ORForise 1.6.1__tar.gz → 1.6.3__tar.gz

{orforise-1.6.1 → orforise-1.6.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ORForise
-Version: 1.6.1
+Version: 1.6.3
 Summary: ORForise - A platform for analysing and comparing genome annotations.
 Author-email: Nicholas Dimonaco <nicholas@dimonaco.co.uk>
 License:                     GNU GENERAL PUBLIC LICENSE
@@ -662,7 +662,7 @@ Example output files from ```Annotation-Compare```, ```Aggregate-Compare```, ```
 For Help: ```Annotation-Compare -h ```
 
 ```python
-ORForise v1.6.1: Annotatione-Compare Run Parameters.
+ORForise v1.6.3: Annotatione-Compare Run Parameters.
 
 Required Arguments:
   -dna GENOME_DNA       Genome DNA file (.fa) which both annotations are based on
@@ -730,7 +730,7 @@ ORForise can be used as the example below.
 For Help: ```Aggregate-Compare -h ```
 
 ```python
-ORForise v1.6.1: Aggregate-Compare Run Parameters.
+ORForise v1.6.3: Aggregate-Compare Run Parameters.
 
 Required Arguments:
   -dna GENOME_DNA       Genome DNA file (.fa) which both annotations are based on
@@ -811,7 +811,7 @@ GFF-Adder combines two existing annotations (GFF or other tool formats).
 For Help: ```GFF-Adder -h ```
 
 ```python
-ORForise v1.6.1: GFF-Adder Run Parameters.
+ORForise v1.6.3: GFF-Adder Run Parameters.
 
 Required Arguments:
   -dna GENOME_DNA       Genome DNA file (.fa) which both annotations are based on
@@ -868,7 +868,7 @@ usage: Annotation_Intersector.py [-h] -ref REFERENCE_ANNOTATION -at
                                  [-cov COVERAGE] [--report-discordance]
                                  [--report-discordance-file REPORT_DISCORDANCE_FILE]
 
-ORForise v1.6.1: Annotation-Intersector Run Parameters
+ORForise v1.6.3: Annotation-Intersector Run Parameters
 
 options:
   -h, --help            show this help message and exit
@@ -947,7 +947,7 @@ Please report any issues to: https://github.com/NickJD/ORForise/issues
 #####
 usage: Convert_To_GFF.py [-h] [-dna GENOME_DNA] -i INPUT_ANNOTATION -fmt FORMAT -o OUTPUT_DIR [-gi GENE_IDENT] [--verbose]
 
-ORForise v1.6.1: Convert-To-GFF Run Parameters
+ORForise v1.6.3: Convert-To-GFF Run Parameters
 
 Required Arguments:
   -dna GENOME_DNA      Genome DNA file (.fa)
@@ -1026,7 +1026,7 @@ Defaults options were used.
 **MetaGeneMark - Version '2020'** - http://exon.gatech.edu/meta_gmhmmp.cgi  
 GFF was chosen as output type.
 
-**Prodigal - Version 2.6.3** - https://github.com/hyattpd/Prodigal  
+**Prodigal (Includes Pyrodigal) - Version 2.6.3** - https://github.com/hyattpd/Prodigal  
 GFF was chosen as output type.
 
 **TransDecoder - Version 5.5.0** - https://github.com/TransDecoder/TransDecoder/wiki  

{orforise-1.6.1 → orforise-1.6.3}/README.md

@@ -21,7 +21,7 @@ Example output files from ```Annotation-Compare```, ```Aggregate-Compare```, ```
 For Help: ```Annotation-Compare -h ```
 
 ```python
-ORForise v1.6.1: Annotatione-Compare Run Parameters.
+ORForise v1.6.3: Annotatione-Compare Run Parameters.
 
 Required Arguments:
   -dna GENOME_DNA       Genome DNA file (.fa) which both annotations are based on
@@ -89,7 +89,7 @@ ORForise can be used as the example below.
 For Help: ```Aggregate-Compare -h ```
 
 ```python
-ORForise v1.6.1: Aggregate-Compare Run Parameters.
+ORForise v1.6.3: Aggregate-Compare Run Parameters.
 
 Required Arguments:
   -dna GENOME_DNA       Genome DNA file (.fa) which both annotations are based on
@@ -170,7 +170,7 @@ GFF-Adder combines two existing annotations (GFF or other tool formats).
 For Help: ```GFF-Adder -h ```
 
 ```python
-ORForise v1.6.1: GFF-Adder Run Parameters.
+ORForise v1.6.3: GFF-Adder Run Parameters.
 
