Workflow v2

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"]
@@ -59,7+59,7 @@
         self.genus_uppercase = self.genus[0].upper() + self.genus[1:]
         self.chado_species_name = "{0} {1}".format(self.species, self.sex)
         self.full_name = ' '.join(utilities.filter_empty_not_empty_items([self.genus_uppercase, self.species, self.strain, self.sex])["not_empty"])
         self.full_name = self.full_name.replace("__", "_").replace("_ ", "_").replace(" _", "_")
         if self.full_name.endswith("_") or self.full_name.endswith(" "):
             self.full_name = self.full_name[0:-2]
 
         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 = {}
 

[Loraine Gueguen]

Sauf erreur de ma part, tout le nettoyage est fait en amont directement sur les attributs self.genus, self.species, self.sex et self.strain. Ces replace() sont donc inutiles.

[Loraine Gueguen]

        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]

idem, je supprimerais les replace()