ }
+ ]
+ },
+ "5": {
+ "annotation": "",
+ "content_id": null,
+ "errors": null,
+ "id": 5,
+ "input_connections": {},
+ "inputs": [
+ {
+ "description": "",
+ "name": "proteins org2"
+ }
+ ],
+ "label": "proteins org2",
+ "name": "Input dataset",
+ "outputs": [],
+ "position": {
+ "bottom": 663.8000030517578,
+ "height": 61.80000305175781,
+ "left": 217,
+ "right": 417,
+ "top": 602,
+ "width": 200,
+ "x": 217,
+ "y": 602
+ },
+ "tool_id": null,
+ "tool_state": "{\"optional\": false}",
+ "tool_version": null,
+ "type": "data_input",
+ "uuid": "b5b82a8a-f73c-4183-bc0a-6956e5ad9d0a",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "output",
+ "uuid": "92d17a84-9137-4437-add9-5b3e551bb6b2"
+ }
+ ]
+ },
+ "6": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_feature_load_fasta/feature_load_fasta/2.3.4+galaxy0",
+ "errors": null,
+ "id": 6,
+ "input_connections": {
+ "fasta": {
+ "id": 0,
+ "output_name": "output"
+ }
+ },
+ "inputs": [
+ {
+ "description": "runtime parameter for tool Chado load fasta",
+ "name": "analysis_id"
+ },
+ {
+ "description": "runtime parameter for tool Chado load fasta",
+ "name": "fasta"
+ },
+ {
+ "description": "runtime parameter for tool Chado load fasta",
+ "name": "organism"
+ },
+ {
+ "description": "runtime parameter for tool Chado load fasta",
+ "name": "wait_for"
+ }
+ ],
+ "label": "Chado load fasta org",
+ "name": "Chado load fasta",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "json"
+ }
+ ],
+ "position": {
+ "bottom": 307.3999938964844,
+ "height": 164.39999389648438,
+ "left": 501,
+ "right": 701,
+ "top": 143,
+ "width": 200,
+ "x": 501,
+ "y": 143
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_feature_load_fasta/feature_load_fasta/2.3.4+galaxy0",
+ "tool_shed_repository": {
+ "changeset_revision": "ba4d07fbaf47",
+ "name": "chado_feature_load_fasta",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"analysis_id\": {\"__class__\": \"RuntimeValue\"}, \"do_update\": \"false\", \"ext_db\": {\"db\": \"\", \"re_db_accession\": \"\"}, \"fasta\": {\"__class__\": \"RuntimeValue\"}, \"match_on_name\": \"false\", \"organism\": {\"__class__\": \"RuntimeValue\"}, \"psql_target\": {\"method\": \"remote\", \"__current_case__\": 0}, \"re_name\": \"\", \"re_uniquename\": \"\", \"relationships\": {\"rel_type\": \"none\", \"__current_case__\": 0}, \"sequence_type\": \"contig\", \"wait_for\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": "2.3.4+galaxy0",
+ "type": "tool",
+ "uuid": "d15253d8-a673-4bfb-8051-e06d6017288e",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "results",
+ "uuid": "c5b2da92-4326-46c1-94cb-e0301e2629f8"
+ }
+ ]
+ },
+ "7": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/jbrowse/jbrowse/1.16.8+galaxy1",
+ "errors": null,
+ "id": 7,
+ "input_connections": {
+ "reference_genome|genome": {
+ "id": 0,
+ "output_name": "output"
+ },
+ "track_groups_0|data_tracks_0|data_format|annotation": {
+ "id": 1,
+ "output_name": "output"
+ }
+ },
+ "inputs": [],
+ "label": "JBrowse org1",
+ "name": "JBrowse",
+ "outputs": [
+ {
+ "name": "output",
+ "type": "html"
+ }
+ ],
+ "position": {
+ "bottom": 868.1999969482422,
+ "height": 205.1999969482422,
+ "left": 513,
+ "right": 713,
+ "top": 663,
+ "width": 200,
+ "x": 513,
+ "y": 663
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/jbrowse/jbrowse/1.16.8+galaxy1",
+ "tool_shed_repository": {
+ "changeset_revision": "fd5dbf0f732e",
+ "name": "jbrowse",
+ "owner": "iuc",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"action\": {\"action_select\": \"create\", \"__current_case__\": 0}, \"gencode\": \"1\", \"jbgen\": {\"defaultLocation\": \"\", \"trackPadding\": \"20\", \"shareLink\": \"true\", \"aboutDescription\": \"\", \"show_tracklist\": \"true\", \"show_nav\": \"true\", \"show_overview\": \"true\", \"show_menu\": \"true\", \"hideGenomeOptions\": \"false\"}, \"plugins\": {\"BlastView\": \"true\", \"ComboTrackSelector\": \"false\", \"GCContent\": \"false\"}, \"reference_genome\": {\"genome_type_select\": \"history\", \"__current_case__\": 1, \"genome\": {\"__class__\": \"ConnectedValue\"}}, \"standalone\": \"false\", \"track_groups\": [{\"__index__\": 0, \"category\": \"Annotation\", \"data_tracks\": [{\"__index__\": 0, \"data_format\": {\"data_format_select\": \"gene_calls\", \"__current_case__\": 2, \"annotation\": {\"__class__\": \"ConnectedValue\"}, \"match_part\": {\"match_part_select\": \"false\", \"__current_case__\": 1}, \"index\": \"false\", \"track_config\": {\"track_class\": \"NeatHTMLFeatures/View/Track/NeatFeatures\", \"__current_case__\": 3, \"html_options\": {\"topLevelFeatures\": \"\"}}, \"jbstyle\": {\"style_classname\": \"transcript\", \"style_label\": \"product,name,id\", \"style_description\": \"note,description\", \"style_height\": \"10px\", \"max_height\": \"600\"}, \"jbcolor_scale\": {\"color_score\": {\"color_score_select\": \"none\", \"__current_case__\": 0, \"color\": {\"color_select\": \"automatic\", \"__current_case__\": 0}}}, \"jb_custom_config\": {\"option\": []}, \"jbmenu\": {\"track_menu\": [{\"__index__\": 0, \"menu_action\": \"iframeDialog\", \"menu_label\": \"View transcript report\", \"menu_title\": \"Transcript {id}\", \"menu_url\": \"__MENU_URL_ORG1__\", \"menu_icon\": \"dijitIconBookmark\"}]}, \"track_visibility\": \"default_off\", \"override_apollo_plugins\": \"False\", \"override_apollo_drag\": \"False\"}}]}], \"uglyTestingHack\": \"\", \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": "1.16.8+galaxy1",
+ "type": "tool",
+ "uuid": "16f56647-e3c0-4bda-a126-9011cd3115b8",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "output",
