From 5c2296d0b2836df7a018870bbf95d2863e90c2c8 Mon Sep 17 00:00:00 2001
From: Arthur Le Bars <arthur.le-bars@sb-roscoff.fr>
Date: Mon, 18 Jan 2021 20:02:44 +0100
Subject: [PATCH] Added demo
---
examples/demo.yaml | 60 +++++++++
gga_init.py | 1 -
gga_load_data.py | 8 +-
run_workflow_phaeoexplorer.py | 216 +++++++++++++++++++++---------
workflows/Galaxy-Workflow-demo.ga | 91 +++++++++++++
5 files changed, 306 insertions(+), 70 deletions(-)
create mode 100644 examples/demo.yaml
create mode 100644 workflows/Galaxy-Workflow-demo.ga
diff --git a/examples/demo.yaml b/examples/demo.yaml
new file mode 100644
index 0000000..9948a4b
--- /dev/null
+++ b/examples/demo.yaml
@@ -0,0 +1,60 @@
+# Input file for the automated creation GGA docker stacks
+# The file consists in a "list" of species for which the script will have to create these stacks/load data into galaxy/run workflows
+
+ectocarpus_sp2_male: # Dummy value the user gives to designate the species (isn't used by the script)
+ # Species description, leave blank if unknown or you don't want it to be used
+ # These parameters are used to set up the various urls and adresses in different containers
+ # The script requires at least the genus to be specified
+ description:
+ genus: "ectocarpus" # Mandatory!
+ species: "sp4"
+ sex: "male"
+ strain: ""
+ common_name: ""
+ origin: ""
+ # Data files scalars contain paths to the source files that have to be loaded into galaxy
+ # WARNING: The paths must be absolute paths!
+ # If any path is left blank and the "parent_directory" scalar is specified, this directory and ALL its subdirectories will be
+ # scanned for files corresponding to the description provided for the species (i.e if the user specified
+ # the sex and strain, the script will look for files containing the genus, species, sex and strain of the species)
+ # If no file corresponding to the description is found, this path will be considered empty and the script will
+ # proceed to the next step (create the directory tree for the GGA docker stack)
+ # If a path is left blank and the "parent_directory" scalar is also blank, no file will be loaded for this "path" scalar
+ # If the files are not named using this nomenclature, please provide all the paths in the corresponding scalars below
+ data:
+ # "parent_directory": (optional) directory from where to search files if a "***_path" scalar is empty
+ # NOTE: Try to set a parent directory "close" to the data files so as not to increase runtime
+ # If empty (""), the script will not search for files and no dataset will be loaded for the corresponding scalar
+ parent_directory: "/path/to/closest/parent/dir"
+ # "***_path": path to the file (optional if parent_directory is set and species "description" scalars are precised)
+ # TODO Not implemented yet
+ genome_path: "/path/to/fasta"
+ transcripts_path: "/path/to/fasta"
+ proteins_path: "/path/to/fasta"
+ gff_path: "/path/to/gff"
+ # If the user has several genomes to upload to galaxy, the next scalar is used by the script to differentiate
+ # between these different versions and name directories according to it.
+ # If left empty, the genome will be considered version "1.0"
+ genome_version: "1.0"
+ # Same as genome version, but for the analysis
+ ogs_version: ""
+ performed_by: ""
+
+# Second example without the comments doc
+ectocarpus_sp2_female:
+ description:
+ genus: "ectocarpus"
+ species: "sp4"
+ sex: "female"
+ strain: ""
+ common_name: ""
+ origin: ""
+ data:
+ parent_directory: "/path/to/closest/parent/dir"
+ genome_path: "/path/to/fasta"
+ transcripts_path: "/path/to/fasta"
+ proteins_path: "/path/to/fasta"
+ gff_path: "/path/to/gff"
+ genome_version: "1.0"
+ ogs_version: "1.0"
+ performed_by: ""
diff --git a/gga_init.py b/gga_init.py
index 2ed11ef..9fd72ae 100644
--- a/gga_init.py
+++ b/gga_init.py
@@ -59,7 +59,6 @@ class DeploySpeciesStack(speciesData.SpeciesData):
if not os.path.isfile("%s/banner.png" % self.species_dir):
shutil.copy("%s/misc/banner.png" % self.script_dir, "%s/banner.png" % self.species_dir)
- # TODO: replace custom_theme in the compose !!
