Set data file and dataset name as constants. Refactor run_wf (WIP)

constants.py

+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+
 # Constants used in the input yaml
 ORG_PARAM_NAME = "name"
 ORG_PARAM_DESC = "description"
@@ -24,7 +27,6 @@ ORG_PARAM_SERVICES = "services"
 ORG_PARAM_SERVICES_BLAST = "blast"
 ORG_PARAM_SERVICES_GO = "go"
 
-
 # Constants used in the config yaml file
 CONF_ALL_HOSTNAME = "hostname"
 CONF_ALL_HTTP_PORT = "http_port"
@@ -45,12 +47,23 @@ CONF_TRIPAL_THEME_NAME = "tripal_theme_name"
 CONF_TRIPAL_THEME_GIT_CLONE = "tripal_theme_git_clone"
 CONF_JBROWSE_MENU_URL = "jbrowse_menu_url"
 
+# Data
+FILENAME_SUFFIX_TRANSCRIPTS = "transcripts_gff.fasta"
+FILENAME_SUFFIX_PROTEINS = "proteins.fasta"
+FILENAME_SUFFIX_INTERPRO = "interproscan.xml"
+FILENAME_SUFFIX_BLASTP = "diamond_blastp_vs_uniref90.xml" # Temporary constant: this value should be in the organism input file
+FILENAME_SUFFIX_BLASTX = "diamond_blastx_vs_uniref90.xml" # Temporary constant: this value should be in the organism input file
+FILENAME_SUFFIX_ORTHOFINDER = "orthologous_one2one_vs_Ec32.tsv" # Temporary constant: this value should be in the organism input file
+DATA_DATE = "2021-02-24" # Temporary constant: this value should be in the organism input file, for each data
+
 # default config file
 DEFAULT_CONFIG = "examples/config"
 
+# Galaxy tools
 GET_ORGANISMS_TOOL = "toolshed.g2.bx.psu.edu/repos/gga/chado_organism_get_organisms/organism_get_organisms/2.3.4+galaxy0"
 DELETE_ORGANISMS_TOOL = "toolshed.g2.bx.psu.edu/repos/gga/chado_organism_delete_organisms/organism_delete_organisms/2.3.4+galaxy0"
 
+# Galaxy library
 HOST_DATA_DIR='src_data'
 CONTAINER_DATA_DIR_ROOT='/project_data'
 GALAXY_LIBRARY_NAME = 'Project Data'

gga_get_data.py

@@ -101,7 +101,7 @@ class GetData(speciesData.SpeciesData):
         for k, v in genome_datasets.items():
             if v:  # If dataset is not present in input file, skip copy
                 logging.info("Copying {0} ({1}) into {2}".format(k, v, organism_genome_dir))
-                genome_fname = "{0}_v{1}.fasta".format(self.dataset_prefix, self.genome_version)
+                genome_fname = self.genome_filename
                 try:
                     shutil.copyfile(os.path.abspath(v), os.path.join(organism_genome_dir, genome_fname))
                 except Exception as exc:
@@ -111,19 +111,19 @@ class GetData(speciesData.SpeciesData):
             if v:  # If dataset is not present in input file, skip copy
                 dataset_fname = ""
                 if k == constants.ORG_PARAM_DATA_GFF_PATH:
-                    dataset_fname = "{0}_OGS{1}_{2}.gff".format(self.dataset_prefix, self.ogs_version, self.get_last_modified_time_string(os.path.abspath(v)))
+                    dataset_fname = self.gff_filename
                 elif k == constants.ORG_PARAM_DATA_TRANSCRIPTS_PATH:
-                    dataset_fname = "{0}_OGS{1}_transcripts.fasta".format(self.dataset_prefix, self.ogs_version)
+                    dataset_fname = self.transcripts_filename
                 elif k == constants.ORG_PARAM_DATA_PROTEINS_PATH:
-                    dataset_fname = "{0}_OGS{1}_proteins.fasta".format(self.dataset_prefix, self.ogs_version)
+                    dataset_fname = self.proteins_filename
                 elif k == constants.ORG_PARAM_DATA_ORTHOFINDER_PATH:
-                    dataset_fname = "{0}_OGS{1}_orthofinder.tsv".format(self.dataset_prefix, self.ogs_version)
+                    dataset_fname = self.orthofinder_filename
                 elif k == constants.ORG_PARAM_DATA_INTERPRO_PATH:
-                    dataset_fname = "{0}_OGS{1}_interproscan.xml".format(self.dataset_prefix, self.ogs_version)
+                    dataset_fname = self.interpro_filename
                 elif k == constants.ORG_PARAM_DATA_BLASTP_PATH:
-                    dataset_fname = "{0}_OGS{1}_blastp.xml".format(self.dataset_prefix, self.ogs_version)
+                    dataset_fname = self.blastp_filename
                 elif k == constants.ORG_PARAM_DATA_BLASTX_PATH:
-                    dataset_fname = "{0}_OGS{1}_blastx.xml".format(self.dataset_prefix, self.ogs_version)
+                    dataset_fname = self.blastx_filename
                 logging.info("Copying {0} ({1}) into {2}".format(k, v, organism_annotation_dir))
                 try:
                     shutil.copyfile(os.path.abspath(v), os.path.join(organism_annotation_dir, dataset_fname))

phaoexplorer_constants.py

+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+
+import constants
+
 ### Workflows
 
 WORKFLOW_LOAD_FASTA_GFF_JBROWSE = "load_fasta_gff_jbrowse"
@@ -17,7 +22,7 @@ ADD_ANALYSIS_TOOL_VERSION = "2.3.4+galaxy0"
 ADD_ANALYSIS_TOOL_ID= ADD_ANALYSIS_TOOL_NAME + ADD_ANALYSIS_TOOL_VERSION
 ADD_ANALYSIS_TOOL_CHANGESET_REVISION = "10b2b1c70e69"
 ADD_ANALYSIS_TOOL_PARAM_PROGRAM = "Performed by Genoscope"
-ADD_ANALYSIS_TOOL_PARAM_DATE = "2021-02-24"
+ADD_ANALYSIS_TOOL_PARAM_DATE = constants.DATA_DATE
 
 GET_ORGANISMS_TOOL_NAME = "toolshed.g2.bx.psu.edu/repos/gga/chado_organism_get_organisms/organism_get_organisms/"
 GET_ORGANISMS_TOOL_VERSION = "2.3.4+galaxy0"

speciesData.py

@@ -116,6 +116,15 @@ class SpeciesData:
         else:
             self.dataset_prefix = self.genus[0].lower() + "_" + self.species_lowercase
 
+        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)
+        self.transcripts_filename = "{0}_OGS{1}_{2}".format(self.dataset_prefix, self.ogs_version, constants.TRANSCRIPTS_FILENAME_SUFFIX)
+        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)
+
         # Bioblend/Chado IDs for an organism analyses/organisms/datasets/history/library
         self.org_id = None
         self.genome_analysis_id = None
@@ -131,8 +140,6 @@ class SpeciesData:
         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()