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

utilities.py

@@ -4,9 +4,6 @@
 import yaml
 import logging
 import sys
-import os
-import subprocess
-import bioblend
 import constants
 
 def load_yaml(yaml_file):
@@ -36,12 +33,16 @@ def parse_config(config_file):
     """
 
     config_dict = load_yaml(config_file)
-    if isinstance(config_dict, dict):
-        #logging.debug("Config dictionary: {0}".format(config_dict))
-        return config_dict
-    else:
-        logging.critical("Config yaml file is not a dictionary" % config_file)
+    if not isinstance(config_dict, dict):
+        logging.critical("Config yaml file is not a dictionary (%s)" % config_file)
         sys.exit()
+    else:
+        for required_parameter in constants.REQUIRED_PARAMETERS:
+            if not config_dict[required_parameter]:
+                logging.critical("{0} parameter improperly configured in config file {1}".format(required_parameter, config_file))
+                sys.exit()
+
+        return config_dict
 
 def parse_input(input_file):
     """
@@ -75,47 +76,13 @@ def filter_empty_not_empty_items(li):
             filtered_dict["not_empty"].append(i)
     return filtered_dict
 
+def no_empty_items(li):
 
-def check_galaxy_state(genus_lowercase, species, script_dir):
-    """
-    Read the logs of the galaxy container for the current species to check if the service is "ready"
-
-    :param genus_lowercase:
-    :param species:
-    :param script_dir:
-    :return:
-    """
-
-    # Run supervisorctl status in the galaxy container via serexec
-    # Change serexec permissions in repo
-    try:
-        os.chmod("%s/serexec" % script_dir, 0o0755)
-    except PermissionError:
-        logging.warning("serexec permissions incorrect in %s" % script_dir)
-    galaxy_logs = subprocess.run(["%s/serexec" % script_dir, "{0}_{1}_galaxy".format(genus_lowercase, species),
-                                  "supervisorctl", "status", "galaxy:"], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
-    if "galaxy:galaxy_web                RUNNING" in str(galaxy_logs.stdout) \
-            and "galaxy:handler0                  RUNNING" in str(galaxy_logs.stdout) \
-            and "galaxy:handler1                  RUNNING" in str(galaxy_logs.stdout):
-        return 1
-    else:
-        return 0
-
-
-def get_species_history_id(instance, full_name):
-    """
-    Set and return the current species history id in its galaxy instance
-
-    :param instance:
-    :param full_name:
-    :return:
-    """
-
-    histories = instance.histories.get_histories(name=str(full_name))
-    history_id = histories[0]["id"]
-    show_history = instance.histories.show_history(history_id=history_id)
-
-    return [history_id, show_history]
+    empty = True
+    for i in li:
+        if i is None or i == "":
+            empty = False
+    return empty
 
 def get_gspecies_string_from_sp_dict(sp_dict):
 
@@ -143,7 +110,6 @@ def get_unique_species_str_list(sp_dict_list):
                 
     return unique_species_li
 
-
 def get_unique_species_dict_list(sp_dict_list):
     """
     Filter the species dictionary list to return only unique genus_species combinations
@@ -162,34 +128,67 @@ def get_unique_species_dict_list(sp_dict_list):
         if gspecies not in unique_species_dict.keys() or ( constants.ORG_PARAM_DESC_MAIN_SPECIES in sp[constants.ORG_PARAM_DESC].keys() and
                                                            sp[constants.ORG_PARAM_DESC][constants.ORG_PARAM_DESC_MAIN_SPECIES] == True ) :
             unique_species_dict[gspecies] = sp
-        else:
-            continue
 
     for k, v in unique_species_dict.items():
         unique_species_list_of_dict.append(v)
 
     return unique_species_list_of_dict
 
-def run_tool(instance, tool_id, history_id, tool_inputs):
+def get_sp_picture(sp_dict_list):
+    """
+    Get the picture for each species: the picture of the main strain if exists, other strain if not
+    """
 
-    output_dict = None
-    try:
-        logging.debug("Running tool {0} with tool inputs: {1}".format(tool_id, tool_inputs))
-        output_dict =  instance.tools.run_tool(
-            tool_id=tool_id,
-            history_id=history_id,
-            tool_inputs=tool_inputs)
-    except bioblend.ConnectionError:
-        logging.error("Unexpected HTTP response (bioblend.ConnectionError) when running tool {0} with tool inputs: {1}".format(tool_id, tool_inputs))
+    sp_picture_dict = {}
+
+    for sp in sp_dict_list:
 
