ORForise 1.4.3__py3-none-any.whl → 1.5.0__py3-none-any.whl

ORForise/Tools/GeneMark/GeneMark.py

@@ -7,48 +7,54 @@ except ImportError:
     from ORForise.utils import revCompIterative
     from ORForise.utils import sortORFs
 
-def GeneMark(tool_pred, genome):
+def GeneMark(*args):
+    tool_pred = args[0]
+    dna_regions = args[1]
     geneMark_ORFs = collections.OrderedDict()
-    genome_size = len(genome)
-    genome_rev = revCompIterative(genome)
-    prev_Start = 0
-    prev_Stop = 0
-    started = False
-    with open(tool_pred, 'r') as GeneMark_input:
-        for line in GeneMark_input:
-            line = line.split()
-            if len(line) == 7:
-                started = True
-                if 'direct' in line[2] or 'complement' in line[
-                    2]:  # Strange Output requires strange code - We select the Longest ORF from each set
-                    start = int(line[0])
-                    stop = int(line[1])
-                    strand = line[2]
-                    if 'complement' in strand:  # Reverse Compliment starts and stops adjusted
-                        if start != prev_Start:
-                            r_start = genome_size - stop
-                            r_stop = genome_size - start
-                            strand = '-'
-                            startCodon = genome_rev[r_start:r_start + 3]
-                            stopCodon = genome_rev[r_stop - 2:r_stop + 1]
-                            po = str(start) + ',' + str(stop)
-                            orf = [strand, startCodon, stopCodon, 'CDS']
-                            geneMark_ORFs.update({po: orf})
-                    elif 'direct' in strand:
-                        if stop != prev_Stop:
-                            startCodon = genome[start - 1:start + 2]
-                            stopCodon = genome[stop - 3:stop]
-                            strand = '+'
-                            po = str(start) + ',' + str(stop)
-                            orf = [strand, startCodon, stopCodon, 'CDS']
-                            geneMark_ORFs.update({po: orf})
-                    prev_Start = start
-                    prev_Stop = stop
-            elif len(line) == 0 and started == True:
-                prev_Stop = 0
-                prev_Start = 0
+    for dna_region in dna_regions:
+        geneMark_ORFs[dna_region] = collections.OrderedDict()
+    for dna_region in dna_regions:
+        genome = dna_regions[dna_region][0]
+        genome_size = len(genome)
+        genome_rev = revCompIterative(genome)
+        prev_Start = 0
+        prev_Stop = 0
+        started = False
+        with open(tool_pred, 'r') as GeneMark_input:
+            for line in GeneMark_input:
+                line = line.split()
+                if len(line) == 7:
+                    started = True
+                    if 'direct' in line[2] or 'complement' in line[2] and dna_region in line[0]:  # Strange Output requires strange code - We select the Longest ORF from each set
+                        start = int(line[0])
+                        stop = int(line[1])
+                        strand = line[2]
+                        if 'complement' in strand:  # Reverse Compliment starts and stops adjusted
+                            if start != prev_Start:
+                                r_start = genome_size - stop
+                                r_stop = genome_size - start
+                                strand = '-'
+                                startCodon = genome_rev[r_start:r_start + 3]
+                                stopCodon = genome_rev[r_stop - 2:r_stop + 1]
+                                po = str(start) + ',' + str(stop)
+                                orf = [strand, startCodon, stopCodon, 'CDS', 'GeneMark']
+                                geneMark_ORFs.update({po: orf})
+                        elif 'direct' in strand:
+                            if stop != prev_Stop:
+                                startCodon = genome[start - 1:start + 2]
+                                stopCodon = genome[stop - 3:stop]
+                                strand = '+'
+                                po = str(start) + ',' + str(stop)
+                                orf = [strand, startCodon, stopCodon, 'CDS', 'GeneMark']
+                                geneMark_ORFs.update({po: orf})
+                        prev_Start = start
+                        prev_Stop = stop
+                elif len(line) == 0 and started == True:
+                    prev_Stop = 0
+                    prev_Start = 0
 
-    geneMark_ORFs = sortORFs(geneMark_ORFs)
+    for group in geneMark_ORFs:
+        geneMark_ORFs[group] = sortORFs(geneMark_ORFs[group])
     return geneMark_ORFs
 
 ############# This section can be used to select the ORF with highest probability score.