+ "uuid": "0a865401-1041-44b8-bd20-2c422bc695fa"
+ }
+ ]
+ },
+ "8": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/jbrowse/jbrowse/1.16.8+galaxy1",
+ "errors": null,
+ "id": 8,
+ "input_connections": {
+ "reference_genome|genome": {
+ "id": 3,
+ "output_name": "output"
+ },
+ "track_groups_0|data_tracks_0|data_format|annotation": {
+ "id": 4,
+ "output_name": "output"
+ }
+ },
+ "inputs": [],
+ "label": "JBrowse org2",
+ "name": "JBrowse",
+ "outputs": [
+ {
+ "name": "output",
+ "type": "html"
+ }
+ ],
+ "position": {
+ "bottom": 1084.1999969482422,
+ "height": 205.1999969482422,
+ "left": 518,
+ "right": 718,
+ "top": 879,
+ "width": 200,
+ "x": 518,
+ "y": 879
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/jbrowse/jbrowse/1.16.8+galaxy1",
+ "tool_shed_repository": {
+ "changeset_revision": "fd5dbf0f732e",
+ "name": "jbrowse",
+ "owner": "iuc",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"action\": {\"action_select\": \"create\", \"__current_case__\": 0}, \"gencode\": \"1\", \"jbgen\": {\"defaultLocation\": \"\", \"trackPadding\": \"20\", \"shareLink\": \"true\", \"aboutDescription\": \"\", \"show_tracklist\": \"true\", \"show_nav\": \"true\", \"show_overview\": \"true\", \"show_menu\": \"true\", \"hideGenomeOptions\": \"false\"}, \"plugins\": {\"BlastView\": \"true\", \"ComboTrackSelector\": \"false\", \"GCContent\": \"false\"}, \"reference_genome\": {\"genome_type_select\": \"history\", \"__current_case__\": 1, \"genome\": {\"__class__\": \"ConnectedValue\"}}, \"standalone\": \"false\", \"track_groups\": [{\"__index__\": 0, \"category\": \"Annotation\", \"data_tracks\": [{\"__index__\": 0, \"data_format\": {\"data_format_select\": \"gene_calls\", \"__current_case__\": 2, \"annotation\": {\"__class__\": \"ConnectedValue\"}, \"match_part\": {\"match_part_select\": \"false\", \"__current_case__\": 1}, \"index\": \"false\", \"track_config\": {\"track_class\": \"NeatHTMLFeatures/View/Track/NeatFeatures\", \"__current_case__\": 3, \"html_options\": {\"topLevelFeatures\": \"\"}}, \"jbstyle\": {\"style_classname\": \"transcript\", \"style_label\": \"product,name,id\", \"style_description\": \"note,description\", \"style_height\": \"10px\", \"max_height\": \"600\"}, \"jbcolor_scale\": {\"color_score\": {\"color_score_select\": \"none\", \"__current_case__\": 0, \"color\": {\"color_select\": \"automatic\", \"__current_case__\": 0}}}, \"jb_custom_config\": {\"option\": []}, \"jbmenu\": {\"track_menu\": [{\"__index__\": 0, \"menu_action\": \"iframeDialog\", \"menu_label\": \"View transcript report\", \"menu_title\": \"Transcript {id}\", \"menu_url\": \"__MENU_URL_ORG2__\", \"menu_icon\": \"dijitIconBookmark\"}]}, \"track_visibility\": \"default_off\", \"override_apollo_plugins\": \"False\", \"override_apollo_drag\": \"False\"}}]}], \"uglyTestingHack\": \"\", \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": "1.16.8+galaxy1",
+ "type": "tool",
+ "uuid": "f4525181-f8b3-47ab-979f-fee0f46f13ba",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "output",
+ "uuid": "4acd10c7-ef6d-4808-8aac-253d91733853"
+ }
+ ]
+ },
+ "9": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_feature_load_gff/feature_load_gff/2.3.4+galaxy0",
+ "errors": null,
+ "id": 9,
+ "input_connections": {
+ "fasta": {
+ "id": 2,
+ "output_name": "output"
+ },
+ "gff": {
+ "id": 1,
+ "output_name": "output"
+ },
+ "wait_for": {
+ "id": 6,
+ "output_name": "results"
+ }
+ },
+ "inputs": [
+ {
+ "description": "runtime parameter for tool Chado load gff",
+ "name": "analysis_id"
+ },
+ {
+ "description": "runtime parameter for tool Chado load gff",
+ "name": "fasta"
+ },
+ {
+ "description": "runtime parameter for tool Chado load gff",
+ "name": "gff"
+ },
+ {
+ "description": "runtime parameter for tool Chado load gff",
+ "name": "organism"
+ },
+ {
+ "description": "runtime parameter for tool Chado load gff",
+ "name": "wait_for"
+ }
+ ],
+ "label": "Chado load gff ",
+ "name": "Chado load gff",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "txt"
+ }
+ ],
+ "position": {
+ "bottom": 317.3999938964844,
+ "height": 174.39999389648438,
+ "left": 787,
+ "right": 987,
+ "top": 143,
+ "width": 200,
+ "x": 787,
+ "y": 143
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_feature_load_gff/feature_load_gff/2.3.4+galaxy0",
+ "tool_shed_repository": {
+ "changeset_revision": "e9a6d7568817",
+ "name": "chado_feature_load_gff",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"add_only\": \"false\", \"analysis_id\": {\"__class__\": \"RuntimeValue\"}, \"fasta\": {\"__class__\": \"RuntimeValue\"}, \"gff\": {\"__class__\": \"RuntimeValue\"}, \"landmark_type\": \"contig\", \"no_seq_compute\": \"false\", \"organism\": {\"__class__\": \"RuntimeValue\"}, \"prot_naming\": {\"method\": \"regex\", \"__current_case__\": 1, \"re_protein_capture\": \"^mRNA(_.+)$\", \"re_protein\": \"prot\\\\1\"}, \"psql_target\": {\"method\": \"remote\", \"__current_case__\": 0}, \"wait_for\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": "2.3.4+galaxy0",
+ "type": "tool",
+ "uuid": "281d98df-9a07-4beb-b3e8-a1ac72d8c0c9",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "results",
+ "uuid": "e92a76f7-7b7e-429c-9aa7-cfc8ce5f0cd1"
+ }
+ ]
+ },
+ "10": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/jbrowse_to_container/jbrowse_to_container/0.5.1",
+ "errors": null,
+ "id": 10,
+ "input_connections": {
+ "organisms_0|jbrowse": {
+ "id": 7,
+ "output_name": "output"
+ },
+ "organisms_1|jbrowse": {
+ "id": 8,
+ "output_name": "output"
+ }
+ },
+ "inputs": [],
+ "label": null,
+ "name": "Add organisms to JBrowse container",
+ "outputs": [
+ {
+ "name": "output",