 Required Arguments:
   -dna GENOME_DNA       Genome DNA file (.fa) which both annotations are based on
@@ -227,7 +227,7 @@ usage: Annotation_Intersector.py [-h] -ref REFERENCE_ANNOTATION -at
                                  [-cov COVERAGE] [--report-discordance]
                                  [--report-discordance-file REPORT_DISCORDANCE_FILE]
 
-ORForise v1.6.1: Annotation-Intersector Run Parameters
+ORForise v1.6.3: Annotation-Intersector Run Parameters
 
 options:
   -h, --help            show this help message and exit
@@ -306,7 +306,7 @@ Please report any issues to: https://github.com/NickJD/ORForise/issues
 #####
 usage: Convert_To_GFF.py [-h] [-dna GENOME_DNA] -i INPUT_ANNOTATION -fmt FORMAT -o OUTPUT_DIR [-gi GENE_IDENT] [--verbose]
 
-ORForise v1.6.1: Convert-To-GFF Run Parameters
+ORForise v1.6.3: Convert-To-GFF Run Parameters
 
 Required Arguments:
   -dna GENOME_DNA      Genome DNA file (.fa)
@@ -385,7 +385,7 @@ Defaults options were used.
 **MetaGeneMark - Version '2020'** - http://exon.gatech.edu/meta_gmhmmp.cgi  
 GFF was chosen as output type.
 
-**Prodigal - Version 2.6.3** - https://github.com/hyattpd/Prodigal  
+**Prodigal (Includes Pyrodigal) - Version 2.6.3** - https://github.com/hyattpd/Prodigal  
 GFF was chosen as output type.
 
 **TransDecoder - Version 5.5.0** - https://github.com/TransDecoder/TransDecoder/wiki  

{orforise-1.6.1 → orforise-1.6.3}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "ORForise"
-version = "1.6.1"
+version = "1.6.3"
 authors = [
     {name = "Nicholas Dimonaco", email = "nicholas@dimonaco.co.uk"}
 ]

{orforise-1.6.1 → orforise-1.6.3}/src/ORForise/Aggregate_Compare.py

@@ -2,14 +2,12 @@ from importlib import import_module
 import argparse
 import csv, os, gzip, sys
 
-
 try:
-    from Comparator import tool_comparison
-    from utils import *
-except ImportError:
     from .Comparator import tool_comparison
     from .utils import *
-
+except (ImportError, ModuleNotFoundError):
+    from Comparator import tool_comparison
+    from utils import *
 ############################################
 
 def comparator(options):

{orforise-1.6.1 → orforise-1.6.3}/src/ORForise/Annotation_Compare.py

@@ -7,11 +7,12 @@ from datetime import datetime
 
 
 try:
-    from utils import *
-    from Comparator import tool_comparison
-except ImportError:
     from .Comparator import tool_comparison
     from .utils import *
+except (ImportError, ModuleNotFoundError):
+    from Comparator import tool_comparison
+    from utils import *
+
 
 ##########################
 

{orforise-1.6.1 → orforise-1.6.3}/src/ORForise/Annotation_Intersector.py

@@ -11,9 +11,9 @@ if not logging.getLogger().handlers:
     logging.basicConfig(stream=sys.stdout, level=logging.INFO, format='%(levelname)s: %(message)s')
 
 try:
-    from utils import *
-except ImportError:
     from .utils import *
+except (ImportError, ModuleNotFoundError):
+    from utils import *
 
 ################################
 

{orforise-1.6.1 → orforise-1.6.3}/src/ORForise/Comparator.py

@@ -1,8 +1,9 @@
 import numpy as np
+
 try:
+    from .utils import *
+except (ImportError, ModuleNotFoundError):
     from utils import *
-except ImportError:
-    from ORForise.utils import *
 
 
 class comparator:  # Class to hold global-type variables

{orforise-1.6.1 → orforise-1.6.3}/src/ORForise/Convert_To_GFF.py

@@ -5,11 +5,13 @@ import os
 import sys
 
 try:
+    from .utils import *
+    from .Aux.TabToGFF.TabToGFF import TabToGFF
+except (ImportError, ModuleNotFoundError):
     from utils import *
     from ORForise.src.ORForise.Aux.TabToGFF import TabToGFF
-except ImportError:
-    from ORForise.utils import *
-    from ORForise.Aux.TabToGFF.TabToGFF import TabToGFF
+
+
 
 
 def setup_logging(outdir, verbose=False):

