Let galaxy decide which versions of tools it wants to use for gga_load_data.py

gga_init.py

@@ -127,12 +127,13 @@ class DeploySpeciesStack(speciesData.SpeciesData):
             gspecies_compose_file.write(gspecies_compose_output)
 
 
-        galaxy_nginx_conf_template = env.get_template("galaxy_nginx.conf.j2")
-        galaxy_nginx_conf_output = galaxy_nginx_conf_template.render(render_vars)
-        with open(os.path.join(self.main_dir, "galaxy_nginx.conf"), "w") as galaxy_nginx_conf_file:
-            logging.debug("Writing the galaxy_nginx.conf file for %s" % self.genus_species)
-            galaxy_nginx_conf_file.truncate(0)
-            galaxy_nginx_conf_file.write(galaxy_nginx_conf_output)
+        if not os.path.isfile(os.path.join(self.main_dir, "galaxy_nginx.conf")):
+            galaxy_nginx_conf_template = env.get_template("galaxy_nginx.conf.j2")
+            galaxy_nginx_conf_output = galaxy_nginx_conf_template.render(render_vars)
+            with open(os.path.join(self.main_dir, "galaxy_nginx.conf"), "w") as galaxy_nginx_conf_file:
+                logging.debug("Writing the galaxy_nginx.conf file for %s" % self.genus_species)
+                galaxy_nginx_conf_file.truncate(0)
+                galaxy_nginx_conf_file.write(galaxy_nginx_conf_output)
 
         # Create the volumes (directory) of the species docker-compose file
         create_mounts(working_dir=".", main_dir=self.main_dir)

gga_load_data.py

@@ -81,43 +81,46 @@ class LoadData(speciesData.SpeciesData):
 
         """
 
-        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_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")
 
-        if delete_organism_tool["version"] != "2.3.4+galaxy0":
-            toolshed_dict = delete_organism_tool["tool_shed_repository"]
-            logging.warning("Changeset for %s is not installed" % toolshed_dict["name"])
-            changeset_revision = "b1aa4f9d82fe"
-            name = toolshed_dict["name"]
-            owner = toolshed_dict["owner"]
-            toolshed = "https://" + toolshed_dict["tool_shed"]
-            logging.warning("Installing changeset for %s" % toolshed_dict["name"])
-
-            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)
-
-
-        if get_organism_tool["version"] != "2.3.3":
-            toolshed_dict = get_organism_tool["tool_shed_repository"]
-            logging.warning("Changeset for %s is not installed" % toolshed_dict["name"])
-            changeset_revision = "b07279b5f3bf"
-            name = toolshed_dict["name"]
-            owner = toolshed_dict["owner"]
-            toolshed = "https://" + toolshed_dict["tool_shed"]
-            logging.warning("Installing changeset for %s" % toolshed_dict["name"])
-
-            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)
+        get_organism_tool_version = get_organism_tool["version"]
+        delete_organism_tool_version = delete_organism_tool["version"]
+
+        # if delete_organism_tool["version"] != "2.3.4+galaxy0":
+        #     toolshed_dict = delete_organism_tool["tool_shed_repository"]
+        #     logging.warning("Changeset for %s is not installed" % toolshed_dict["name"])
+        #     changeset_revision = "b1aa4f9d82fe"
+        #     name = toolshed_dict["name"]
+        #     owner = toolshed_dict["owner"]
+        #     toolshed = "https://" + toolshed_dict["tool_shed"]
+        #     logging.warning("Installing changeset for %s" % toolshed_dict["name"])
+
+        #     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)
+
+
+        # 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 for %s" % toolshed_dict["name"])
+
+        #     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)
 
         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"]
@@ -128,7 +131,7 @@ 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:

run_workflow_phaeoexplorer.py

@@ -640,25 +640,26 @@ class RunWorkflow(speciesData.SpeciesData):
             if dataset_dict["history_id"] == self.history_id:
                 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"] 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"] 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"] 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"] 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"] 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)
@@ -1200,6 +1201,8 @@ if __name__ == "__main__":
                 workflow_dict["steps"]["10"]["tool_state"] = workflow_dict["steps"]["10"]["tool_state"].replace("__FULL_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("__FULL_NAME_ORG2__", org2_full_name).replace("__UNIQUE_ID_ORG2__", org2_species_folder_name)
 
+                print(workflow_dict)
+                
                 # Import the workflow in galaxy as a dict
                 instance.workflows.import_workflow_dict(workflow_dict=workflow_dict)
 

speciesData.py

@@ -87,7 +87,9 @@ 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("-", "_").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 = {}