+ "type": "html"
+ }
+ ],
+ "position": {
+ "bottom": 995.8000030517578,
+ "height": 184.8000030517578,
+ "left": 883,
+ "right": 1083,
+ "top": 811,
+ "width": 200,
+ "x": 883,
+ "y": 811
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/jbrowse_to_container/jbrowse_to_container/0.5.1",
+ "tool_shed_repository": {
+ "changeset_revision": "11033bdad2ca",
+ "name": "jbrowse_to_container",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"organisms\": [{\"__index__\": 0, \"jbrowse\": {\"__class__\": \"ConnectedValue\"}, \"name\": \"__FULL_NAME_ORG1__\", \"advanced\": {\"unique_id\": \"__UNIQUE_ID_ORG1__\"}}, {\"__index__\": 1, \"jbrowse\": {\"__class__\": \"ConnectedValue\"}, \"name\": \"__FULL_NAME_ORG2__\", \"advanced\": {\"unique_id\": \"__UNIQUE_ID_ORG2__\"}}], \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": "0.5.1",
+ "type": "tool",
+ "uuid": "0f70a2d4-f599-4514-846d-16a558251a9a",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "output",
+ "uuid": "0e8e64c8-7dc6-46f1-aca2-d4a6ffce638b"
+ }
+ ]
+ },
+ "11": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_feature_sync/feature_sync/3.2.1.0",
+ "errors": null,
+ "id": 11,
+ "input_connections": {
+ "wait_for": {
+ "id": 9,
+ "output_name": "results"
+ }
+ },
+ "inputs": [
+ {
+ "description": "runtime parameter for tool Synchronize features",
+ "name": "organism_id"
+ }
+ ],
+ "label": "Synchronize features org1",
+ "name": "Synchronize features",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "txt"
+ }
+ ],
+ "position": {
+ "bottom": 300.3999938964844,
+ "height": 154.39999389648438,
+ "left": 1069,
+ "right": 1269,
+ "top": 146,
+ "width": 200,
+ "x": 1069,
+ "y": 146
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_feature_sync/feature_sync/3.2.1.0",
+ "tool_shed_repository": {
+ "changeset_revision": "64e36c3f0dd6",
+ "name": "tripal_feature_sync",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"organism_id\": {\"__class__\": \"RuntimeValue\"}, \"repeat_ids\": [], \"repeat_types\": [{\"__index__\": 0, \"types\": \"mRNA\"}, {\"__index__\": 1, \"types\": \"polypeptide\"}], \"wait_for\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": "3.2.1.0",
+ "type": "tool",
+ "uuid": "7ed6c0a0-f36b-4a57-9fd8-4900af93b39c",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "results",
+ "uuid": "ddd66d56-b81b-4ad7-a96d-baf365d8b85a"
+ }
+ ]
+ },
+ "12": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_feature_load_fasta/feature_load_fasta/2.3.4+galaxy0",
+ "errors": null,
+ "id": 12,
+ "input_connections": {
+ "fasta": {
+ "id": 3,
+ "output_name": "output"
+ },
+ "wait_for": {
+ "id": 11,
+ "output_name": "results"
+ }
+ },
+ "inputs": [
+ {
+ "description": "runtime parameter for tool Chado load fasta",
+ "name": "analysis_id"
+ },
+ {
+ "description": "runtime parameter for tool Chado load fasta",
+ "name": "fasta"
+ },
+ {
+ "description": "runtime parameter for tool Chado load fasta",
+ "name": "organism"
+ },
+ {
+ "description": "runtime parameter for tool Chado load fasta",
+ "name": "wait_for"
+ }
+ ],
+ "label": "Chado load fasta org2",
+ "name": "Chado load fasta",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "json"
+ }
+ ],
+ "position": {
+ "bottom": 562.3999938964844,
+ "height": 164.39999389648438,
+ "left": 514,
+ "right": 714,
+ "top": 398,
+ "width": 200,
+ "x": 514,
+ "y": 398
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_feature_load_fasta/feature_load_fasta/2.3.4+galaxy0",
+ "tool_shed_repository": {
+ "changeset_revision": "ba4d07fbaf47",
+ "name": "chado_feature_load_fasta",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"analysis_id\": {\"__class__\": \"RuntimeValue\"}, \"do_update\": \"false\", \"ext_db\": {\"db\": \"\", \"re_db_accession\": \"\"}, \"fasta\": {\"__class__\": \"RuntimeValue\"}, \"match_on_name\": \"false\", \"organism\": {\"__class__\": \"RuntimeValue\"}, \"psql_target\": {\"method\": \"remote\", \"__current_case__\": 0}, \"re_name\": \"\", \"re_uniquename\": \"\", \"relationships\": {\"rel_type\": \"none\", \"__current_case__\": 0}, \"sequence_type\": \"contig\", \"wait_for\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": "2.3.4+galaxy0",
+ "type": "tool",
+ "uuid": "049f96ea-620a-434c-b32a-886cac9174ef",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "results",
+ "uuid": "e67a8a18-2a9d-4906-8960-3d76455de221"
+ }
+ ]
+ },
+ "13": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_feature_load_gff/feature_load_gff/2.3.4+galaxy0",
+ "errors": null,
+ "id": 13,
+ "input_connections": {
+ "fasta": {
+ "id": 5,
+ "output_name": "output"
+ },
+ "gff": {
+ "id": 4,
+ "output_name": "output"
+ },
+ "wait_for": {
+ "id": 12,
+ "output_name": "results"
+ }
+ },
+ "inputs": [
+ {
+ "description": "runtime parameter for tool Chado load gff",
+ "name": "analysis_id"
+ },
+ {
+ "description": "runtime parameter for tool Chado load gff",
+ "name": "fasta"
+ },
+ {
+ "description": "runtime parameter for tool Chado load gff",
+ "name": "gff"
+ },
+ {
+ "description": "runtime parameter for tool Chado load gff",
+ "name": "organism"
+ },
+ {
+ "description": "runtime parameter for tool Chado load gff",
+ "name": "wait_for"
+ }
+ ],
+ "label": "Chado load gff org2",
+ "name": "Chado load gff",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "txt"
+ }
+ ],
+ "position": {
+ "bottom": 594.8000030517578,
+ "height": 194.8000030517578,
+ "left": 799,
+ "right": 999,
+ "top": 400,
+ "width": 200,
+ "x": 799,
+ "y": 400
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_feature_load_gff/feature_load_gff/2.3.4+galaxy0",
+ "tool_shed_repository": {
+ "changeset_revision": "e9a6d7568817",