-    return output_dict
+        genus_species = get_gspecies_string_from_sp_dict(sp)
+        # logging.debug("picture path for {0} {1}: {2}".format(genus_species,
+        #                                                      sp[constants.ORG_PARAM_DESC][constants.ORG_PARAM_DESC_STRAIN],
+        #                                                      sp[constants.ORG_PARAM_DESC][constants.ORG_PARAM_DESC_PICTURE_PATH]))
+
+        # no picture stored yet for this genus_species
+        if genus_species not in sp_picture_dict.keys() \
+            or (genus_species in sp_picture_dict.keys()
+                and sp_picture_dict[genus_species] == None):
+
+            if constants.ORG_PARAM_DESC_PICTURE_PATH in sp[constants.ORG_PARAM_DESC].keys() \
+                and sp[constants.ORG_PARAM_DESC][constants.ORG_PARAM_DESC_PICTURE_PATH] != None \
+                and sp[constants.ORG_PARAM_DESC][constants.ORG_PARAM_DESC_PICTURE_PATH] != "":
+                sp_picture_dict[genus_species] = sp[constants.ORG_PARAM_DESC][constants.ORG_PARAM_DESC_PICTURE_PATH]
+            else:
+                sp_picture_dict[genus_species] = None
+
+        # overwrite stored picture if a picture exists for the main strain
+        if (constants.ORG_PARAM_DESC_MAIN_SPECIES in sp[constants.ORG_PARAM_DESC].keys()
+            and sp[constants.ORG_PARAM_DESC][constants.ORG_PARAM_DESC_MAIN_SPECIES] == True )\
+            and (constants.ORG_PARAM_DESC_PICTURE_PATH in sp[constants.ORG_PARAM_DESC].keys()
+                and sp[constants.ORG_PARAM_DESC][constants.ORG_PARAM_DESC_PICTURE_PATH] != None
+                and sp[constants.ORG_PARAM_DESC][constants.ORG_PARAM_DESC_PICTURE_PATH] != ""):
+
+            sp_picture_dict[genus_species] = sp[constants.ORG_PARAM_DESC][constants.ORG_PARAM_DESC_PICTURE_PATH]
+
+    # logging.debug("picture dict: %s" % sp_picture_dict)
+
+    return sp_picture_dict
+
+def get_sp_jbrowse_links(org_list):
+    """
+    Get the jbrowse links from all strains for each species
+    """
 
-def run_tool_and_get_single_output_dataset_id(instance, tool_id, history_id, tool_inputs):
+    jbrowse_links_dict = {}
 
-    output_dict = run_tool(instance, tool_id, history_id, tool_inputs)
-    single_output_dataset_id = output_dict["outputs"][0]["id"]
+    for org in org_list:
+        gspecies = org.genus_species
+        if org.contig_prefix != "":
+            if gspecies not in jbrowse_links_dict.keys():
+                jbrowse_links_dict[gspecies] = org.contig_prefix + ">" + org.species_folder_name
+            else:
+                jbrowse_links_dict[gspecies] = jbrowse_links_dict[gspecies] + ";" + org.contig_prefix + ">" + org.species_folder_name
 
-    return single_output_dataset_id
+    return jbrowse_links_dict
 
 def create_org_param_dict_from_constants():
     """
@@ -206,9 +205,11 @@ def create_org_param_dict_from_constants():
     org_param_dict["org_param_desc_strain"] = constants.ORG_PARAM_DESC_STRAIN
     org_param_dict["org_param_desc_common_name"] = constants.ORG_PARAM_DESC_COMMON_NAME
     org_param_dict["org_param_desc_origin"] = constants.ORG_PARAM_DESC_ORIGIN
+    org_param_dict["org_param_desc_picture_path"] = constants.ORG_PARAM_DESC_PICTURE_PATH
     org_param_dict["org_param_desc_main_species"] = constants.ORG_PARAM_DESC_MAIN_SPECIES
     org_param_dict["org_param_data"] = constants.ORG_PARAM_DATA
     org_param_dict["org_param_data_genome_path"] = constants.ORG_PARAM_DATA_GENOME_PATH
+    org_param_dict["org_param_data_genome_contig_prefix"] = constants.ORG_PARAM_DATA_GENOME_CONTIG_PREFIX
     org_param_dict["org_param_data_transcripts_path"] = constants.ORG_PARAM_DATA_TRANSCRIPTS_PATH
     org_param_dict["org_param_data_proteins_path"] = constants.ORG_PARAM_DATA_PROTEINS_PATH
     org_param_dict["org_param_data_gff_path"] = constants.ORG_PARAM_DATA_GFF_PATH
@@ -218,8 +219,8 @@ def create_org_param_dict_from_constants():
     org_param_dict["org_param_data_blastx_path"] = constants.ORG_PARAM_DATA_BLASTX_PATH
     org_param_dict["org_param_data_genome_version"] = constants.ORG_PARAM_DATA_GENOME_VERSION
     org_param_dict["org_param_data_ogs_version"] = constants.ORG_PARAM_DATA_OGS_VERSION
-    org_param_dict["org_param_data_performed_by"] = constants.ORG_PARAM_DATA_PERFORMED_BY
     org_param_dict["org_param_services"] = constants.ORG_PARAM_SERVICES
     org_param_dict["org_param_services_blast"] = constants.ORG_PARAM_SERVICES_BLAST
+    org_param_dict["org_param_services_go"] = constants.ORG_PARAM_SERVICES_GO
 
-    return org_param_dict
\ No newline at end of file
+    return org_param_dict