PyamilySeq 1.1.0__tar.gz → 1.1.1__tar.gz

{pyamilyseq-1.1.0 → pyamilyseq-1.1.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: PyamilySeq
-Version: 1.1.0
+Version: 1.1.1
 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 v1.1.0: A tool for gene clustering and analysis.
+PyamilySeq v1.1.1: A tool for gene clustering and analysis.
 
 positional arguments:
   {Full,Partial}  Choose a mode: 'Full' or 'Partial'.
@@ -75,7 +75,7 @@ Escherichia_coli_110957|ENSB_TIZS9kbTvShDvyX	Escherichia_coli_110957|ENSB_TIZS9k
 ```
 ### Example output:
 ```
-Running PyamilySeq v1.1.0
+Running PyamilySeq v1.1.1
 Calculating Groups
 Number of Genomes: 10
 Gene Groups
@@ -220,7 +220,7 @@ Seq-Combiner -input_dir .../test_data/genomes -name_split_gff .gff3 -output_dir
 ```
 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 v1.1.0: Seq-Combiner - A tool to extract sequences from GFF/FASTA files and prepare them for PyamilySeq.
+PyamilySeq v1.1.1: 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
@@ -263,7 +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 v1.1.0: Group-Splitter - A tool to split multi-copy gene groups
+PyamilySeq v1.1.1: Group-Splitter - A tool to split multi-copy gene groups
 identified by PyamilySeq.
 
 options:
@@ -316,7 +316,7 @@ Cluster-Summary -genome_num 10 -input_clstr .../test_data/species/E-coli/E-coli_
 usage: Cluster_Summary.py [-h] -input_clstr INPUT_CLSTR -output OUTPUT -genome_num GENOME_NUM
                           [-output_dir OUTPUT_DIR] [-verbose] [-v]
 
-PyamilySeq v1.1.0: Cluster-Summary - A tool to summarise CD-HIT clustering files.
+PyamilySeq v1.1.1: Cluster-Summary - A tool to summarise CD-HIT clustering files.
 
 options:
   -h, --help            show this help message and exit

{pyamilyseq-1.1.0 → pyamilyseq-1.1.1}/README.md

@@ -29,7 +29,7 @@ To update to the newest version add '-U' to end of the pip install command.
 ```commandline
 usage: PyamilySeq.py [-h] {Full,Partial} ...
 
-PyamilySeq v1.1.0: A tool for gene clustering and analysis.
+PyamilySeq v1.1.1: A tool for gene clustering and analysis.
 
 positional arguments:
   {Full,Partial}  Choose a mode: 'Full' or 'Partial'.
@@ -59,7 +59,7 @@ Escherichia_coli_110957|ENSB_TIZS9kbTvShDvyX	Escherichia_coli_110957|ENSB_TIZS9k
 ```
 ### Example output:
 ```
-Running PyamilySeq v1.1.0
+Running PyamilySeq v1.1.1
 Calculating Groups
 Number of Genomes: 10
 Gene Groups
@@ -204,7 +204,7 @@ Seq-Combiner -input_dir .../test_data/genomes -name_split_gff .gff3 -output_dir
 ```
 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 v1.1.0: Seq-Combiner - A tool to extract sequences from GFF/FASTA files and prepare them for PyamilySeq.
+PyamilySeq v1.1.1: 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
@@ -247,7 +247,7 @@ usage: Group_Splitter.py [-h] -input_fasta INPUT_FASTA -sequence_type {AA,DNA}
                          [-M CLUSTERING_MEMORY] [-no_delete_temp_files]
                          [-verbose] [-v]
 
-PyamilySeq v1.1.0: Group-Splitter - A tool to split multi-copy gene groups
+PyamilySeq v1.1.1: Group-Splitter - A tool to split multi-copy gene groups
 identified by PyamilySeq.
 
 options:
@@ -300,7 +300,7 @@ Cluster-Summary -genome_num 10 -input_clstr .../test_data/species/E-coli/E-coli_
 usage: Cluster_Summary.py [-h] -input_clstr INPUT_CLSTR -output OUTPUT -genome_num GENOME_NUM
                           [-output_dir OUTPUT_DIR] [-verbose] [-v]
 
-PyamilySeq v1.1.0: Cluster-Summary - A tool to summarise CD-HIT clustering files.
+PyamilySeq v1.1.1: Cluster-Summary - A tool to summarise CD-HIT clustering files.
