reworked datasets and Chado IDs assignation

gga_get_data.py

@@ -124,12 +124,18 @@ class GetData(speciesData.SpeciesData):
         # search_excluded_datasets = ["interpro_path", "orthofinder_path", "blastp_path", "blastx_path"]  
         # # These datasets will not be searched if missing in the input file
 
+        dataset_shortname = ""
+        if self.sex is not None or self.sex != "":
+            dataset_shortname = self.genus[0].lower() + "_" + self.species.lower() + "_" + self.sex[0].lower()
+        else:
+            dataset_shortname = self.genus[0].lower() + "_" + self.species.lower()
+
         # Copy datasets in the organism src_data dir tree correct folder
         for k, v in datasets_to_get.items():
             if v:  # If dataset is not present in input file, skip copy
                 if k in genome_datasets:
                     logging.info("Copying {0} ({1}) into {2}".format(k, v, organism_genome_dir))
-                    genome_fname = "v%s.fasta" % self.genome_version
+                    genome_fname = "{0}_v{1}.fasta".format(dataset_shortname, self.genome_version)
                     try:
                         shutil.copyfile(os.path.abspath(v), os.path.join(organism_genome_dir, genome_fname))
                     except Exception as exc:
@@ -137,19 +143,19 @@ class GetData(speciesData.SpeciesData):
                 elif k in annotation_datasets:
                     dataset_fname = ""
                     if k == "gff_path":
-                        dataset_fname = "OGS%s.gff" % self.ogs_version
+                        dataset_fname = "{0}_OGS{1}.gff".format(dataset_shortname, self.genome_version)
                     elif k == "transcripts_path":
-                        dataset_fname = "OGS%s_transcripts.fasta" % self.ogs_version
+                        dataset_fname = "{0}_OGS{1}_transcripts.fasta".format(dataset_shortname, self.genome_version)
                     elif k == "proteins_path":
-                        dataset_fname = "OGS%s_proteins.fasta" % self.ogs_version
+                        dataset_fname = "{0}_OGS{1}_proteins.fasta".format(dataset_shortname, self.genome_version)
                     elif k == "orthofinder_path":
-                        dataset_fname = "OGS%s_orthofinder.tsv" % self.ogs_version
+                        dataset_fname = "{0}_OGS{1}_orthofinder.tsv".format(dataset_shortname, self.genome_version)
                     elif k == "interpro_path":
-                        dataset_fname = "OGS%s_interproscan.xml" % self.ogs_version
+                        dataset_fname = "{0}_OGS{1}_interproscan.xml".format(dataset_shortname, self.genome_version)
                     elif k == "blastp_path":
-                        dataset_fname = "OGS%s_blastp.xml" % self.ogs_version
+                        dataset_fname = "{0}_OGS{1}_blastp.xml".format(dataset_shortname, self.genome_version)
                     elif k == "blastx_path":
-                        dataset_fname = "OGS%s_blastx.xml" % self.ogs_version
+                        dataset_fname = "{0}_OGS{1}_blastx.xml".format(dataset_shortname, self.genome_version)
                     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))