ORForise/Tools/GeneMark_HA/GeneMark_HA.py

@@ -8,28 +8,35 @@ except ImportError:
     from ORForise.utils import sortORFs
 
 
-def GeneMark_HA(tool_pred, genome):
+def GeneMark_HA(*args):
+    tool_pred = args[0]
+    dna_regions = args[1]
     geneMark_HA_ORFs = collections.OrderedDict()
-    genome_size = len(genome)
-    genome_rev = revCompIterative(genome)
-    with open(tool_pred, 'r') as GeneMark_HA_input:
-        for line in GeneMark_HA_input:
-            line = line.split()
-            if len(line) >= 9 and "CDS" in line[5]:
-                start = int(line[6])
-                stop = int(line[7])
-                strand = line[9]
-                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, 'CDS']
-                geneMark_HA_ORFs.update({po: orf})
+    for dna_region in dna_regions:
+        geneMark_HA_ORFs[dna_region] = collections.OrderedDict()
+    for dna_region in dna_regions:
+        genome = dna_regions[dna_region][0]
+        genome_size = len(genome)
+        genome_rev = revCompIterative(genome)
+        with open(tool_pred, 'r') as GeneMark_HA_input:
+            for line in GeneMark_HA_input:
+                line = line.split()
+                if len(line) >= 9 and "CDS" in line[5] and dna_region in line[0]:
+                    start = int(line[6])
+                    stop = int(line[7])
+                    strand = line[9]
+                    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, 'CDS', 'GeneMark_HA']
+                    geneMark_HA_ORFs.update({po: orf})
 
-    geneMark_HA_ORFs = sortORFs(geneMark_HA_ORFs)
+    for group in geneMark_HA_ORFs:
+        geneMark_HA_ORFs[group] = sortORFs(geneMark_HA_ORFs[group])
     return geneMark_HA_ORFs

ORForise/Tools/GeneMark_HMM/GeneMark_HMM.py

@@ -9,28 +9,35 @@ except ImportError:
 
 
 
-def GeneMark_HMM(tool_pred, genome):
+def GeneMark_HMM(*args):
+    tool_pred = args[0]
+    dna_regions = args[1]
     geneMark_HMM_ORFs = collections.OrderedDict()
-    genome_size = len(genome)
-    genome_rev = revCompIterative(genome)
-    with open(tool_pred, 'r') as GeneMark_HMM_input:
-        for line in GeneMark_HMM_input:
-            line = line.split('\t')
-            if len(line) >= 9 and "CDS" in line[2]:
-                start = int(line[3])
-                stop = int(line[4])
-                strand = line[6]
-                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, 'CDS']
-                geneMark_HMM_ORFs.update({po: orf})
+    for dna_region in dna_regions:
+        geneMark_HMM_ORFs[dna_region] = collections.OrderedDict()
+    for dna_region in dna_regions:
+        genome = dna_regions[dna_region][0]
+        genome_size = len(genome)
+        genome_rev = revCompIterative(genome)
+        with open(tool_pred, 'r') as GeneMark_HMM_input:
+            for line in GeneMark_HMM_input:
+                line = line.split('\t')
+                if len(line) >= 9 and "CDS" in line[2] and dna_region in line[0]:
+                    start = int(line[3])
+                    stop = int(line[4])
+                    strand = line[6]
+                    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, 'CDS', 'GeneMark_HMM']
+                    geneMark_HMM_ORFs.update({po: orf})
 
-    geneMark_HMM_ORFs = sortORFs(geneMark_HMM_ORFs)
+    for group in geneMark_HMM_ORFs:
+        geneMark_HMM_ORFs[group] = sortORFs(geneMark_HMM_ORFs[group])
     return geneMark_HMM_ORFs

ORForise/Tools/GeneMark_S/GeneMark_S.py

@@ -8,28 +8,35 @@ except ImportError:
     from ORForise.utils import sortORFs
 
 
-def GeneMark_S(tool_pred, genome):
+def GeneMark_S(*args):
+    tool_pred = args[0]
+    dna_regions = args[1]
     geneMark_S_ORFs = collections.OrderedDict()
-    genome_size = len(genome)
-    genome_rev = revCompIterative(genome)
-    with open(tool_pred, 'r') as prodigal_input:
-        for line in prodigal_input:
-            line = line.split()
-            if len(line) >= 9 and "CDS" in line[5]:
-                start = int(line[6])
-                stop = int(line[7])
-                strand = line[9]
-                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, 'CDS']
-                geneMark_S_ORFs.update({po: orf})
+    for dna_region in dna_regions:
+        geneMark_S_ORFs[dna_region] = collections.OrderedDict()
+    for dna_region in dna_regions:
+        genome = dna_regions[dna_region][0]
+        genome_size = len(genome)
+        genome_rev = revCompIterative(genome)
+        with open(tool_pred, 'r') as prodigal_input:
+            for line in prodigal_input:
+                line = line.split()
+                if len(line) >= 9 and "CDS" in line[5] and dna_region in line[0]:
+                    start = int(line[6])
+                    stop = int(line[7])
+                    strand = line[9]
+                    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, 'CDS', 'GeneMark_S']
+                    geneMark_S_ORFs.update({po: orf})
 
