PyamilySeq 1.0.0__py3-none-any.whl → 1.0.1__py3-none-any.whl

PyamilySeq/PyamilySeq.py

@@ -0,0 +1,316 @@
+import argparse
+
+
+try:
+    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 as species_cluster
+    from PyamilySeq_Genus import cluster as genus_cluster
+    from constants import *
+    from utils import *
+
+
+
+
+def run_cd_hit(options, input_file, clustering_output, clustering_mode):
+    cdhit_command = [
+        clustering_mode,
+        '-i', input_file,
+        '-o', clustering_output,
+        '-c', str(options.pident),
+        '-s', str(options.len_diff),
+        '-T', str(options.threads),
+        '-M', str(options.mem),
+        '-d', "0",
+        '-g', str(options.fast_mode),
+        '-sc', "1",
+        '-sf', "1"
+    ]
+    if options.verbose == True:
+        subprocess.run(cdhit_command)
+    else:
+        subprocess.run(cdhit_command, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
+
+
+def main():
+    parser = argparse.ArgumentParser(description=f"PyamilySeq {PyamilySeq_Version}: A tool for gene clustering and analysis.")
+
+    # Add subparsers for Full and Partial modes
+    subparsers = parser.add_subparsers(dest="run_mode", required=True, help="Choose a mode: 'Full' or 'Partial'.")
+
+    # Full Mode Subparser
+    full_parser = subparsers.add_parser("Full",
+                                        help="Full mode: PyamilySeq to cluster with CD-HIT and process output.")
+    #full_parser.add_argument("-clustering_format", choices=['CD-HIT', 'MMseqs', 'BLAST'], required=True,
+    #                         help="Clustering format to use: CD-HIT, MMseqs2, or BLAST.")
+    full_parser.add_argument("-output_dir", required=True,
+                             help="Directory for all output files.")
+    full_parser.add_argument("-input_type", choices=['separate', 'combined', 'fasta'], required=True,
+                             help="Type of input files: 'separate' for matching FASTA and GFF files, 'combined' for GFF+FASTA, or 'fasta' for a prepared FASTA file.")
+    full_parser.add_argument("-input_dir", required=False,
+                             help="Directory containing GFF/FASTA files - Use with -input_type separate/combined.")
+    full_parser.add_argument("-input_fasta", required=False,
+                             help="Input FASTA file - Use with - input_type fasta.")
+    full_parser.add_argument("-name_split", required=False,
+                             help="Substring to split filenames and extract genome names (e.g., '_combined.gff3') - Use with -input_type separate/combined.")
+    full_parser.add_argument("-sequence_type", choices=['AA', 'DNA'], default="AA", required=False,
+                             help="Clustering mode: 'DNA' or 'AA'.")
+    full_parser.add_argument("-gene_ident", default="CDS", required=False,
+                             help="Gene identifiers to extract sequences (e.g., 'CDS, tRNA').")
+    full_parser.add_argument("-c", type=float, dest="pident", default=0.90, required=False,
+                             help="Sequence identity threshold for clustering (default: 0.90) - CD-HIT parameter '-c'.")
+    full_parser.add_argument("-s", type=float, dest="len_diff", default=0.80, required=False,
+                             help="Length difference threshold for clustering (default: 0.80) - CD-HIT parameter '-s'.")
+    full_parser.add_argument("-fast_mode", action="store_true", required=False,
+                             help="Enable fast mode for CD-HIT (not recommended) - CD-HIT parameter '-g'.")
+
+
+    # Partial Mode Subparser
+    partial_parser = subparsers.add_parser("Partial", help="Partial mode: PyamilySeq to process pre-clustered data.")
+    partial_parser.add_argument("-clustering_format", choices=['CD-HIT', 'MMseqs', 'BLAST'], required=True,
+                                help="Clustering format used: CD-HIT, MMseqs2, or BLAST.")
+    partial_parser.add_argument("-cluster_file", required=True,
+                                help="Cluster file containing pre-clustered groups from CD-HIT, MMseqs, BLAST etc.")
+    partial_parser.add_argument("-original_fasta", required=True,
+                                help="FASTA file used in pre-clustering (Provide sequences in DNA form).")