 
 options:
   -h, --help            show this help message and exit

{pyamilyseq-1.1.0 → pyamilyseq-1.1.1}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = PyamilySeq
-version = v1.1.0
+version = v1.1.1
 license_files = LICENSE
 author = Nicholas Dimonaco
 author_email = nicholas@dimonaco.co.uk

pyamilyseq-1.1.1/src/PyamilySeq/Cluster_Compare.py

@@ -0,0 +1,108 @@
+import argparse
+from collections import defaultdict
+
+def read_cd_hit_output(clstr_file):
+    """
+    Reads a CD-HIT .clstr file and extracts sequence clusters.
+    Returns a dictionary where keys are sequence headers and values are cluster IDs.
+    """
+    seq_to_cluster = {}  # Maps sequence header -> cluster ID
+    cluster_id = 0  # Generic ID for clusters (since CD-HIT names don't matter)
+
+    with open(clstr_file, 'r') as f:
+        for line in f:
+            line = line.strip()
+            if line.startswith(">Cluster"):
+                cluster_id += 1  # Increment cluster ID
+            elif line:
+                parts = line.split('\t')
+                if len(parts) > 1:
+                    seq_header = parts[1].split('>')[1].split('...')[0]  # Extract sequence header
+                    seq_to_cluster[seq_header] = cluster_id
+
+    return seq_to_cluster
+
+def compare_cd_hit_clusters(file1, file2, output_file):
+    """
+    Compares two CD-HIT .clstr files to check if clusters are the same.
+    Writes the results to a TSV file.
+    """
+    # Read both clustering files
+    clusters1 = read_cd_hit_output(file1)
+    clusters2 = read_cd_hit_output(file2)
+
+    # Reverse mappings: cluster ID -> list of sequences
+    grouped_clusters1 = defaultdict(set)
+    grouped_clusters2 = defaultdict(set)
+
+    for seq, cluster_id in clusters1.items():
+        grouped_clusters1[cluster_id].add(seq)
+    for seq, cluster_id in clusters2.items():
+        grouped_clusters2[cluster_id].add(seq)
+
+    # Initialize metrics counters
+    cluster_name_changes = 0
+    sequence_shifts = 0
+    only_in_file1 = defaultdict(list)
+    only_in_file2 = defaultdict(list)
+    cluster_mismatches = defaultdict(list)
+
+    # Prepare data for the TSV output
+    tsv_data = []
+
+    # Track changes
+    for seq, cluster_id in clusters1.items():
+        if seq not in clusters2:
+            only_in_file1[cluster_id].append(seq)
+            tsv_data.append([seq, cluster_id, "NA", "Only in file1"])
+        elif clusters2[seq] != cluster_id:
+            # Sequence shifts: sequence in different clusters between files
+            sequence_shifts += 1
+            cluster_mismatches[seq].append((cluster_id, clusters2[seq]))
+            tsv_data.append([seq, cluster_id, clusters2[seq], "Mismatch"])
+
+    for seq, cluster_id in clusters2.items():
+        if seq not in clusters1:
+            only_in_file2[cluster_id].append(seq)
+            tsv_data.append([seq, "NA", cluster_id, "Only in file2"])
+        elif clusters1[seq] != cluster_id:
+            # Sequence shifts: sequence in different clusters between files
+            sequence_shifts += 1
+            cluster_mismatches[seq].append((clusters1[seq], cluster_id))
+            tsv_data.append([seq, clusters1[seq], cluster_id, "Mismatch"])
+
+    # Track cluster name changes (same sequences in different clusters)
+    for cluster_id1, seqs1 in grouped_clusters1.items():
+        for cluster_id2, seqs2 in grouped_clusters2.items():
+            if seqs1 == seqs2 and cluster_id1 != cluster_id2:
+                cluster_name_changes += 1
+                for seq in seqs1:
+                    tsv_data.append([seq, cluster_id1, cluster_id2, "Cluster name change"])
+
+    # Print metrics
+    print("🔢 Clustering Comparison Metrics:")
+    print(f"Cluster name changes: {cluster_name_changes}")
+    print(f"Sequence shifts (sequences assigned to different clusters): {sequence_shifts}")
+    print(f"Sequences only in the first file: {len(only_in_file1)}")
+    print(f"Sequences only in the second file: {len(only_in_file2)}")
+    print()
+
+    # Write the results to a TSV file
+    with open(output_file, 'w') as out_file:
+        out_file.write("Sequence\tCluster ID (File 1)\tCluster ID (File 2)\tChange Type\n")
+        for row in tsv_data:
+            out_file.write("\t".join(map(str, row)) + "\n")
+
+    print(f"✅ Results have been written to {output_file}")
+
+def main():
+    parser = argparse.ArgumentParser(description="Compare two CD-HIT .clstr files to check for clustering consistency.")