+ "name": "chado_feature_load_gff",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"add_only\": \"false\", \"analysis_id\": {\"__class__\": \"RuntimeValue\"}, \"fasta\": {\"__class__\": \"RuntimeValue\"}, \"gff\": {\"__class__\": \"RuntimeValue\"}, \"landmark_type\": \"contig\", \"no_seq_compute\": \"false\", \"organism\": {\"__class__\": \"RuntimeValue\"}, \"prot_naming\": {\"method\": \"regex\", \"__current_case__\": 1, \"re_protein_capture\": \"^mRNA(_.+)$\", \"re_protein\": \"prot\\\\1\"}, \"psql_target\": {\"method\": \"remote\", \"__current_case__\": 0}, \"wait_for\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": "2.3.4+galaxy0",
+ "type": "tool",
+ "uuid": "9293d4b6-7cad-4d6b-8143-e134f58c75fe",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "results",
+ "uuid": "975db068-46e0-4c0a-a74f-80c7d2137ac8"
+ }
+ ]
+ },
+ "14": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_feature_sync/feature_sync/3.2.1.0",
+ "errors": null,
+ "id": 14,
+ "input_connections": {
+ "wait_for": {
+ "id": 13,
+ "output_name": "results"
+ }
+ },
+ "inputs": [
+ {
+ "description": "runtime parameter for tool Synchronize features",
+ "name": "organism_id"
+ }
+ ],
+ "label": "Synchronize features org2",
+ "name": "Synchronize features",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "txt"
+ }
+ ],
+ "position": {
+ "bottom": 560.3999938964844,
+ "height": 154.39999389648438,
+ "left": 1078,
+ "right": 1278,
+ "top": 406,
+ "width": 200,
+ "x": 1078,
+ "y": 406
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_feature_sync/feature_sync/3.2.1.0",
+ "tool_shed_repository": {
+ "changeset_revision": "64e36c3f0dd6",
+ "name": "tripal_feature_sync",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"organism_id\": {\"__class__\": \"RuntimeValue\"}, \"repeat_ids\": [], \"repeat_types\": [{\"__index__\": 0, \"types\": \"mRNA\"}, {\"__index__\": 1, \"types\": \"polypeptide\"}], \"wait_for\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": "3.2.1.0",
+ "type": "tool",
+ "uuid": "090a12c8-f931-4f3c-8853-9ae581c7c091",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "results",
+ "uuid": "f51aa0a5-e2f8-41af-bb56-dbfe220e7fc8"
+ }
+ ]
+ },
+ "15": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_db_populate_mviews/db_populate_mviews/3.2.1.0",
+ "errors": null,
+ "id": 15,
+ "input_connections": {
+ "wait_for": {
+ "id": 14,
+ "output_name": "results"
+ }
+ },
+ "inputs": [],
+ "label": null,
+ "name": "Populate materialized views",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "txt"
+ }
+ ],
+ "position": {
+ "bottom": 456.3999938964844,
+ "height": 154.39999389648438,
+ "left": 1362,
+ "right": 1562,
+ "top": 302,
+ "width": 200,
+ "x": 1362,
+ "y": 302
+ },
+ "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": "0a3bd8c6-240b-45f6-a90d-e88ff3703fa7",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "results",
+ "uuid": "c7229bc3-fbe7-4c7f-9a08-8ad631d57766"
+ }
+ ]
+ },
+ "16": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_db_index/db_index/3.2.1.1",
+ "errors": null,
+ "id": 16,
+ "input_connections": {
+ "wait_for": {
+ "id": 15,
+ "output_name": "results"
+ }
+ },
+ "inputs": [],
+ "label": null,
+ "name": "Index Tripal data",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "txt"
+ }
+ ],
+ "position": {
+ "bottom": 416.6000061035156,
+ "height": 113.60000610351562,
+ "left": 1638,
+ "right": 1838,
+ "top": 303,
+ "width": 200,
+ "x": 1638,
+ "y": 303
+ },
+ "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": "b01a554e-a43a-494e-876c-ebe134c4c48f",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "results",
+ "uuid": "0547bccc-451b-4de1-9452-83fe86d8bc2a"
+ }
+ ]
+ }
+ },
+ "tags": [],
+ "uuid": "ef44b9b7-f9df-454e-bbba-070299d056d1",
+ "version": 1
+}
\ No newline at end of file
diff --git a/workflows_phaeoexplorer/Galaxy-Workflow-chado_load_tripal_synchronize_jbrowse_2org_v4.ga b/workflows_phaeoexplorer/Galaxy-Workflow-chado_load_tripal_synchronize_jbrowse_2org_v4.ga
new file mode 100644
index 0000000000000000000000000000000000000000..045e442219face7eed174cafcec206dd9de0ffa0
--- /dev/null
+++ b/workflows_phaeoexplorer/Galaxy-Workflow-chado_load_tripal_synchronize_jbrowse_2org_v4.ga
@@ -0,0 +1,881 @@
+{
+ "a_galaxy_workflow": "true",
+ "annotation": "",
+ "format-version": "0.1",
+ "name": "chado_load_tripal_synchronize_jbrowse_2org_v4",
+ "steps": {
+ "0": {
+ "annotation": "",
+ "content_id": null,
+ "errors": null,
+ "id": 0,
+ "input_connections": {},
+ "inputs": [
+ {
+ "description": "",
+ "name": "annotations org1"
+ }
+ ],
+ "label": "annotations org1",
+ "name": "Input dataset",
+ "outputs": [],
+ "position": {
+ "bottom": 64.80000305175781,
+ "height": 61.80000305175781,
+ "left": 233,
+ "right": 433,
+ "top": 3,
+ "width": 200,
+ "x": 233,
+ "y": 3
+ },
+ "tool_id": null,
+ "tool_state": "{\"optional\": false}",
+ "tool_version": null,
+ "type": "data_input",
+ "uuid": "c82b756f-2ef5-41d5-9e14-eb9a7ef942c7",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "output",
+ "uuid": "cd6ee602-9669-4542-820c-c4655bc573b0"
+ }
+ ]
+ },
+ "1": {
+ "annotation": "",
+ "content_id": null,
+ "errors": null,
+ "id": 1,
+ "input_connections": {},
+ "inputs": [
+ {
+ "description": "",
+ "name": "genome org1"
+ }
+ ],
+ "label": "genome org1",
+ "name": "Input dataset",
+ "outputs": [],
+ "position": {
+ "bottom": -25.199996948242188,
+ "height": 61.80000305175781,
+ "left": 234,
+ "right": 434,
+ "top": -87,
+ "width": 200,
+ "x": 234,
+ "y": -87
+ },
+ "tool_id": null,
+ "tool_state": "{\"optional\": false}",
+ "tool_version": null,
+ "type": "data_input",
