ORForise 1.4.1__tar.gz → 1.4.3__tar.gz

{ORForise-1.4.1 → orforise-1.4.3}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: ORForise
-Version: 1.4.1
+Version: 1.4.3
 Summary: ORForise - Platform for analysing and comparing Prokaryote CoDing Sequence (CDS) Gene Predictions.
 Home-page: https://github.com/NickJD/ORForise
 Author: Nicholas Dimonaco
@@ -12,6 +12,8 @@ Classifier: Operating System :: OS Independent
 Requires-Python: >=3.6
 Description-Content-Type: text/markdown
 License-File: LICENSE
+Requires-Dist: numpy
+Dynamic: license-file
 
 # ORForise - Prokaryote Genome Annotation Analysis and Comparison Platform
 ## Published in Bioinformatics :   https://academic.oup.com/bioinformatics/article/38/5/1198/6454948
@@ -61,7 +63,7 @@ Please report any issues to: https://github.com/NickJD/ORForise/issues
 usage: Annotation_Compare.py [-h] -dna GENOME_DNA -ref REFERENCE_ANNOTATION -t TOOL -tp TOOL_PREDICTION
                              [-rt REFERENCE_TOOL] [-o OUTNAME] [-v {True,False}]
 
-ORForise v1.4.1: Annotatione-Compare Run Parameters.
+ORForise v1.4.3: Annotatione-Compare Run Parameters.
 
 Required Arguments:
   -dna GENOME_DNA       Genome DNA file (.fa) which both annotations are based on
@@ -111,7 +113,7 @@ Please report any issues to: https://github.com/NickJD/ORForise/issues
 usage: Aggregate_Compare.py [-h] -dna GENOME_DNA -t TOOLS -tp TOOL_PREDICTIONS -ref REFERENCE_ANNOTATION
                             [-rt REFERENCE_TOOL] [-o OUTNAME] [-v {True,False}]
 
-ORForise v1.4.1: Aggregate-Compare Run Parameters.
+ORForise v1.4.3: Aggregate-Compare Run Parameters.
 
 Required Arguments:
   -dna GENOME_DNA       Genome DNA file (.fa) which both annotations are based on
@@ -265,7 +267,7 @@ Please report any issues to: https://github.com/NickJD/ORForise/issues
 usage: GFF_Adder.py [-h] -dna GENOME_DNA -ref REFERENCE_ANNOTATION -at ADDITIONAL_TOOL -add ADDITIONAL_ANNOTATION -o
                     OUTPUT_FILE [-rt REFERENCE_TOOL] [-gi GENE_IDENT] [-gene_ident GENE_IDENT] [-olap OVERLAP]
 
-ORForise v1.4.1: GFF-Adder Run Parameters.
+ORForise v1.4.3: GFF-Adder Run Parameters.
 
 Required Arguments:
   -dna GENOME_DNA       Genome DNA file (.fa) which both annotations are based on
@@ -327,7 +329,7 @@ Please report any issues to: https://github.com/NickJD/ORForise/issues
 usage: GFF_Intersector.py [-h] -dna GENOME_DNA -ref REFERENCE_ANNOTATION -at ADDITIONAL_TOOL -add
                           ADDITIONAL_ANNOTATION -o OUTPUT_FILE [-rt REFERENCE_TOOL] [-gi GENE_IDENT] [-cov COVERAGE]
 
-ORForise v1.4.1: GFF-Intersector Run Parameters.
+ORForise v1.4.3: GFF-Intersector Run Parameters.
 
 Required Arguments:
   -dna GENOME_DNA       Genome DNA file (.fa) which both annotations are based on

{ORForise-1.4.1 → orforise-1.4.3}/README.md

@@ -46,7 +46,7 @@ Please report any issues to: https://github.com/NickJD/ORForise/issues
 usage: Annotation_Compare.py [-h] -dna GENOME_DNA -ref REFERENCE_ANNOTATION -t TOOL -tp TOOL_PREDICTION
                              [-rt REFERENCE_TOOL] [-o OUTNAME] [-v {True,False}]
 
-ORForise v1.4.1: Annotatione-Compare Run Parameters.
+ORForise v1.4.3: Annotatione-Compare Run Parameters.
 
