PyamilySeq 1.0.1__py3-none-any.whl → 1.1.0__py3-none-any.whl

PyamilySeq/Group_Extractor.py

@@ -0,0 +1,83 @@
+import argparse
+import os
+import csv
+
+
+def parse_fasta(fasta_file):
+    """
+    Parses a FASTA file and returns a dictionary of gene IDs and sequences.
+    """
+    sequences = {}
+    with open(fasta_file, 'r') as f:
+        gene_id = None
+        sequence = []
+        for line in f:
+            line = line.strip()
+            if line.startswith(">"):
+                if gene_id:  # Save the previous gene
+                    sequences[gene_id] = ''.join(sequence)
+                gene_id = line[1:].split()[0].split('|')[1].replace('ENSB_','')  # Extract the gene ID after ">"
+                sequence = []
+            else:
+                sequence.append(line)
+        if gene_id:  # Save the last gene
+            sequences[gene_id] = ''.join(sequence)
+    return sequences
+
+
+def parse_csv(csv_file):
+    """
+    Parses a CSV file to extract group IDs and gene IDs (skipping the first line).
+    """
+    groups = {}
+    with open(csv_file, 'r') as f:
+        reader = csv.reader(f, delimiter=',')  # Assuming tab-delimited CSV
+        next(reader)  # Skip the first line
+        for row in reader:
+            group_id = row[0]
+            gene_ids = row[14:]  # Read from column 14 onward
+            gene_ids = [gene.strip() for genes in gene_ids for gene in genes.split(';') if
+                        gene.strip()]  # Flatten and clean
+            groups[group_id] = gene_ids
+    return groups
+
+
+def write_group_fastas(groups, sequences, output_dir):
+    """
+    Writes individual FASTA files for each group with the relevant sequences.
+    """
+    if not os.path.exists(output_dir):
+        os.makedirs(output_dir)
+
+    for group_id, gene_ids in groups.items():
+        group_file = os.path.join(output_dir, f"{group_id}.fasta")
+        with open(group_file, 'w') as f:
+            for gene_id in gene_ids:
+                if gene_id in sequences:
+                    f.write(f">{gene_id}\n{sequences[gene_id]}\n")
+                else:
+                    print(f"Warning: Gene ID {gene_id} not found in FASTA file.")
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Process FASTA and CSV files to create grouped FASTA outputs.")
+    parser.add_argument("-fasta", required=True, help="Input FASTA file containing gene sequences.")
+    parser.add_argument("-csv", required=True, help="Input CSV file containing group and gene information.")
+    parser.add_argument("-output_dir", required=True, help="Directory to save the grouped FASTA files.")
+
+    args = parser.parse_args()
+
+    # Parse the input files
+    print("Parsing FASTA file...")
+    sequences = parse_fasta(args.fasta)
+    print("Parsing CSV file...")
+    groups = parse_csv(args.csv)
+
+    # Write the grouped FASTA files
+    print("Writing grouped FASTA files...")
+    write_group_fastas(groups, sequences, args.output_dir)
+    print("Process completed successfully.")
+
+
+if __name__ == "__main__":
+    main()

PyamilySeq/Group_Sizes.py

@@ -0,0 +1,87 @@
+import argparse
+import os
+import csv
+
+
+def parse_fasta_stats(fasta_file):
+    """
+    Parses a FASTA file and calculates sequence statistics.
+    """
+    lengths = []
+    with open(fasta_file, 'r') as f:
+        sequence = []
+        for line in f:
+            line = line.strip()
+            if line.startswith(">"):
+                if sequence:  # Save the previous sequence length
+                    lengths.append(len(''.join(sequence)))
+                sequence = []  # Reset for the next sequence
+            else:
+                sequence.append(line)
+        if sequence:  # Save the last sequence length
+            lengths.append(len(''.join(sequence)))
+
+    # Calculate statistics
+    num_sequences = len(lengths)
+    if num_sequences > 0:
+        avg_length = sum(lengths) / num_sequences
+        min_length = min(lengths)
+        max_length = max(lengths)
+        length_diff = max_length - min_length
+        percent_diff = (length_diff / min_length * 100) if min_length > 0 else 0
+    else:
+        avg_length = min_length = max_length = length_diff = percent_diff = 0
+
+    return {
+        "num_sequences": num_sequences,
+        "min_length": min_length,
+        "max_length": max_length,
+        "avg_length": avg_length,
+        "length_diff": length_diff,
+        "percent_diff": percent_diff
+    }
+
+
+def process_fasta_directory(input_dir, output_csv):
+    """
+    Processes a directory of FASTA files and writes statistics to a CSV file.
+    """
+    results = []
+    for filename in os.listdir(input_dir):
+        if filename.endswith(".fasta"):
+            file_path = os.path.join(input_dir, filename)
+            stats = parse_fasta_stats(file_path)
+            results.append({
+                "file_name": filename,
+                "num_sequences": stats["num_sequences"],
+                "min_length": stats["min_length"],
+                "max_length": stats["max_length"],
+                "avg_length": stats["avg_length"],
+                "length_diff": stats["length_diff"],
+                "percent_diff": stats["percent_diff"]
+            })
+
+    # Write results to a CSV file
+    with open(output_csv, 'w', newline='') as csvfile:
+        fieldnames = ["file_name", "num_sequences", "min_length", "max_length", "avg_length", "length_diff",
+                      "percent_diff"]
+        writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
+        writer.writeheader()
+        writer.writerows(results)
+
+
+def main():
+    parser = argparse.ArgumentParser(description="Summarize sequence statistics for a directory of FASTA files.")
+    parser.add_argument("-input_dir", required=True, help="Directory containing FASTA files.")
+    parser.add_argument("-output_csv", required=True, help="Output CSV file to save statistics.")
+
+    args = parser.parse_args()
+
+    # Process the directory of FASTA files
+    print("Processing FASTA files...")
+    process_fasta_directory(args.input_dir, args.output_csv)
+    print(f"Statistics saved to {args.output_csv}")
+
+
+if __name__ == "__main__":
+    main()

PyamilySeq/PyamilySeq.py

@@ -54,8 +54,10 @@ def main():
                              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("-name_split_gff", required=False,
+                             help="Substring to split filenames and extract genome names for gff files (e.g., '_combined.gff3') - Use with -input_type separate/combined.")
+    full_parser.add_argument("-name_split_fasta", required=False,
+                             help="Substring to split filenames and extract genome names for fasta files if named differently to paired gff files (e.g., '_dna.fasta') - 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,
@@ -91,12 +93,12 @@ def main():
                                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,
+        subparser.add_argument("-write_groups", default=None, dest="write_groups", required=False,
+                               help="Output gene groups as a single FASTA file (specify levels: e.g., '-w 99,95'). - triggers '-wig'.")
+        subparser.add_argument("-write_individual_groups", 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", action="store_true", dest="align_core", required=False,
+                               help="Align and concatenate sequences for 'core' groups specified with '-w'.")
         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,
@@ -115,6 +117,9 @@ def main():
     # Parse Arguments
     options = parser.parse_args()
 