+ "uuid": "59f823c8-fd7c-441c-84b6-21c367ba12f6",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "output",
+ "uuid": "6b57ff4d-58c7-4a22-a2c7-66acca4ebe33"
+ }
+ ]
+ },
+ "2": {
+ "annotation": "",
+ "content_id": null,
+ "errors": null,
+ "id": 2,
+ "input_connections": {},
+ "inputs": [
+ {
+ "description": "",
+ "name": "proteins org1"
+ }
+ ],
+ "label": "proteins org1",
+ "name": "Input dataset",
+ "outputs": [],
+ "position": {
+ "bottom": 159.8000030517578,
+ "height": 61.80000305175781,
+ "left": 234,
+ "right": 434,
+ "top": 98,
+ "width": 200,
+ "x": 234,
+ "y": 98
+ },
+ "tool_id": null,
+ "tool_state": "{\"optional\": false}",
+ "tool_version": null,
+ "type": "data_input",
+ "uuid": "0a0ac416-68b8-4c48-980e-04c6230c721e",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "output",
+ "uuid": "64cd0c64-5d21-400f-a3c8-3a035978be06"
+ }
+ ]
+ },
+ "3": {
+ "annotation": "",
+ "content_id": null,
+ "errors": null,
+ "id": 3,
+ "input_connections": {},
+ "inputs": [
+ {
+ "description": "",
+ "name": "genome org2"
+ }
+ ],
+ "label": "genome org2",
+ "name": "Input dataset",
+ "outputs": [],
+ "position": {
+ "bottom": 249.8000030517578,
+ "height": 61.80000305175781,
+ "left": 233,
+ "right": 433,
+ "top": 188,
+ "width": 200,
+ "x": 233,
+ "y": 188
+ },
+ "tool_id": null,
+ "tool_state": "{\"optional\": false}",
+ "tool_version": null,
+ "type": "data_input",
+ "uuid": "ddd5f0f8-9e14-42f0-a866-2971d02e5435",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "output",
+ "uuid": "bcf5bb6d-9796-4e37-bcf8-ac3d90efd7bf"
+ }
+ ]
+ },
+ "4": {
+ "annotation": "",
+ "content_id": null,
+ "errors": null,
+ "id": 4,
+ "input_connections": {},
+ "inputs": [
+ {
+ "description": "",
+ "name": "annotations org2"
+ }
+ ],
+ "label": "annotations org2",
+ "name": "Input dataset",
+ "outputs": [],
+ "position": {
+ "bottom": 343.8000030517578,
+ "height": 61.80000305175781,
+ "left": 235,
+ "right": 435,
+ "top": 282,
+ "width": 200,
+ "x": 235,
+ "y": 282
+ },
+ "tool_id": null,
+ "tool_state": "{\"optional\": false}",
+ "tool_version": null,
+ "type": "data_input",
+ "uuid": "c7f3b553-5cd2-46e6-a792-e864ab0d2459",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "output",
+ "uuid": "2de7390d-d075-4122-80ee-63217adf4f24"
+ }
+ ]
+ },
+ "5": {
+ "annotation": "",
+ "content_id": null,
+ "errors": null,
+ "id": 5,
+ "input_connections": {},
+ "inputs": [
+ {
+ "description": "",
+ "name": "proteins org2"
+ }
+ ],
+ "label": "proteins org2",
+ "name": "Input dataset",
+ "outputs": [],
+ "position": {
+ "bottom": 433.8000030517578,
+ "height": 61.80000305175781,
+ "left": 236,
+ "right": 436,
+ "top": 372,
+ "width": 200,
+ "x": 236,
+ "y": 372
+ },
+ "tool_id": null,
+ "tool_state": "{\"optional\": false}",
+ "tool_version": null,
+ "type": "data_input",
+ "uuid": "b5b82a8a-f73c-4183-bc0a-6956e5ad9d0a",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "output",
+ "uuid": "84bb8de5-0039-40bc-98b0-2524a8958443"
+ }
+ ]
+ },
+ "6": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_feature_load_fasta/feature_load_fasta/2.3.4+galaxy0",
+ "errors": null,
+ "id": 6,
+ "input_connections": {
+ "fasta": {
+ "id": 1,
+ "output_name": "output"
+ }
+ },
+ "inputs": [
+ {
+ "description": "runtime parameter for tool Chado load fasta",
+ "name": "analysis_id"
+ },
+ {
+ "description": "runtime parameter for tool Chado load fasta",
+ "name": "organism"
+ },
+ {
+ "description": "runtime parameter for tool Chado load fasta",
+ "name": "wait_for"
+ }
+ ],
+ "label": "Chado load fasta org",
+ "name": "Chado load fasta",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "json"
+ }
+ ],
+ "position": {
+ "bottom": 77.39999389648438,
+ "height": 164.39999389648438,
+ "left": 519,
+ "right": 719,
+ "top": -87,
+ "width": 200,
+ "x": 519,
+ "y": -87
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_feature_load_fasta/feature_load_fasta/2.3.4+galaxy0",
+ "tool_shed_repository": {
+ "changeset_revision": "ba4d07fbaf47",
+ "name": "chado_feature_load_fasta",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"analysis_id\": {\"__class__\": \"RuntimeValue\"}, \"do_update\": \"false\", \"ext_db\": {\"db\": \"\", \"re_db_accession\": \"\"}, \"fasta\": {\"__class__\": \"ConnectedValue\"}, \"match_on_name\": \"false\", \"organism\": {\"__class__\": \"RuntimeValue\"}, \"psql_target\": {\"method\": \"remote\", \"__current_case__\": 0}, \"re_name\": \"\", \"re_uniquename\": \"\", \"relationships\": {\"rel_type\": \"none\", \"__current_case__\": 0}, \"sequence_type\": \"contig\", \"wait_for\": {\"__class__\": \"RuntimeValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": "2.3.4+galaxy0",
+ "type": "tool",
+ "uuid": "d706dd73-5dc7-4c06-8c56-825aa81394a1",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "results",
+ "uuid": "b058f83f-8d18-4ef4-b3a6-bae86dc0f9f6"
+ }
+ ]
+ },
+ "7": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/jbrowse/jbrowse/1.16.11+galaxy0",
+ "errors": null,
+ "id": 7,
+ "input_connections": {
+ "reference_genome|genome": {
+ "id": 1,
+ "output_name": "output"
+ },
+ "track_groups_0|data_tracks_0|data_format|annotation": {
+ "id": 0,
+ "output_name": "output"
+ }
+ },
+ "inputs": [
+ {
+ "description": "runtime parameter for tool JBrowse",
+ "name": "reference_genome"
+ }
+ ],
+ "label": "JBrowse org1",
+ "name": "JBrowse",
+ "outputs": [
+ {
+ "name": "output",
+ "type": "html"
+ }
+ ],
+ "position": {
+ "bottom": 638.1999969482422,
+ "height": 205.1999969482422,
+ "left": 532,
+ "right": 732,
+ "top": 433,
+ "width": 200,
+ "x": 532,
+ "y": 433
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/jbrowse/jbrowse/1.16.11+galaxy0",