try:
os.mkdir("./nginx/")
os.mkdir("./nginx/conf")
diff --git a/gga_load_data.py b/gga_load_data.py
index c499ca1..cff2747 100644
--- a/gga_load_data.py
+++ b/gga_load_data.py
@@ -309,8 +309,6 @@ class LoadData(speciesData.SpeciesData):
# - Get any other existing organisms IDs before updating the galaxy instance --> separate
# Calling this function is mandatory to have a working galaxy instance history
-
- # TODO Move this function to utils (it's also used in "run_workflow")
# TODO Run a check to see if the instance is correctly set up
# :return:
@@ -706,10 +704,10 @@ if __name__ == "__main__":
# # Set or get the history for the current organism
# load_data_for_current_species.set_get_history()
- #
- # # Remove H. sapiens from database if here
+
+ # Remove H. sapiens from database if here TODO: set a dedicated history for removing H. sapiens (instead of doing it into a species history)
# logging.info("Removing H. sapiens from Chado database for %s" % load_data_for_current_species.full_name)
- # load_data_for_current_species.remove_homo_sapiens_from_db()
+ load_data_for_current_species.remove_homo_sapiens_from_db()
# logging.info("Successfully removed H. sapiens from Chado database for %s" % load_data_for_current_species.full_name)
# logging.info("Importing datasets into history for %s" % load_data_for_current_species.full_name)
diff --git a/run_workflow_phaeoexplorer.py b/run_workflow_phaeoexplorer.py
index 330707b..35e645f 100644
--- a/run_workflow_phaeoexplorer.py
+++ b/run_workflow_phaeoexplorer.py
@@ -11,6 +11,7 @@ import json
import utilities
import speciesData
+from bioblend.galaxy.objects import GalaxyInstance
from bioblend import galaxy
"""
@@ -122,17 +123,17 @@ class RunWorkflow(speciesData.SpeciesData):
- def import_datasets_to_history(self):
- """
- Load the datasets into the current species history
+ # def import_datasets_to_history(self):
+ # """
+ # Load the datasets into the current species history
- """
+ # """
- logging.info("Uploading datasets into history %s" % self.history_id)
- self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=self.datasets["genome_file"])
- self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=self.datasets["gff_file"])
- self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=self.datasets["transcripts_file"])
- self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=self.datasets["proteins_file"])
+ # logging.info("Uploading datasets into history %s" % self.history_id)
+ # self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=self.datasets["genome_file"])
+ # self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=self.datasets["gff_file"])
+ # self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=self.datasets["transcripts_file"])
+ # self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=self.datasets["proteins_file"])
def connect_to_instance(self):
"""
@@ -196,7 +197,7 @@ class RunWorkflow(speciesData.SpeciesData):
history_id=self.history_id,
tool_inputs={"name": self.full_name_lowercase + " OGS" + self.ogs_version,
"program": "Performed by Genoscope",
- "programversion": str("OGS" + self.ogs_version),
+ "programversion": str(self.sex + " OGS" + self.ogs_version),
"sourcename": "Genoscope",
"date_executed": self.date})
@@ -207,10 +208,13 @@ class RunWorkflow(speciesData.SpeciesData):
history_id=self.history_id,
tool_inputs={"name": self.full_name_lowercase + " genome v" + self.genome_version,
"program": "Performed by Genoscope",
- "programversion": str("genome v" + self.genome_version),
+ "programversion": str(self.sex + "genome v" + self.genome_version),
"sourcename": "Genoscope",
"date_executed": self.date})
+
+ # Also get the organism and analyses IDs