+    parser.add_argument("-file1", required=True, help="First CD-HIT .clstr file")
+    parser.add_argument("-file2", required=True, help="Second CD-HIT .clstr file")
+    parser.add_argument("-output", required=True, help="Output file (TSV format)")
+    args = parser.parse_args()
+
+    compare_cd_hit_clusters(args.file1, args.file2, args.output)
+
+if __name__ == "__main__":
+    main()

{pyamilyseq-1.1.0 → pyamilyseq-1.1.1}/src/PyamilySeq/Cluster_Summary.py

@@ -1,33 +1,32 @@
 import argparse
-from collections import OrderedDict
-from collections import defaultdict
+from collections import OrderedDict, defaultdict
 
 try:
     from .constants import *
     from .utils import *
-except (ModuleNotFoundError, ImportError, NameError, TypeError) as error:
+except (ModuleNotFoundError, ImportError, NameError, TypeError):
     from constants import *
     from utils import *
 
 
 def categorise_percentage(percent):
     """Categorise the percentage of genomes with multicopy genes."""
-    if 20 <= percent < 40:
-        return "20-40%"
-    elif 40 <= percent < 60:
-        return "40-60%"
-    elif 60 <= percent < 80:
-        return "60-80%"
-    elif 80 <= percent < 95:
-        return "80-95%"
-    elif 95 <= percent < 99:
-        return "95-99%"
-    elif 99 <= percent <= 100:
-        return "99-100%"
+    categories = {
+        (20, 40): "20-40%",
+        (40, 60): "40-60%",
+        (60, 80): "60-80%",
+        (80, 95): "80-95%",
+        (95, 99): "95-99%",
+        (99, 100): "99-100%"
+    }
+    for (low, high), label in categories.items():
+        if low <= percent < high:
+            return label
     return None
 
-# Read cd-hit .clstr file and extract information
+
 def read_cd_hit_output(clustering_output):
+    """Parse CD-HIT .cluster file and extract clustering information."""
     clusters = OrderedDict()
 
     with open(clustering_output, 'r') as f:
@@ -42,10 +41,8 @@ def read_cd_hit_output(clustering_output):
                 parts = line.split('\t')
                 if len(parts) > 1:
                     clustered_info = parts[1]
-                    length = clustered_info.split(',')[0]
-                    length = int(''.join(c for c in length if c.isdigit()))
-                    clustered_header = clustered_info.split('>')[1].split('...')[0]
-                    clustered_header = '>' + clustered_header
+                    length = int(''.join(c for c in clustered_info.split(',')[0] if c.isdigit()))
+                    clustered_header = '>' + clustered_info.split('>')[1].split('...')[0]
 
                     if 'at ' in clustered_info and '%' in clustered_info.split('at ')[-1]:
                         percent_identity = extract_identity(clustered_info)
@@ -63,12 +60,14 @@ def read_cd_hit_output(clustering_output):
     return clusters
 
 
-# Summarise the information for each cluster
-def summarise_clusters(options,clusters, output):
-    multicopy_groups = defaultdict(int)  # Counter for groups with multicopy genes
+def summarise_clusters(options, clusters, output):
+    """Generate a detailed cluster summary report."""