{orforise-1.6.1 → orforise-1.6.3}/src/ORForise/GFF_Adder.py

@@ -6,9 +6,9 @@ from datetime import date
 import sys
 
 try:
-    from utils import *
-except ImportError:
     from .utils import *
+except (ImportError, ModuleNotFoundError):
+    from utils import *
 
 
 ########################################
@@ -370,7 +370,7 @@ def gff_adder(options):
 
     else:
         # Reference tool provided: attempt to call it with dna_regions first (multi-contig aware), fallback to legacy signature
-        reference_tool = options.reference_tool if options.reference_tool != 'StORF_Reporter' else 'StORF_Reporter'
+        reference_tool = options.reference_tool if options.reference_tool != 'StORF-Reporter' else 'StORF-Reporter'
         try:
             reference_tool_mod = import_module('Tools.' + reference_tool + '.' + reference_tool, package='my_current_pkg')
         except ModuleNotFoundError:

{orforise-1.6.1 → orforise-1.6.3}/src/ORForise/List_Tools.py

@@ -1,17 +1,10 @@
 from importlib import import_module
-import argparse
-import sys, os
-import gzip, csv
-import logging
-from datetime import datetime
-
+import  os
 
 try:
-    from utils import *
-    from Comparator import tool_comparison
-except ImportError:
-    from .Comparator import tool_comparison
     from .utils import *
+except (ImportError, ModuleNotFoundError):
+    from utils import *
 
 
 

{orforise-1.6.1 → orforise-1.6.3}/src/ORForise/StORForise.py

@@ -3,11 +3,11 @@ import argparse
 import csv
 
 try:
-    from utils import *
-    from Comparator import tool_comparison
-except ImportError:
     from .Comparator import tool_comparison
     from .utils import *
+except (ImportError, ModuleNotFoundError):
+    from Comparator import tool_comparison
+    from utils import *
 
 ###################
 

{orforise-1.6.1 → orforise-1.6.3}/src/ORForise/Tools/Augustus/Augustus.py

@@ -11,11 +11,23 @@ except ImportError:
 def Augustus(*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 Augustus_input:
+            for line in Augustus_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
+
     augustus_ORFs = collections.OrderedDict()
     for dna_region in dna_regions:
         augustus_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 Augustus_input:

{orforise-1.6.1 → orforise-1.6.3}/src/ORForise/Tools/Balrog/Balrog.py

@@ -11,11 +11,23 @@ except ImportError:
 def Balrog(*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 Balrog_input:
+            for line in Balrog_input:
+                line = line.split()
+                if "CDS" in line[2] and line[0] not in dna_regions:
+                    dna_regions[line[0]] = []  # Placeholder for genome sequence
+        return dna_regions
+
     Balrog_ORFs = collections.OrderedDict()
     for dna_region in dna_regions:
         Balrog_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)
 

{orforise-1.6.1 → orforise-1.6.3}/src/ORForise/Tools/FGENESB/FGENESB.py

@@ -11,11 +11,23 @@ except ImportError:
 def FGENESB(*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 FGENESB_input:
+            for line in FGENESB_input:
+                line = line.split()
+                if len(line) == 10 and ">GENE" in line[0] and line[0] not in dna_regions:
+                    dna_regions[line[0]] = []  # Placeholder for genome sequence
+        return dna_regions
+
     FGENESB_ORFs = collections.OrderedDict()
     for dna_region in dna_regions:
         FGENESB_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 FGENESB_input:

{orforise-1.6.1 → orforise-1.6.3}/src/ORForise/Tools/FragGeneScan/FragGeneScan.py

@@ -11,11 +11,23 @@ except ImportError:
 def FragGeneScan(*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 fragGeneScan_input:
+            for line in fragGeneScan_input:
+                line = line.split()
+                if len(line) == 10 and "FGS" in line[1] and "CDS" in line[2] and line[0] not in dna_regions:
+                    dna_regions[line[0]] = []  # Placeholder for genome sequence
+        return dna_regions
+
     fragGeneScan_ORFs = collections.OrderedDict()
     for dna_region in dna_regions:
         fragGeneScan_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 fragGeneScan_input:

{orforise-1.6.1 → orforise-1.6.3}/src/ORForise/Tools/GFF/GFF.py

@@ -1,5 +1,4 @@
 import collections
-import sys
 try:
     from utils import revCompIterative
     from utils import sortORFs
@@ -11,11 +10,23 @@ except ImportError:
 def GFF(*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 GFF_input:
+            for line in GFF_input:
+                line = line.split()
+                if 'CDS' in line[2] and len(line) == 9 and line[0] not in dna_regions:
+                    dna_regions[line[0]] = []  # Placeholder for genome sequence
+        return dna_regions
+
     GFF_ORFs = collections.OrderedDict()
     for dna_region in dna_regions:
         GFF_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 gff_input:

{orforise-1.6.1 → orforise-1.6.3}/src/ORForise/Tools/GLIMMER3/GLIMMER3.py

@@ -11,11 +11,23 @@ except ImportError:
 def GLIMMER_3(*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 GLIMKMER_input:
+            for line in GLIMMER_input:
+                line = line.split()
+                if len(line) == 5 and "orf" in line[0] and line[0] not in dna_regions:
+                    dna_regions[line[0]] = []  # Placeholder for genome sequence
+        return dna_regions
+
     GLIMMER_ORFs = collections.OrderedDict()
     for dna_region in dna_regions:
         GLIMMER_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,

{orforise-1.6.1 → orforise-1.6.3}/src/ORForise/Tools/GeneMark/GeneMark.py

@@ -10,11 +10,23 @@ except ImportError:
 def GeneMark(*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 GeneMark_input:
+            for line in GeneMark_input:
+                line = line.split()
+                if 'direct' in line[2] or 'complement' in line[2] and line[0] not in dna_regions:
+                    dna_regions[line[0]] = []  # Placeholder for genome sequence
+        return dna_regions
+
     geneMark_ORFs = collections.OrderedDict()
     for dna_region in dna_regions:
         geneMark_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)
         prev_Start = 0

{orforise-1.6.1 → orforise-1.6.3}/src/ORForise/Tools/GeneMarkHA/GeneMarkHA.py

@@ -11,15 +11,27 @@ except ImportError:
 def GeneMark_HA(*args):
     tool_pred = args[0]
     dna_regions = args[1]
-    geneMark_HA_ORFs = collections.OrderedDict()
+    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 GeneMarkHA_input:
+            for line in GeneMarkHA_input:
+                line = line.split()
+                if len(line) >= 9 and "CDS" in line[5] and line[0] not in dna_regions:
+                    dna_regions[line[0]] = []  # Placeholder for genome sequence
+        return dna_regions
+
+    geneMarkHA_ORFs = collections.OrderedDict()
     for dna_region in dna_regions:
-        geneMark_HA_ORFs[dna_region] = collections.OrderedDict()
+        geneMarkHA_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 GeneMark_HA_input:
-            for line in GeneMark_HA_input:
+        with open(tool_pred, 'r') as GeneMarkHA_input:
+            for line in GeneMarkHA_input:
                 line = line.split()
                 if len(line) >= 9 and "CDS" in line[5] and dna_region in line[0]:
                     start = int(line[6])
@@ -35,8 +47,8 @@ def GeneMark_HA(*args):
                         stopCodon = genome[stop - 3:stop]
                     po = str(start) + ',' + str(stop)
                     orf = [strand, startCodon, stopCodon, 'CDS', 'GeneMarkHA']
-                    geneMark_HA_ORFs.update({po: orf})
+                    geneMarkHA_ORFs.update({po: orf})
 
-    for group in geneMark_HA_ORFs:
-        geneMark_HA_ORFs[group] = sortORFs(geneMark_HA_ORFs[group])
-    return geneMark_HA_ORFs
+    for group in geneMarkHA_ORFs:
+        geneMarkHA_ORFs[group] = sortORFs(geneMarkHA_ORFs[group])
+    return geneMarkHA_ORFs

orforise-1.6.1/src/ORForise/Tools/GeneMark_HMM/GeneMark_HMM.py → orforise-1.6.3/src/ORForise/Tools/GeneMarkHMM/GeneMarkHMM.py