+    if options.write_groups != None and options.write_individual_groups == False:
+        options.write_individual_groups = True
+
     # 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:
@@ -129,13 +134,13 @@ def main():
             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])
+            required_full_mode.extend([options.input_dir, options.name_split_gff])
         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
+                               ['input_type', 'input_dir', 'name_split_gff', '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:
@@ -234,10 +239,10 @@ def main():
             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)
+            read_separate_files(options.input_dir, options.name_split_gff, options.name_split_fasta, 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)
+            read_combined_files(options.input_dir, options.name_split_gff, 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

PyamilySeq/PyamilySeq_Genus.py

@@ -23,8 +23,8 @@ def gene_presence_absence_output(options, genus_dict, pangenome_clusters_First_s
     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)+
-                         '","","","","","","","","",""')
+        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():
@@ -34,7 +34,7 @@ def gene_presence_absence_output(options, genus_dict, pangenome_clusters_First_s
                 if value.split('_')[0] == genus:
                     tmp_list.append(value)
             if tmp_list:
-                full_out += ',"'+''.join(tmp_list)+'"'
+                full_out += ',"'+'  '.join(tmp_list)+'"'
             else:
                 full_out = ',""'
             gpa_outfile.write(full_out)

PyamilySeq/PyamilySeq_Species.py

@@ -21,7 +21,7 @@ def gene_presence_absence_output(options, genome_dict, pangenome_clusters_First_
     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)+
+        gpa_outfile.write('"group_'+str(cluster)+'","","","'+str(len(pangenome_clusters_First_sorted[cluster]))+'","'+str(len(sequences))+'","'+str(average_sequences_per_genome)+
                          '","","","","","","","","",""')
 
 
@@ -32,7 +32,7 @@ def gene_presence_absence_output(options, genome_dict, pangenome_clusters_First_
                 if value.split('|')[0] == genome:
                     tmp_list.append(value.split('|')[1])
             if tmp_list:
-                full_out += ',"'+'\t'.join(tmp_list)+'"'
+                full_out += ',"'+'  '.join(tmp_list)+'"'
             else:
                 full_out = ',""'
             gpa_outfile.write(full_out)

PyamilySeq/Seq_Combiner.py

@@ -22,14 +22,17 @@ def main():
                              ' "combined" for GFF files with embedded FASTA sequences and "fasta" for combining multiple '
                                'FASTA files together.',
                           required=True)
-    required.add_argument("-name_split", action="store", dest="name_split",
-                          help="substring used to split the filename and extract the genome name ('_combined.gff3' or '.gff').",
-                          required=True)
+    required.add_argument("-name_split_gff", action="store", dest="name_split_gff",
+                          help="Substring used to split the filename and extract the genome name ('_combined.gff3' or '.gff'). - Not needed with -input_type fasta",
+                          required=False)
+    required.add_argument("-name_split_fasta", action="store", dest="name_split_fasta",
+                          help="Substring used to split filenames and extract genome names for fasta files if named differently to paired gff files (e.g., '_dna.fasta').",
+                          required=False)
     required.add_argument("-output_dir", action="store", dest="output_dir",
                           help="Directory for all output files.",
                           required=True)
     required.add_argument("-output_name", action="store", dest="output_file",
-                          help="Output file name (without .fasta).",
+                          help="Output file name.",
                           required=True)
 
     optional = parser.add_argument_group('Optional Arguments')
@@ -48,19 +51,33 @@ def main():
     options = parser.parse_args()
 
 
+    if options.input_type == 'separate' and options.name_split_gff is None:
+        print("Please provide a substring to split the filename and extract the genome name.")
+        exit(1)
+    if options.input_type == 'combined' and options.name_split_gff is None:
+        print("Please provide a substring to split the filename and extract the genome name.")
+        exit(1)
+    if options.input_type == 'fasta' and options.name_split_fasta is None:
+        print("Please provide a substring to split the filename and extract the genome name.")
+        exit
 
     output_path = os.path.abspath(options.output_dir)
     if not os.path.exists(output_path):
         os.makedirs(output_path)
 
-    combined_out_file = os.path.join(output_path, options.output_file + '.fasta')
+    output_file = options.output_file + '.fasta'
+    if os.path.exists(os.path.join(output_path, output_file)):
+        print(f"Output file {output_file} already exists in the output directory. Please delete or rename the file and try again.")
+        exit(1)
+
+    combined_out_file = os.path.join(output_path, output_file )
 
     if options.input_type == 'separate':
-        read_separate_files(options.input_dir, options.name_split, options.gene_ident, combined_out_file, options.translate)
+        read_separate_files(options.input_dir, options.name_split_gff, options.name_split_fasta, options.gene_ident, combined_out_file, options.translate)
     elif options.input_type == 'combined':
-        read_combined_files(options.input_dir, options.name_split, options.gene_ident, combined_out_file, options.translate)
+        read_combined_files(options.input_dir, options.name_split_gff, options.gene_ident, combined_out_file, options.translate)
     elif options.input_type == 'fasta':
-        read_fasta_files(options.input_dir, options.name_split, combined_out_file, options.translate)
+        read_fasta_files(options.input_dir, options.name_split_fasta, combined_out_file, options.translate)
 
 if __name__ == "__main__":
     main()

PyamilySeq/constants.py

@@ -1,2 +1,2 @@
-PyamilySeq_Version = 'v1.0.1'
+PyamilySeq_Version = 'v1.1.0'
 

PyamilySeq/utils.py

@@ -228,15 +228,33 @@ def run_mafft_on_sequences(options, sequences, output_file):
 
 
 