+    partial_parser.add_argument("-output_dir", required=True,
+                                help="Directory for all output files.")
+    partial_parser.add_argument("-reclustered", required=False,
+                                help="Clustering output file from a second round of clustering.")
+    partial_parser.add_argument("-seq_tag", default="StORF", dest="sequence_tag", required=False,
+                                help="Tag for distinguishing reclustered sequences.")
+
+    # Common Grouping Arguments
+    for subparser in [full_parser, partial_parser]:
+        subparser.add_argument("-group_mode", choices=['Species', 'Genus'], default="Species", required=False,
+                               help="Grouping mode: 'Species' or 'Genus'.")
+        subparser.add_argument("-species_groups", default="99,95,15", required=False,
+                               help="Gene groupings for 'Species' mode (default: '99,95,15').")
+        subparser.add_argument("-genus_groups", default="1,2,3,4,5,6,7,8,9,10", required=False,
+                               help="Gene groupings for 'Genus' mode (default: '1-10').")
+        subparser.add_argument("-w", default=None, dest="write_groups", required=False,
+                               help="Output gene groups as a single FASTA file (specify levels: e.g., '-w 99,95').")
+        subparser.add_argument("-wi", action="store_true", dest="write_individual_groups", required=False,
+                               help="Output individual FASTA files for each group.")
+        subparser.add_argument("-a", action="store_true", dest="align_core", required=False,
+                               help="Align and concatenate sequences for 'core' groups.")
+        subparser.add_argument("-align_aa", action="store_true", required=False,
+                               help="Align sequences as amino acids.")
+        subparser.add_argument("-no_gpa", action="store_false", dest="gene_presence_absence_out", required=False,
+                               help="Skip creation of gene_presence_absence.csv.")
+        subparser.add_argument("-M", type=int, default=4000, dest="mem", required=False,
+                                 help="Memory allocation for clustering (MB) - CD-HIT parameter '-M'.")
+        subparser.add_argument("-T", type=int, default=8, dest="threads", required=False,
+                                 help="Number of threads for clustering/alignment - CD-HIT parameter '-T' | MAFFT parameter '--thread'.")
+
+        # Miscellaneous Arguments
+        subparser.add_argument("-verbose", action="store_true", required=False,
+                            help="Print verbose output.")
+        subparser.add_argument("-v", "--version", action="version",
+                            version=f"PyamilySeq {PyamilySeq_Version}: Exiting.", help="Print version number and exit.")
+
+    # Parse Arguments
+    options = parser.parse_args()
+
+    # Example of conditional logic based on selected mode
+    print(f"Running PyamilySeq {PyamilySeq_Version} in {options.run_mode} mode:")
+    if options.run_mode == "Full" and options.verbose == True:
+        print("Processing Full mode with options:", vars(options))
+    elif options.run_mode == "Partial" and options.verbose == True:
+        print("Processing Partial mode with options:", vars(options))
+
+    ### Checking all required parameters are provided by user #!!# Doesn't seem to work
+    if options.run_mode == 'Full':
+        options.clustering_format = 'CD-HIT'
+        if getattr(options, 'reclustered', None) is not None:
+            sys.exit("Currently reclustering only works on Partial Mode.")
+        required_full_mode = [options.input_type, options.pident, options.len_diff]
+        if options.input_type != 'fasta':
+            required_full_mode.extend([options.input_dir, options.name_split])
+        if all(required_full_mode):
+            # Proceed with the Full mode
+            pass
+        else:
+            missing_options = [opt for opt in
+                               ['input_type', 'input_dir', 'name_split', 'clustering_format', 'pident', 'len_diff'] if
+                               not options.__dict__.get(opt)]
+            sys.exit(f"Missing required options for Full mode: {', '.join(missing_options)}")
+        if options.align_core:
+            options.write_individual_groups = True
+            if options.write_groups == None:
+                sys.exit('Must provide "-w" to output gene groups before alignment "-a" can be done.')