+ "tool_shed_repository": {
+ "changeset_revision": "4542035c1075",
+ "name": "jbrowse",
+ "owner": "iuc",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"action\": {\"action_select\": \"create\", \"__current_case__\": 0}, \"gencode\": \"1\", \"jbgen\": {\"defaultLocation\": \"\", \"trackPadding\": \"20\", \"shareLink\": \"true\", \"aboutDescription\": \"\", \"show_tracklist\": \"true\", \"show_nav\": \"true\", \"show_overview\": \"true\", \"show_menu\": \"true\", \"hideGenomeOptions\": \"false\"}, \"plugins\": {\"BlastView\": \"true\", \"ComboTrackSelector\": \"false\", \"GCContent\": \"false\"}, \"reference_genome\": {\"genome_type_select\": \"history\", \"__current_case__\": 1, \"genome\": {\"__class__\": \"RuntimeValue\"}}, \"standalone\": \"complete\", \"track_groups\": [{\"__index__\": 0, \"category\": \"Annotation\", \"data_tracks\": [{\"__index__\": 0, \"data_format\": {\"data_format_select\": \"gene_calls\", \"__current_case__\": 2, \"annotation\": {\"__class__\": \"RuntimeValue\"}, \"match_part\": {\"match_part_select\": \"false\", \"__current_case__\": 1}, \"index\": \"false\", \"track_config\": {\"track_class\": \"NeatHTMLFeatures/View/Track/NeatFeatures\", \"__current_case__\": 3, \"html_options\": {\"topLevelFeatures\": \"\"}}, \"jbstyle\": {\"style_classname\": \"transcript\", \"style_label\": \"product,name,id\", \"style_description\": \"note,description\", \"style_height\": \"10px\", \"max_height\": \"600\"}, \"jbcolor_scale\": {\"color_score\": {\"color_score_select\": \"none\", \"__current_case__\": 0, \"color\": {\"color_select\": \"automatic\", \"__current_case__\": 0}}}, \"jb_custom_config\": {\"option\": []}, \"jbmenu\": {\"track_menu\": [{\"__index__\": 0, \"menu_action\": \"iframeDialog\", \"menu_label\": \"View transcript report\", \"menu_title\": \"Transcript {id}\", \"menu_url\": \"__MENU_URL_ORG1__\", \"menu_icon\": \"dijitIconBookmark\"}]}, \"track_visibility\": \"default_off\", \"override_apollo_plugins\": \"False\", \"override_apollo_drag\": \"False\"}}]}], \"uglyTestingHack\": \"\", \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": "1.16.11+galaxy0",
+ "type": "tool",
+ "uuid": "ab159045-e72e-46cc-9e9f-d7ad2b50687e",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "output",
+ "uuid": "e93e82c7-7a3b-4219-a2f6-09afbe60b1e0"
+ }
+ ]
+ },
+ "8": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/iuc/jbrowse/jbrowse/1.16.11+galaxy0",
+ "errors": null,
+ "id": 8,
+ "input_connections": {
+ "reference_genome|genome": {
+ "id": 3,
+ "output_name": "output"
+ },
+ "track_groups_0|data_tracks_0|data_format|annotation": {
+ "id": 4,
+ "output_name": "output"
+ }
+ },
+ "inputs": [
+ {
+ "description": "runtime parameter for tool JBrowse",
+ "name": "reference_genome"
+ }
+ ],
+ "label": "JBrowse org2",
+ "name": "JBrowse",
+ "outputs": [
+ {
+ "name": "output",
+ "type": "html"
+ }
+ ],
+ "position": {
+ "bottom": 854.1999969482422,
+ "height": 205.1999969482422,
+ "left": 537,
+ "right": 737,
+ "top": 649,
+ "width": 200,
+ "x": 537,
+ "y": 649
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/iuc/jbrowse/jbrowse/1.16.11+galaxy0",
+ "tool_shed_repository": {
+ "changeset_revision": "4542035c1075",
+ "name": "jbrowse",
+ "owner": "iuc",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"action\": {\"action_select\": \"create\", \"__current_case__\": 0}, \"gencode\": \"1\", \"jbgen\": {\"defaultLocation\": \"\", \"trackPadding\": \"20\", \"shareLink\": \"true\", \"aboutDescription\": \"\", \"show_tracklist\": \"true\", \"show_nav\": \"true\", \"show_overview\": \"true\", \"show_menu\": \"true\", \"hideGenomeOptions\": \"false\"}, \"plugins\": {\"BlastView\": \"true\", \"ComboTrackSelector\": \"false\", \"GCContent\": \"false\"}, \"reference_genome\": {\"genome_type_select\": \"history\", \"__current_case__\": 1, \"genome\": {\"__class__\": \"RuntimeValue\"}}, \"standalone\": \"complete\", \"track_groups\": [{\"__index__\": 0, \"category\": \"Annotation\", \"data_tracks\": [{\"__index__\": 0, \"data_format\": {\"data_format_select\": \"gene_calls\", \"__current_case__\": 2, \"annotation\": {\"__class__\": \"RuntimeValue\"}, \"match_part\": {\"match_part_select\": \"false\", \"__current_case__\": 1}, \"index\": \"false\", \"track_config\": {\"track_class\": \"NeatHTMLFeatures/View/Track/NeatFeatures\", \"__current_case__\": 3, \"html_options\": {\"topLevelFeatures\": \"\"}}, \"jbstyle\": {\"style_classname\": \"transcript\", \"style_label\": \"product,name,id\", \"style_description\": \"note,description\", \"style_height\": \"10px\", \"max_height\": \"600\"}, \"jbcolor_scale\": {\"color_score\": {\"color_score_select\": \"none\", \"__current_case__\": 0, \"color\": {\"color_select\": \"automatic\", \"__current_case__\": 0}}}, \"jb_custom_config\": {\"option\": []}, \"jbmenu\": {\"track_menu\": [{\"__index__\": 0, \"menu_action\": \"iframeDialog\", \"menu_label\": \"View transcript report\", \"menu_title\": \"Transcript {id}\", \"menu_url\": \"__MENU_URL_ORG2__\", \"menu_icon\": \"dijitIconBookmark\"}]}, \"track_visibility\": \"default_off\", \"override_apollo_plugins\": \"False\", \"override_apollo_drag\": \"False\"}}]}], \"uglyTestingHack\": \"\", \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": "1.16.11+galaxy0",
+ "type": "tool",
+ "uuid": "a06b4426-5546-4393-aa6a-23a0c490eb8f",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "output",
+ "uuid": "a44c76ce-c7f4-4f24-bc96-be90aafc9efb"
+ }
+ ]
+ },
+ "9": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_feature_load_gff/feature_load_gff/2.3.4+galaxy0",
+ "errors": null,