-def read_separate_files(input_dir, name_split, gene_ident, combined_out, translate):
+def read_separate_files(input_dir, name_split_gff, name_split_fasta, gene_ident, combined_out, translate):
+    paired_files_found = None
     with open(combined_out, 'w') as combined_out_file, open(combined_out.replace('_dna.fasta','_aa.fasta'), 'w') as combined_out_file_aa:
-        for gff_file in glob.glob(os.path.join(input_dir, '*' + name_split)):
-            genome_name = os.path.basename(gff_file).split(name_split)[0]
-            corresponding_fasta_file = os.path.splitext(gff_file)[0] + '.fa'
-            if not os.path.exists(corresponding_fasta_file):
-                continue
+        gff_files = glob.glob(os.path.join(input_dir, '*' + name_split_gff))
+        if not gff_files:
+            sys.exit("Error: No GFF files found.")
+        for gff_file in gff_files:
+            genome_name = os.path.basename(gff_file).split(name_split_gff)[0]
+            if name_split_fasta == None:
+                possible_extensions = ['.fa', '.fasta', '.fna']
+                corresponding_fasta_file = None
+                for ext in possible_extensions:
+                    temp_file = os.path.splitext(gff_file)[0] + ext
+                    if os.path.exists(temp_file):
+                        corresponding_fasta_file = temp_file
+                        break
+                if corresponding_fasta_file is None:
+                    print("Corresponding FASTA file for GFF file '" + gff_file + "' not found. Skipping. - Try using the -name_split_fasta option.")
+                    continue
+            else:
+                corresponding_fasta_file = os.path.join(input_dir, genome_name + name_split_fasta)
+                if not os.path.exists(corresponding_fasta_file):
+                    print("Corresponding FASTA file for GFF file '" + gff_file + "' not found. Skipping. - Try using the -name_split_fasta option.")
+                    continue
 
             gff_features = []
+            paired_files_found = True
             with open(gff_file, 'r') as file:
                 seen_seq_ids = collections.defaultdict(int)
                 lines = file.readlines()
@@ -244,6 +262,7 @@ def read_separate_files(input_dir, name_split, gene_ident, combined_out, transla
                     line_data = line.split('\t')
                     if len(line_data) == 9:
                         if any(gene_type in line_data[2] for gene_type in gene_ident):
+                            seq_id = line_data[8].split('ID=')[1].split(';')[0]
                             contig = line_data[0]
                             feature = line_data[2]
                             strand = line_data[6]
@@ -253,7 +272,6 @@ def read_separate_files(input_dir, name_split, gene_ident, combined_out, transla
                                 seen_seq_ids[seq_id] + 1
                             else:
                                 seen_seq_ids[seq_id] = 1
-                            seq_id = line_data[8].split('ID=')[1].split(';')[0]
                             gff_features.append((contig, start, end, strand, feature,  seq_id))
             fasta_dict = collections.defaultdict(str)
             with open(corresponding_fasta_file, 'r') as file:
@@ -288,14 +306,20 @@ def read_separate_files(input_dir, name_split, gene_ident, combined_out, transla
                         wrapped_sequence = '\n'.join([seq[i:i + 60] for i in range(0, len(seq), 60)])
                         combined_out_file.write(f">{genome_name}|{seq_id}\n{wrapped_sequence}\n")
 
-    if translate == False:
+    if not paired_files_found:
+        sys.exit("Could not find matching GFF/FASTA files - Please check input directory and -name_split_gff and -name_split_fasta parameters.")
+    if translate == False or translate == None:
         #Clean up unused file
-        os.remove(combined_out_file_aa.name)
+        if combined_out_file.name != combined_out_file_aa.name:
+            os.remove(combined_out_file_aa.name)
 
 
 def read_combined_files(input_dir, name_split, gene_ident, combined_out, translate):
     with open(combined_out, 'w') as combined_out_file, open(combined_out.replace('_dna.fasta','_aa.fasta'), 'w') as combined_out_file_aa:
-        for gff_file in glob.glob(os.path.join(input_dir, '*' + name_split)):
+        gff_files = glob.glob(os.path.join(input_dir, '*' + name_split))
+        if not gff_files:
+            sys.exit("Error: No GFF files found - check input directory and -name_split_gff parameter.")
+        for gff_file in gff_files:
             genome_name = os.path.basename(gff_file).split(name_split)[0]
             fasta_dict = collections.defaultdict(str)
             gff_features = []
@@ -352,16 +376,20 @@ def read_combined_files(input_dir, name_split, gene_ident, combined_out, transla
                             wrapped_sequence = '\n'.join([seq[i:i + 60] for i in range(0, len(seq), 60)])
                             combined_out_file.write(f">{genome_name}|{seq_id}\n{wrapped_sequence}\n")
 
-    if translate == False:
+    if translate == False or translate == None:
         #Clean up unused file
-        os.remove(combined_out_file_aa.name)
+        if combined_out_file.name != combined_out_file_aa.name:
+            os.remove(combined_out_file_aa.name)
 
 
 
-def read_fasta_files(input_dir, name_split, combined_out, translate):
+def read_fasta_files(input_dir, name_split_fasta, combined_out, translate):
     with open(combined_out, 'w') as combined_out_file, open(combined_out.replace('_dna.fasta','_aa.fasta'), 'w') as combined_out_file_aa:
-        for fasta_file in glob.glob(os.path.join(input_dir, '*' + name_split)):
-            genome_name = os.path.basename(fasta_file).split(name_split)[0]
+        fasta_files = glob.glob(os.path.join(input_dir, '*' + name_split_fasta))
+        if not fasta_files:
+            sys.exit("Error: No GFF files found.")
+        for fasta_file in fasta_files:
+            genome_name = os.path.basename(fasta_file).split(name_split_fasta)[0]
             fasta_dict = collections.defaultdict(str)
             with open(fasta_file, 'r') as file:
                 lines = file.readlines()
@@ -379,9 +407,10 @@ def read_fasta_files(input_dir, name_split, combined_out, translate):
                     wrapped_sequence = '\n'.join([seq[i:i + 60] for i in range(0, len(seq), 60)])
                     combined_out_file.write(f">{genome_name}|{seq_id}\n{wrapped_sequence}\n")
 
-    if translate == False:
+    if translate == False or translate == None:
         #Clean up unused file
-        os.remove(combined_out_file_aa)
+        if combined_out_file.name != combined_out_file_aa.name:
+            os.remove(combined_out_file_aa.name)
 
 def write_groups_func(options, output_dir, key_order, cores, sequences,
                  pangenome_clusters_First_sequences_sorted, combined_pangenome_clusters_Second_sequences):
@@ -401,63 +430,65 @@ def write_groups_func(options, output_dir, key_order, cores, sequences,
     if not os.path.exists(output_dir):
         os.makedirs(output_dir)
 
