Gtf creation

bin/3.1_create_gtf/Modules/CrossMapper.py

@@ -24,7 +24,7 @@ def __init__(self, org, wd, out, is_dir):
         #                  out    = path to output-file -> Parameter
         #                  is_dir = boolean if wd is data_dir or just working directory
 
-        # Get path to tempfile / outputfile and chainfile
+        # Get path to tempfile / outputfile and chain-file
 
         if is_dir:
             self.infile = os.path.join(wd + "/temp/" + org + ".gtf")
@@ -48,8 +48,8 @@ def get_chain_file(self, org, wd, is_data_dir):
         #                  wd          = working directory
         #                  is_data_dir = is wd data_dir or not
 
-        # return_value: Link to Chainfile for conversion.
-        # Custom chainfiles and chainfiles for more organism can be specified in this section
+        # return_value: Link to chain-file for conversion.
+        # Custom chain-files and chain-files for more organism can be specified in this section
 
         if org == "hg19":
             if is_data_dir:

bin/3.1_create_gtf/Modules/Ensembl/FTPHandling/VersionChecker.py

@@ -138,11 +138,11 @@ def download_currentversion_version(self, version, organism, wd, data_dir):
         # Iterate over Celltype List and Download in corresponding subfolder
 
         for celltype in celltypes_list:
-            link_local = os.path.join(activityfolder_local, celltype)
+            link_local = os.pathchainfil.join(activityfolder_local, celltype)
             link_origin = activityfolder_remote+"/"+celltype
             os.mkdir(link_local)
             self.site_ftp.save_entries_to_file(link_origin, link_local)
 
 
 # Debug section
-# e = EnsemblRegulationFTPRetriever("mus_musculus")
+# e = EnsemblRegulationFTPRetriever("mus_musculus")

bin/3.1_create_gtf/Modules/Ensembl/GTFGen.py

@@ -17,7 +17,7 @@ def __init__(self, organism, release, wd, data_dir):
         # Constructor for GTFGen
         # input_parameter: organism = input organism
         #                  release  = used Ensembl release
-        #                  wd       = working directory (default is ".")
+        #                  wd       = working directory (default is "."), this is used if data_dir is not specified.
         #                  data_dir = data directory (if specified this is used)
 
         self.gff_lines = self.get_organism_as_gff(organism, release, wd, data_dir)

bin/3.1_create_gtf/Modules/SaveResults.py

@@ -5,8 +5,7 @@ class ResultSaver:
 
     """
 
-    Class to save the results. Path is dependent on the data_dir, tissuetype and mapped = True or False.
-    The output is saved to the temp directory in the data folder if crossmapping is necessary.
+    Class to save the results. The output is saved to the temp directory in the data folder if crossmapping is necessary.
 
     @author: Sebastian Beyvers
     @contact: sebastian.beyvers@med.uni-giessen.de
@@ -22,7 +21,6 @@ def __init__(self, results, organism, wd,  mapped, is_data_dir, out):
         #                  wd          = working directory
         #                  mapped      = boolean if crossmapping is necessary
         #                  is_data_dir = boolean if wd is a data_dir (true) or not (false)
-        #                  is_data_dir = boolean if wd is a data_dir (true) or not (false)
 
         print("Save results to File !")
         self.path = ""

bin/3.1_create_gtf/Modules/Validator.py

@@ -10,14 +10,14 @@ class Validator:
     def __init__(self, out_file):
 
         # Constructor
-        # input_parameter: out_file = Path to Outputfile
+        # input_parameter: out_file = path to output file
 
         self.out_file = out_file
         self.test_read_file()
 
     def test_read_file(self):
 
-        # Method to testread the file
+        # Method to test the output file-format
 
         with open(self.out_file) as outfile:
             line = outfile.readline()
@@ -32,4 +32,4 @@ def test_read_file(self):
                 exit(1)
 
 # Debug
-# v = Validator("/home/basti/Schreibtisch/test_hg38.gtf")
+# v = Validator("/home/basti/Schreibtisch/test_hg38.gtf")

bin/3.1_create_gtf/Modules/ucsc/ucsc.py

@@ -44,14 +44,14 @@ def __init__(self, org, wd, data_dir):
 
     def generate_gff_file(self):
 
-        # Call bigBedToBed binary to get a Bed file in the UCSCData folder
+        # Call bigBedToBed binary to get a BED-file in the UCSCData folder
 
         callstring = [self.path_to_bin, self.link, self.output]
         subprocess.call(callstring)
 
     def read_gff_to_gtf(self):
 
-        # Reads Bed File and return a gtf-formatted list of elements.
+        # Reads BED-file and return a GTF-formatted list of elements.
         # return_value: GTF-formatted List of regulation entries from UCSC
 
         gtf_lines = []
@@ -75,8 +75,8 @@ def read_gff_to_gtf(self):
     def find_ID(self, line):
 
         # Find RefSeq ID in Line
-        # input_parameter: line = current line from bedfile
-        # return_value: string with gene_id in gtf-format
+        # input_parameter: line = current line from BED-file
+        # return_value: string with gene_id in GTF-format
 
         pattern = re.compile(r'ID:[0-9]{,9}|$')
         ref_id = re.search(pattern, line).group()
@@ -90,8 +90,8 @@ def find_ID(self, line):
 
     def get_activity(self, line):
 
-        # Find activity categories in bed file
-        # input_parameter: line = current line from bedfile
+        # Find activity categories in BED-file
+        # input_parameter: line = current line from BED-file
         # return_value: list with activity for specified line("keystatus")
 
         key_status = []
@@ -122,7 +122,7 @@ def get_activity_categories(organism, wd):
 
         # Method to get ucsc-celltype categories from JSON config
         # input_parameter: organism = organism parameter
-        #                  wd       = working directory, to find config fil
+        #                  wd       = working directory, to find config file
         # return_value: List of categories from config.
 
         path_to_config = os.path.join(wd+"/config/celltypes_" + organism + ".json")