+ "id": 9,
+ "input_connections": {
+ "fasta": {
+ "id": 2,
+ "output_name": "output"
+ },
+ "gff": {
+ "id": 0,
+ "output_name": "output"
+ },
+ "wait_for": {
+ "id": 6,
+ "output_name": "results"
+ }
+ },
+ "inputs": [
+ {
+ "description": "runtime parameter for tool Chado load gff",
+ "name": "analysis_id"
+ },
+ {
+ "description": "runtime parameter for tool Chado load gff",
+ "name": "organism"
+ }
+ ],
+ "label": "Chado load gff ",
+ "name": "Chado load gff",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "txt"
+ }
+ ],
+ "position": {
+ "bottom": 87.39999389648438,
+ "height": 174.39999389648438,
+ "left": 806,
+ "right": 1006,
+ "top": -87,
+ "width": 200,
+ "x": 806,
+ "y": -87
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_feature_load_gff/feature_load_gff/2.3.4+galaxy0",
+ "tool_shed_repository": {
+ "changeset_revision": "e9a6d7568817",
+ "name": "chado_feature_load_gff",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"add_only\": \"false\", \"analysis_id\": {\"__class__\": \"RuntimeValue\"}, \"fasta\": {\"__class__\": \"ConnectedValue\"}, \"gff\": {\"__class__\": \"ConnectedValue\"}, \"landmark_type\": \"contig\", \"no_seq_compute\": \"false\", \"organism\": {\"__class__\": \"RuntimeValue\"}, \"prot_naming\": {\"method\": \"regex\", \"__current_case__\": 1, \"re_protein_capture\": \"^mRNA(_.+)$\", \"re_protein\": \"prot\\\\1\"}, \"psql_target\": {\"method\": \"remote\", \"__current_case__\": 0}, \"wait_for\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": "2.3.4+galaxy0",
+ "type": "tool",
+ "uuid": "f93c9145-6484-4c19-ab15-97f042fa4f1e",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "results",
+ "uuid": "4b935868-ea0a-4ccf-9fe4-90d8fbe280df"
+ }
+ ]
+ },
+ "10": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/jbrowse_to_container/jbrowse_to_container/0.5.1",
+ "errors": null,
+ "id": 10,
+ "input_connections": {
+ "organisms_0|jbrowse": {
+ "id": 7,
+ "output_name": "output"
+ },
+ "organisms_1|jbrowse": {
+ "id": 8,
+ "output_name": "output"
+ }
+ },
+ "inputs": [],
+ "label": null,
+ "name": "Add organisms to JBrowse container",
+ "outputs": [
+ {
+ "name": "output",
+ "type": "html"
+ }
+ ],
+ "position": {
+ "bottom": 765.8000030517578,
+ "height": 184.8000030517578,
+ "left": 902,
+ "right": 1102,
+ "top": 581,
+ "width": 200,
+ "x": 902,
+ "y": 581
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/jbrowse_to_container/jbrowse_to_container/0.5.1",
+ "tool_shed_repository": {
+ "changeset_revision": "11033bdad2ca",
+ "name": "jbrowse_to_container",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"organisms\": [{\"__index__\": 0, \"jbrowse\": {\"__class__\": \"RuntimeValue\"}, \"name\": \"__DISPLAY_NAME_ORG1__\", \"advanced\": {\"unique_id\": \"__UNIQUE_ID_ORG1__\"}}, {\"__index__\": 1, \"jbrowse\": {\"__class__\": \"RuntimeValue\"}, \"name\": \"__DISPLAY_NAME_ORG2__\", \"advanced\": {\"unique_id\": \"__UNIQUE_ID_ORG2__\"}}], \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": "0.5.1",
+ "type": "tool",
+ "uuid": "2c90cac2-d1ef-4d3b-bf43-d01e27059823",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "output",
+ "uuid": "91511518-e85c-4a29-a929-77334cad6a1c"
+ }
+ ]
+ },
+ "11": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_feature_sync/feature_sync/3.2.1.0",
+ "errors": null,
+ "id": 11,
+ "input_connections": {
+ "wait_for": {
+ "id": 9,
+ "output_name": "results"
+ }
+ },
+ "inputs": [
+ {
+ "description": "runtime parameter for tool Synchronize features",
+ "name": "organism_id"
+ }
+ ],
+ "label": "Synchronize features org1",
+ "name": "Synchronize features",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "txt"
+ }
+ ],
+ "position": {
+ "bottom": 70.39999389648438,
+ "height": 154.39999389648438,
+ "left": 1088,
+ "right": 1288,
+ "top": -84,
+ "width": 200,
+ "x": 1088,
+ "y": -84
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_feature_sync/feature_sync/3.2.1.0",
+ "tool_shed_repository": {
+ "changeset_revision": "64e36c3f0dd6",
+ "name": "tripal_feature_sync",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"organism_id\": {\"__class__\": \"RuntimeValue\"}, \"repeat_ids\": [], \"repeat_types\": [{\"__index__\": 0, \"types\": \"mRNA\"}, {\"__index__\": 1, \"types\": \"polypeptide\"}], \"wait_for\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": "3.2.1.0",
+ "type": "tool",
+ "uuid": "7ed6c0a0-f36b-4a57-9fd8-4900af93b39c",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "results",
+ "uuid": "ef7589b7-bd80-48c5-bd44-f275d49ea324"
+ }
+ ]
+ },
+ "12": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_feature_load_fasta/feature_load_fasta/2.3.4+galaxy0",
+ "errors": null,
+ "id": 12,
+ "input_connections": {
+ "fasta": {
+ "id": 3,
+ "output_name": "output"
+ },
+ "wait_for": {
+ "id": 11,
+ "output_name": "results"
+ }
+ },
+ "inputs": [
+ {
+ "description": "runtime parameter for tool Chado load fasta",
+ "name": "analysis_id"
+ },
+ {
+ "description": "runtime parameter for tool Chado load fasta",
+ "name": "organism"
+ }
+ ],
+ "label": "Chado load fasta org2",
+ "name": "Chado load fasta",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "json"
+ }
+ ],
+ "position": {
+ "bottom": 332.3999938964844,
+ "height": 164.39999389648438,
+ "left": 533,
+ "right": 733,
+ "top": 168,
+ "width": 200,
+ "x": 533,
+ "y": 168
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_feature_load_fasta/feature_load_fasta/2.3.4+galaxy0",
+ "tool_shed_repository": {
+ "changeset_revision": "ba4d07fbaf47",