 Required Arguments:
   -dna GENOME_DNA       Genome DNA file (.fa) which both annotations are based on
@@ -96,7 +96,7 @@ Please report any issues to: https://github.com/NickJD/ORForise/issues
 usage: Aggregate_Compare.py [-h] -dna GENOME_DNA -t TOOLS -tp TOOL_PREDICTIONS -ref REFERENCE_ANNOTATION
                             [-rt REFERENCE_TOOL] [-o OUTNAME] [-v {True,False}]
 
-ORForise v1.4.1: Aggregate-Compare Run Parameters.
+ORForise v1.4.3: Aggregate-Compare Run Parameters.
 
 Required Arguments:
   -dna GENOME_DNA       Genome DNA file (.fa) which both annotations are based on
@@ -250,7 +250,7 @@ Please report any issues to: https://github.com/NickJD/ORForise/issues
 usage: GFF_Adder.py [-h] -dna GENOME_DNA -ref REFERENCE_ANNOTATION -at ADDITIONAL_TOOL -add ADDITIONAL_ANNOTATION -o
                     OUTPUT_FILE [-rt REFERENCE_TOOL] [-gi GENE_IDENT] [-gene_ident GENE_IDENT] [-olap OVERLAP]
 
-ORForise v1.4.1: GFF-Adder Run Parameters.
+ORForise v1.4.3: GFF-Adder Run Parameters.
 
 Required Arguments:
   -dna GENOME_DNA       Genome DNA file (.fa) which both annotations are based on
@@ -312,7 +312,7 @@ Please report any issues to: https://github.com/NickJD/ORForise/issues
 usage: GFF_Intersector.py [-h] -dna GENOME_DNA -ref REFERENCE_ANNOTATION -at ADDITIONAL_TOOL -add
                           ADDITIONAL_ANNOTATION -o OUTPUT_FILE [-rt REFERENCE_TOOL] [-gi GENE_IDENT] [-cov COVERAGE]
 
-ORForise v1.4.1: GFF-Intersector Run Parameters.
+ORForise v1.4.3: GFF-Intersector Run Parameters.
 
 Required Arguments:
   -dna GENOME_DNA       Genome DNA file (.fa) which both annotations are based on

{ORForise-1.4.1 → orforise-1.4.3}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = ORForise
-version = 1.4.1
+version = 1.4.3
 author = Nicholas Dimonaco
 author_email = nicholas@dimonaco.co.uk
 description = ORForise - Platform for analysing and comparing Prokaryote CoDing Sequence (CDS) Gene Predictions.

{ORForise-1.4.1 → orforise-1.4.3}/src/ORForise/Annotation_Compare.py

@@ -72,11 +72,11 @@ def comparator(options):
     rep_metric_description = list(all_rep_Metrics.keys())
     rep_metrics = list(all_rep_Metrics.values())
     ############## Printing to std-out and optional csv file
-    print('Genome Used: ' + str(options.reference_annotation.split('/')[-1]))
+    print('Genome Used: ' + str(options.genome_DNA.split('/')[-1]))
     if options.reference_tool:
         print('Reference Tool Used: '+str(options.reference_tool))
     else:
-        print('Reference Used: ' + str(options.reference_annotation))
+        print('Reference Used: ' + str(options.reference_annotation.split('/')[-1]))
     print('Tool Compared: '+str(options.tool))
     print('Perfect Matches: ' + str(len(perfect_Matches)) + ' [' + str(len(ref_genes))+ '] - '+ format(100 * len(perfect_Matches)/len(ref_genes),'.2f')+'%')
     print('Partial Matches: ' + str(len(partial_Hits)) + ' [' + str(len(ref_genes))+ '] - '+ format(100 * len(partial_Hits)/len(ref_genes),'.2f')+'%')

