ORForise 1.5.1__py3-none-any.whl → 1.6.1__py3-none-any.whl

ORForise/List_Tools.py

@@ -0,0 +1,63 @@
+from importlib import import_module
+import argparse
+import sys, os
+import gzip, csv
+import logging
+from datetime import datetime
+
+
+try:
+    from utils import *
+    from Comparator import tool_comparison
+except ImportError:
+    from .Comparator import tool_comparison
+    from .utils import *
+
+
+
+
+
+def main():
+    print(WELCOME)
+
+    print('ORForise ' + ORForise_Version + ': List Tools Run Parameters')
+
+    tools = set()
+    base_dirs = [
+        os.path.join(os.path.dirname(__file__), 'Tools'),
+        os.path.abspath(os.path.join(os.path.dirname(__file__), '..', 'Tools')),
+    ]
+
+    for base in base_dirs:
+        if not os.path.isdir(base):
+            continue
+        try:
+            for entry in os.listdir(base):
+                entry_path = os.path.join(base, entry)
+                if os.path.isdir(entry_path) and not entry.startswith('.') and entry != '__pycache__':
+                    tools.add(entry)
+        except OSError:
+            continue
+
+    if not tools:
+        print('No tools found in the searched directories.')
+        return
+
+    print('Available tools:')
+    for tool_name in sorted(tools):
+        print(' -', tool_name)
+        try:
+            tool_ = import_module('Tools.' + tool_name + '.' + tool_name)
+            print('    Imported from Tools.' + tool_name)
+        except ModuleNotFoundError:
+            try:
+                tool_ = import_module('ORForise.Tools.' + tool_name + '.' + tool_name)
+                print('    Imported from ORForise.Tools.' + tool_name)
+            except ModuleNotFoundError:
+                print('    Tool not importable')
+
+
+
+if __name__ == "__main__":
+    main()
+    print("Complete")

ORForise/StORForise.py

@@ -1,10 +1,13 @@
 from importlib import import_module
-
 import argparse
-import collections
 import csv
 
-from Comparator import tool_comparison
+try:
+    from utils import *
+    from Comparator import tool_comparison
+except ImportError:
+    from .Comparator import tool_comparison
+    from .utils import *
 
 ###################
 
@@ -98,7 +101,8 @@ def comparator(tool, input_to_analyse, storfs_to_find_missing, genome_to_compare
 
 
 def main():
-    parser = argparse.ArgumentParser()
+    print(WELCOME)
+    parser = argparse.ArgumentParser(description='ORForise ' + ORForise_Version + ': StORForise Run Parameters.')
     parser.add_argument('-t', '--tool', default='GFF', help='Which tool/format would you analyse with StORF-R?')
     parser.add_argument('-i', '--input_to_analyse', default='', help='Location of file containing missed genes')
     parser.add_argument('-stf', '--storfs_to_find_missing', default='', help='STORFs to find missing.')

ORForise/Tools/EasyGene/EasyGene.py

@@ -11,11 +11,23 @@ except ImportError:
 def EasyGene(*args):
     tool_pred = args[0]
     dna_regions = args[1]
+    if not dna_regions: # This triggers if dna_regions is an empty dict (GFF_Intersect passed nothing)
+        dna_regions = collections.OrderedDict()
+        with open(tool_pred, 'r') as EasyGene_input:
+            for line in EasyGene_input:
+                line = line.split()
+                if len(line) == 10 and line[0] and "CDS" in line[2] and line[0] not in dna_regions:
+                    dna_regions[line[0]] = []  # Placeholder for genome sequence
+        return dna_regions
+
     easyGene_ORFs = collections.OrderedDict()
     for dna_region in dna_regions:
         easyGene_ORFs[dna_region] = collections.OrderedDict()
     for dna_region in dna_regions:
-        genome = dna_regions[dna_region][0]
+        try:
+            genome = dna_regions[dna_region][0]
+        except IndexError:
+            genome = dna_regions[dna_region]
         genome_size = len(genome)
         genome_rev = revCompIterative(genome)
         with open(tool_pred, 'r') as EasyGene_input:

ORForise/Tools/{GLIMMER_3/GLIMMER_3.py → GLIMMER3/GLIMMER3.py}

@@ -19,7 +19,7 @@ def GLIMMER_3(*args):
         genome_size = len(genome)
         genome_rev = revCompIterative(genome)
         with open(tool_pred,
-                  'r') as glimmer_input:  # GLIMMER_3 reverses the start and stop positions for ORFS on the negative strand
+                  'r') as glimmer_input:  # GLIMMER3 reverses the start and stop positions for ORFS on the negative strand
             for line in glimmer_input:
                 if '>' not in line:  # This will not work with multiple contigs
                     line = line.split()
@@ -39,7 +39,7 @@ def GLIMMER_3(*args):
                             startCodon = genome[start - 1:start + 3]
                             stopCodon = genome[stop - 3:stop]
                         po = str(start) + ',' + str(stop)
-                        orf = [strand, startCodon, stopCodon, 'CDS', 'GLIMMER_3']
+                        orf = [strand, startCodon, stopCodon, 'CDS', 'GLIMMER3']
                         GLIMMER_ORFs.update({po: orf})
 
     for group in GLIMMER_ORFs:

ORForise/Tools/{GeneMark_HA/GeneMark_HA.py → GeneMarkHA/GeneMarkHA.py}

@@ -34,7 +34,7 @@ def GeneMark_HA(*args):
                         startCodon = genome[start - 1:start + 2]
                         stopCodon = genome[stop - 3:stop]
                     po = str(start) + ',' + str(stop)
-                    orf = [strand, startCodon, stopCodon, 'CDS', 'GeneMark_HA']
+                    orf = [strand, startCodon, stopCodon, 'CDS', 'GeneMarkHA']
                     geneMark_HA_ORFs.update({po: orf})
 
     for group in geneMark_HA_ORFs:

ORForise/Tools/Prodigal/Prodigal.py

@@ -11,11 +11,23 @@ except ImportError:
 def Prodigal(*args):
     tool_pred = args[0]
     dna_regions = args[1]
+    if not dna_regions: # This triggers if dna_regions is an empty dict (GFF_Intersect passed nothing)
+        dna_regions = collections.OrderedDict()
+        with open(tool_pred, 'r') as EasyGene_input:
+            for line in EasyGene_input:
+                line = line.split()
+                if len(line) == 10 and "CDS" in line[2] and line[0] not in dna_regions:
+                    dna_regions[line[0]] = []  # Placeholder for genome sequence
+        return dna_regions
+
     prodigal_ORFs = collections.OrderedDict()
     for dna_region in dna_regions:
         prodigal_ORFs[dna_region] = collections.OrderedDict()
     for dna_region in dna_regions:
-        genome = dna_regions[dna_region][0]
+        try:
+            genome = dna_regions[dna_region][0]
+        except IndexError:
+            genome = dna_regions[dna_region]
         genome_size = len(genome)
         genome_rev = revCompIterative(genome)
         with open(tool_pred, 'r') as prodigal_input:

ORForise/utils.py

@@ -4,7 +4,10 @@ import collections
 # Constants
 SHORT_ORF_LENGTH = 300
 MIN_COVERAGE = 75
-ORForise_Version = 'v1.5.1'
+ORForise_Version = 'v1.6.1'
+WELCOME=("Thank you for using ORForise\nPlease report any issues to: https://github.com/NickJD/ORForise/issues\n"
+        "Please Cite: https://doi.org/10.1093/bioinformatics/btab827\n"
+        "#####")
 
 
 def revCompIterative(watson):  # Gets Reverse Complement