@@ -12,15 +12,27 @@ except ImportError:
 def GeneMark_HMM(*args):
     tool_pred = args[0]
     dna_regions = args[1]
-    geneMark_HMM_ORFs = collections.OrderedDict()
+    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 GeneMarkHMM_input:
+            for line in GeneMarkHMM_input:
+                line = line.split()
+                if len(line) >= 9 and "CDS" in line[2] and line[0] not in dna_regions:
+                    dna_regions[line[0]] = []  # Placeholder for genome sequence
+        return dna_regions
+
+    geneMarkHMM_ORFs = collections.OrderedDict()
     for dna_region in dna_regions:
-        geneMark_HMM_ORFs[dna_region] = collections.OrderedDict()
+        geneMarkHMM_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 GeneMark_HMM_input:
-            for line in GeneMark_HMM_input:
+        with open(tool_pred, 'r') as GeneMarkHMM_input:
+            for line in GeneMarkHMM_input:
                 line = line.split('\t')
                 if len(line) >= 9 and "CDS" in line[2] and dna_region in line[0]:
                     start = int(line[3])
@@ -35,9 +47,9 @@ def GeneMark_HMM(*args):
                         startCodon = genome[start - 1:start + 2]
                         stopCodon = genome[stop - 3:stop]
                     po = str(start) + ',' + str(stop)
-                    orf = [strand, startCodon, stopCodon, 'CDS', 'GeneMark_HMM']
-                    geneMark_HMM_ORFs.update({po: orf})
+                    orf = [strand, startCodon, stopCodon, 'CDS', 'GeneMarkHMM']
+                    geneMarkHMM_ORFs.update({po: orf})
 
-    for group in geneMark_HMM_ORFs:
-        geneMark_HMM_ORFs[group] = sortORFs(geneMark_HMM_ORFs[group])
-    return geneMark_HMM_ORFs
+    for group in geneMarkHMM_ORFs:
+        geneMarkHMM_ORFs[group] = sortORFs(geneMarkHMM_ORFs[group])
+    return geneMarkHMM_ORFs

orforise-1.6.1/src/ORForise/Tools/GeneMark_S/GeneMark_S.py → orforise-1.6.3/src/ORForise/Tools/GeneMarkS/GeneMarkS.py

@@ -11,15 +11,27 @@ except ImportError:
 def GeneMark_S(*args):
     tool_pred = args[0]
     dna_regions = args[1]
-    geneMark_S_ORFs = collections.OrderedDict()
+    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 GeneMarkS_input:
+            for line in GeneMarkS_input:
+                line = line.split()
+                if len(line) >= 9 and "CDS" in line[5] and line[0] not in dna_regions:
+                    dna_regions[line[0]] = []  # Placeholder for genome sequence
+        return dna_regions
+
+    geneMarkS_ORFs = collections.OrderedDict()
     for dna_region in dna_regions:
-        geneMark_S_ORFs[dna_region] = collections.OrderedDict()
+        geneMarkS_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:
-            for line in prodigal_input:
+        with open(tool_pred, 'r') as GeneMarkS_input:
+            for line in GeneMarkS_input:
                 line = line.split()
                 if len(line) >= 9 and "CDS" in line[5] and dna_region in line[0]:
                     start = int(line[6])
@@ -34,9 +46,9 @@ def GeneMark_S(*args):
                         startCodon = genome[start - 1:start + 2]
                         stopCodon = genome[stop - 3:stop]
                     po = str(start) + ',' + str(stop)
-                    orf = [strand, startCodon, stopCodon, 'CDS', 'GeneMark_S']
-                    geneMark_S_ORFs.update({po: orf})
+                    orf = [strand, startCodon, stopCodon, 'CDS', 'GeneMarkS']
+                    geneMarkS_ORFs.update({po: orf})
 
-    for group in geneMark_S_ORFs:
-        geneMark_S_ORFs[group] = sortORFs(geneMark_S_ORFs[group])
-    return geneMark_S_ORFs
+    for group in geneMarkS_ORFs:
+        geneMarkS_ORFs[group] = sortORFs(geneMarkS_ORFs[group])
+    return geneMarkS_ORFs

orforise-1.6.1/src/ORForise/Tools/GeneMark_S_2/GeneMark_S_2.py → orforise-1.6.3/src/ORForise/Tools/GeneMarkS2/GeneMarkS2.py

