Release v2.1.0

General

• Bump cryptography requirement version to 3.2
• Create tools to handle multiple docker stacks in docker_tools repository (toggl galaxy state, update service)

Input config.yml file

• Fix typo in parameter galaxy_default_admin_user
• Add parameter galaxy_default_admin_key (required to create the admin user galaxy_default_admin_user in Galaxy)
• Check that all required parameters are not empty

Input organisms.yml file

• Add the parameter picture_path in the description section to add this picture in the Tripal homepage
• Add parameter contig_prefix in the data section to list the prefixes used for contig names. Required when they are multiple strains from the same species to map the contig name prefix to the right JBrowse dataset ID in Tripal (see Step "init")
• Add the go summary functionality in Tripal. This functionality can be activated with parameter go set to 1 in the services section
• Remove unused performed_by parameter
• Fix code for empty strain and/or sex

Step "init"

• Add a picture of the species in the Tripal homepage (the picture of the main strain if exists, the picture of another strain if not)
• Fix Tripal site name
• Add env variable JBROWSE_LINKS in the Tripal service, to map the contig name prefix to the right JBrowse dataset ID in Tripal (for Tripal hyperlinks to JBrowse)

Step "get data"

• Change data file names: use prefix strain_sex

Step "run workflow Phaeoexplorer"

• Create a parent module run_workflow_phaeo.py, with classes and methods used by the workflow scripts
• Create file constants_phaeo.py to store constants used in step "run workflow Phaeoexplorer" (workflows and galaxy tools details)
• Script gga_run_workflow_phaeo_jbrowse.py: runs a Galaxy workflow to load the genome, the annotations and the proteins to Chado, Tripal and JBrowse, for one or two strains of the same species
• Work in progress: workflows to load blast and interpro results

species_data.py

@@ -9,6 +9,30 @@ import constants
 
 from _datetime import datetime
 
+def clean_string(string):
+    if not string is None and string != "":
+        cleaned_string = string \
+            .strip() \
+            .replace(" ", "_") \
+            .replace("-", "_") \
+            .replace(".", "_") \
+            .replace("#", "_") \
+            .replace("(", "") \
+            .replace(")", "") \
+            .replace("'", "")
+        return cleaned_string
+    else:
+        return string
+
+def set_service_attribute(service, parameters_dictionary):
+    parameters_dictionary_services = parameters_dictionary[constants.ORG_PARAM_SERVICES]
+    service_value = "0"
+    if (service in parameters_dictionary_services.keys()
+            and parameters_dictionary_services[service] is not None
+            and parameters_dictionary_services[service] != ""):
+        service_value = parameters_dictionary_services[service]
+    return service_value
+
 class SpeciesData:
     """
     This class contains attributes and functions to interact with the galaxy container of the GGA environment
@@ -40,34 +64,31 @@ class SpeciesData:
             sys.exit(0)
         return 1
 
-    def clean_string(self, string):
-        if not string is None and string != "":
-            clean_string = string.replace(" ", "_").replace("-", "_").replace("(", "").replace(")", "").replace("'", "").strip()
-            return clean_string
-        else:
-            return string
-
     def __init__(self, parameters_dictionary):
         self.parameters_dictionary = parameters_dictionary
         self.name = parameters_dictionary[constants.ORG_PARAM_NAME]
         parameters_dictionary_description=parameters_dictionary[constants.ORG_PARAM_DESC]
         parameters_dictionary_data = parameters_dictionary[constants.ORG_PARAM_DATA]
-        parameters_dictionary_services = parameters_dictionary[constants.ORG_PARAM_SERVICES]
 
-        self.species = self.clean_string(parameters_dictionary_description[constants.ORG_PARAM_DESC_SPECIES])
-        self.genus = self.clean_string(parameters_dictionary_description[constants.ORG_PARAM_DESC_GENUS])
-        self.strain = self.clean_string(parameters_dictionary_description[constants.ORG_PARAM_DESC_STRAIN])
-        self.sex = self.clean_string(parameters_dictionary_description[constants.ORG_PARAM_DESC_SEX])
-        self.common = self.clean_string(parameters_dictionary_description[constants.ORG_PARAM_DESC_COMMON_NAME])
+        self.species = clean_string(parameters_dictionary_description[constants.ORG_PARAM_DESC_SPECIES])
+        self.genus = clean_string(parameters_dictionary_description[constants.ORG_PARAM_DESC_GENUS])
+        self.strain = clean_string(parameters_dictionary_description[constants.ORG_PARAM_DESC_STRAIN])
+        if self.strain is None:
+            self.strain = ""
+        self.sex = clean_string(parameters_dictionary_description[constants.ORG_PARAM_DESC_SEX])
+        self.common_name = parameters_dictionary_description[constants.ORG_PARAM_DESC_COMMON_NAME]
+        if self.sex is None:
+            self.sex = ""
+        self.common_name = parameters_dictionary_description[constants.ORG_PARAM_DESC_COMMON_NAME]
 
         self.date = datetime.today().strftime("%Y-%m-%d")
         self.origin = parameters_dictionary_description[constants.ORG_PARAM_DESC_ORIGIN]
-        self.performed = parameters_dictionary_data[constants.ORG_PARAM_DATA_PERFORMED_BY]
 
         if parameters_dictionary_data[constants.ORG_PARAM_DATA_GENOME_VERSION] == "":
             self.genome_version = "1.0"
         else:
             self.genome_version = str(parameters_dictionary_data[constants.ORG_PARAM_DATA_GENOME_VERSION])
+
         if parameters_dictionary_data[constants.ORG_PARAM_DATA_OGS_VERSION] == "":
             self.ogs_version = "1.0"
         else:
@@ -75,6 +96,7 @@ class SpeciesData:
 