-    geneMark_S_ORFs = sortORFs(geneMark_S_ORFs)
+    for group in geneMark_S_ORFs:
+        geneMark_S_ORFs[group] = sortORFs(geneMark_S_ORFs[group])
     return geneMark_S_ORFs

ORForise/Tools/GeneMark_S_2/GeneMark_S_2.py

@@ -10,30 +10,34 @@ except ImportError:
 
 def GeneMark_S_2(*args):
     tool_pred = args[0]
-    genome = args[1]
-    types = args[2]
-    geneMark_S_2_ORFs = collections.defaultdict(list)
-    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:
-            line = line.split('\t')
-            if len(line) >= 9 and "CDS" in line[2]:
-                start = int(line[3])
-                stop = int(line[4])
-                strand = line[6]
-                info = line[8]
-                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, 'CDS', 'GeneMark_S_2|'+info]
-                geneMark_S_2_ORFs.update({po: orf})
+    dna_regions = args[1]
+    geneMark_S_2_ORFs = collections.defaultdict()
+    for dna_region in dna_regions:
+        geneMark_S_2_ORFs[dna_region] = collections.OrderedDict()
+    for dna_region in dna_regions:
+        genome = dna_regions[dna_region][0]
+        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:
+                line = line.split('\t')
+                if len(line) >= 9 and dna_region in line[0] and "CDS" in line[2]:
+                    start = int(line[3])
+                    stop = int(line[4])
+                    strand = line[6]
+                    info = line[8]
+                    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, 'CDS', 'GeneMark_S_2']
+                    geneMark_S_2_ORFs[dna_region].update({po: orf})
 
-    geneMark_S_2_ORFs = sortORFs(geneMark_S_2_ORFs)
+    for group in geneMark_S_2_ORFs:
+        geneMark_S_2_ORFs[group] = sortORFs(geneMark_S_2_ORFs[group])
     return geneMark_S_2_ORFs

ORForise/Tools/MetaGene/MetaGene.py

@@ -8,28 +8,35 @@ except ImportError:
     from ORForise.utils import sortORFs
 
 
-def MetaGene(tool_pred, genome):
+def MetaGene(*args):
+    tool_pred = args[0]
+    dna_regions = args[1]
     metaGene_ORFs = collections.OrderedDict()
-    genome_size = len(genome)
-    genome_rev = revCompIterative(genome)
-    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):
-                start = int(line[0])
-                stop = int(line[1])
-                strand = line[2]
-                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, 'CDS']
-                metaGene_ORFs.update({po: orf})
+    for dna_region in dna_regions:
+        metaGene_ORFs[dna_region] = collections.OrderedDict()
+    for dna_region in dna_regions:
+        genome = dna_regions[dna_region][0]
+        genome_size = len(genome)
+        genome_rev = revCompIterative(genome)
+        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 dna_region in line[0]:
+                    start = int(line[0])
+                    stop = int(line[1])
+                    strand = line[2]
+                    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, 'CDS', 'MetaGene']
+                    metaGene_ORFs.update({po: orf})
 
-    metaGene_ORFs = sortORFs(metaGene_ORFs)
+    for group in metaGene_ORFs:
+        metaGene_ORFs[group] = sortORFs(metaGene_ORFs[group])
     return metaGene_ORFs