{ORForise-1.4.1 → orforise-1.4.3}/src/ORForise/Comparator.py

@@ -47,13 +47,30 @@ comp = comparator()
 
 def is_double_range(range1, range2):
     return len(range1) >= 2 * len(range2)
-def nuc_Count(start, stop, strand):  # Gets correct seq then returns GC
-    if strand == '-':
-        r_Start = comp.genome_Size - stop
-        r_Stop = comp.genome_Size - start
-        seq = (comp.genome_Seq_Rev[r_Start:r_Stop + 1])
-    elif strand == '+':
-        seq = (comp.genome_Seq[start - 1:stop])
+def nuc_Count(verbose, start, stop, strand):  # Gets correct seq then returns GC
+    if stop >= comp.genome_Size:
+        if verbose == True:
+            print("There is a wrap around gene and I am dealing with it the best I can - Start: " + str(start) + " Stop: " + str(stop))
+        extra_stop = stop - comp.genome_Size
+        stop = comp.genome_Size
+        if strand == '-':
+            r_Start = comp.genome_Size - stop
+            r_Stop = comp.genome_Size - start
+            seq = (comp.genome_Seq_Rev[r_Start:r_Stop + 1])
+            extra_seq = (comp.genome_Seq_Rev[-extra_stop-1:])
+            seq = extra_seq+seq
+        elif strand == '+':
+            seq = comp.genome_Seq[start - 1:stop]
+            extra_seq = comp.genome_Seq[:extra_stop +1]
+            seq = seq+extra_seq
+            #seq = (comp.genome_Seq[start - 1:stop])
+    else:
+        if strand == '-':
+            r_Start = comp.genome_Size - stop
+            r_Stop = comp.genome_Size - start
+            seq = (comp.genome_Seq_Rev[r_Start:r_Stop + 1])
+        elif strand == '+':
+            seq = (comp.genome_Seq[start - 1:stop])
     c = 0
     a = 0
     g = 0
@@ -213,7 +230,8 @@ def candidate_ORF_Selection(gene_Set,
     for c_Pos, c_ORF_Details in candidate_ORFs.items():
         o_Start = int(c_Pos.split(',')[0])
         o_Stop = int(c_Pos.split(',')[1])
-        coverage = c_ORF_Details[3]
+        # Below is not a long term fix
+        coverage = c_ORF_Details[-1]
         orf_Set = set(range(o_Start, o_Stop + 1))
         if coverage > current_Coverage:
             current_Coverage = coverage
@@ -323,8 +341,8 @@ def tool_comparison(ref_genes, orfs, genome, verbose):
             comp.genes_Detected.update({str(gene_details): g_pos})
             match_Statistics(o_Start, o_Stop, g_Start, g_Stop, g_Strand)
             perfect_Matched_Genes(g_Start, g_Stop, g_Strand)
-            if verbose == True:
-                print('Perfect Match')
+            #if verbose == True:
+            #    print('Perfect Match')
         elif perfect_Match == False and len(
                 overlapping_ORFs) == 1:  # If we do not have a perfect match but 1 ORF which has passed the filtering