-    combined_fasta_filename = os.path.join(output_dir, "combined_group_sequences_dna.fasta")
-
-    # Open combined FASTA file for writing all sequences
-    with open(combined_fasta_filename, 'w') as combined_fasta, open(combined_fasta_filename.replace('_dna.fasta','_aa.fasta'), 'w') as combined_fasta_aa:
-        for key_prefix in key_order:
-            for key, values in cores.items():
-                if any(part in options.write_groups.split(',') for part in key.split('_')):
-                    if key.startswith(key_prefix):
-                        for value in values:
-                            output_filename = f"{key}_{value}_dna.fasta"
-                            if 'First' in key_prefix:
-                                sequences_to_write = pangenome_clusters_First_sequences_sorted[value]
-                            else:
-                                sequences_to_write = combined_pangenome_clusters_Second_sequences[value]
-
-                            # Write individual FASTA file
-                            with open(os.path.join(output_dir,output_filename), 'w') as outfile, open(os.path.join(output_dir, output_filename.replace('_dna.fasta','_aa.fasta')), 'w') as outfile_aa:
-                                for header in sequences_to_write:
-                                    if header in sequences:
-                                        sequence = sequences[header]
-                                        wrapped_sequence = wrap_sequence(sequence)
-                                        # Handle Amino Acid Sequences (AA)
-                                        if options.sequence_type == 'AA':
-                                            seq_aa = translate_frame(sequence)
-                                            wrapped_sequence_aa = wrap_sequence(seq_aa)
-                                            # Write individual group file for AA, if option is enabled
+    for group in options.write_groups.split(','):
+
+        combined_fasta_filename = os.path.join(output_dir, "combined_group_sequences_" + group + "_dna.fasta")
+
+        # Open combined FASTA file for writing all sequences
+        with open(combined_fasta_filename, 'w') as combined_fasta, open(combined_fasta_filename.replace('_dna.fasta','_aa.fasta'), 'w') as combined_fasta_aa:
+            for key_prefix in key_order:
+                for key, values in cores.items():
+                    if any(part in group for part in key.split('_')):
+                        if key.startswith(key_prefix):
+                            for value in values:
+                                output_filename = f"{key}_{value}_dna.fasta"
+                                if 'First' in key_prefix:
+                                    sequences_to_write = pangenome_clusters_First_sequences_sorted[value]
+                                else:
+                                    sequences_to_write = combined_pangenome_clusters_Second_sequences[value]
+
+                                # Write individual FASTA file
+                                with open(os.path.join(output_dir,output_filename), 'w') as outfile, open(os.path.join(output_dir, output_filename.replace('_dna.fasta','_aa.fasta')), 'w') as outfile_aa:
+                                    for header in sequences_to_write:
+                                        if header in sequences:
+                                            sequence = sequences[header]
+                                            wrapped_sequence = wrap_sequence(sequence)
+                                            # Handle Amino Acid Sequences (AA)
+                                            if options.sequence_type == 'AA':
+                                                seq_aa = translate_frame(sequence)
+                                                wrapped_sequence_aa = wrap_sequence(seq_aa)
+                                                # Write individual group file for AA, if option is enabled
+                                                if options.write_individual_groups:
+                                                    outfile_aa.write(f">{header}\n")
+                                                    outfile_aa.write(f"{wrapped_sequence_aa}\n")
+                                                else:
+                                                    os.remove(outfile_aa.name)  # Delete individual file if option is disabled
+                                                # Always write to the combined AA file
+                                                combined_fasta_aa.write(f">Group_{value}|{header}\n")
+                                                combined_fasta_aa.write(f"{wrapped_sequence_aa}\n")
+                                            # Handle Nucleotide Sequences
+                                            else:
+                                                # If the option is disabled, delete individual AA file (if created)
+                                                try:
+                                                    os.remove(outfile_aa.name)  # Ensure outfile_aa is removed when sequence_type isn't 'AA'
+                                                except FileNotFoundError:
+                                                    pass
+                                            # Write individual group file for nucleotide sequence, if option is enabled
                                             if options.write_individual_groups:
-                                                outfile_aa.write(f">{header}\n")
-                                                outfile_aa.write(f"{wrapped_sequence_aa}\n")
+                                                outfile.write(f">{header}\n")
+                                                outfile.write(f"{wrapped_sequence}\n")
                                             else:
-                                                os.remove(outfile_aa.name)  # Delete individual file if option is disabled
-                                            # Always write to the combined AA file
-                                            combined_fasta_aa.write(f">Group_{value}|{header}\n")
-                                            combined_fasta_aa.write(f"{wrapped_sequence_aa}\n")
-                                        # Handle Nucleotide Sequences
-                                        else:
-                                            # If the option is disabled, delete individual AA file (if created)
-                                            try:
-                                                os.remove(outfile_aa.name)  # Ensure outfile_aa is removed when sequence_type isn't 'AA'
-                                            except FileNotFoundError:
-                                                pass
-                                        # Write individual group file for nucleotide sequence, if option is enabled
-                                        if options.write_individual_groups:
-                                            outfile.write(f">{header}\n")
-                                            outfile.write(f"{wrapped_sequence}\n")
+                                                os.remove(outfile.name)  # Delete individual file if option is disabled
+                                            # Always write to the combined nucleotide file
+                                            combined_fasta.write(f">Group_{value}|{header}\n")
+                                            combined_fasta.write(f"{wrapped_sequence}\n")
+
                                         else:
-                                            os.remove(outfile.name)  # Delete individual file if option is disabled
-                                        # Always write to the combined nucleotide file
-                                        combined_fasta.write(f">Group_{value}|{header}\n")
-                                        combined_fasta.write(f"{wrapped_sequence}\n")
-
-                                    else:
-                                        if options.verbose == True:
-                                            print(f"Sequence {header} not found in original_fasta file.")
-    if options.sequence_type != 'AA':
-        #Clean up unused file
-        os.remove(combined_fasta_aa.name)
+                                            if options.verbose == True:
+                                                print(f"Sequence {header} not found in original_fasta file.")
+        if options.sequence_type != 'AA':
+            #Clean up unused file
+            os.remove(combined_fasta_aa.name)
     print(f"Combined FASTA file saved to: {combined_fasta_filename}")
 
 
@@ -539,22 +570,23 @@ def process_gene_groups(options, group_directory, sub_group_directory, paralog_g
     else:
         affix = '_dna.fasta'
 
-    # Iterate over each gene family file
-    for gene_file in os.listdir(group_directory):
-        if gene_file.endswith(affix) and not gene_file.startswith('combined_group_sequences'):
-            #print(gene_file)
-            current_group = int(gene_file.split('_')[3].split('.')[0])
-            gene_path = os.path.join(group_directory, gene_file)
-
-            # Check for matching group in paralog_groups
-            if sub_group_directory and paralog_groups and '>Group_'+str(current_group) in paralog_groups:
-                for subgroup, size in enumerate(paralog_groups['>Group_' + str(current_group)]['sizes']):
-                    if size >= threshold_size:
-                        gene_path = os.path.join(sub_group_directory,f"Group_{current_group}_subgroup_{subgroup}{affix}")
-                        concatenated_sequences = perform_alignment(gene_path, group_directory, gene_file, options, concatenated_sequences, True)
+    if options.align_core == True:
+        # Iterate over each gene family file
+        for gene_file in os.listdir(group_directory):
+            if gene_file.endswith(affix) and not gene_file.startswith('combined_group_sequences'):
+                #print(gene_file)
+                current_group = int(gene_file.split('_')[3].split('.')[0])
+                gene_path = os.path.join(group_directory, gene_file)
+
+                # Check for matching group in paralog_groups
+                if sub_group_directory and paralog_groups and '>Group_'+str(current_group) in paralog_groups:
+                    for subgroup, size in enumerate(paralog_groups['>Group_' + str(current_group)]['sizes']):
+                        if size >= threshold_size:
+                            gene_path = os.path.join(sub_group_directory,f"Group_{current_group}_subgroup_{subgroup}{affix}")
+                            concatenated_sequences = perform_alignment(gene_path, group_directory, gene_file, options, concatenated_sequences, True)
 