ORForise/Tools/MetaGeneAnnotator/MetaGeneAnnotator.py

@@ -8,29 +8,36 @@ except ImportError:
     from ORForise.utils import sortORFs
 
 
-def MetaGeneAnnotator(tool_pred, genome):
+def MetaGeneAnnotator(*args):
+    tool_pred = args[0]
+    dna_regions = args[1]
     metaGeneAnnotator_ORFs = collections.OrderedDict()
-    genome_size = len(genome)
-    genome_rev = revCompIterative(genome)
-    with open(tool_pred, 'r') as MetaGeneAnnotator_input:
-        for line in MetaGeneAnnotator_input:
-            line = line.split()
-            if len(line) == 11:
-                if "gene_" in line[0]:
-                    start = int(line[1])
-                    stop = int(line[2])
-                    strand = line[3]
-                    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, 'CDS']
-                    metaGeneAnnotator_ORFs.update({po: orf})
+    for dna_region in dna_regions:
+        metaGeneAnnotator_ORFs[dna_region] = collections.OrderedDict()
+    for dna_region in dna_regions:
+        genome = dna_regions[dna_region][0]
+        genome_size = len(genome)
+        genome_rev = revCompIterative(genome)
+        with open(tool_pred, 'r') as MetaGeneAnnotator_input:
+            for line in MetaGeneAnnotator_input:
+                line = line.split()
+                if len(line) == 11 and dna_region in line[0]:
+                    if "gene_" in line[0]:
+                        start = int(line[1])
+                        stop = int(line[2])
+                        strand = line[3]
+                        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, 'CDS', 'MetaGeneAnnotator']
+                        metaGeneAnnotator_ORFs.update({po: orf})
 
-    metaGeneAnnotator_ORFs = sortORFs(metaGeneAnnotator_ORFs)
+    for group in metaGeneAnnotator_ORFs:
+        metaGeneAnnotator_ORFs[group] = sortORFs(metaGeneAnnotator_ORFs[group])
     return metaGeneAnnotator_ORFs

ORForise/Tools/MetaGeneMark/MetaGeneMark.py

@@ -8,29 +8,36 @@ except ImportError:
     from ORForise.utils import sortORFs
 
 
-def MetaGeneMark(tool_pred, genome):
+def MetaGeneMark(*args):
+    tool_pred = args[0]
+    dna_regions = args[1]
     metaGeneMarkORFs = collections.OrderedDict()
-    genome_size = len(genome)
-    genome_rev = revCompIterative(genome)
-    with open(tool_pred, 'r') as metaGeneMark_input:
-        for line in metaGeneMark_input:
-            line = line.split()
-            if len(line) == 19:
-                if 'GeneMark.hmm' in line[4] and "CDS" in line[5]:
-                    start = int(line[6])
-                    stop = int(line[7])
-                    strand = line[9]
-                    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, 'CDS']
-                    metaGeneMarkORFs.update({po: orf})
+    for dna_region in dna_regions:
+        metaGeneMarkORFs[dna_region] = collections.OrderedDict()
+    for dna_region in dna_regions:
+        genome = dna_regions[dna_region][0]
+        genome_size = len(genome)
+        genome_rev = revCompIterative(genome)
+        with open(tool_pred, 'r') as metaGeneMark_input:
+            for line in metaGeneMark_input:
+                line = line.split()
+                if len(line) == 19:
+                    if 'GeneMark.hmm' in line[4] and "CDS" in line[5] and dna_region in line[0]:
+                        start = int(line[6])
+                        stop = int(line[7])
+                        strand = line[9]
+                        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, 'CDS', 'MetaGeneMark']
+                        metaGeneMarkORFs.update({po: orf})
 
-    metaGeneMarkORFs = sortORFs(metaGeneMarkORFs)
+    for group in metaGeneMarkORFs:
+        metaGeneMarkORFs[group] = sortORFs(metaGeneMarkORFs[group])
     return metaGeneMarkORFs

ORForise/Tools/Prodigal/Prodigal.py

@@ -10,30 +10,34 @@ except ImportError:
 
 def Prodigal(*args):
     tool_pred = args[0]
-    genome = args[1]
-    #types = args[2]
-    prodigalORFs = collections.OrderedDict()
-    genome_size = len(genome)
-    genome_rev = revCompIterative(genome)
-    with open(tool_pred, 'r') as prodigal_input:
-        for line in prodigal_input:
-            line = line.split()
-            if "Prodigal" in line[1] and "CDS" in line[2]:
-                start = int(line[3])
-                stop = int(line[4])
-                strand = line[6]
-                info = line[8]
-                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, 'CDS', 'Prodigal|'+info]
-                prodigalORFs.update({po: orf})
+    dna_regions = args[1]
+    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]
+        genome_size = len(genome)
+        genome_rev = revCompIterative(genome)
+        with open(tool_pred, 'r') as prodigal_input:
+            for line in prodigal_input:
+                line = line.split()
+                if "Prodigal" in line[1] and dna_region in line[0] and "CDS" in line[2]:
+                    start = int(line[3])
+                    stop = int(line[4])
+                    strand = line[6]
+                    info = line[8]
+                    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, 'CDS', 'Prodigal']
+                    prodigal_ORFs[dna_region].update({po: orf})
 
-    prodigalORFs = sortORFs(prodigalORFs)
-    return prodigalORFs
+    for group in prodigal_ORFs:
+        prodigal_ORFs[group] = sortORFs(prodigal_ORFs[group])
+    return prodigal_ORFs