PyamilySeq 0.5.2__tar.gz → 0.6.0__tar.gz

{pyamilyseq-0.5.2/src/PyamilySeq.egg-info → pyamilyseq-0.6.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: PyamilySeq
-Version: 0.5.2
+Version: 0.6.0
 Summary: PyamilySeq - A a tool to look for sequence-based gene families identified by clustering methods such as CD-HIT, DIAMOND, BLAST or MMseqs2.
 Home-page: https://github.com/NickJD/PyamilySeq
 Author: Nicholas Dimonaco
@@ -57,10 +57,11 @@ Total Number of Gene Groups (Including Singletons): 11128
 
 ## Usage - Menu
 ```
-usage: PyamilySeq.py [-h] -run_mode {Full,Partial} -group_mode {Species} -clust_tool {CD-HIT} -output_dir OUTPUT_DIR [-input_type {separate,combined}] [-input_dir INPUT_DIR] [-name_split NAME_SPLIT] [-pid PIDENT] [-len_diff LEN_DIFF] [-mem CLUSTERING_MEMORY] [-t CLUSTERING_THREADS] [-cluster_file CLUSTER_FILE]
-                     [-reclustered RECLUSTERED] [-seq_tag SEQUENCE_TAG] [-groups CORE_GROUPS] [-w WRITE_FAMILIES] [-con CON_CORE] [-original_fasta ORIGINAL_FASTA] [-gpa GENE_PRESENCE_ABSENCE_OUT] [-verbose {True,False}] [-v]
+usage: PyamilySeq.py [-h] -run_mode {Full,Partial} -group_mode {Species,Genus} -clust_tool {CD-HIT} -output_dir OUTPUT_DIR [-input_type {separate,combined}] [-input_dir INPUT_DIR] [-name_split NAME_SPLIT]
+                     [-pid PIDENT] [-len_diff LEN_DIFF] [-mem CLUSTERING_MEMORY] [-t CLUSTERING_THREADS] [-cluster_file CLUSTER_FILE] [-reclustered RECLUSTERED] [-seq_tag SEQUENCE_TAG]
+                     [-core_groups CORE_GROUPS] [-genus_groups GENUS_GROUPS] [-w WRITE_FAMILIES] [-con CON_CORE] [-original_fasta ORIGINAL_FASTA] [-gpa GENE_PRESENCE_ABSENCE_OUT] [-verbose {True,False}] [-v]
 
-PyamilySeq v0.5.2: PyamilySeq Run Parameters.
+PyamilySeq v0.6.0: PyamilySeq Run Parameters.
 
 options:
   -h, --help            show this help message and exit
@@ -68,8 +69,8 @@ options:
 Required Arguments:
   -run_mode {Full,Partial}
                         Run Mode: Should PyamilySeq be run in "Full" or "Partial" mode?
-  -group_mode {Species}
-                        Group Mode: Should PyamilySeq be run in "Species" or "Genus" mode? - Genus mode not currently functioning
+  -group_mode {Species,Genus}
+                        Group Mode: Should PyamilySeq be run in "Species" or "Genus" mode?
   -clust_tool {CD-HIT}  Clustering tool to use: CD-HIT, DIAMOND, BLAST or MMseqs2.
   -output_dir OUTPUT_DIR
                         Directory for all output files.
@@ -95,10 +96,13 @@ Partial-Mode Arguments - Required when "-run_mode Partial" is used:
 
 Grouping Arguments - Use to fine-tune grouping of genes after clustering:
   -reclustered RECLUSTERED
-                        Clustering output file from secondary round of clustering
+                        Currently only works on Partial Mode: Clustering output file from secondary round of clustering.
   -seq_tag SEQUENCE_TAG
                         Default - "StORF": Unique identifier to be used to distinguish the second of two rounds of clustered sequences
-  -groups CORE_GROUPS   Default - ('99,95,15'): Gene family groups to use
+  -core_groups CORE_GROUPS
+                        Default - ('99,95,15'): Gene family groups to use for "Species" mode
+  -genus_groups GENUS_GROUPS
+                        Default - ('1,2,3,4,5,6'): Gene family groups to use for "Genus" mode
 
 Output Parameters:
   -w WRITE_FAMILIES     Default - No output: Output sequences of identified families (provide levels at which to output "-w 99,95" - Must provide FASTA file with -fasta
@@ -113,7 +117,6 @@ Misc:
                         Default - False: Print out runtime messages
   -v                    Default - False: Print out version number and exit
 