+    elif options.run_mode == 'Partial':
+        required_partial_mode = [options.cluster_file, options.original_fasta]
+        if all(required_partial_mode):
+            # Proceed with the Partial mode
+            pass
+        else:
+            missing_options = [opt for opt in
+                               ['cluster_file','original_fasta'] if
+                               not options.__dict__[opt]]
+            sys.exit(f"Missing required options for Partial mode: {', '.join(missing_options)}")
+        if options.align_core:
+            options.write_individual_groups = True
+            if options.write_groups == None or options.original_fasta == None:
+                sys.exit('Must provide "-w" to output gene groups before alignment "-a" can be done.')
+
+    if options.clustering_format == 'CD-HIT':
+        clust_affix = '.clstr'
+    elif options.clustering_format == 'TSV':
+        clust_affix = '.tsv'
+    elif options.clustering_format == 'CSV':
+        clust_affix = '.csv'
+
+    ###External tool checks:
+    ##MAFFT
+    if options.align_core == True:
+        if is_tool_installed('mafft'):
+            if options.verbose == True:
+                print("mafft is installed. Proceeding with alignment.")
+        else:
+            exit("mafft is not installed. Please install mafft to proceed.")
+    ##CD-HIT
+    if options.run_mode == 'Full':
+        if is_tool_installed('cd-hit'):
+            if options.verbose == True:
+                print("cd-hit is installed. Proceeding with clustering.")
+            if options.sequence_type == 'DNA':
+                clustering_mode = 'cd-hit-est'
+            elif options.sequence_type == 'AA':
+                clustering_mode = 'cd-hit'
+            if options.fast_mode == True:
+                options.fast_mode = 0
+                if options.verbose == True:
+                    print("Running CD-HIT in fast mode.")
+            else:
+                options.fast_mode = 1
+                if options.verbose == True:
+                    print("Running CD-HIT in slow mode.")
+        else:
+            exit("cd-hit is not installed. Please install cd-hit to proceed.")
+
+
+    # if options.write_groups != None and options.original_fasta == False:
+    #     exit("-fasta must br provided if -w is used")
+
+    if hasattr(options, 'cluster_file') and options.cluster_file:
+        options.cluster_file = fix_path(options.cluster_file)
+    if hasattr(options, 'reclustered') and options.reclustered:
+        options.reclustered = fix_path(options.reclustered)
+    if hasattr(options, 'input_dir') and options.input_dir:
+        options.input_dir = fix_path(options.input_dir)
+    if hasattr(options, 'output_dir') and options.output_dir:
+        options.output_dir = fix_path(options.output_dir)
+
+    output_path = os.path.abspath(options.output_dir)
+    combined_out_file = os.path.join(output_path, "combined_sequences_dna.fasta")
+    clustering_output = os.path.join(output_path, 'clustering_' + options.clustering_format)
+
+    if options.group_mode == 'Species':
+        options.species_groups = options.species_groups + ',0'
+        groups_to_use = options.species_groups
+    elif options.group_mode == 'Genus':
+        options.genus_groups = options.genus_groups + ',>'
+        groups_to_use = options.genus_groups
+        if options.align_core != None:
+            sys.exit("-a align_core not a valid option in Genus mode.")