-            else:
-                concatenated_sequences = perform_alignment(gene_path, group_directory, gene_file, options, concatenated_sequences, False)
+                else:
+                    concatenated_sequences = perform_alignment(gene_path, group_directory, gene_file, options, concatenated_sequences, False)
 
 
     # Write the concatenated sequences to the output file

{PyamilySeq-1.0.1.dist-info → pyamilyseq-1.1.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.2
 Name: PyamilySeq
-Version: 1.0.1
+Version: 1.1.0
 Summary: PyamilySeq - A a tool to investigate sequence-based gene groups identified by clustering methods such as CD-HIT, DIAMOND, BLAST or MMseqs2.
 Home-page: https://github.com/NickJD/PyamilySeq
 Author: Nicholas Dimonaco
@@ -45,7 +45,7 @@ To update to the newest version add '-U' to end of the pip install command.
 ```commandline
 usage: PyamilySeq.py [-h] {Full,Partial} ...
 
-PyamilySeq v1.0.1: A tool for gene clustering and analysis.
+PyamilySeq v1.1.0: A tool for gene clustering and analysis.
 
 positional arguments:
   {Full,Partial}  Choose a mode: 'Full' or 'Partial'.
@@ -58,24 +58,24 @@ options:
 ```
 ### 'Full Mode': Will conduct clustering of sequences with CD-HIT as part of PyamilySeq run
 ```
-PyamilySeq Full -output_dir .../PyamilySeq_10_AA_90_80_Full_GFFs -input_type combined -input_dir .../genomes/ -name_split _combined.gff3
+PyamilySeq Full -output_dir .../PyamilySeq_10_AA_90_80_Full_GFFs -input_type combined -input_dir .../genomes/ -name_split_gff _combined.gff3
 ```
 ### 'Partial Mode': Will process the output of a sequence clustering from MMseqs, BLAST, DIAMOND etc.
 ```
-PyamilySeq Partial -clustering_format CD-HIT -cluster_file .../all_10_combined_pep_CD-HIT_90_80.clstr  -original_fasta .../all_10_combined_pep.fasta -output_dir .../PyamilySeq_10_AA_90_80_Partial-w 99 -a 
+PyamilySeq Partial -clustering_format CD-HIT -cluster_file .../all_10_combined_pep_CD-HIT_90_80.clstr  -original_fasta .../all_10_combined_pep.fasta -output_dir .../PyamilySeq_10_AA_90_80_Partial -write_groups 99 -align 
 ```
 
 
 #### Note: using a '-clustering_format' other than the default CD-HIT, requires input to be two in two columns as below (Same format as MMseqs2 tsv and BLAST outfmt 6) - Genome name and sequence name are separated by '|'.
 ```
-Escherichia_coli_110957|ENSB:lL-zIKt-gh0oSno	Escherichia_coli_110957|ENSB:lL-zIKt-gh0oSno
-Escherichia_coli_110957|ENSB:lL-zIKt-gh0oSno	Escherichia_coli_113290|ENSB:2fj4rJ8e8Z9PNdX
-Escherichia_coli_110957|ENSB:lL-zIKt-gh0oSno	Escherichia_coli_b185|ENSB:G_PVe28-ej8q-3S
-Escherichia_coli_110957|ENSB:TIZS9kbTvShDvyX	Escherichia_coli_110957|ENSB:TIZS9kbTvShDvyX
+Escherichia_coli_110957|ENSB_lL-zIKt-gh0oSno	Escherichia_coli_110957|ENSB_lL-zIKt-gh0oSno
+Escherichia_coli_110957|ENSB_lL-zIKt-gh0oSno	Escherichia_coli_113290|ENSB_2fj4rJ8e8Z9PNdX
+Escherichia_coli_110957|ENSB_lL-zIKt-gh0oSno	Escherichia_coli_b185|ENSB_G_PVe28-ej8q-3S
+Escherichia_coli_110957|ENSB_TIZS9kbTvShDvyX	Escherichia_coli_110957|ENSB_TIZS9kbTvShDvyX
 ```
 ### Example output:
 ```
-Running PyamilySeq v1.0.1
+Running PyamilySeq v1.1.0
 Calculating Groups
 Number of Genomes: 10
 Gene Groups
@@ -92,51 +92,11 @@ Thank you for using PyamilySeq -- A detailed user manual can be found at https:/
 Please report any issues to: https://github.com/NickJD/PyamilySeq/issues
 ```
 
-[//]: # (## Genus mode: )
-
-[//]: # (### In addition to "Species mode" (see above) which reports gene groups the same as pangenome tools such as Roary and Panaroo, Genus mode reports gene groups identified across multiple genera.)
-
-[//]: # (#### Example:)
-
-[//]: # (```)
-
-[//]: # (PyamilySeq -run_mode Partial -group_mode Genus -clustering_format CD-HIT -output_dir .../test_data/genus/testing/)
-
-[//]: # ( -cluster_file .../test_data/genus/CD-HIT/combined_cds_cd-hit_80_60.clstr -gpa )
-
-[//]: # (```)
-
-[//]: # (```commandline)
-
-[//]: # (Running PyamilySeq v1.0.1)
-
-[//]: # (Calculating Groups)
-
-[//]: # (Genus Groups:)
-[//]: # (First_genera_1:	28549)
-
-[//]: # (First_genera_2:	12)
-
-[//]: # (First_genera_3:	0)
-
-[//]: # (First_genera_>:	0)
-
-[//]: # (Total Number of First Gene Groups (Including Singletons): 28561)
-
-[//]: # (Outputting gene_presence_absence file)
-
-[//]: # (Thank you for using PyamilySeq -- A detailed user manual can be found at https://github.com/NickJD/PyamilySeq)
-
-[//]: # (Please report any issues to: https://github.com/NickJD/PyamilySeq/issues)
-
-[//]: # (#####)
-
-[//]: # (```)
 