-
 ```
 
 
@@ -126,7 +129,7 @@ Seq-Combiner -input_dir .../test_data/genomes -name_split _combined.gff3 -output
 ```bash
 usage: Seq_Combiner.py [-h] -input_dir INPUT_DIR -input_type {separate,combined} -name_split NAME_SPLIT -output_dir OUTPUT_DIR -output_name OUTPUT_FILE
 
-Seq-Combiner v0.5.2: Seq-Combiner Run Parameters.
+Seq-Combiner v0.6.0: Seq-Combiner Run Parameters.
 
 options:
   -h, --help            show this help message and exit

{pyamilyseq-0.5.2 → pyamilyseq-0.6.0}/README.md

@@ -42,10 +42,11 @@ Total Number of Gene Groups (Including Singletons): 11128
 
 ## Usage - Menu
 ```
-usage: PyamilySeq.py [-h] -run_mode {Full,Partial} -group_mode {Species} -clust_tool {CD-HIT} -output_dir OUTPUT_DIR [-input_type {separate,combined}] [-input_dir INPUT_DIR] [-name_split NAME_SPLIT] [-pid PIDENT] [-len_diff LEN_DIFF] [-mem CLUSTERING_MEMORY] [-t CLUSTERING_THREADS] [-cluster_file CLUSTER_FILE]
-                     [-reclustered RECLUSTERED] [-seq_tag SEQUENCE_TAG] [-groups CORE_GROUPS] [-w WRITE_FAMILIES] [-con CON_CORE] [-original_fasta ORIGINAL_FASTA] [-gpa GENE_PRESENCE_ABSENCE_OUT] [-verbose {True,False}] [-v]
+usage: PyamilySeq.py [-h] -run_mode {Full,Partial} -group_mode {Species,Genus} -clust_tool {CD-HIT} -output_dir OUTPUT_DIR [-input_type {separate,combined}] [-input_dir INPUT_DIR] [-name_split NAME_SPLIT]
+                     [-pid PIDENT] [-len_diff LEN_DIFF] [-mem CLUSTERING_MEMORY] [-t CLUSTERING_THREADS] [-cluster_file CLUSTER_FILE] [-reclustered RECLUSTERED] [-seq_tag SEQUENCE_TAG]
+                     [-core_groups CORE_GROUPS] [-genus_groups GENUS_GROUPS] [-w WRITE_FAMILIES] [-con CON_CORE] [-original_fasta ORIGINAL_FASTA] [-gpa GENE_PRESENCE_ABSENCE_OUT] [-verbose {True,False}] [-v]
 
-PyamilySeq v0.5.2: PyamilySeq Run Parameters.
+PyamilySeq v0.6.0: PyamilySeq Run Parameters.
 
 options:
   -h, --help            show this help message and exit
@@ -53,8 +54,8 @@ options:
 Required Arguments:
   -run_mode {Full,Partial}
                         Run Mode: Should PyamilySeq be run in "Full" or "Partial" mode?
-  -group_mode {Species}
-                        Group Mode: Should PyamilySeq be run in "Species" or "Genus" mode? - Genus mode not currently functioning
+  -group_mode {Species,Genus}
+                        Group Mode: Should PyamilySeq be run in "Species" or "Genus" mode?
   -clust_tool {CD-HIT}  Clustering tool to use: CD-HIT, DIAMOND, BLAST or MMseqs2.
   -output_dir OUTPUT_DIR
                         Directory for all output files.
@@ -80,10 +81,13 @@ Partial-Mode Arguments - Required when "-run_mode Partial" is used:
 