+
+
+    if options.run_mode == 'Full':
+        if options.clustering_format != 'CD-HIT':
+            sys.exit('Only CD-HIT clsutering works in Full Mode')
+
+        if not os.path.exists(output_path):
+            os.makedirs(output_path)
+        if options.sequence_type == 'AA':
+            clustering_mode = 'cd-hit'
+            file_to_cluster = combined_out_file.replace('_dna.fasta','_aa.fasta')
+            translate = True
+        elif options.sequence_type == 'DNA':
+            clustering_mode = 'cd-hit-est'
+            translate = False
+            file_to_cluster = combined_out_file
+        if options.input_type == 'separate':
+            read_separate_files(options.input_dir, options.name_split, options.gene_ident, combined_out_file, translate)
+            run_cd_hit(options, file_to_cluster, clustering_output, clustering_mode)
+        elif options.input_type == 'combined':
+            read_combined_files(options.input_dir, options.name_split, options.gene_ident, combined_out_file, translate)
+            run_cd_hit(options, file_to_cluster, clustering_output, clustering_mode)
+        elif options.input_type == 'fasta':
+            combined_out_file = options.input_fasta
+            ### FIX write code to detect if DNA or AA and if sequence tpye is AA then translate
+            # Detect if the input FASTA file contains DNA or AA sequences
+            is_dna = detect_sequence_type(options.input_fasta)
+            # If the sequence type is AA and the input is DNA, translate the DNA to AA
+            if options.sequence_type == 'AA' and is_dna:
+                translated_fasta = os.path.join(output_path, os.path.splitext(os.path.basename(options.input_fasta))[0] + '_aa.fasta')
+                translate_dna_to_aa(options.input_fasta, translated_fasta)
+                file_to_cluster = translated_fasta
+            else:
+                file_to_cluster = options.input_fasta
+            run_cd_hit(options, file_to_cluster, clustering_output, clustering_mode)
+
+
+        class clustering_options:
+            def __init__(self):
+                self.run_mode = options.run_mode
+                self.cluster_format = options.clustering_format
+                self.sequence_type = options.sequence_type
+                self.reclustered = None
+                self.sequence_tag = None
+                self.species_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_groups = options.write_groups
+                self.write_individual_groups = options.write_individual_groups
+                self.threads = options.threads
+                self.align_core = options.align_core
+                self.align_aa = options.align_aa
+                self.fasta = combined_out_file
+                self.verbose = options.verbose
+
+        clustering_options = clustering_options()
+
+    elif options.run_mode == 'Partial':
+        class clustering_options:
+            def __init__(self):
+                self.run_mode = options.run_mode
+                self.cluster_format = options.clustering_format
+                self.sequence_type = None
+                self.reclustered = options.reclustered
+                self.sequence_tag = options.sequence_tag
+                self.species_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_groups = options.write_groups
+                self.write_individual_groups = options.write_individual_groups
+                self.threads = options.threads
+                self.align_core = options.align_core
+                self.align_aa = options.align_aa
+                self.fasta = options.original_fasta
+                self.verbose = options.verbose
+
+        clustering_options = clustering_options()
+
+
+    if options.group_mode == 'Species':
+        species_cluster(clustering_options)
+    elif options.group_mode == 'Genus':
+        genus_cluster((clustering_options))
+
+
+    # Save arguments to a text file
+    with open(output_path+"/PyamilySeq_params.txt", "w") as outfile:
+        for arg, value in vars(options).items():
+            outfile.write(f"{arg}: {value}\n")
+
+    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#####")
+
+if __name__ == "__main__":
+    main()

PyamilySeq/PyamilySeq_Genus.py

@@ -0,0 +1,242 @@
+#from line_profiler_pycharm import profile
+
+
+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 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, 'gene_presence_absence.csv')
+    gpa_outfile = open(gpa_outfile, '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):
+    ##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_num,  cores):
+    try:
+        cores['First_genera_' + str(First_num)].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_' + str(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_' + str(group)].append(cluster)
+    except KeyError:
+        cores['combined_genera_>'].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_genomes, pangenome_clusters_First_sequences, reps = cluster_CDHIT(options, '_')
+    elif 'TSV' in options.cluster_format or 'CSV' in options.cluster_format:
+        genus_dict, pangenome_clusters_First, pangenome_clusters_First_genomes, pangenome_clusters_First_sequences, reps = cluster_EdgeList(options, '_')
+
+    ###
+    cores, groups = get_cores(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_pangenome_clusters_Second_sequences = combined_clustering_CDHIT(options, genus_dict, '_')
+        elif 'TSV' in options.cluster_format or 'CSV' in options.cluster_format:
+            combined_pangenome_clusters_First_Second_clustered,not_Second_only_cluster_ids,combined_pangenome_clusters_Second, combined_pangenome_clusters_Second_sequences = combined_clustering_Edge_List(options, '_')
+        pangenome_clusters_Type = combined_clustering_counting(options, pangenome_clusters_First, reps, combined_pangenome_clusters_First_Second_clustered, pangenome_clusters_First_genomes, '_')
+    else:
+        pangenome_clusters_Type = single_clustering_counting(pangenome_clusters_First, reps)
+
+
+
+    Number_Of_Second_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")
+    seen_groupings = []
+    for cluster, numbers in pangenome_clusters_Type_sorted.items():
+    ############################### Calculate First only
+        cluster = str(cluster)
+        for grouping in numbers[2]: #!!# Could do with a more elegant solution
+            current_cluster = grouping[0].split(':')[0]
+            if current_cluster not in seen_groupings:
+                seen_groupings.append(current_cluster)
+                current_cluster_size = grouping[0].split(':')[1]
+                calc_First_only_core(current_cluster, current_cluster_size, cores)
+            ############################# 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], cores, numbers[3])
+                elif numbers[0] > 1 and numbers[3] >= 1:  # If unique Seconds combined multiple Firsts
+                    calc_multi_First_extended_Second_only_core(cluster, numbers[1], cores, numbers[3])
+                elif numbers[4] >= 1:
+                    Number_Of_Second_Extending_But_Same_Genomes += 1
+            else:
+                if options.verbose == True:
+                    print("First cluster " + current_cluster + " already processed - This is likely because it was clustered with another First representative.")