self.get_organism_and_analyses_ids()
+
logging.info("Finished initializing instance")
@@ -230,8 +234,8 @@ class RunWorkflow(speciesData.SpeciesData):
:return:
"""
- logging.debug("running workflow: " + str(workflow_path))
- workflow_name = self.full_name + "_base"
+ logging.info("importing workflow: " + str(workflow_path))
+ workflow_name = "demo" # for workflow demo
workflow_ga_file = workflow_path
# Name the workflow in galaxy
@@ -247,29 +251,24 @@ class RunWorkflow(speciesData.SpeciesData):
# Solving format issues in the .ga (encoding errors when importing the file via bioblend)
with open(workflow_ga_file, 'r') as ga_in_file:
- workflow = str(ga_in_file.readlines())
- # Ugly fix for the jbrowse parameters (formatting)
- workflow = workflow.replace('{\\\\\\\\\\\\"unique_id\\\\\\\\\\\\": \\\\\\\\\\\\"UNIQUE_ID\\\\\\\\\\\\"}',
- str('{\\\\\\\\\\\\"unique_id\\\\\\\\\\\\": \\\\\\\\\\\\"' + self.genus + " " + self.species) + '\\\\\\\\\\\\"')
- workflow = workflow.replace('\\\\\\\\\\\\"name\\\\\\\\\\\\": \\\\\\\\\\\\"NAME\\\\\\\\\\\\"',
- str('\\\\\\\\\\\\"name\\\\\\\\\\\\": \\\\\\\\\\\\"' + self.genus.lower()[0] + self.species) + '\\\\\\\\\\\\"')
+ # workflow = str(ga_in_file.readlines())
+ # # Ugly fix for the jbrowse parameters (formatting) --> TODO: OBSOLETE (everything set at runtime)
+ # workflow = workflow.replace('{\\\\\\\\\\\\"unique_id\\\\\\\\\\\\": \\\\\\\\\\\\"UNIQUE_ID\\\\\\\\\\\\"}',
+ # str('{\\\\\\\\\\\\"unique_id\\\\\\\\\\\\": \\\\\\\\\\\\"' + self.genus + " " + self.species) + '\\\\\\\\\\\\"')
+ # workflow = workflow.replace('\\\\\\\\\\\\"name\\\\\\\\\\\\": \\\\\\\\\\\\"NAME\\\\\\\\\\\\"',
+ # str('\\\\\\\\\\\\"name\\\\\\\\\\\\": \\\\\\\\\\\\"' + self.genus.lower()[0] + self.species) + '\\\\\\\\\\\\"')
# workflow = workflow.replace("\\\\", "\\") # to restore the correct amount of backslashes in the workflow string before import
- # testing with scratchgmodv1
- workflow = workflow.replace('http://localhost/sp/genus_species/feature/Genus/species/mRNA/{id}',
- "http://http://scratchgmodv1:8888/sp/" + self.genus_lowercase+ "_" + self.species + "/feature/" + self.genus + "/mRNA/{id}")
- # TODO: Uncomment next lines in production
+ # # OBSOLETE
# workflow = workflow.replace('http://localhost/sp/genus_species/feature/Genus/species/mRNA/{id}',
- # "http://abims-gga.sb-roscoff.fr/sp/" + self.genus_lowercase + "_" + self.species + "/feature/" + self.genus + "/mRNA/{id}")
- # workflow = workflow[2:-2] # if the line under doesn't output a correct json
- # workflow = "r'" + workflow
- # workflow = workflow + "'"
- # workflow = workflow[:-2] # if the line above doesn't output a correct json
+ # "http://" + self.config["custom_host"] + ":8888/sp/" + self.genus_lowercase+ "_" + self.species + "/feature/" + self.genus + "/mRNA/{id}")
- print(workflow[4516])
- print(workflow)
+ # # The json dict might sometimes turn to be invalid for unknown reasons and the json module will fail to decode it (galaxy export error)
+ # workflow = workflow[2:-2] # if the line under doesn't output a correct json
+ # # workflow = workflow[:-2] # if the line above doesn't output a correct json
- workflow_dict = json.loads(workflow)
+ # Store the decoded json dictionary
+ workflow_dict = json.load(ga_in_file)
self.instance.workflows.import_workflow_dict(workflow_dict=workflow_dict)
self.workflow_name = workflow_name
@@ -278,15 +277,78 @@ class RunWorkflow(speciesData.SpeciesData):
show_workflow = self.instance.workflows.show_workflow(workflow_id=workflow_id)
logging.debug("Workflow ID: " + workflow_id)
- logging.debug("Inputs:")
- logging.debug(show_workflow["Inputs"])
self.instance.workflows.invoke_workflow(workflow_id=workflow_id,
history_id=self.history_id,
params=workflow_parameters,