 Grouping Arguments - Use to fine-tune grouping of genes after clustering:
   -reclustered RECLUSTERED
-                        Clustering output file from secondary round of clustering
+                        Currently only works on Partial Mode: Clustering output file from secondary round of clustering.
   -seq_tag SEQUENCE_TAG
                         Default - "StORF": Unique identifier to be used to distinguish the second of two rounds of clustered sequences
-  -groups CORE_GROUPS   Default - ('99,95,15'): Gene family groups to use
+  -core_groups CORE_GROUPS
+                        Default - ('99,95,15'): Gene family groups to use for "Species" mode
+  -genus_groups GENUS_GROUPS
+                        Default - ('1,2,3,4,5,6'): Gene family groups to use for "Genus" mode
 
 Output Parameters:
   -w WRITE_FAMILIES     Default - No output: Output sequences of identified families (provide levels at which to output "-w 99,95" - Must provide FASTA file with -fasta
@@ -98,7 +102,6 @@ Misc:
                         Default - False: Print out runtime messages
   -v                    Default - False: Print out version number and exit
 
-
 ```
 
 
@@ -111,7 +114,7 @@ Seq-Combiner -input_dir .../test_data/genomes -name_split _combined.gff3 -output
 ```bash
 usage: Seq_Combiner.py [-h] -input_dir INPUT_DIR -input_type {separate,combined} -name_split NAME_SPLIT -output_dir OUTPUT_DIR -output_name OUTPUT_FILE
 
-Seq-Combiner v0.5.2: Seq-Combiner Run Parameters.
+Seq-Combiner v0.6.0: Seq-Combiner Run Parameters.
 
 options:
   -h, --help            show this help message and exit

{pyamilyseq-0.5.2 → pyamilyseq-0.6.0}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = PyamilySeq
-version = v0.5.2
+version = v0.6.0
 author = Nicholas Dimonaco
 author_email = nicholas@dimonaco.co.uk
 description = PyamilySeq - A a tool to look for sequence-based gene families identified by clustering methods such as CD-HIT, DIAMOND, BLAST or MMseqs2.

pyamilyseq-0.6.0/src/PyamilySeq/Constants.py

@@ -0,0 +1,2 @@
+PyamilySeq_Version = 'v0.6.0'
+

{pyamilyseq-0.5.2 → pyamilyseq-0.6.0}/src/PyamilySeq/PyamilySeq.py

@@ -7,11 +7,13 @@ import subprocess
 
 
 try:
-    from .PyamilySeq_Species import cluster
+    from .PyamilySeq_Species import cluster as species_cluster
+    from .PyamilySeq_Genus import cluster as genus_cluster
     from .Constants import *
     from .utils import *
 except (ModuleNotFoundError, ImportError, NameError, TypeError) as error:
-    from PyamilySeq_Species import cluster
+    from PyamilySeq_Species import cluster as species_cluster
+    from PyamilySeq_Genus import cluster as genus_cluster
     from Constants import *
     from utils import *
 
@@ -44,8 +46,8 @@ def main():
     required.add_argument('-run_mode', action='store', dest='run_mode', choices=['Full','Partial'],
                           help='Run Mode: Should PyamilySeq be run in "Full" or "Partial" mode?',
                           required=True)
-    required.add_argument('-group_mode', action='store', dest='group_type', choices=['Species'],
-                          help='Group Mode: Should PyamilySeq be run in "Species" or "Genus" mode? - Genus mode not currently functioning',
+    required.add_argument('-group_mode', action='store', dest='group_type', choices=['Species', 'Genus'],
+                          help='Group Mode: Should PyamilySeq be run in "Species" or "Genus" mode? ',
                           required=True)
     required.add_argument("-clust_tool", action="store", dest="clust_tool", choices=['CD-HIT'],
                           help="Clustering tool to use: CD-HIT, DIAMOND, BLAST or MMseqs2.",
@@ -88,13 +90,17 @@ def main():
 