 ## Reclustering:
 ### Reclustering can be used to see where additional sequences/genes lay in relation to a contemporary pangenome/gene grouping.
 ```
-PyamilySeq Partial -clustering_format CD-HIT -cluster_file .../all_10_combined_pep_CD-HIT_90_80.clstr -reclustered .../all_10_combined_pep_CD-HIT_90_80_AND_StORFs_CD-HIT_90_80.clstr -original_fasta .../all_10_combined_pep_AND_StORFs.fasta -output_dir .../PyamilySeq_10_AA_90_80_Partial_Reclustered_StORFs -w 99 -a 
+PyamilySeq Partial -clustering_format CD-HIT -cluster_file .../all_10_combined_pep_CD-HIT_90_80.clstr -reclustered .../all_10_combined_pep_CD-HIT_90_80_AND_StORFs_CD-HIT_90_80.clstr -original_fasta .../all_10_combined_pep_AND_StORFs.fasta -output_dir .../PyamilySeq_10_AA_90_80_Partial_Reclustered_StORFs -write_groups 99 -align 
 ```
 #### As can be seen below, the additional sequences recovered by the StORF-Reporter annotation tool have 'extended' contemporary or created entirely new gene groups. 'First' corresponds to the groups identified from the first clustering round and 'Second' for the second. In 'reclustering' mode, First_core_# groups are unaffected thus retaining the initial grouping information. 
 ```commandline
@@ -170,25 +130,22 @@ Total Number of First Gene Groups That Had Additional Second Sequences But Not N
 ## PyamilySeq is separated into two main 'run modes', Full and Partial. They each have their own set of required and optional arguments.
 ### PyamilySeq - Full Menu: 
 ```
-usage: PyamilySeq.py Full [-h] -output_dir OUTPUT_DIR -input_type {separate,combined,fasta} [-input_dir INPUT_DIR]
-                          [-input_fasta INPUT_FASTA] [-name_split NAME_SPLIT] [-sequence_type {AA,DNA}] [-gene_ident GENE_IDENT]
-                          [-c PIDENT] [-s LEN_DIFF] [-fast_mode] [-group_mode {Species,Genus}] [-species_groups SPECIES_GROUPS]
-                          [-genus_groups GENUS_GROUPS] [-w WRITE_GROUPS] [-wi] [-a] [-align_aa] [-no_gpa] [-M MEM] [-T THREADS]
-                          [-verbose] [-v]
+usage: PyamilySeq.py Full [-h] -output_dir OUTPUT_DIR -input_type {separate,combined,fasta} [-input_dir INPUT_DIR] [-input_fasta INPUT_FASTA] [-name_split_gff NAME_SPLIT_GFF] [-name_split_fasta NAME_SPLIT_FASTA] [-sequence_type {AA,DNA}] [-gene_ident GENE_IDENT] [-c PIDENT] [-s LEN_DIFF] [-fast_mode]
+                          [-group_mode {Species,Genus}] [-species_groups SPECIES_GROUPS] [-genus_groups GENUS_GROUPS] [-write_groups WRITE_GROUPS] [-write_individual_groups] [-align] [-align_aa] [-no_gpa] [-M MEM] [-T THREADS] [-verbose] [-v]
 
 options:
   -h, --help            show this help message and exit
   -output_dir OUTPUT_DIR
                         Directory for all output files.
   -input_type {separate,combined,fasta}
-                        Type of input files: 'separate' for matching FASTA and GFF files, 'combined' for GFF+FASTA, or 'fasta'
-                        for a prepared FASTA file.
+                        Type of input files: 'separate' for matching FASTA and GFF files, 'combined' for GFF+FASTA, or 'fasta' for a prepared FASTA file.
   -input_dir INPUT_DIR  Directory containing GFF/FASTA files - Use with -input_type separate/combined.
   -input_fasta INPUT_FASTA
                         Input FASTA file - Use with - input_type fasta.
-  -name_split NAME_SPLIT
-                        Substring to split filenames and extract genome names (e.g., '_combined.gff3') - Use with -input_type
-                        separate/combined.
+  -name_split_gff NAME_SPLIT_GFF
+                        Substring to split filenames and extract genome names for gff files (e.g., '_combined.gff3') - Use with -input_type separate/combined.
+  -name_split_fasta NAME_SPLIT_FASTA
+                        Substring to split filenames and extract genome names for fasta files if named differently to paired gff files (e.g., '_dna.fasta') - Use with -input_type separate/combined.
   -sequence_type {AA,DNA}
                         Clustering mode: 'DNA' or 'AA'.
   -gene_ident GENE_IDENT
@@ -202,21 +159,23 @@ options:
                         Gene groupings for 'Species' mode (default: '99,95,15').
   -genus_groups GENUS_GROUPS
                         Gene groupings for 'Genus' mode (default: '1-10').
-  -w WRITE_GROUPS       Output gene groups as a single FASTA file (specify levels: e.g., '-w 99,95').
-  -wi                   Output individual FASTA files for each group.
-  -a                    Align and concatenate sequences for 'core' groups.
+  -write_groups WRITE_GROUPS
+                        Output gene groups as a single FASTA file (specify levels: e.g., '-w 99,95'). - triggers '-wig'.
+  -write_individual_groups
+                        Output individual FASTA files for each group.
+  -align                Align and concatenate sequences for 'core' groups specified with '-w'.
   -align_aa             Align sequences as amino acids.
   -no_gpa               Skip creation of gene_presence_absence.csv.
   -M MEM                Memory allocation for clustering (MB) - CD-HIT parameter '-M'.
   -T THREADS            Number of threads for clustering/alignment - CD-HIT parameter '-T' | MAFFT parameter '--thread'.
   -verbose              Print verbose output.
   -v, --version         Print version number and exit.
+
 ```
 ### PyamilySeq - Partial Menu: 
 ```commandline
-usage: PyamilySeq.py Partial [-h] -clustering_format {CD-HIT,MMseqs,BLAST} -cluster_file CLUSTER_FILE -original_fasta ORIGINAL_FASTA -output_dir OUTPUT_DIR
-                             [-reclustered RECLUSTERED] [-seq_tag SEQUENCE_TAG] [-group_mode {Species,Genus}] [-species_groups SPECIES_GROUPS] [-genus_groups GENUS_GROUPS]
-                             [-w WRITE_GROUPS] [-wi] [-a] [-align_aa] [-no_gpa] [-M MEM] [-T THREADS] [-verbose] [-v]
+usage: PyamilySeq.py Partial [-h] -clustering_format {CD-HIT,MMseqs,BLAST} -cluster_file CLUSTER_FILE -original_fasta ORIGINAL_FASTA -output_dir OUTPUT_DIR [-reclustered RECLUSTERED] [-seq_tag SEQUENCE_TAG] [-group_mode {Species,Genus}] [-species_groups SPECIES_GROUPS] [-genus_groups GENUS_GROUPS]
+                             [-write_groups WRITE_GROUPS] [-write_individual_groups] [-align] [-align_aa] [-no_gpa] [-M MEM] [-T THREADS] [-verbose] [-v]
 