             orf_Pos = list(overlapping_ORFs.keys())[0]
@@ -344,8 +362,8 @@ def tool_comparison(ref_genes, orfs, genome, verbose):
             comp.matched_ORFs.update({orf_Pos: m_ORF_Details})
             comp.genes_Detected.update({str(gene_details): orf_Pos})
             match_Statistics(o_Start, o_Stop, g_Start, g_Stop, g_Strand)
-            if verbose == True:
-                print('Partial Match')
+            #if verbose == True:
+            #    print('Partial Match')
             partial_Hit_Calc(g_Start, g_Stop, g_Strand, o_Start, o_Stop)
         elif perfect_Match == False and len(
                 overlapping_ORFs) >= 1:  # If we have more than 1 potential ORF match, we check to see which is the 'best' hit
@@ -374,8 +392,8 @@ def tool_comparison(ref_genes, orfs, genome, verbose):
             genes_Unmatched(g_Start, g_Stop, g_Strand)  #
         else:
             genes_Unmatched(g_Start, g_Stop, g_Strand)  # No hit
-            if verbose == True:
-                print("No Hit")
+            #if verbose == True:
+            #    print("No Hit")
     for orf_Key in comp.matched_ORFs:  # Remove ORFs from out of frame if ORF was correctly matched to another Gene
         if orf_Key in comp.out_Of_Frame_ORFs:
             del comp.out_Of_Frame_ORFs[orf_Key]
@@ -409,7 +427,7 @@ def tool_comparison(ref_genes, orfs, genome, verbose):
         if gene_Length == 0: print(g_Start, g_Stop, "!!!!!!!!!!!!!!!!!!!!!!!!")
         comp.gene_Lengths.append(gene_Length)
         gene_Nuc_Array[g_Start - 1:g_Stop] = True  # Changing all between the two positions to 1's
-        comp.gene_GC.append(nuc_Count(g_Start, g_Stop, g_Strand))
+        comp.gene_GC.append(nuc_Count(verbose, g_Start, g_Stop, g_Strand))
         if gene_Length <= SHORT_ORF_LENGTH:  # .utils
             comp.gene_Short.append(gene_Length)
         ### Calculate overlapping Genes -
@@ -453,7 +471,7 @@ def tool_comparison(ref_genes, orfs, genome, verbose):
         orf_Length = (o_Stop - o_Start) +1
         comp.orf_Lengths.append(orf_Length)
         orf_Nuc_Array[o_Start - 1:o_Stop] = True  # Changing all between the two positions to 1's
-        comp.orf_GC.append(nuc_Count(o_Start, o_Stop, o_Strand))
+        comp.orf_GC.append(nuc_Count(verbose, o_Start, o_Stop, o_Strand))
         if orf_Length <= SHORT_ORF_LENGTH:  # .utils
             comp.orf_Short.append(orf_Length)
         ### Calculate overlapping ORFs -
@@ -487,7 +505,7 @@ def tool_comparison(ref_genes, orfs, genome, verbose):
         mo_Length = (mo_Stop - mo_Start)
         matched_ORF_Nuc_Array[mo_Start - 1:mo_Stop] = True  # This is the complete matched orf not the matched orf bits
 