inputs=datamap,
inputs_by="")
- # self.instance.workflows.delete_workflow(workflow_id=workflow_id) # TODO : Keep for prod (add a "if test" condition)
+ # self.instance.workflows.delete_workflow(workflow_id=workflow_id) # TODO : Keep for prod? (add a "if test" condition)
+
+ def import_datasets_into_history(self):
+ """
+ Find datasets in a library, get their ID and import thme into the current history if they are not already
+
+ :return:
+ """
+
+ # Instanciate the instance
+ gio = GalaxyInstance(url=self.instance_url,
+ email=self.config["custom_galaxy_default_admin_email"],
+ password=self.config["custom_galaxy_default_admin_password"])
+
+ prj_lib = gio.libraries.get_previews(name="Project Data")
+ self.library_id = prj_lib[0].id
+
+ instance_source_data_folders = self.instance.libraries.get_folders(library_id=str(self.library_id))
+
+ folders_ids = {}
+ current_folder_name = ""
+ # Loop over the folders in the library and map folders names to their IDs
+ for i in instance_source_data_folders:
+ for k, v in i.items():
+ if k == "name":
+ folders_ids[v] = 0
+ current_folder_name = v
+ if k == "id":
+ folders_ids[current_folder_name] = v
+
+ # Iterating over the folders to find datasets and map datasets to their IDs
+ logging.info("Datasets IDs: ")
+ for k, v in folders_ids.items():
+ if k == "/genome":
+ sub_folder_content = self.instance.folders.show_folder(folder_id=v, contents=True)
+ final_sub_folder_content = self.instance.folders.show_folder(folder_id=sub_folder_content["folder_contents"][0]["id"], contents=True)
+ for k2, v2 in final_sub_folder_content.items():
+ for e in v2:
+ if type(e) == dict:
+ if e["name"].endswith(".fa"):
+ self.datasets["genome_file"] = e["ldda_id"]
+ logging.info("\t" + e["name"] + ": " + e["ldda_id"])
+ if k == "/annotation":
+ sub_folder_content = self.instance.folders.show_folder(folder_id=v, contents=True)
+ final_sub_folder_content = self.instance.folders.show_folder(folder_id=sub_folder_content["folder_contents"][0]["id"], contents=True)
+ for k2, v2 in final_sub_folder_content.items():
+ for e in v2:
+ if type(e) == dict:
+ # TODO: manage versions? (differentiate between the correct folders using self.config)
+ if "transcripts" in e["name"]:
+ self.datasets["transcripts_file"] = e["ldda_id"]
+ logging.info("\t" + e["name"] + ": " + e["ldda_id"])
+ elif "proteins" in e["name"]:
+ self.datasets["proteins_file"] = e["ldda_id"]
+ logging.info("\t" + e["name"] + ": " + e["ldda_id"])
+ elif "gff" in e["name"]:
+ self.datasets["gff_file"] = e["ldda_id"]
+ logging.info("\t" + e["name"] + ": " + e["ldda_id"])
+
+ logging.info("Uploading datasets into history %s" % self.history_id)
+ self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=self.datasets["genome_file"])
+ self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=self.datasets["gff_file"])
+ self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=self.datasets["transcripts_file"])
+ self.instance.histories.upload_dataset_from_library(history_id=self.history_id, lib_dataset_id=self.datasets["proteins_file"])
+
+ return {"history_id": self.history_id, "library_id": self.library_id, "datasets": self.datasets}
def get_organism_and_analyses_ids(self):
@@ -425,48 +487,74 @@ if __name__ == "__main__":
run_workflow_for_current_organism.set_get_history()
# run_workflow_for_current_organism.get_species_history_id()
- # Prepare the instance+history for the current organism (add organism and analyses in Chado) --> add argument? (no risk as chado refuses to duplicate an analysis/organism)
- # run_workflow_for_current_organism.prepare_history()
+ # Prepare the instance+history for the current organism (add organism and analyses in Chado) --> add argument?