     ###Grouping Arguments
     grouping_args = parser.add_argument_group('Grouping Arguments - Use to fine-tune grouping of genes after clustering')
-    grouping_args.add_argument('-reclustered', action='store', dest='reclustered', help='Clustering output file from secondary round of clustering',
+    grouping_args.add_argument('-reclustered', action='store', dest='reclustered',
+                        help='Currently only works on Partial Mode: Clustering output file from secondary round of clustering.',
                         required=False)
     grouping_args.add_argument('-seq_tag', action='store', dest='sequence_tag', default='StORF',
                         help='Default - "StORF": Unique identifier to be used to distinguish the second of two rounds of clustered sequences',
                         required=False)
-    grouping_args.add_argument('-groups', action="store", dest='core_groups', default="99,95,15",
-                        help='Default - (\'99,95,15\'): Gene family groups to use',
+    grouping_args.add_argument('-core_groups', action="store", dest='core_groups', default="99,95,15",
+                        help='Default - (\'99,95,15\'): Gene family groups to use for "Species" mode',
+                        required=False)
+    grouping_args.add_argument('-genus_groups', action="store", dest='genus_groups', default="1,2,3,4,5,6",
+                        help='Default - (\'1,2,3,4,5,6\'): Gene family groups to use for "Genus" mode',
                         required=False)
 
     ###Output Arguments
@@ -126,6 +132,8 @@ def main():
 
     ### Checking all required parameters are provided by user
     if options.run_mode == 'Full':
+        if options.reclustered != None:
+            sys.exit("Currently reclustering only works on Partial Mode.")
         required_full_mode = [options.input_type, options.input_dir, options.name_split, options.clust_tool,
                               options.pident, options.len_diff]
         if all(required_full_mode):
@@ -165,7 +173,7 @@ def main():
         else:
             exit("mafft is not installed. Please install mafft to proceed.")
     ##CD-HIT
-    if options.clust_tool == 'CD-HIT':
+    if options.clust_tool == 'CD-HIT' and options.run_mode == 'Full':
         if is_tool_installed('cd-hit'):
             if options.verbose == True:
                 print("cd-hit is installed. Proceeding with clustering.")
@@ -175,7 +183,7 @@ def main():
     if options.write_families != None and options.original_fasta == False:
         exit("-fasta must br provided if -w is used")
 
-    options.core_groups = options.core_groups + ',0'
+
 
 
     if options.cluster_file:
@@ -191,24 +199,30 @@ def main():
     combined_out_file = os.path.join(output_path, "combined_sequences.fasta")
     clustering_output = os.path.join(output_path, 'clustering_' + options.clust_tool)
 
-
-    if options.run_mode == 'Full':
-
+    if options.group_type == 'Species':
+        options.core_groups = options.core_groups + ',0'
+        groups_to_use = options.core_groups
+    else:
+        options.genus_groups = options.genus_groups + ',>'
+        groups_to_use = options.genus_groups
 
 
+    if options.run_mode == 'Full':
         if options.input_type == 'separate':
             read_separate_files(options.input_dir, options.name_split, combined_out_file)
         else:
             read_combined_files(options.input_dir, options.name_split, combined_out_file)
 
         run_cd_hit(combined_out_file, clustering_output, options)
+
         class clustering_options:
             def __init__(self):
                 self.cluster_format = options.clust_tool
                 self.reclustered = options.reclustered
                 self.sequence_tag = options.sequence_tag
-                self.core_groups = '99,95,15,0'
+                self.core_groups = groups_to_use
                 self.clusters = clustering_output + clust_affix
+                self.output_dir = options.output_dir
                 self.gene_presence_absence_out = options.gene_presence_absence_out
                 self.write_families = options.write_families
                 self.con_core = options.con_core
@@ -223,8 +237,9 @@ def main():
                 self.cluster_format = options.clust_tool
                 self.reclustered = options.reclustered
                 self.sequence_tag = options.sequence_tag
-                self.core_groups = '99,95,15,0'
+                self.core_groups = groups_to_use
                 self.clusters = options.cluster_file
+                self.output_dir = options.output_dir
                 self.gene_presence_absence_out = options.gene_presence_absence_out
                 self.write_families = options.write_families
                 self.con_core = options.con_core
@@ -234,9 +249,10 @@ def main():
         clustering_options = clustering_options()
 