-        comp.m_ORF_GC.append(nuc_Count(mo_Start, mo_Stop, mo_Strand))
+        comp.m_ORF_GC.append(nuc_Count(verbose, mo_Start, mo_Stop, mo_Strand))
         if mo_Length <= SHORT_ORF_LENGTH:  # .utils
             comp.m_ORF_Short.append(mo_Length)
         ### Calculate overlapping Matched ORFs -

orforise-1.4.3/src/ORForise/Tools/GFF/GFF.py

@@ -0,0 +1,62 @@
+import collections
+import sys
+try:
+    from utils import revCompIterative
+    from utils import sortORFs
+except ImportError:
+    from ORForise.utils import revCompIterative
+    from ORForise.utils import sortORFs
+
+
+def GFF(*args):
+    tool_pred = args[0]
+    genome = args[1]
+    #types = args[2]
+    GFF_ORFs = collections.OrderedDict()
+    genome_size = len(genome)
+    genome_rev = revCompIterative(genome)
+    with open(tool_pred, 'r') as gff_input:
+        for line in gff_input:
+            if '#' not in line:
+                line = line.split('\t')
+                #gene_types = types.split(',') - Temporary fix
+                #if any(gene_type == line[2] for gene_type in gene_types) and len(line) == 9:  # line[2] for normalrun
+                if 'CDS' in line[2] and len(line) == 9:
+                    start = int(line[3])
+                    stop = int(line[4])
+                    strand = line[6]
+                    info = line[8]
+                    if stop >= genome_size:
+                        extra_stop = stop - genome_size
+                        corrected_stop = genome_size
+                        if '-' in strand:  # Reverse Compliment starts and stops adjusted
+                            r_start = genome_size - corrected_stop
+                            r_stop = genome_size - start
+                            seq = genome_rev[r_start:r_stop + 1]
+                            extra_seq = genome_rev[-extra_stop - 1:]
+                            seq = extra_seq+seq
+                            startCodon = seq[:3]
+                            stopCodon = seq[-3:]
+                        elif '+' in strand:
+                            seq = genome[start -1 :corrected_stop]
+                            extra_seq = genome[:extra_stop +1]
+                            seq = seq+extra_seq
+                            startCodon = seq[:3]
+                            stopCodon = seq[-3:]
+                    else:
+                        if '-' in strand:  # Reverse Compliment starts and stops adjusted
+                            r_start = genome_size - stop
+                            r_stop = genome_size - start
+                            startCodon = genome_rev[r_start:r_start + 3]
+                            stopCodon = genome_rev[r_stop - 2:r_stop + 1]
+                        elif '+' in strand:
+                            startCodon = genome[start - 1:start + 2]
+                            stopCodon = genome[stop - 3:stop]
+                    po = str(start) + ',' + str(stop)
+                    orf = [strand, startCodon, stopCodon, line[2],info] # This needs to detect the type
+                    GFF_ORFs.update({po: orf})
+                # elif "CDS" in line[2]:
+                #     sys.exit("SAS")
+
+    GFF_ORFs = sortORFs(GFF_ORFs)
+    return GFF_ORFs

{ORForise-1.4.1 → orforise-1.4.3}/src/ORForise/utils.py

@@ -4,7 +4,7 @@ import collections
 # Constants
 SHORT_ORF_LENGTH = 300
 MIN_COVERAGE = 75
-ORForise_Version = 'v1.4.1'
+ORForise_Version = 'v1.4.3'
 
 
 def revCompIterative(watson):  # Gets Reverse Complement

{ORForise-1.4.1 → orforise-1.4.3}/src/ORForise.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: ORForise
-Version: 1.4.1
+Version: 1.4.3
 Summary: ORForise - Platform for analysing and comparing Prokaryote CoDing Sequence (CDS) Gene Predictions.
 Home-page: https://github.com/NickJD/ORForise
 Author: Nicholas Dimonaco
@@ -12,6 +12,8 @@ Classifier: Operating System :: OS Independent
 Requires-Python: >=3.6
 Description-Content-Type: text/markdown
 License-File: LICENSE
+Requires-Dist: numpy
+Dynamic: license-file
 
 # ORForise - Prokaryote Genome Annotation Analysis and Comparison Platform
 ## Published in Bioinformatics :   https://academic.oup.com/bioinformatics/article/38/5/1198/6454948
@@ -61,7 +63,7 @@ Please report any issues to: https://github.com/NickJD/ORForise/issues
 usage: Annotation_Compare.py [-h] -dna GENOME_DNA -ref REFERENCE_ANNOTATION -t TOOL -tp TOOL_PREDICTION
                              [-rt REFERENCE_TOOL] [-o OUTNAME] [-v {True,False}]
 
-ORForise v1.4.1: Annotatione-Compare Run Parameters.
+ORForise v1.4.3: Annotatione-Compare Run Parameters.
 