+    multicopy_groups = defaultdict(int)  # Counter for clusters with multicopy genes
 
     with open(output, 'w') as out_f:
-        out_f.write("Cluster_ID\tNum_Sequences\tAvg_Length\tLength_Range\tAvg_Identity\tIdentity_Range\n")
+        out_f.write(
+            "Cluster_ID\tNum_Sequences\tNum_Genomes\tAvg_Length\tLength_Range\tAvg_Identity\tIdentity_Range\tGenomes_With_Multiple_Genes\tMulticopy_Percentage\n"
+        )
 
         for cluster_id, seqs in clusters.items():
             num_seqs = len(seqs)
@@ -81,82 +80,78 @@ def summarise_clusters(options,clusters, output):
             avg_identity = sum(identities) / num_seqs if num_seqs > 0 else 0
             identity_range = f"{min(identities):.2f}-{max(identities):.2f}" if num_seqs > 0 else "N/A"
 
-            out_f.write(
-                f"{cluster_id}\t{num_seqs}\t{avg_length:.2f}\t{length_range}\t{avg_identity:.2f}\t{identity_range}\n")
-
-            # Count genomes with more than one gene
+            # Count genomes in cluster
             genome_to_gene_count = defaultdict(int)
             for seq in seqs:
-                genome = seq['header'].split('|')[0].replace('>','')
+                genome = seq['header'].split('|')[0].replace('>', '')
                 genome_to_gene_count[genome] += 1
 
+            num_genomes = len(genome_to_gene_count)
             num_genomes_with_multiple_genes = sum(1 for count in genome_to_gene_count.values() if count > 1)
+            multicopy_percentage = (num_genomes_with_multiple_genes / options.genome_num) * 100 if options.genome_num > 0 else 0
 
-            # Calculate the percentage of genomes with multicopy genes
-
-            multicopy_percentage = (num_genomes_with_multiple_genes / options.genome_num) * 100
+            # Categorize multicopy percentage
             category = categorise_percentage(multicopy_percentage)
             if category:
                 multicopy_groups[category] += 1
 
-        # Define the order of categories for printout
-        category_order = ["20-40%", "40-60%", "60-80%", "80-95%", "95-99%", "99-100%"]
+            # Write detailed output for each cluster
+            out_f.write(
+                f"{cluster_id}\t{num_seqs}\t{num_genomes}\t{avg_length:.2f}\t{length_range}\t{avg_identity:.2f}\t{identity_range}\t"
+                f"{num_genomes_with_multiple_genes}\t{multicopy_percentage:.2f}\n"
+            )
 
-        # Print the number of clusters with multicopy genes in each percentage range, in the correct order
+        # Define order for multicopy statistics output
+        category_order = ["20-40%", "40-60%", "60-80%", "80-95%", "95-99%", "99-100%"]
         for category in category_order:
-            print(f"Number of clusters with multicopy genes in {category} range: {multicopy_groups[category]}")
+            print(f"Clusters with multicopy genes in {category} range: {multicopy_groups[category]}")
 
 
-# Main function to parse arguments and run the analysis
 def main():
-    parser = argparse.ArgumentParser(description='PyamilySeq ' + PyamilySeq_Version + ': Cluster-Summary - A tool to summarise CD-HIT clustering files.')
-    ### Required Arguments
-    required = parser.add_argument_group('Required Parameters')
-    required.add_argument('-input_clstr', action="store", dest="input_clstr",
-                          help='Input CD-HIT .clstr file',
-                          required=True)
-    required.add_argument('-output', action="store", dest="output",
-                          help="Output TSV file to store cluster summaries - Will add '.tsv' if not provided by user",
-                          required=True)
-    required.add_argument('-genome_num', action='store', dest='genome_num', type=int,
-                          help='The total number of genomes must be provide',
-                          required=True)
-    #required.add_argument("-clustering_format", action="store", dest="clustering_format", choices=['CD-HIT','TSV','CSV'],
-    #                      help="Clustering format to use: CD-HIT or TSV (MMseqs2, BLAST, DIAMOND) / CSV edge-list file (Node1\tNode2).",
-    #                      required=True)
+    """Main function to parse arguments and process clustering files."""
+    parser = argparse.ArgumentParser(
+        description='PyamilySeq ' + PyamilySeq_Version + ': Cluster-Summary - A tool to summarise CD-HIT clustering files.')