@@ -8,18 +8,30 @@ except ImportError:
     from ORForise.utils import sortORFs
 
 
-def GeneMark_S_2(*args):
+def GeneMarkS2(*args):
     tool_pred = args[0]
     dna_regions = args[1]
-    geneMark_S_2_ORFs = collections.defaultdict()
+    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 GeneMarkS2_input:
+            for line in GeneMarkS2_input:
+                line = line.split()
+                if len(line) >= 9 and "CDS" in line[2] and line[0] not in dna_regions:
+                    dna_regions[line[0]] = []  # Placeholder for genome sequence
+        return dna_regions
+
+    geneMarkS2_ORFs = collections.defaultdict()
     for dna_region in dna_regions:
-        geneMark_S_2_ORFs[dna_region] = collections.OrderedDict()
+        geneMarkS2_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 GeneMark_S_2_input:
-            for line in GeneMark_S_2_input:
+        with open(tool_pred, 'r') as GeneMarkS2_input:
+            for line in GeneMarkS2_input:
                 line = line.split('\t')
                 if len(line) >= 9 and dna_region in line[0] and "CDS" in line[2]:
                     start = int(line[3])
@@ -35,9 +47,9 @@ def GeneMark_S_2(*args):
                         startCodon = genome[start - 1:start + 2]
                         stopCodon = genome[stop - 3:stop]
                     po = str(start) + ',' + str(stop)
-                    orf = [strand, startCodon, stopCodon, 'CDS', 'GeneMark_S_2']
-                    geneMark_S_2_ORFs[dna_region].update({po: orf})
+                    orf = [strand, startCodon, stopCodon, 'CDS', 'GeneMarkS2']
+                    geneMarkS2_ORFs[dna_region].update({po: orf})
 
-    for group in geneMark_S_2_ORFs:
-        geneMark_S_2_ORFs[group] = sortORFs(geneMark_S_2_ORFs[group])
-    return geneMark_S_2_ORFs
+    for group in geneMarkS2_ORFs:
+        geneMarkS2_ORFs[group] = sortORFs(geneMarkS2_ORFs[group])
+    return geneMarkS2_ORFs

{orforise-1.6.1 → orforise-1.6.3}/src/ORForise/Tools/MetaGene/MetaGene.py

@@ -11,11 +11,23 @@ except ImportError:
 def MetaGene(*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 MetaGene_input:
+            for line in MetaGene_input:
+                line = line.split()
+                if len(line) >= 6 and ("-" in line or '+' in line) and line[0] not in dna_regions:
+                    dna_regions[line[0]] = []  # Placeholder for genome sequence
+        return dna_regions
+
     metaGene_ORFs = collections.OrderedDict()
     for dna_region in dna_regions:
         metaGene_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 MetaGene_input:

{orforise-1.6.1 → orforise-1.6.3}/src/ORForise/Tools/MetaGeneAnnotator/MetaGeneAnnotator.py

@@ -11,11 +11,23 @@ except ImportError:
 def MetaGeneAnnotator(*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 MetaGeneAnnotator_input:
+            for line in MetaGeneAnnotator_input:
+                line = line.split()
+                if len(line) == 11 and line[0] not in dna_regions:
+                    dna_regions[line[0]] = []  # Placeholder for genome sequence
+        return dna_regions
+
     metaGeneAnnotator_ORFs = collections.OrderedDict()
     for dna_region in dna_regions:
         metaGeneAnnotator_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 MetaGeneAnnotator_input:

{orforise-1.6.1 → orforise-1.6.3}/src/ORForise/Tools/MetaGeneMark/MetaGeneMark.py

@@ -11,11 +11,23 @@ except ImportError:
 def MetaGeneMark(*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 MetaGeneMark_input:
+            for line in MetaGeneMark_input:
+                line = line.split()
+                if 'GeneMark.hmm' in line[4] and "CDS" in line[5] and line[0] not in dna_regions:
+                    dna_regions[line[0]] = []  # Placeholder for genome sequence
+        return dna_regions
+
     metaGeneMarkORFs = collections.OrderedDict()
     for dna_region in dna_regions:
         metaGeneMarkORFs[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 metaGeneMark_input:

{orforise-1.6.1 → orforise-1.6.3}/src/ORForise/Tools/Prodigal/Prodigal.py

@@ -13,10 +13,10 @@ def Prodigal(*args):
     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:
+        with open(tool_pred, 'r') as Prodigal_input:
+            for line in Prodigal_input:
                 line = line.split()
-                if len(line) == 10 and "CDS" in line[2] and line[0] not in dna_regions:
+                if "Prodigal" in line[1] and "CDS" in line[2] and line[0] not in dna_regions:
                     dna_regions[line[0]] = []  # Placeholder for genome sequence
         return dna_regions
 