 
-
-
-    cluster(clustering_options)
+    if options.group_type == 'Species':
+        species_cluster(clustering_options)
+    elif options.group_type == 'Genus':
+        genus_cluster((clustering_options))
 
     print("Thank you for using PyamilySeq -- A detailed user manual can be found at https://github.com/NickJD/PyamilySeq\n"
           "Please report any issues to: https://github.com/NickJD/PyamilySeq/issues\n#####")

pyamilyseq-0.6.0/src/PyamilySeq/PyamilySeq_Genus.py

@@ -0,0 +1,259 @@
+#from line_profiler_pycharm import profile
+
+import copy
+import sys
+import math
+from collections import Counter
+
+
+try:
+    from .Constants import *
+    from .clusterings import *
+    from .utils import *
+except (ModuleNotFoundError, ImportError, NameError, TypeError) as error:
+    from Constants import *
+    from clusterings import *
+    from utils import *
+
+
+
+def process_gene_families(options, directory, output_file):
+    """Process each gene family file to select the longest sequence per genome and concatenate aligned sequences."""
+    concatenated_sequences = {}
+    output_file = directory.replace('Gene_Families_Output',output_file)
+
+    # Iterate over each gene family file
+    for gene_file in os.listdir(directory):
+        if gene_file.endswith('.fasta'):
+            gene_path = os.path.join(directory, gene_file)
+
+            # Read sequences from the gene family file
+            sequences = read_fasta(gene_path)
+
+            # Select the longest sequence for each genome
+            longest_sequences = select_longest_gene(sequences)
+
+            # Run mafft on the longest sequences
+            aligned_file = f"{gene_file}_aligned.fasta"
+            run_mafft_on_sequences(options, {seq_id: seq for seq_id, seq in longest_sequences.values()}, aligned_file)
+
+            # Read aligned sequences and concatenate them
+            aligned_sequences = read_fasta(aligned_file)
+            for genome, aligned_seq in aligned_sequences.items():
+                genome_name = genome.split('|')[0]
+                if genome_name not in concatenated_sequences:
+                    concatenated_sequences[genome_name] = ""
+                concatenated_sequences[genome_name] += aligned_seq
+
+            # Clean up aligned file
+            os.remove(aligned_file)
+
+    # Write the concatenated sequences to the output file
+    with open(output_file, 'w') as out:
+        for genome, sequence in concatenated_sequences.items():
+            out.write(f">{genome}\n")
+            wrapped_sequence = wrap_sequence(sequence, 60)
+            out.write(f"{wrapped_sequence}\n")
+
+def gene_presence_absence_output(options, genus_dict, pangenome_clusters_First_sorted, pangenome_clusters_First_sequences_sorted):
+    print("Outputting gene_presence_absence file")
+    output_dir = os.path.abspath(options.output_dir)
+    in_name = options.clusters.split('.')[0].split('/')[-1]
+    gpa_outfile = os.path.join(output_dir, in_name)
+    gpa_outfile = open(gpa_outfile+'_gene_presence_absence.csv','w')
+    gpa_outfile.write('"Gene","Non-unique Gene name","Annotation","No. isolates","No. sequences","Avg sequences per isolate","Genome Fragment","Order within Fragment","'
+                     '"Accessory Fragment","Accessory Order with Fragment","QC","Min group size nuc","Max group size nuc","Avg group size nuc","')
+    gpa_outfile.write('","'.join(genus_dict.keys()))
+    gpa_outfile.write('"\n')
+    for cluster, sequences in pangenome_clusters_First_sequences_sorted.items():
+        average_sequences_per_genome = len(sequences) / len(pangenome_clusters_First_sorted[cluster])
+        gpa_outfile.write('"group_'+str(cluster)+'","","'+str(len(pangenome_clusters_First_sorted[cluster]))+'","'+str(len(sequences))+'","'+str(average_sequences_per_genome)+
+                         '","","","","","","","","",""')
+
+
+        for genus in genus_dict.keys():
+            full_out = ''
+            tmp_list = []
+            for value in sequences:
+                if value.split('_')[0] == genus:
+                    tmp_list.append(value)
+            if tmp_list:
+                full_out += ',"'+''.join(tmp_list)+'"'
+            else:
+                full_out = ',""'
+            gpa_outfile.write(full_out)