+
+    if options.reclustered != None:
+        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
+    output_path = os.path.abspath(options.output_dir)
+    if not os.path.exists(output_path):
+        os.makedirs(output_path)
+    stats_out = os.path.join(output_path,'summary_statistics.txt')
+    key_order = list(cores.keys())
+    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 First 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.reclustered!= None:
+            print("Total Number of Second Gene Groups (Including Singletons): " + str(
+                len(combined_pangenome_clusters_Second_sequences)))
+            print("Total Number of First Gene Groups That Had Additional Second Sequences But Not New Genomes: " + str(
+                Number_Of_Second_Extending_But_Same_Genomes))
+            outfile.write("\nTotal Number of Second Gene Groups (Including Singletons): " + str(
+                len(combined_pangenome_clusters_Second_sequences)))
+            outfile.write("\nTotal Number of First Gene Groups That Had Additional Second Sequences But Not New Genomes: " + str(
+                Number_Of_Second_Extending_But_Same_Genomes))
+
+    if options.gene_presence_absence_out != False:
+        gene_presence_absence_output(options,genus_dict, pangenome_clusters_First_sorted, pangenome_clusters_First_sequences_sorted)
+
+    if options.run_mode == 'Full':
+        if options.reclustered == None:
+            combined_pangenome_clusters_Second_sequences = None
+        if options.write_groups != None:
+            print("Outputting gene group FASTA files")
+            sequences = read_fasta(options.fasta)
+            #output_dir = os.path.dirname(os.path.abspath(options.output_dir))
+            output_dir = os.path.join(options.output_dir, 'Gene_Groups_Output')
+            write_groups_func(options,output_dir, key_order, cores, sequences,
+                         pangenome_clusters_First_sequences_sorted, combined_pangenome_clusters_Second_sequences)
+
+    elif options.run_mode == 'Partial':
+        if options.reclustered == None:
+            combined_pangenome_clusters_Second_sequences = None
+        if options.write_groups != None and options.fasta != None:
+            print("Outputting gene group FASTA files")
+            sequences = read_fasta(options.fasta)
+            #output_dir = os.path.dirname(os.path.abspath(options.output_dir))
+            output_dir = os.path.join(options.output_dir, 'Gene_Groups_Output')
+            write_groups_func(options,output_dir, key_order, cores, sequences,
+                         pangenome_clusters_First_sequences_sorted, combined_pangenome_clusters_Second_sequences)
+
+
+    # if options.write_groups != None and options.fasta != None:
+    #     sequences = read_fasta(options.fasta)
+    #     output_dir = os.path.join(output_path, 'Gene_Families_Output')
+    #
+    #     write_groups(options,output_dir, key_order, cores, sequences,
+    #                  pangenome_clusters_First_sequences_sorted, combined_pangenome_clusters_Second_sequences)
+
+
+    #!!# - Currently only align in Species Mode
+    #if options.align_core != None and options.fasta != None and options.write_groups != None:
+    #    process_gene_families(options, os.path.join(output_path, 'Gene_Families_Output'), 'concatenated_genes_aligned.fasta')
+
+
+
+