 
+    # Required Arguments
+    required = parser.add_argument_group('Required Parameters')
+    required.add_argument('-input_cluster', action="store", dest="input_cluster", required=True,
+                          help='Input CD-HIT .cluster file')
+    required.add_argument('-output', action="store", dest="output", required=True,
+                          help="Output TSV file to store cluster summaries - Will add '.tsv' if not provided by user")
+    required.add_argument('-genome_num', action='store', dest='genome_num', type=int, required=True,
+                          help='Total number of genomes in dataset')
+
+    # Optional Arguments
     optional = parser.add_argument_group('Optional Arguments')
     optional.add_argument('-output_dir', action="store", dest="output_dir",
-                          help='Default: Same as input file',
-                          required=False)
+                          help='Default: Same as input file', required=False)
 
     misc = parser.add_argument_group("Misc Parameters")
     misc.add_argument("-verbose", action="store_true", dest="verbose",
-                      help="Print verbose output.",
-                      required=False)
+                      help="Print verbose output.", required=False)
     misc.add_argument("-v", "--version", action="version",
                       version=f"PyamilySeq: Group-Summary version {PyamilySeq_Version} - Exiting",
                       help="Print out version number and exit")
 
-
     options = parser.parse_args()
-    print("Running PyamilySeq " + PyamilySeq_Version+ ": Group-Summary ")
+    print("Running PyamilySeq " + PyamilySeq_Version + ": Group-Summary ")
 
-    ### File handling
-    options.input_clstr = fix_path(options.input_clstr)
+    # File handling
+    options.input_cluster = fix_path(options.input_cluster)
     if options.output_dir is None:
-        options.output_dir = os.path.dirname(os.path.abspath(options.input_clstr))
+        options.output_dir = os.path.dirname(os.path.abspath(options.input_cluster))
     output_path = os.path.abspath(options.output_dir)
     if not os.path.exists(output_path):
         os.makedirs(output_path)
+
     output_name = options.output
     if not output_name.endswith('.tsv'):
         output_name += '.tsv'
     output_file_path = os.path.join(output_path, output_name)
-    ###
 
-    clusters = read_cd_hit_output(options.input_clstr)
-    summarise_clusters(options,clusters, output_file_path)
+    # Process clusters and generate summary
+    clusters = read_cd_hit_output(options.input_cluster)
+    summarise_clusters(options, clusters, output_file_path)
 
 
 if __name__ == "__main__":

{pyamilyseq-1.1.0 → pyamilyseq-1.1.1}/src/PyamilySeq/PyamilySeq.py

@@ -20,8 +20,8 @@ def run_cd_hit(options, input_file, clustering_output, clustering_mode):
         clustering_mode,
         '-i', input_file,
         '-o', clustering_output,
-        '-c', str(options.pident),
-        '-s', str(options.len_diff),
+        '-c', f"{float(options.pident):.2f}",
+        '-s', f"{float(options.len_diff):.2f}",
         '-T', str(options.threads),
         '-M', str(options.mem),
         '-d', "0",
@@ -62,10 +62,11 @@ def main():
                              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,
+    full_parser.add_argument("-c", type=str, 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,
+    full_parser.add_argument("-s", type=str, 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'.")
 
@@ -98,7 +99,7 @@ def main():
         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("-align", action="store_true", dest="align_core", required=False,
-                               help="Align and concatenate sequences for 'core' groups specified with '-w'.")
+                               help="Align and concatenate sequences for 'core' groups (those in 99-100% of genomes).")
         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,
@@ -187,13 +188,13 @@ def main():
             elif options.sequence_type == 'AA':
                 clustering_mode = 'cd-hit'
             if options.fast_mode == True:
-                options.fast_mode = 0
+                options.fast_mode = 1
                 if options.verbose == True:
                     print("Running CD-HIT in fast mode.")
             else:
-                options.fast_mode = 1
+                options.fast_mode = 0
                 if options.verbose == True:
-                    print("Running CD-HIT in slow mode.")
+                    print("Running CD-HIT in accurate mode.")
         else:
             exit("cd-hit is not installed. Please install cd-hit to proceed.")
 
@@ -239,10 +240,10 @@ def main():
             translate = False
             file_to_cluster = combined_out_file
         if options.input_type == 'separate':
-            read_separate_files(options.input_dir, options.name_split_gff, options.name_split_fasta, 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, False)
             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_gff, options.gene_ident, combined_out_file, translate)
+            read_combined_files(options.input_dir, options.name_split_gff, options.gene_ident, combined_out_file, translate, False)
             run_cd_hit(options, file_to_cluster, clustering_output, clustering_mode)
         elif options.input_type == 'fasta':
             combined_out_file = options.input_fasta
@@ -281,6 +282,8 @@ def main():
         clustering_options = clustering_options()
 
     elif options.run_mode == 'Partial':
+        if not os.path.exists(output_path):
+            os.makedirs(output_path)
         class clustering_options:
             def __init__(self):
                 self.run_mode = options.run_mode

{pyamilyseq-1.1.0 → pyamilyseq-1.1.1}/src/PyamilySeq/PyamilySeq_Species.py

@@ -120,12 +120,14 @@ def calc_Second_only_core(cluster, Second_num, groups, cores):
 
 #@profile
 def calc_only_Second_only_core(cluster, Second_num, groups, cores): # only count the true storf onlies
-    groups_as_list = list(groups.values())
-    for idx in (idx for idx, (sec, fir) in enumerate(groups_as_list) if sec <= Second_num <= fir):
-        res = idx
-    family_group = list(groups)[res]
-    cores['only_Second_core_' + family_group].append(cluster)
-
+    try:
+        groups_as_list = list(groups.values())
+        for idx in (idx for idx, (sec, fir) in enumerate(groups_as_list) if sec <= Second_num <= fir):
+            res = idx
+        family_group = list(groups)[res]
+        cores['only_Second_core_' + family_group].append(cluster)
+    except UnboundLocalError:
+        sys.exit("Error in calc_only_Second_only_core")
 
 
 #@profile

{pyamilyseq-1.1.0 → pyamilyseq-1.1.1}/src/PyamilySeq/Seq_Combiner.py

@@ -65,17 +65,17 @@ def main():
     if not os.path.exists(output_path):
         os.makedirs(output_path)
 
-    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.")