+        gpa_outfile.write('\n')
+
+### Below is some unfinished code
+    # edge_list_outfile = open(in_name+'_edge_list.csv','w')
+    # for cluster, sequences in pangenome_clusters_First_sequences_sorted.items():
+    #     output = []
+    #     for entry in sequences:
+    #         # Split each entry at '|'
+    #         genome, gene = entry.split('|')
+    #         # Format the result as "gene  genome"
+    #         output.append(f"{gene}\t{genome}")
+    #     for line in output:
+    #         edge_list_outfile.write(line + '\n')
+
+
+
+
+def get_cores(options,genus_dict):
+    ##Calculate core groups
+    groups = OrderedDict()
+    cores = OrderedDict()
+    for group in options.core_groups.split(','):
+        first_core_group = 'First_genera_' + group
+        cores[first_core_group] = []
+        if options.reclustered != None:
+            extended_core_group = 'extended_genera_' + group
+            cores[extended_core_group] = []
+            combined_core_group = 'combined_genera_' + group
+            cores[combined_core_group] = []
+            second_core_group = 'Second_genera_' + group
+            cores[second_core_group] = []
+            only_second_core_group = 'only_Second_genera_' + group
+            cores[only_second_core_group] = []
+    return cores, groups
+
+
+#@profile
+def calc_First_only_core(cluster, First_number,  cores):
+    try:
+        cores['First_genera_'+str(First_number)].append(cluster)
+    except KeyError:
+        cores['First_genera_>'].append(cluster)
+#@profile
+def calc_single_First_extended_Second_only_core(cluster, First_num, cores, Second_num): # Count gene families extended with StORFs
+    group = First_num + Second_num
+    try:
+        cores['extended_genera_' + group].append(cluster)
+    except KeyError:
+        cores['extended_genera_>'].append(cluster)
+#@profile
+def calc_multi_First_extended_Second_only_core(cluster, First_num, cores, Second_num): # Count seperately those gene families extended with StORF_Reporter but combined >1 PEP
+    group = First_num + Second_num
+    try:
+        cores['combined_genera_' + group].append(cluster)
+    except KeyError:
+        cores['combined_genera_>' + group].append(cluster)
+#@profile
+def calc_Second_only_core(cluster, cores, Second_num):
+    try:
+        cores['Second_genera_' + str(Second_num)].append(cluster)
+    except KeyError:
+        cores['Second_genera_>'].append(cluster)
+#@profile
+def calc_only_Second_only_core(cluster, cores, Second_num): # only count the true storf onlies
+    try:
+        cores['only_Second_genera_' + str(Second_num)].append(cluster)
+    except:
+        cores['only_Second_genera_>'].append(cluster)
+
+
+
+#@profile
+def cluster(options):
+
+    if options.cluster_format == 'CD-HIT':
+        genus_dict, pangenome_clusters_First, pangenome_clusters_First_sequences, reps = cluster_CDHIT(options, '_')
+    elif options.cluster_format in ['TSV','CSV']:
+        genus_dict, pangenome_clusters_First, pangenome_clusters_First_sequences, reps = cluster_EdgeList(options, '_')
+
+
+
+    if options.reclustered != None:
+
+        if options.cluster_format == 'CD-HIT':
+            combined_pangenome_clusters_First_Second_clustered,not_Second_only_cluster_ids,combined_pangenome_clusters_Second = combined_clustering_CDHIT(options, genus_dict, '_')
+        if options.cluster_format == ['TSV','CSV']:
+            combined_pangenome_clusters_First_Second_clustered,not_Second_only_cluster_ids,combined_pangenome_clusters_Second = combined_clustering_Edge_List(options, '_')
+        pangenome_clusters_Type = combined_clustering_counting(options, pangenome_clusters_First, reps, combined_pangenome_clusters_First_Second_clustered, '_')
+    else:
+
+        pangenome_clusters_Type = single_clustering_counting(pangenome_clusters_First, reps)
+
+    ###
+    cores, groups = get_cores(options, genus_dict)
+    ###
+
+    Number_Of_StORF_Extending_But_Same_Genomes = 0
+
+    sorted_first_keys = sort_keys_by_values(pangenome_clusters_First, pangenome_clusters_First_sequences)
+    pangenome_clusters_First_sorted = reorder_dict_by_keys(pangenome_clusters_First, sorted_first_keys)
+    pangenome_clusters_First_sequences_sorted = reorder_dict_by_keys(pangenome_clusters_First_sequences, sorted_first_keys)