+ # (althought there is no risk as chado refuses to duplicate an analysis/organism)
+ run_workflow_for_current_organism.prepare_history()
# Get the attributes of the instance and project data files
run_workflow_for_current_organism.get_instance_attributes()
+ # Import datasets into history (needs to be done in gga_load_data??)
+ run_workflow_for_current_organism.import_datasets_into_history()
+
+
workflow_parameters = dict()
# Explicit workflow parameter names
# TODO: Use an external mapping file instead?
- # Base worflow (loading data in chado and first sync into tripal)
- PARAM_LOAD_FILE1_INTO_HISTORY, PARAM_LOAD_FILE2_INTO_HISTORY, PARAM_LOAD_FILE3_INTO_HISTORY, PARAM_LOAD_FILE4_INTO_HISTORY = "0", "1", "2", "3"
- PARAM_LOAD_FASTA_IN_CHADO = "4"
- PARAM_LOAD_GFF_IN_CHADO = "5"
- PARAM_SYNC_ORGANISM_INTO_TRIPAL = "6"
- PARAM_SYNC_GENOME_ANALYSIS_INTO_TRIPAL = "7"
- PARAM_SYNC_OGS_ANALYSIS_INTO_TRIPAL = "8"
- PARAM_SYNC_FEATURES_INTO_TRIPAL = "9"
-
+ # DEMO WORKFLOW
+ PARAM_LOAD_FASTA_IN_HISTORY = "0"
+ PARAM_LOAD_FASTA_IN_CHADO = "1"
+ # PARAM_SYNC_ORGANISM_INTO_TRIPAL = "2"
+ # PARAM_SYNC_GENOME_ANALYSIS_INTO_TRIPAL = "3"
+ # PARAM_SYNC_FEATURES_INTO_TRIPAL = "4"
- workflow_parameters[PARAM_LOAD_FILE1_INTO_HISTORY] = {}
- workflow_parameters[PARAM_LOAD_FILE2_INTO_HISTORY] = {}
- workflow_parameters[PARAM_LOAD_FILE3_INTO_HISTORY] = {}
- workflow_parameters[PARAM_LOAD_FILE4_INTO_HISTORY] = {}
+ # Mapping parameters
+ workflow_parameters[PARAM_LOAD_FASTA_IN_HISTORY] = {}
workflow_parameters[PARAM_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"}
- workflow_parameters[PARAM_LOAD_GFF_IN_CHADO] = {"organism": run_workflow_for_current_organism.org_id,
- "analysis_id": run_workflow_for_current_organism.ogs_analysis_id}
- workflow_parameters[PARAM_SYNC_ORGANISM_INTO_TRIPAL] = {"organism_id": run_workflow_for_current_organism.org_id}
- workflow_parameters[PARAM_SYNC_GENOME_ANALYSIS_INTO_TRIPAL] = {"analysis_id": run_workflow_for_current_organism.ogs_analysis_id}
- workflow_parameters[PARAM_SYNC_OGS_ANALYSIS_INTO_TRIPAL] = {"analysis_id": run_workflow_for_current_organism.genome_analysis_id}
- workflow_parameters[PARAM_SYNC_FEATURES_INTO_TRIPAL] = {"organism_id": run_workflow_for_current_organism.org_id}
-
- # Loading files into history works a bit different than the others as it's not a GMOD tool but a standard Galaxy tool
- # It requires this additional "datamap" (conveniently named "datamap" here), requiring the source type of the file and its corresponding ID (unique)
+ "analysis_id": run_workflow_for_current_organism.genome_analysis_id,
+ "do_update": "true"}
+ # workflow_parameters[PARAM_SYNC_ORGANISM_INTO_TRIPAL] = {"organism_id": run_workflow_for_current_organism.org_id}