+    #output_file = options.output_file + '.fasta'
+    if os.path.exists(os.path.join(output_path, options.output_file)):
+        print(f"Output file {options.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 )
+    combined_out_file = os.path.join(output_path, options.output_file )
 
     if options.input_type == 'separate':
-        read_separate_files(options.input_dir, options.name_split_gff, options.name_split_fasta, 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, True)
     elif options.input_type == 'combined':
-        read_combined_files(options.input_dir, options.name_split_gff, 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, True)
     elif options.input_type == 'fasta':
         read_fasta_files(options.input_dir, options.name_split_fasta, combined_out_file, options.translate)
 

{pyamilyseq-1.1.0 → pyamilyseq-1.1.1}/src/PyamilySeq/clusterings.py

@@ -279,8 +279,6 @@ def combined_clustering_CDHIT(options, taxa_dict, splitter):
     first = True
     for line in Second_in:
         if line.startswith('>'):
-            if '>Cluster 1997' in line:
-                print()
             if first == False:
                 cluster_size = len(Combined_clusters[cluster_id])
                 Combined_reps.update({rep: cluster_size})

pyamilyseq-1.1.1/src/PyamilySeq/constants.py

@@ -0,0 +1,2 @@
+PyamilySeq_Version = 'v1.1.1'
+

{pyamilyseq-1.1.0 → pyamilyseq-1.1.1}/src/PyamilySeq/utils.py

@@ -228,9 +228,15 @@ def run_mafft_on_sequences(options, sequences, output_file):
 
 
 
-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:
+def read_separate_files(input_dir, name_split_gff, name_split_fasta, gene_ident, combined_out, translate, run_as_combiner):
+    if run_as_combiner == True:
+        combined_out_file_aa = None
+    else:
+        combined_out_file_aa = combined_out.replace('_dna.fasta','_aa.fasta')
+
+    with open(combined_out, 'w') as combined_out_file, (open(combined_out_file_aa, 'w') if combined_out_file_aa else open(os.devnull, 'w')) as combined_out_file_aa:
+        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:
         gff_files = glob.glob(os.path.join(input_dir, '*' + name_split_gff))
         if not gff_files:
             sys.exit("Error: No GFF files found.")
@@ -299,23 +305,40 @@ def read_separate_files(input_dir, name_split_gff, name_split_fasta, gene_ident,
                             full_sequence = fasta_dict[contig][1]
                             seq = full_sequence[corrected_start:corrected_stop]
 
-                        if translate == True:
-                            seq_aa = translate_frame(seq)
-                            wrapped_sequence_aa = '\n'.join([seq_aa[i:i + 60] for i in range(0, len(seq_aa), 60)])
-                            combined_out_file_aa.write(f">{genome_name}|{seq_id}\n{wrapped_sequence_aa}\n")
-                        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 run_as_combiner == True:
+                            if translate == True:
+                                seq_aa = translate_frame(seq)
+                                wrapped_sequence_aa = '\n'.join([seq_aa[i:i + 60] for i in range(0, len(seq_aa), 60)])
+                                combined_out_file.write(f">{genome_name}|{seq_id}\n{wrapped_sequence_aa}\n")
+                            else:
+                                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")
+                        else:
+                            if translate == True:
+                                seq_aa = translate_frame(seq)
+                                wrapped_sequence_aa = '\n'.join([seq_aa[i:i + 60] for i in range(0, len(seq_aa), 60)])
+                                combined_out_file_aa.write(f">{genome_name}|{seq_id}\n{wrapped_sequence_aa}\n")
+                            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 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
-        if combined_out_file.name != combined_out_file_aa.name:
-            os.remove(combined_out_file_aa.name)
+        try: # Catches is combined_out_file_aa is None
+            if combined_out_file.name != combined_out_file_aa.name:
+                os.remove(combined_out_file_aa.name)
+        except AttributeError:
+            pass
 
 
-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:
+def read_combined_files(input_dir, name_split, gene_ident, combined_out, translate, run_as_combiner):
+    if run_as_combiner == True:
+        combined_out_file_aa = None
+    else:
+        combined_out_file_aa = combined_out.replace('_dna.fasta','_aa.fasta')
+    #with open(combined_out, 'w') as combined_out_file, open(combined_out_file_aa, 'w') if combined_out_file_aa else open(os.devnull, 'w'):
+    with open(combined_out, 'w') as combined_out_file, (open(combined_out_file_aa, 'w') if combined_out_file_aa else open(os.devnull, 'w')) as combined_out_file_aa:
         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.")
