changeset 1:df03033c3bb2 draft

Uploaded separated data entry points for hg19, hg38, mm9, mm10
author trinity_ctat
date Mon, 04 Jun 2018 14:54:49 -0400
parents 1da522a43f15
children cc020da34af0
files data_manager/add_ctat_lncrna_annotations.py
diffstat 1 files changed, 44 insertions(+), 11 deletions(-) [+]
line wrap: on
line diff
--- a/data_manager/add_ctat_lncrna_annotations.py	Mon Jun 04 14:20:45 2018 -0400
+++ b/data_manager/add_ctat_lncrna_annotations.py	Mon Jun 04 14:54:49 2018 -0400
@@ -13,7 +13,7 @@
 from datetime import *
 
 # Remove the following line when testing without galaxy package:
-from galaxy.util.json import to_json_string
+# from galaxy.util.json import to_json_string
 # Am not using the following:
 # from galaxy.util.json import from_json_string
 
@@ -244,43 +244,76 @@
     print "\nThe location of the Lncrna annotations is {:s}.\n".format(annotations_directory)
     files_in_annotations_directory = set(os.listdir(annotations_directory))
     annotations_file_found = False
-    annotations_file_path = annotations_directory
+    annotations_file_path_mm9 = annotations_directory+"/mm9"
+    annotations_file_path_mm10 = annotations_directory+"/mm10"
+    annotations_file_path_hg19 = annotations_directory+"/hg19"
+    annotations_file_path_hg38 = annotations_directory+"/hg38"
 
     # Set the display_name
     if (args.display_name is None) or (args.display_name == ""):
         # Use the root_annotations_dirname.
         if (root_annotations_dirname != None) and (root_annotations_dirname != ""):
-            display_name = _CTAT_lncrna_DisplayNamePrefix + root_annotations_dirname
+            display_name_hg19 = "hg19"
+            display_name_hg38 = "hg38"
+            display_name_mm10 = "mm10"
+            display_name_mm9 = "mm9"
         else:
             display_name = _CTAT_lncrna_DisplayNamePrefix + _CTAT_lncrnaDir_Name
             print "WARNING: Did not set the display name. Using the default: {:s}".format(display_name_value)
     else:
         display_name = _CTAT_lncrna_annotations_DisplayNamePrefix + args.display_name
-    display_name = display_name.replace(" ","_")
+    # display_name = display_name.replace(" ","_")
 
     # Set the unique_id
     datetime_stamp = datetime.now().strftime("_%Y_%m_%d_%H_%M_%S_%f")
     if (root_annotations_dirname != None) and (root_annotations_dirname != ""):
-        unique_id = root_annotations_dirname + datetime_stamp
+        hg19_unique_id = "ctat_lncrna_hg19" + datetime_stamp
+        mm10_unique_id = "ctat_lncrna_mm10" + datetime_stamp
+        mm9_unique_id = "ctat_lncrna_mm9" + datetime_stamp
+        hg38_unique_id = "ctat_lncrna_hg38" + datetime_stamp
     else:
         unique_id = _CTAT_lncrnaDir_Name + datetime_stamp
 
-    print "The Index's display_name will be set to: {:s}\n".format(display_name)
-    print "Its unique_id will be set to: {:s}\n".format(unique_id)
-    print "Its dir_path will be set to: {:s}\n".format(annotations_file_path)
+    print "The hg19 Index's display_name will be set to: {:s}\n".format(display_name_hg19)
+    print "Its hg19 unique_id will be set to: {:s}\n".format(hg19_unique_id)
+    print "Its hg19 dir_path will be set to: {:s}\n".format(annotations_file_path_hg19)
+
+
+    print "The hg38 Index's display_name will be set to: {:s}\n".format(display_name_hg38)
+    print "Its hg38 unique_id will be set to: {:s}\n".format(hg38_unique_id)
+    print "Its hg38 dir_path will be set to: {:s}\n".format(annotations_file_path_hg38)
+
+
+    print "The mm9 Index's display_name will be set to: {:s}\n".format(display_name_mm9)
+    print "Its mm9 unique_id will be set to: {:s}\n".format(mm9_unique_id)
+    print "Its mm9 dir_path will be set to: {:s}\n".format(annotations_file_path_mm9)
+
+
+    print "The mm10 Index's display_name will be set to: {:s}\n".format(display_name_mm10)
+    print "Its mm10 unique_id will be set to: {:s}\n".format(mm10_unique_id)
+    print "Its mm10 dir_path will be set to: {:s}\n".format(annotations_file_path_mm10)
 
     data_manager_dict = {}
     data_manager_dict['data_tables'] = {}
     data_manager_dict['data_tables'][_CTAT_lncrnaTableName] = []
-    data_table_entry = dict(value=unique_id, name=display_name, path=annotations_file_path)
-    data_manager_dict['data_tables'][_CTAT_lncrnaTableName].append(data_table_entry)
+    data_table_entry_mm9 = dict(value=mm9_unique_id, name=display_name_mm9, path=annotations_file_path_mm9)
+    data_manager_dict['data_tables'][_CTAT_lncrnaTableName].append(data_table_entry_mm9)
+
+    data_table_entry_mm10 = dict(value=mm10_unique_id, name=display_name_mm10, path=annotations_file_path_mm10)
+    data_manager_dict['data_tables'][_CTAT_lncrnaTableName].append(data_table_entry_mm10)
+
+    data_table_entry_hg19 = dict(value=hg19_unique_id, name=display_name_hg19, path=annotations_file_path_hg19)
+    data_manager_dict['data_tables'][_CTAT_lncrnaTableName].append(data_table_entry_hg19)
+
+    data_table_entry_hg38 = dict(value=hg38_unique_id, name=display_name_hg38, path=annotations_file_path_hg38)
+    data_manager_dict['data_tables'][_CTAT_lncrnaTableName].append(data_table_entry_hg38)
 
     # Temporarily the output file's dictionary is written for debugging:
     print "The dictionary for the output file is:\n\t{:s}".format(str(data_manager_dict))
     # Save info to json file. This is used to transfer data from the DataManager tool, to the data manager,
     # which then puts it into the correct .loc file (I think).
     # Remove the following line when testing without galaxy package.
-    open(args.output_filename, 'wb').write(to_json_string(data_manager_dict))
+    # open(args.output_filename, 'wb').write(to_json_string(data_manager_dict))
 
 if __name__ == "__main__":
     main()