         # TODO: catch blocks if key is absent in input
         self.genome_path = parameters_dictionary_data[constants.ORG_PARAM_DATA_GENOME_PATH]
+        self.contig_prefix = parameters_dictionary_data[constants.ORG_PARAM_DATA_GENOME_CONTIG_PREFIX]
         self.transcripts_path = parameters_dictionary_data[constants.ORG_PARAM_DATA_TRANSCRIPTS_PATH]
         self.proteins_path = parameters_dictionary_data[constants.ORG_PARAM_DATA_PROTEINS_PATH]
         self.gff_path = parameters_dictionary_data[constants.ORG_PARAM_DATA_GFF_PATH]
@@ -83,49 +105,54 @@ class SpeciesData:
         self.blastx_path = parameters_dictionary_data[constants.ORG_PARAM_DATA_BLASTX_PATH]
         self.orthofinder_path = parameters_dictionary_data[constants.ORG_PARAM_DATA_ORTHOFINDER_PATH]
 
-        if(constants.ORG_PARAM_SERVICES_BLAST in parameters_dictionary_services.keys()):
-            self.blast = parameters_dictionary_services[constants.ORG_PARAM_SERVICES_BLAST]
-        else:
-            self.blast = "0"
+        self.blast = set_service_attribute(constants.ORG_PARAM_SERVICES_BLAST, parameters_dictionary)
+        self.go = set_service_attribute(constants.ORG_PARAM_SERVICES_GO, parameters_dictionary)
 
-        self.genus_lowercase = self.genus[0].lower() + self.genus[1:]
-        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.genus_lowercase = self.genus.lower()
+        self.species_lowercase = self.species.lower()
+        try:
+            self.strain_lowercase = self.strain.lower()
+        except AttributeError as exc:
+            self.strain_lowercase = None
+        try:
+            self.sex_lowercase = self.sex.lower()
+        except AttributeError as exc:
+            self.sex_lowercase = None
+
+        self.genus_uppercase = self.genus[0].upper() + self.genus_lowercase[1:]
+        self.genus_species = "{0}_{1}".format(self.genus_lowercase, self.species_lowercase)
+        self.strain_sex = '_'.join(utilities.filter_empty_not_empty_items([self.strain_lowercase, self.sex_lowercase])["not_empty"])
 
+        self.full_name = ' '.join(utilities.filter_empty_not_empty_items([self.genus_uppercase, self.species_lowercase, self.strain, self.sex])["not_empty"])
         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 = "{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.species_folder_name = "_".join(utilities.filter_empty_not_empty_items(
+            [self.genus_lowercase,
+             self.species_lowercase,
+             self.strain_lowercase,
+             self.sex_lowercase])["not_empty"])
+
+        self.dataset_prefix = self.strain_sex
+        # If both strain and sex are empty attributes, change the dataset prefix to nothing instead of "_"
+        if self.dataset_prefix == "_":
+            self.dataset_prefix = ""
+
+        self.genome_filename = "{0}_v{1}.fasta".format(self.dataset_prefix, self.genome_version)
+        self.gff_filename = "{0}_OGS{1}_{2}.gff".format(self.dataset_prefix, self.ogs_version, constants.DATA_DATE.replace("-",""))
+        self.transcripts_filename = "{0}_OGS{1}_{2}".format(self.dataset_prefix, self.ogs_version, constants.FILENAME_SUFFIX_TRANSCRIPTS)
+        self.proteins_filename = "{0}_OGS{1}_{2}".format(self.dataset_prefix, self.ogs_version, constants.FILENAME_SUFFIX_PROTEINS)
+        self.interpro_filename = "{0}_OGS{1}_{2}".format(self.dataset_prefix, self.ogs_version, constants.FILENAME_SUFFIX_INTERPRO)
+        self.blastp_filename = "{0}_OGS{1}_{2}".format(self.dataset_prefix, self.ogs_version, constants.FILENAME_SUFFIX_BLASTP)
+        self.blastx_filename = "{0}_OGS{1}_{2}".format(self.dataset_prefix, self.ogs_version, constants.FILENAME_SUFFIX_BLASTX)
+        self.orthofinder_filename = "{0}_OGS{1}_{2}".format(self.dataset_prefix, self.ogs_version, constants.FILENAME_SUFFIX_ORTHOFINDER)
 
         self.script_dir = os.path.dirname(os.path.realpath(sys.argv[0]))
         self.main_dir = None
         self.species_dir = None
-
-        self.tool_panel = None
-        self.datasets = dict()
-        self.datasets_name = dict()
-        self.source_files = dict()
-        self.workflow_name = None
-        self.metadata = dict()
-        self.api_key = None  # API key used to communicate with the galaxy instance. Cannot be used to do user-tied actions
-        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"])
+
+        # # Bioblend/Chado IDs for an organism analyses/organisms/datasets/history/library
+        self.instance_url = None
+        self.instance = None
+        self.history_id = None
+        self.history_name = str(self.genus_species)