 Required Arguments:
   -dna GENOME_DNA       Genome DNA file (.fa) which both annotations are based on
@@ -111,7 +113,7 @@ Please report any issues to: https://github.com/NickJD/ORForise/issues
 usage: Aggregate_Compare.py [-h] -dna GENOME_DNA -t TOOLS -tp TOOL_PREDICTIONS -ref REFERENCE_ANNOTATION
                             [-rt REFERENCE_TOOL] [-o OUTNAME] [-v {True,False}]
 
-ORForise v1.4.1: Aggregate-Compare Run Parameters.
+ORForise v1.4.3: Aggregate-Compare Run Parameters.
 
 Required Arguments:
   -dna GENOME_DNA       Genome DNA file (.fa) which both annotations are based on
@@ -265,7 +267,7 @@ Please report any issues to: https://github.com/NickJD/ORForise/issues
 usage: GFF_Adder.py [-h] -dna GENOME_DNA -ref REFERENCE_ANNOTATION -at ADDITIONAL_TOOL -add ADDITIONAL_ANNOTATION -o
                     OUTPUT_FILE [-rt REFERENCE_TOOL] [-gi GENE_IDENT] [-gene_ident GENE_IDENT] [-olap OVERLAP]
 
-ORForise v1.4.1: GFF-Adder Run Parameters.
+ORForise v1.4.3: GFF-Adder Run Parameters.
 
 Required Arguments:
   -dna GENOME_DNA       Genome DNA file (.fa) which both annotations are based on
@@ -327,7 +329,7 @@ Please report any issues to: https://github.com/NickJD/ORForise/issues
 usage: GFF_Intersector.py [-h] -dna GENOME_DNA -ref REFERENCE_ANNOTATION -at ADDITIONAL_TOOL -add
                           ADDITIONAL_ANNOTATION -o OUTPUT_FILE [-rt REFERENCE_TOOL] [-gi GENE_IDENT] [-cov COVERAGE]
 
-ORForise v1.4.1: GFF-Intersector Run Parameters.
+ORForise v1.4.3: GFF-Intersector Run Parameters.
 
 Required Arguments:
   -dna GENOME_DNA       Genome DNA file (.fa) which both annotations are based on

ORForise-1.4.1/src/ORForise/Tools/GFF/GFF.py

@@ -1,45 +0,0 @@
-import collections
-import sys
-try:
-    from utils import revCompIterative
-    from utils import sortORFs
-except ImportError:
-    from ORForise.utils import revCompIterative
-    from ORForise.utils import sortORFs
-
-
-def GFF(*args):
-    tool_pred = args[0]
-    genome = args[1]
-    #types = args[2]
-    GFF_ORFs = collections.OrderedDict()
-    genome_size = len(genome)
-    genome_rev = revCompIterative(genome)
-    with open(tool_pred, 'r') as gff_input:
-        for line in gff_input:
-            if '#' not in line:
-                line = line.split('\t')
-                #gene_types = types.split(',') - Temporary fix
-                #if any(gene_type == line[2] for gene_type in gene_types) and len(line) == 9:  # line[2] for normalrun
-                if 'CDS' in line[2] and len(line) == 9:
-                    start = int(line[3])
-                    stop = int(line[4])
-                    strand = line[6]
-                    info = line[8]
-                    #name = line[8].split('Name=')[1].split(';')[0] # Issue with multiple records for each gene.
-                    if '-' in strand:  # Reverse Compliment starts and stops adjusted
-                        r_start = genome_size - stop
-                        r_stop = genome_size - start
-                        startCodon = genome_rev[r_start:r_start + 3]
-                        stopCodon = genome_rev[r_stop - 2:r_stop + 1]
-                    elif '+' in strand:
-                        startCodon = genome[start - 1:start + 2]
-                        stopCodon = genome[stop - 3:stop]
-                    po = str(start) + ',' + str(stop)
-                    orf = [strand, startCodon, stopCodon, line[2],info] # This needs to detect the type
-                    GFF_ORFs.update({po: orf})
-                # elif "CDS" in line[2]:
-                #     sys.exit("SAS")
-
-    GFF_ORFs = sortORFs(GFF_ORFs)
-    return GFF_ORFs