+ # workflow_parameters[PARAM_SYNC_GENOME_ANALYSIS_INTO_TRIPAL] = {"analysis_id": run_workflow_for_current_organism.ogs_analysis_id}
+ # workflow_parameters[PARAM_SYNC_FEATURES_INTO_TRIPAL] = {"organism_id": run_workflow_for_current_organism.org_id}
+
run_workflow_for_current_organism.datamap = dict()
- run_workflow_for_current_organism.datamap[PARAM_LOAD_FILE1_INTO_HISTORY] = {"src": "hda", "id": run_workflow_for_current_organism.datasets["genome_file"]}
- run_workflow_for_current_organism.datamap[PARAM_LOAD_FILE2_INTO_HISTORY] = {"src": "hda", "id": run_workflow_for_current_organism.datasets["gff_file"]}
- run_workflow_for_current_organism.datamap[PARAM_LOAD_FILE3_INTO_HISTORY] = {"src": "hda", "id": run_workflow_for_current_organism.datasets["proteins_file"]}
- run_workflow_for_current_organism.datamap[PARAM_LOAD_FILE4_INTO_HISTORY] = {"src": "hda", "id": run_workflow_for_current_organism.datasets["transcripts_file"]}
+ run_workflow_for_current_organism.datamap[PARAM_LOAD_FASTA_IN_HISTORY] = {"src": "hda", "id": run_workflow_for_current_organism.datasets["genome_file"]}
+
+
+ """COMMENTED FOR THE DEMO"""
+ # # Base worflow (loading data in chado and first sync into tripal)
+ # PARAM_LOAD_FILE1_INTO_HISTORY, PARAM_LOAD_FILE2_INTO_HISTORY, PARAM_LOAD_FILE3_INTO_HISTORY, PARAM_LOAD_FILE4_INTO_HISTORY = "0", "1", "2", "3"
+ # PARAM_LOAD_FASTA_IN_CHADO = "4"
+ # PARAM_LOAD_GFF_IN_CHADO = "5"
+ # PARAM_SYNC_ORGANISM_INTO_TRIPAL = "6"
+ # PARAM_SYNC_GENOME_ANALYSIS_INTO_TRIPAL = "7"
+ # PARAM_SYNC_OGS_ANALYSIS_INTO_TRIPAL = "8"
+ # PARAM_SYNC_FEATURES_INTO_TRIPAL = "9"
+
+
+ # workflow_parameters[PARAM_LOAD_FILE1_INTO_HISTORY] = {}
+ # workflow_parameters[PARAM_LOAD_FILE2_INTO_HISTORY] = {}
+ # workflow_parameters[PARAM_LOAD_FILE3_INTO_HISTORY] = {}
+ # workflow_parameters[PARAM_LOAD_FILE4_INTO_HISTORY] = {}
+ # workflow_parameters[PARAM_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"}
+ # workflow_parameters[PARAM_LOAD_GFF_IN_CHADO] = {"organism": run_workflow_for_current_organism.org_id,
+ # "analysis_id": run_workflow_for_current_organism.ogs_analysis_id}
+ # workflow_parameters[PARAM_SYNC_ORGANISM_INTO_TRIPAL] = {"organism_id": run_workflow_for_current_organism.org_id}
+ # workflow_parameters[PARAM_SYNC_GENOME_ANALYSIS_INTO_TRIPAL] = {"analysis_id": run_workflow_for_current_organism.ogs_analysis_id}
+ # workflow_parameters[PARAM_SYNC_OGS_ANALYSIS_INTO_TRIPAL] = {"analysis_id": run_workflow_for_current_organism.genome_analysis_id}
+ # workflow_parameters[PARAM_SYNC_FEATURES_INTO_TRIPAL] = {"organism_id": run_workflow_for_current_organism.org_id}
+
+ # # Loading files into history works a bit different than the others as it's not a GMOD tool but a standard Galaxy tool