{orforise-1.6.1 → orforise-1.6.3}/src/ORForise/Tools/Prokka/Prokka.py

@@ -8,15 +8,27 @@ except ImportError:
     from ORForise.utils import sortORFs
 
 
-def Prokka(*args):
+def Prokka(*args): # UNFINISHED
     tool_pred = args[0]
     dna_regions = args[1]
     types = args[2]
+    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 PROKKA_input:
+            for line in PROKKA_input:
+                line = line.split()
+                if "Prodigal" in line[1] and "CDS" in line[2] and line[0] not in dna_regions:
+                    dna_regions[line[0]] = []  # Placeholder for genome sequence
+        return dna_regions
+
     prokkaORFs = collections.defaultdict(list)
     for dna_region in dna_regions:
         prokkaORFs[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-1.6.1/src/ORForise/Tools/StORF_Reporter/StORF_Reporter.py → orforise-1.6.3/src/ORForise/Tools/StORF-Reporter/StORF-Reporter.py

@@ -11,18 +11,30 @@ except ImportError:
 def StORF_Reporter(*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 StORF_Reporter_input:
+            for line in StORF_Reporter_input:
+                line = line.split()
+                if 'StORF-Reporter' in line[1] or 'StoRF_Reporter' in line[1]  or 'StORF' in line[1] or 'StORF-Reporter' in line[1] and line[0] not in dna_regions:
+                    dna_regions[line[0]] = []  # Placeholder for genome sequence
+        return dna_regions
+
     storf_ORFs = collections.OrderedDict()
     for dna_region in dna_regions:
         storf_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 storf_input:
             for line in storf_input:
                 if not line.startswith('#') and not line.startswith('\n'):
                     line = line.split()
-                    if 'StORF_Reporter' in line[1] or 'StoRF_Reporter' in line[1]  or 'StORF' in line[1] or 'StORF-Reporter' in line[1] and dna_region in line[0]: # need to harmonise this.
+                    if 'StORF-Reporter' in line[1] or 'StoRF_Reporter' in line[1]  or 'StORF' in line[1] or 'StORF-Reporter' in line[1] and dna_region in line[0]: # need to harmonise this.
                         start = int(line[3])
                         stop = int(line[4])
                         strand = line[6]

{orforise-1.6.1 → orforise-1.6.3}/src/ORForise/Tools/TransDecoder/TransDecoder.py

@@ -11,11 +11,23 @@ except ImportError:
 def TransDecoder(*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 TransDecoder_input:
+            for line in TransDecoder_input:
+                line = line.split()
+                if len(line) == 9 and "transdecoder" in line[1] and "CDS" in line[2] and line[0] not in dna_regions:
+                    dna_regions[line[0]] = []  # Placeholder for genome sequence
+        return dna_regions
+
     transDecoder_ORFs = collections.OrderedDict()
     for dna_region in dna_regions:
         transDecoder_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 transDecoder_Input:

{orforise-1.6.1 → orforise-1.6.3}/src/ORForise.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ORForise
-Version: 1.6.1
+Version: 1.6.3
 Summary: ORForise - A platform for analysing and comparing genome annotations.
 Author-email: Nicholas Dimonaco <nicholas@dimonaco.co.uk>
 License:                     GNU GENERAL PUBLIC LICENSE
@@ -662,7 +662,7 @@ Example output files from ```Annotation-Compare```, ```Aggregate-Compare```, ```
 For Help: ```Annotation-Compare -h ```
 
 ```python
-ORForise v1.6.1: Annotatione-Compare Run Parameters.
+ORForise v1.6.3: Annotatione-Compare Run Parameters.
 
 Required Arguments:
   -dna GENOME_DNA       Genome DNA file (.fa) which both annotations are based on
@@ -730,7 +730,7 @@ ORForise can be used as the example below.
 For Help: ```Aggregate-Compare -h ```
 
 ```python
-ORForise v1.6.1: Aggregate-Compare Run Parameters.
+ORForise v1.6.3: Aggregate-Compare Run Parameters.
 