@@ -355,7 +378,7 @@ def read_combined_files(input_dir, name_split, gene_ident, combined_out, transla
 
                 for contig, fasta in fasta_dict.items():
                     reverse_sequence = reverse_complement(fasta[0])
-                    fasta_dict[contig][1]=reverse_sequence
+                    fasta_dict[contig][1] = reverse_sequence
 
                 if fasta_dict and gff_features:
                     for contig, start, end, strand, feature, seq_id in gff_features:
@@ -369,22 +392,38 @@ def read_combined_files(input_dir, name_split, gene_ident, combined_out, transla
                                 full_sequence = fasta_dict[contig][1]
                                 seq = full_sequence[corrected_start:corrected_stop]
 
-                            if translate == True:
-                                seq_aa = translate_frame(seq)
-                                wrapped_sequence_aa = '\n'.join([seq_aa[i:i + 60] for i in range(0, len(seq_aa), 60)])
-                                combined_out_file_aa.write(f">{genome_name}|{seq_id}\n{wrapped_sequence_aa}\n")
-                            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 run_as_combiner == True:
+                                if translate == True:
+                                    seq_aa = translate_frame(seq)
+                                    wrapped_sequence_aa = '\n'.join([seq_aa[i:i + 60] for i in range(0, len(seq_aa), 60)])
+                                    combined_out_file.write(f">{genome_name}|{seq_id}\n{wrapped_sequence_aa}\n")
+                                else:
+                                    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")
+                            else:
+                                if translate == True:
+                                    seq_aa = translate_frame(seq)
+                                    wrapped_sequence_aa = '\n'.join([seq_aa[i:i + 60] for i in range(0, len(seq_aa), 60)])
+                                    combined_out_file_aa.write(f">{genome_name}|{seq_id}\n{wrapped_sequence_aa}\n")
+                                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 or translate == None:
         #Clean up unused file
-        if combined_out_file.name != combined_out_file_aa.name:
-            os.remove(combined_out_file_aa.name)
+        try: # Catches is combined_out_file_aa is None
+            if combined_out_file.name != combined_out_file_aa.name:
+                os.remove(combined_out_file_aa.name)
+        except AttributeError:
+            pass
 
 
 
-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:
+def read_fasta_files(input_dir, name_split_fasta, combined_out, translate, run_as_combiner):
+    if run_as_combiner == True:
+        combined_out_file_aa = None
+    else:
+        combined_out_file_aa = combined_out.replace('_dna.fasta','_aa.fasta')
+    with open(combined_out, 'w') as combined_out_file, (open(combined_out_file_aa, 'w') if combined_out_file_aa else open(os.devnull, 'w')) as combined_out_file_aa:
         fasta_files = glob.glob(os.path.join(input_dir, '*' + name_split_fasta))
         if not fasta_files:
             sys.exit("Error: No GFF files found.")