 options:
   -h, --help            show this help message and exit
@@ -238,9 +197,11 @@ options:
                         Gene groupings for 'Species' mode (default: '99,95,15').
   -genus_groups GENUS_GROUPS
                         Gene groupings for 'Genus' mode (default: '1-10').
-  -w WRITE_GROUPS       Output gene groups as a single FASTA file (specify levels: e.g., '-w 99,95').
-  -wi                   Output individual FASTA files for each group.
-  -a                    Align and concatenate sequences for 'core' groups.
+  -write_groups WRITE_GROUPS
+                        Output gene groups as a single FASTA file (specify levels: e.g., '-w 99,95'). - triggers '-wig'.
+  -write_individual_groups
+                        Output individual FASTA files for each group.
+  -align                Align and concatenate sequences for 'core' groups specified with '-w'.
   -align_aa             Align sequences as amino acids.
   -no_gpa               Skip creation of gene_presence_absence.csv.
   -M MEM                Memory allocation for clustering (MB) - CD-HIT parameter '-M'.
@@ -253,14 +214,13 @@ options:
 ## Seq-Combiner: This tool is provided to enable the pre-processing of multiple GFF/FASTA files together ready to be clustered by the user.
 ### Example:
 ```bash
-Seq-Combiner -input_dir .../test_data/genomes -name_split .gff3 -output_dir .../test_data/genomes -output_name combine_fasta_seqs.fa -input_type combined
+Seq-Combiner -input_dir .../test_data/genomes -name_split_gff .gff3 -output_dir .../test_data/genomes -output_name combine_fasta_seqs.fa -input_type combined
 ```
 ### Seq-Combiner Menu:
 ```
-usage: Seq_Combiner.py [-h] -input_dir INPUT_DIR -input_type {separate,combined,fasta} -name_split NAME_SPLIT -output_dir OUTPUT_DIR -output_name
-                       OUTPUT_FILE [-gene_ident GENE_IDENT] [-translate] [-v]
+usage: Seq_Combiner.py [-h] -input_dir INPUT_DIR -input_type {separate,combined,fasta} [-name_split_gff NAME_SPLIT_GFF] [-name_split_fasta NAME_SPLIT_FASTA] -output_dir OUTPUT_DIR -output_name OUTPUT_FILE [-gene_ident GENE_IDENT] [-translate] [-v]
 
-PyamilySeq v1.0.1: Seq-Combiner - A tool to extract sequences from GFF/FASTA files and prepare them for PyamilySeq.
+PyamilySeq v1.1.0: Seq-Combiner - A tool to extract sequences from GFF/FASTA files and prepare them for PyamilySeq.
 
 options:
   -h, --help            show this help message and exit
@@ -268,10 +228,11 @@ options:
 Required Arguments:
   -input_dir INPUT_DIR  Directory location where the files are located.
   -input_type {separate,combined,fasta}
-                        Type of input files: "separate" for separate FASTA and GFF files, "combined" for GFF files with embedded FASTA sequences and "fasta"
-                        for combining multiple FASTA files together.
-  -name_split NAME_SPLIT
-                        substring used to split the filename and extract the genome name ('_combined.gff3' or '.gff').
+                        Type of input files: "separate" for separate FASTA and GFF files, "combined" for GFF files with embedded FASTA sequences and "fasta" for combining multiple FASTA files together.
+  -name_split_gff NAME_SPLIT_GFF
+                        Substring used to split the filename and extract the genome name ('_combined.gff3' or '.gff'). - Not needed with -input_type fasta
+  -name_split_fasta NAME_SPLIT_FASTA
+                        Substring used to split filenames and extract genome names for fasta files if named differently to paired gff files (e.g., '_dna.fasta').
   -output_dir OUTPUT_DIR
                         Directory for all output files.
   -output_name OUTPUT_FILE
@@ -279,19 +240,19 @@ Required Arguments:
 
 Optional Arguments:
   -gene_ident GENE_IDENT
-                        Default - "CDS": Identifier used for extraction of sequences such as
-                        "misc_RNA,gene,mRNA,CDS,rRNA,tRNA,tmRNA,CRISPR,ncRNA,regulatory_region,oriC,pseudo" - Not compatible with "fasta" input mode.
-  -translate            Default - False: Translate extracted sequences to their AA counterpart?
+                        Default - "CDS": Identifier used for extraction of sequences such as "misc_RNA,gene,mRNA,CDS,rRNA,tRNA,tmRNA,CRISPR,ncRNA,regulatory_region,oriC,pseudo" - Not compatible with "fasta" input mode.
+  -translate            Default - False: Translate extracted sequences to their AA counterpart? - appends _aa.fasta to given output_name
 
 Misc Arguments:
   -v, --version         Print out version number and exit
 
+
 ```
 
 ## Group-Splitter: This tool can split multi-copy gene groups using CD-HIT after initial PyamilySeq analysis.
 ### Example:
 ```bash
-Group-Splitter -genome_num 74 -input_fasta .../test/species/ -output_dir .../test/species/ -sequence_type AA
+Group-Splitter -genome_num 10 -input_fasta .../test/species/ -output_dir .../test/species/ -sequence_type AA
 ```
 ### Group-Splitter Menu:
 ```
@@ -302,7 +263,7 @@ usage: Group_Splitter.py [-h] -input_fasta INPUT_FASTA -sequence_type {AA,DNA}
                          [-M CLUSTERING_MEMORY] [-no_delete_temp_files]
                          [-verbose] [-v]
 
-PyamilySeq v1.0.1: Group-Splitter - A tool to split multi-copy gene groups
+PyamilySeq v1.1.0: Group-Splitter - A tool to split multi-copy gene groups
 identified by PyamilySeq.
 
 options:
@@ -348,14 +309,14 @@ Misc Parameters:
 ## Cluster-Summary menu: This tool can be used to summarise CD-HIT .clstr files:
 ### Example:
 ```bash
-Cluster-Summary -genome_num 74 -input_clstr .../test_data/species/E-coli/E-coli_extracted_pep_cd-hit_80.clstr -output_tsv .../test_data/species/E-coli/E-coli_extracted_pep_cd-hit_80_Summary.tsv
+Cluster-Summary -genome_num 10 -input_clstr .../test_data/species/E-coli/E-coli_extracted_pep_cd-hit_80.clstr -output_tsv .../test_data/species/E-coli/E-coli_extracted_pep_cd-hit_80_Summary.tsv
 ```
 ### Cluster-Summary Menu: 
 ```
 usage: Cluster_Summary.py [-h] -input_clstr INPUT_CLSTR -output OUTPUT -genome_num GENOME_NUM
                           [-output_dir OUTPUT_DIR] [-verbose] [-v]
 
-PyamilySeq v1.0.1: Cluster-Summary - A tool to summarise CD-HIT clustering files.
+PyamilySeq v1.1.0: Cluster-Summary - A tool to summarise CD-HIT clustering files.
 