+ # # It requires this additional "datamap" (conveniently named "datamap" here), requiring the source type of the file and its corresponding ID (unique)
+ # run_workflow_for_current_organism.datamap = dict()
+ # run_workflow_for_current_organism.datamap[PARAM_LOAD_FILE1_INTO_HISTORY] = {"src": "hda", "id": run_workflow_for_current_organism.datasets["genome_file"]}
+ # run_workflow_for_current_organism.datamap[PARAM_LOAD_FILE2_INTO_HISTORY] = {"src": "hda", "id": run_workflow_for_current_organism.datasets["gff_file"]}
+ # run_workflow_for_current_organism.datamap[PARAM_LOAD_FILE3_INTO_HISTORY] = {"src": "hda", "id": run_workflow_for_current_organism.datasets["proteins_file"]}
+ # run_workflow_for_current_organism.datamap[PARAM_LOAD_FILE4_INTO_HISTORY] = {"src": "hda", "id": run_workflow_for_current_organism.datasets["transcripts_file"]}
# Run the workflow with the parameters set above
run_workflow_for_current_organism.run_workflow(workflow_path=workflow,
diff --git a/workflows/Galaxy-Workflow-demo.ga b/workflows/Galaxy-Workflow-demo.ga
new file mode 100644
index 0000000..c59f6ee
--- /dev/null
+++ b/workflows/Galaxy-Workflow-demo.ga
@@ -0,0 +1,91 @@
+{
+ "a_galaxy_workflow": "true",
+ "annotation": "",
+ "format-version": "0.1",
+ "name": "demo",
+ "steps": {
+ "0": {
+ "annotation": "",
+ "content_id": null,
+ "errors": null,
+ "id": 0,
+ "input_connections": {},
+ "inputs": [],
+ "label": null,
+ "name": "Input dataset",
+ "outputs": [],
+ "position": {
+ "left": 222,
+ "top": 286.8500061035156
+ },
+ "tool_id": null,
+ "tool_state": "{\"optional\": false}",
+ "tool_version": null,
+ "type": "data_input",
+ "uuid": "74f22d9b-e764-45e4-b0eb-579c9b647ea0",
+ "workflow_outputs": []
+ },
+ "1": {
+ "annotation": "",
+ "content_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_feature_load_fasta/feature_load_fasta/2.3.3",
+ "errors": null,
+ "id": 1,
+ "input_connections": {
+ "fasta": {
+ "id": 0,
+ "output_name": "output"
+ },
+ "wait_for": {
+ "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": null,
+ "name": "Chado load fasta",
+ "outputs": [
+ {
+ "name": "results",
+ "type": "json"
+ }
+ ],
+ "position": {
+ "left": 509.9000244140625,
+ "top": 271
+ },
+ "post_job_actions": {},
+ "tool_id": "toolshed.g2.bx.psu.edu/repos/gga/chado_feature_load_fasta/feature_load_fasta/2.3.3",
+ "tool_shed_repository": {
+ "changeset_revision": "a7ab30ded37d",
+ "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": "2.3.3",
+ "type": "tool",
+ "uuid": "f3655d26-08b8-408e-bfef-6e8a4aaab355",
+ "workflow_outputs": []
+ }
+ },
+ "tags": [],
+ "uuid": "ca4cf11f-76c0-40dd-925b-b20284bcc857",
+ "version": 3
+}
\ No newline at end of file
--
GitLab