@@ -400,17 +439,30 @@ def read_fasta_files(input_dir, name_split_fasta, combined_out, translate):
                     else:
                         fasta_dict[current_seq] +=line.strip()
                 for seq_id, seq in fasta_dict.items():
-                    if translate == True:
-                        seq_aa = translate_frame(seq)
-                        wrapped_sequence_aa = '\n'.join([seq_aa[i:i + 60] for i in range(0, len(seq_aa), 60)])
-                        combined_out_file_aa.write(f">{genome_name}|{seq_id}\n{wrapped_sequence_aa}\n")
-                    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 run_as_combiner == True:
+                        if translate == True:
+                            seq_aa = translate_frame(seq)
+                            wrapped_sequence_aa = '\n'.join([seq_aa[i:i + 60] for i in range(0, len(seq_aa), 60)])
+                            combined_out_file.write(f">{genome_name}|{seq_id}\n{wrapped_sequence_aa}\n")
+                        else:
+                            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")
+                    else:
+                        if translate == True:
+                            seq_aa = translate_frame(seq)
+                            wrapped_sequence_aa = '\n'.join([seq_aa[i:i + 60] for i in range(0, len(seq_aa), 60)])
+                            combined_out_file_aa.write(f">{genome_name}|{seq_id}\n{wrapped_sequence_aa}\n")
+                        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 or translate == None:
         #Clean up unused file
-        if combined_out_file.name != combined_out_file_aa.name:
-            os.remove(combined_out_file_aa.name)
+        try: # Catches is combined_out_file_aa is None
+            if combined_out_file.name != combined_out_file_aa.name:
+                os.remove(combined_out_file_aa.name)
+        except AttributeError:
+            pass
+
 
 def write_groups_func(options, output_dir, key_order, cores, sequences,
                  pangenome_clusters_First_sequences_sorted, combined_pangenome_clusters_Second_sequences):
@@ -533,7 +585,8 @@ def write_groups_func(options, output_dir, key_order, cores, sequences,
 def perform_alignment(gene_path,group_directory, gene_file, options, concatenated_sequences, subgrouped):
     # Read sequences from the gene family file
     sequences = read_fasta(gene_path)
-
+    if len(sequences) == 1: # We can't align a single sequence
+        return concatenated_sequences
     # Select the longest sequence for each genome
     longest_sequences = select_longest_gene(sequences, subgrouped)
 
@@ -574,20 +627,18 @@ def process_gene_groups(options, group_directory, sub_group_directory, paralog_g
         # 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)
-
+                # Could add more catches here to work with First and Secondary groups - This ensures only core '99/100' are aligned
+                if 'First_core_99' in gene_file or 'First_core_100' in 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)
 
     # Write the concatenated sequences to the output file
     with open(output_file, 'w') as out:

{pyamilyseq-1.1.0 → pyamilyseq-1.1.1}/src/PyamilySeq.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: PyamilySeq
-Version: 1.1.0
+Version: 1.1.1
 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 v1.1.0: A tool for gene clustering and analysis.
+PyamilySeq v1.1.1: A tool for gene clustering and analysis.
 
 positional arguments:
   {Full,Partial}  Choose a mode: 'Full' or 'Partial'.
@@ -75,7 +75,7 @@ Escherichia_coli_110957|ENSB_TIZS9kbTvShDvyX	Escherichia_coli_110957|ENSB_TIZS9k
 ```
 ### Example output:
 ```
-Running PyamilySeq v1.1.0
+Running PyamilySeq v1.1.1
 Calculating Groups
 Number of Genomes: 10
 Gene Groups
@@ -220,7 +220,7 @@ Seq-Combiner -input_dir .../test_data/genomes -name_split_gff .gff3 -output_dir
 ```
 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 v1.1.0: Seq-Combiner - A tool to extract sequences from GFF/FASTA files and prepare them for PyamilySeq.
+PyamilySeq v1.1.1: 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
@@ -263,7 +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 v1.1.0: Group-Splitter - A tool to split multi-copy gene groups
+PyamilySeq v1.1.1: Group-Splitter - A tool to split multi-copy gene groups
 identified by PyamilySeq.
 
 options:
@@ -316,7 +316,7 @@ Cluster-Summary -genome_num 10 -input_clstr .../test_data/species/E-coli/E-coli_
 usage: Cluster_Summary.py [-h] -input_clstr INPUT_CLSTR -output OUTPUT -genome_num GENOME_NUM
                           [-output_dir OUTPUT_DIR] [-verbose] [-v]
 
-PyamilySeq v1.1.0: Cluster-Summary - A tool to summarise CD-HIT clustering files.
+PyamilySeq v1.1.1: Cluster-Summary - A tool to summarise CD-HIT clustering files.
 
 options:
   -h, --help            show this help message and exit

{pyamilyseq-1.1.0 → pyamilyseq-1.1.1}/src/PyamilySeq.egg-info/SOURCES.txt

@@ -2,6 +2,7 @@ LICENSE
 README.md
 pyproject.toml
 setup.cfg
+src/PyamilySeq/Cluster_Compare.py
 src/PyamilySeq/Cluster_Summary.py
 src/PyamilySeq/Group_Extractor.py
 src/PyamilySeq/Group_Sizes.py

pyamilyseq-1.1.0/src/PyamilySeq/constants.py

@@ -1,2 +0,0 @@
-PyamilySeq_Version = 'v1.1.0'
-