 options:
   -h, --help            show this help message and exit

pyamilyseq-1.1.0.dist-info/RECORD

@@ -0,0 +1,20 @@
+PyamilySeq/Cluster_Summary.py,sha256=xkzkC9mHRqHNm2bp0gcBWOobKTabltBrVv6ze4nikyg,6982
+PyamilySeq/Group_Extractor.py,sha256=oe2VmOVxdvTmAcy8NKwD1F27IdN2utAfczxsyxg96yc,2898
+PyamilySeq/Group_Sizes.py,sha256=3snkAN19o3Y4IY6IqSim1qy415FfQe1Wb8vzWTKF0Wo,3028
+PyamilySeq/Group_Splitter.py,sha256=OcMj9GnAyybs_DaNKRyvfL_nl2dB2gUI4BD_EQrBbWo,25653
+PyamilySeq/PyamilySeq.py,sha256=iyLU8YYn06ppCBCb-HaARm0ez_uagkj4FRtqr3pFu9Q,17396
+PyamilySeq/PyamilySeq_Genus.py,sha256=mBZNTWWk4a_5gsHzq0cG82Qck-SL9Xgg6jpByH6oKuk,12414
+PyamilySeq/PyamilySeq_Species.py,sha256=yyMHBQhTq1yFUKbiba6vL9nYJ4rlKsmS30hQNimGEB8,16120
+PyamilySeq/Seq_Combiner.py,sha256=wusCDrGwcVqQw3h5iPSY0_E5sauRFNHj0bXMBtELpl0,4700
+PyamilySeq/Seq_Extractor.py,sha256=KMR0KcTJzrh99HcBN4qb76R2FuBvpYCDf4NwkmwhTPU,2870
+PyamilySeq/Seq_Finder.py,sha256=ht-fSQ_opWKydcoWI9D3nTwLt6Rpgevnf2y0KxVjw4M,1881
+PyamilySeq/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+PyamilySeq/clusterings.py,sha256=9fXnFZSypeZKtJK8OYONQKVpvLoeJCSxx2BRo5Vir38,22355
+PyamilySeq/constants.py,sha256=7zjA69Blx4ycagDKCvaKdVuXidVVwu7adnmgm53_CTI,31
+PyamilySeq/utils.py,sha256=EwZQP5eFaXiXVGw0Vckhu9tJkm8SOKAgGh7-JnIu_j4,29355
+pyamilyseq-1.1.0.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+pyamilyseq-1.1.0.dist-info/METADATA,sha256=f8hZWEdD06WYoflfPls02q_6FVFYL18np1BGzWXwlGA,17957
+pyamilyseq-1.1.0.dist-info/WHEEL,sha256=nn6H5-ilmfVryoAQl3ZQ2l8SH5imPWFpm1A5FgEuFV4,91
+pyamilyseq-1.1.0.dist-info/entry_points.txt,sha256=Qao6g8F37k35MQFkUpGt9xoozRBaTkIKUptXWAUs5-E,554
+pyamilyseq-1.1.0.dist-info/top_level.txt,sha256=J6JhugUQTq4rq96yibAlQu3o4KCM9WuYfqr3w1r119M,11
+pyamilyseq-1.1.0.dist-info/RECORD,,

{PyamilySeq-1.0.1.dist-info → pyamilyseq-1.1.0.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.3.0)
+Generator: setuptools (75.8.1)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

{PyamilySeq-1.0.1.dist-info → pyamilyseq-1.1.0.dist-info}/entry_points.txt

@@ -5,3 +5,9 @@ PyamilySeq = PyamilySeq.PyamilySeq:main
 Seq-Combiner = PyamilySeq.Seq_Combiner:main
 Seq-Extractor = PyamilySeq.Seq_Extractor:main
 Seq-Finder = PyamilySeq.Seq_Finder:main
+cluster-summary = PyamilySeq.Cluster_Summary:main
+group-splitter = PyamilySeq.Group_Splitter:main
+pyamilyseq = PyamilySeq.PyamilySeq:main
+seq-combiner = PyamilySeq.Seq_Combiner:main
+seq-extractor = PyamilySeq.Seq_Extractor:main
+seq-finder = PyamilySeq.Seq_Finder:main

PyamilySeq-1.0.1.dist-info/RECORD

@@ -1,18 +0,0 @@
-PyamilySeq/Cluster_Summary.py,sha256=xkzkC9mHRqHNm2bp0gcBWOobKTabltBrVv6ze4nikyg,6982
-PyamilySeq/Group_Splitter.py,sha256=OcMj9GnAyybs_DaNKRyvfL_nl2dB2gUI4BD_EQrBbWo,25653
-PyamilySeq/PyamilySeq.py,sha256=QjaBK6t_CYlE1ojIhH1k_2LJw97oT6UblA1dk-3bcDk,16854
-PyamilySeq/PyamilySeq_Genus.py,sha256=RdW-WU07fhXSi-mWfhXkUfffaQWCJ3UZmJBILUcGJG8,12414
-PyamilySeq/PyamilySeq_Species.py,sha256=0i7cW14UyRwCTbuxFgp8heH4xadbUHRja4dsPrBj_Ms,16119
-PyamilySeq/Seq_Combiner.py,sha256=V91AMp0VwObQe4x9kOCNsvwiUJ9L64y9gdcC22-vvtY,3530
-PyamilySeq/Seq_Extractor.py,sha256=KMR0KcTJzrh99HcBN4qb76R2FuBvpYCDf4NwkmwhTPU,2870
-PyamilySeq/Seq_Finder.py,sha256=ht-fSQ_opWKydcoWI9D3nTwLt6Rpgevnf2y0KxVjw4M,1881
-PyamilySeq/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-PyamilySeq/clusterings.py,sha256=9fXnFZSypeZKtJK8OYONQKVpvLoeJCSxx2BRo5Vir38,22355
-PyamilySeq/constants.py,sha256=vV8JkmE7De4xQucZiXP1sQm_kHAM74Ua5KOOp2ULeYE,31
-PyamilySeq/utils.py,sha256=819POQB1h8Wm35XTZJa_GETealGjJGs-SBSpnj4eTwg,27226
-PyamilySeq-1.0.1.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-PyamilySeq-1.0.1.dist-info/METADATA,sha256=TINmitLl74gWpOjLOQtbXxo8gjklnH7LUmFpluj6xr0,18363
-PyamilySeq-1.0.1.dist-info/WHEEL,sha256=P9jw-gEje8ByB7_hXoICnHtVCrEwMQh-630tKvQWehc,91
-PyamilySeq-1.0.1.dist-info/entry_points.txt,sha256=FhxILgre1lrvXRO5nod3UMcHmDeiutUwpU05uLNj66M,286
-PyamilySeq-1.0.1.dist-info/top_level.txt,sha256=J6JhugUQTq4rq96yibAlQu3o4KCM9WuYfqr3w1r119M,11
-PyamilySeq-1.0.1.dist-info/RECORD,,