 Required Arguments:
   -dna GENOME_DNA       Genome DNA file (.fa) which both annotations are based on
@@ -811,7 +811,7 @@ GFF-Adder combines two existing annotations (GFF or other tool formats).
 For Help: ```GFF-Adder -h ```
 
 ```python
-ORForise v1.6.1: GFF-Adder Run Parameters.
+ORForise v1.6.3: GFF-Adder Run Parameters.
 
 Required Arguments:
   -dna GENOME_DNA       Genome DNA file (.fa) which both annotations are based on
@@ -868,7 +868,7 @@ usage: Annotation_Intersector.py [-h] -ref REFERENCE_ANNOTATION -at
                                  [-cov COVERAGE] [--report-discordance]
                                  [--report-discordance-file REPORT_DISCORDANCE_FILE]
 
-ORForise v1.6.1: Annotation-Intersector Run Parameters
+ORForise v1.6.3: Annotation-Intersector Run Parameters
 
 options:
   -h, --help            show this help message and exit
@@ -947,7 +947,7 @@ Please report any issues to: https://github.com/NickJD/ORForise/issues
 #####
 usage: Convert_To_GFF.py [-h] [-dna GENOME_DNA] -i INPUT_ANNOTATION -fmt FORMAT -o OUTPUT_DIR [-gi GENE_IDENT] [--verbose]
 
-ORForise v1.6.1: Convert-To-GFF Run Parameters
+ORForise v1.6.3: Convert-To-GFF Run Parameters
 
 Required Arguments:
   -dna GENOME_DNA      Genome DNA file (.fa)
@@ -1026,7 +1026,7 @@ Defaults options were used.
 **MetaGeneMark - Version '2020'** - http://exon.gatech.edu/meta_gmhmmp.cgi  
 GFF was chosen as output type.
 
-**Prodigal - Version 2.6.3** - https://github.com/hyattpd/Prodigal  
+**Prodigal (Includes Pyrodigal) - Version 2.6.3** - https://github.com/hyattpd/Prodigal  
 GFF was chosen as output type.
 
 **TransDecoder - Version 5.5.0** - https://github.com/TransDecoder/TransDecoder/wiki  

{orforise-1.6.1 → orforise-1.6.3}/src/ORForise.egg-info/SOURCES.txt

@@ -53,12 +53,12 @@ src/ORForise/Tools/GeneMark/GeneMark.py
 src/ORForise/Tools/GeneMark/__init__.py
 src/ORForise/Tools/GeneMarkHA/GeneMarkHA.py
 src/ORForise/Tools/GeneMarkHA/__init__.py
-src/ORForise/Tools/GeneMark_HMM/GeneMark_HMM.py
-src/ORForise/Tools/GeneMark_HMM/__init__.py
-src/ORForise/Tools/GeneMark_S/GeneMark_S.py
-src/ORForise/Tools/GeneMark_S/__init__.py
-src/ORForise/Tools/GeneMark_S_2/GeneMark_S_2.py
-src/ORForise/Tools/GeneMark_S_2/__init__.py
+src/ORForise/Tools/GeneMarkHMM/GeneMarkHMM.py
+src/ORForise/Tools/GeneMarkHMM/__init__.py
+src/ORForise/Tools/GeneMarkS/GeneMarkS.py
+src/ORForise/Tools/GeneMarkS/__init__.py
+src/ORForise/Tools/GeneMarkS2/GeneMarkS2.py
+src/ORForise/Tools/GeneMarkS2/__init__.py
 src/ORForise/Tools/MetaGene/MetaGene.py
 src/ORForise/Tools/MetaGene/__init__.py
 src/ORForise/Tools/MetaGeneAnnotator/MetaGeneAnnotator.py
@@ -69,7 +69,7 @@ src/ORForise/Tools/Prodigal/Prodigal.py
 src/ORForise/Tools/Prodigal/__init__.py
 src/ORForise/Tools/Prokka/Prokka.py
 src/ORForise/Tools/Prokka/__init__.py
-src/ORForise/Tools/StORF_Reporter/StORF_Reporter.py
-src/ORForise/Tools/StORF_Reporter/__init__.py
+src/ORForise/Tools/StORF-Reporter/StORF-Reporter.py
+src/ORForise/Tools/StORF-Reporter/__init__.py
 src/ORForise/Tools/TransDecoder/TransDecoder.py
 src/ORForise/Tools/TransDecoder/__init__.py