+ "name": "chado_feature_load_fasta",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"analysis_id\": {\"__class__\": \"RuntimeValue\"}, \"do_update\": \"false\", \"ext_db\": {\"db\": \"\", \"re_db_accession\": \"\"}, \"fasta\": {\"__class__\": \"ConnectedValue\"}, \"match_on_name\": \"false\", \"organism\": {\"__class__\": \"RuntimeValue\"}, \"psql_target\": {\"method\": \"remote\", \"__current_case__\": 0}, \"re_name\": \"\", \"re_uniquename\": \"\", \"relationships\": {\"rel_type\": \"none\", \"__current_case__\": 0}, \"sequence_type\": \"contig\", \"wait_for\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": "2.3.4+galaxy0",
+ "type": "tool",
+ "uuid": "c860eb94-43cb-468e-ad5e-257a519b66ca",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "results",
+ "uuid": "a742ac3c-b152-464e-bcfd-5139efd90599"
+ }
+ ]
+ },
+ "13": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_feature_load_gff/feature_load_gff/2.3.4+galaxy0",
+ "errors": null,
+ "id": 13,
+ "input_connections": {
+ "fasta": {
+ "id": 5,
+ "output_name": "output"
+ },
+ "gff": {
+ "id": 4,
+ "output_name": "output"
+ },
+ "wait_for": {
+ "id": 12,
+ "output_name": "results"
+ }
+ },
+ "inputs": [
+ {
+ "description": "runtime parameter for tool Chado load gff",
+ "name": "analysis_id"
+ },
+ {
+ "description": "runtime parameter for tool Chado load gff",
+ "name": "organism"
+ }
+ ],
+ "label": "Chado load gff org2",
+ "name": "Chado load gff",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "txt"
+ }
+ ],
+ "position": {
+ "bottom": 364.8000030517578,
+ "height": 194.8000030517578,
+ "left": 818,
+ "right": 1018,
+ "top": 170,
+ "width": 200,
+ "x": 818,
+ "y": 170
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_feature_load_gff/feature_load_gff/2.3.4+galaxy0",
+ "tool_shed_repository": {
+ "changeset_revision": "e9a6d7568817",
+ "name": "chado_feature_load_gff",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"add_only\": \"false\", \"analysis_id\": {\"__class__\": \"RuntimeValue\"}, \"fasta\": {\"__class__\": \"ConnectedValue\"}, \"gff\": {\"__class__\": \"ConnectedValue\"}, \"landmark_type\": \"contig\", \"no_seq_compute\": \"false\", \"organism\": {\"__class__\": \"RuntimeValue\"}, \"prot_naming\": {\"method\": \"regex\", \"__current_case__\": 1, \"re_protein_capture\": \"^mRNA(_.+)$\", \"re_protein\": \"prot\\\\1\"}, \"psql_target\": {\"method\": \"remote\", \"__current_case__\": 0}, \"wait_for\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": "2.3.4+galaxy0",
+ "type": "tool",
+ "uuid": "a4d0333d-bcbc-44bb-88ff-7bba058a50d8",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "results",
+ "uuid": "0d07b3da-3317-4d92-bb85-c301ee2d0753"
+ }
+ ]
+ },
+ "14": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_feature_sync/feature_sync/3.2.1.0",
+ "errors": null,
+ "id": 14,
+ "input_connections": {
+ "wait_for": {
+ "id": 13,
+ "output_name": "results"
+ }
+ },
+ "inputs": [
+ {
+ "description": "runtime parameter for tool Synchronize features",
+ "name": "organism_id"
+ }
+ ],
+ "label": "Synchronize features org2",
+ "name": "Synchronize features",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "txt"
+ }
+ ],
+ "position": {
+ "bottom": 330.3999938964844,
+ "height": 154.39999389648438,
+ "left": 1097,
+ "right": 1297,
+ "top": 176,
+ "width": 200,
+ "x": 1097,
+ "y": 176
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_feature_sync/feature_sync/3.2.1.0",
+ "tool_shed_repository": {
+ "changeset_revision": "64e36c3f0dd6",
+ "name": "tripal_feature_sync",
+ "owner": "gga",
+ "tool_shed": "toolshed.g2.bx.psu.edu"
+ },
+ "tool_state": "{\"organism_id\": {\"__class__\": \"RuntimeValue\"}, \"repeat_ids\": [], \"repeat_types\": [{\"__index__\": 0, \"types\": \"mRNA\"}, {\"__index__\": 1, \"types\": \"polypeptide\"}], \"wait_for\": {\"__class__\": \"ConnectedValue\"}, \"__page__\": null, \"__rerun_remap_job_id__\": null}",
+ "tool_version": "3.2.1.0",
+ "type": "tool",
+ "uuid": "090a12c8-f931-4f3c-8853-9ae581c7c091",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "results",
+ "uuid": "b896a431-ea9b-42e7-a2e8-99c5c43a6069"
+ }
+ ]
+ },
+ "15": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_db_populate_mviews/db_populate_mviews/3.2.1.0",
+ "errors": null,
+ "id": 15,
+ "input_connections": {
+ "wait_for": {
+ "id": 14,
+ "output_name": "results"
+ }
+ },
+ "inputs": [],
+ "label": null,
+ "name": "Populate materialized views",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "txt"
+ }
+ ],
+ "position": {
+ "bottom": 226.39999389648438,
+ "height": 154.39999389648438,
+ "left": 1381,
+ "right": 1581,
+ "top": 72,
+ "width": 200,
+ "x": 1381,
+ "y": 72
+ },
+ "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": "0a3bd8c6-240b-45f6-a90d-e88ff3703fa7",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "results",
+ "uuid": "ba904db6-a017-4090-8d13-e3076f0052c4"
+ }
+ ]
+ },
+ "16": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/tripal_db_index/db_index/3.2.1.1",
+ "errors": null,
+ "id": 16,
+ "input_connections": {
+ "wait_for": {
+ "id": 15,
+ "output_name": "results"
+ }
+ },
+ "inputs": [],
+ "label": null,
+ "name": "Index Tripal data",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "txt"
+ }
+ ],
+ "position": {
+ "bottom": 186.60000610351562,
+ "height": 113.60000610351562,
+ "left": 1657,
+ "right": 1857,
+ "top": 73,
+ "width": 200,
+ "x": 1657,
+ "y": 73
+ },
+ "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": "b01a554e-a43a-494e-876c-ebe134c4c48f",
+ "workflow_outputs": [
+ {
+ "label": null,
+ "output_name": "results",
+ "uuid": "f431f362-7ad4-484f-bce7-b5d290b782d6"
+ }
+ ]
+ }
+ },
+ "tags": [],
+ "uuid": "43552d52-cef0-4601-8a5f-0a9e209c1426",
+ "version": 1
+}
\ No newline at end of file