+    pangenome_clusters_Type_sorted = reorder_dict_by_keys(pangenome_clusters_Type, sorted_first_keys)
+
+    print("Calculating Groups")
+    for cluster, numbers in pangenome_clusters_Type_sorted.items():
+    ############################### Calculate First only
+        calc_First_only_core(cluster, numbers[1], cores)
+
+    if options.reclustered != None:
+        ############################# Calculate First and Reclustered-Second
+        if numbers[0] == 1 and numbers[3] >= 1:  # If Seconds did not combine First reps
+            calc_single_First_extended_Second_only_core(cluster, numbers[1], groups, cores, numbers[3])
+        elif numbers[0] > 1 and numbers[3] >= 1:  # If unique Secondss combined multiple Firsts
+            calc_multi_First_extended_Second_only_core(cluster, numbers[1], groups, cores, numbers[3])
+        elif numbers[4] >= 1:
+            Number_Of_StORF_Extending_But_Same_Genomes += 1
+
+        combined_pangenome_clusters_ONLY_Second_Type = defaultdict(list)
+        combined_pangenome_clusters_Second_Type = defaultdict(list)
+        for cluster, genomes in combined_pangenome_clusters_Second.items():
+            if cluster in not_Second_only_cluster_ids:
+                combined_pangenome_clusters_Second_Type[cluster] = [cluster, len(genomes)]
+            else:
+                combined_pangenome_clusters_ONLY_Second_Type[cluster] = [cluster, len(genomes)]
+        for cluster, data in combined_pangenome_clusters_Second_Type.items():
+            if data[1] >=1:
+                calc_Second_only_core(cluster, cores, data[1])
+        for cluster, data in combined_pangenome_clusters_ONLY_Second_Type.items():
+            if data[1] >= 1 :
+                calc_only_Second_only_core(cluster,  cores, data[1])
+    ###########################
+    ### Output
+    key_order = list(cores.keys())
+    output_path = os.path.abspath(options.output_dir)
+    stats_out = os.path.join(output_path,'summary_statistics.txt')
+    with open(stats_out,'w') as outfile:
+        print("Genus Groups:")
+        outfile.write("Genus Groups:\n")
+        for key in key_order:
+            print(key+':\t'+str(len(cores[key])))
+            outfile.write(key + ':\t' + str(len(cores[key]))+'\n')
+        print("Total Number of Gene Groups (Including Singletons): " + str(len(pangenome_clusters_First_sequences_sorted)))
+        outfile.write("Total Number of Gene Groups (Including Singletons): " + str(len(pangenome_clusters_First_sequences_sorted)))
+
+    if options.gene_presence_absence_out != None:
+        gene_presence_absence_output(options,genus_dict, pangenome_clusters_First_sorted, pangenome_clusters_First_sequences_sorted)
+
+    if options.write_families != None and options.fasta != None:
+        sequences = read_fasta(options.fasta)
+        output_dir = os.path.join(output_path, 'Gene_Families_Output')
+
+        # Create output directory if it doesn't exist
+        if not os.path.exists(output_dir):
+            os.makedirs(output_dir)
+        for key_prefix in key_order:
+            for key, values in cores.items():
+                if any(part in options.write_families.split(',') for part in key.split('_')):
+                    if key.startswith(key_prefix):
+                        for value in values:
+                            output_filename = f"{key}_{value}.fasta"
+                            sequences_to_write = pangenome_clusters_First_sequences_sorted[value]
+                            # Write sequences to output file that are in the sequences dictionary
+                            with open(os.path.join(output_dir, output_filename), 'w') as outfile:
+                                for header in sequences_to_write:
+                                    if header in sequences:
+                                        outfile.write(f">{header}\n")
+                                        wrapped_sequence = wrap_sequence(sequences[header])
+                                        outfile.write(f"{wrapped_sequence}\n")
+
+    if options.con_core != None and options.fasta != None and options.write_families != None:
+        process_gene_families(options, os.path.join(output_dir, 'Gene_Families_Output'), 'concatonated_genes_aligned.fasta')
+
+
+
+