PyamilySeq 0.5.1__py3-none-any.whl → 0.6.0__py3-none-any.whl

PyamilySeq/clusterings.py

@@ -0,0 +1,324 @@
+import subprocess
+import shutil
+import os
+import glob
+import sys
+import copy
+from collections import OrderedDict
+from collections import defaultdict
+
+def cluster_CDHIT(options, splitter):
+    First_in = open(options.clusters, 'r')
+    clusters = OrderedDict()
+    pangenome_clusters_First = OrderedDict()
+    pangenome_clusters_First_sequences = OrderedDict()
+    first = True
+    taxa_dict = defaultdict(int)
+    reps = OrderedDict()
+    ## Load in all data for easier reuse later
+    for line in First_in:
+        if '>Cluster 7575' in line:
+            print()
+        if line.startswith('>'):
+            if first == False:
+                cluster_size = len(clusters[cluster_id])
+                reps.update({rep: [cluster_size, len(pangenome_clusters_First[cluster_id])]})
+            cluster_id = line.strip('>')
+            cluster_id = cluster_id.strip('\n')
+            cluster_id = cluster_id.split(' ')[1]
+            clusters.update({cluster_id: []})
+            pangenome_clusters_First.update({cluster_id: []})
+            pangenome_clusters_First_sequences.update({cluster_id: []})
+
+            first = False
+        else:
+            clustered = line.split('\t')[1]
+            clustered = clustered.split('>')[1]
+            clustered = clustered.split('...')[0]
+            taxa = clustered.split(splitter)[0]
+            taxa_dict[taxa] += 1
+            if '*' in line:
+                rep = clustered
+                reps.update({rep: [0, 0]})
+            if first == False:
+                clusters[cluster_id].append(clustered)
+                clustered_taxa = clustered.split(splitter)[0]
+                if clustered_taxa not in pangenome_clusters_First[cluster_id]:
+                    pangenome_clusters_First[cluster_id].append(clustered_taxa)
+                pangenome_clusters_First_sequences[cluster_id].append(clustered)
+    return taxa_dict, pangenome_clusters_First, pangenome_clusters_First_sequences, reps
+
+
+
+#@profile
+def combined_clustering_counting(options, pangenome_clusters_First, reps, combined_pangenome_clusters_First_Second_clustered, splitter):
+    num_clustered_First = defaultdict(list)
+    pangenome_clusters_Type = copy.deepcopy(pangenome_clusters_First)
+    list_of_reps = list(reps.keys())
+    for cluster, pep_genomes in pangenome_clusters_First.items():
+        rep = list_of_reps[int(cluster)]  # get the rep of the current pep cluster
+        Com_PEP_Genomes = 0
+        Seconds = 0
+        seen_Seconds = []
+        added_Second_genomes = 0
+        try:  # get the cluster from the storf clusters which contains this rep
+            clustered_combined = combined_pangenome_clusters_First_Second_clustered[rep]  # Not true clusters - I put a PEP as key myself
+            seen_clust_Genomes = []
+            num_clustered_First[cluster].append(rep + '_' + str(len(pep_genomes)))
+            for clust in clustered_combined:
+                if options.sequence_tag not in clust:  # Not good enough at the moment
+                    clust_Genome = clust.split(splitter)[0]
+                    if clust_Genome not in seen_clust_Genomes:
+                        seen_clust_Genomes.append(clust_Genome)
+                        if clust_Genome not in pep_genomes:
+                            Com_PEP_Genomes += 1
+                    num_clustered_First[cluster].append(clust + '_' + str(reps[clust][1]))
+                elif options.sequence_tag in clust:
+                    Seconds += 1
+                    clust_Genome = clust.split(splitter)[0]
+                    if clust_Genome not in seen_Seconds:
+                        seen_Seconds.append(clust_Genome)
+                    if clust_Genome not in seen_clust_Genomes:
+                        seen_clust_Genomes.append(clust_Genome)
+                        if clust_Genome not in pep_genomes:
+                            added_Second_genomes += 1
+                else:
+                    sys.exit("Error: looking for sequence_tag")
+
+            size_of_pep_clusters = []
+            peps = num_clustered_First[cluster]
+            for pep in peps:
+                pep = pep.rsplit('_', 1)
+                size_of_pep_clusters.append(int(pep[1]))
+            pangenome_clusters_Type[cluster] = [len(num_clustered_First[cluster]), sum(size_of_pep_clusters),
+                                                size_of_pep_clusters, added_Second_genomes, Seconds, len(seen_Seconds)]
+
+        except KeyError:
+            ###Singleton
+            num_pep_genomes = [len(pep_genomes)]
+            pangenome_clusters_Type[cluster] = [1, len(pep_genomes), num_pep_genomes, added_Second_genomes, Seconds,
+                                                len(seen_Seconds)]
+    # pangenome_clusters_Type = [Number of First clustered genomes or genera, Size of the cluster, Ditto, Added Seconds,Number of Seconds,Unique Seconds ]
+    return pangenome_clusters_Type
+
+
+#@profile
+def single_clustering_counting(pangenome_clusters_First, reps):
+    num_clustered_First = defaultdict(list)
+    recorded_First = []
+    pangenome_clusters_Type = copy.deepcopy(pangenome_clusters_First)
+    list_of_reps = list(reps.keys())
+    for cluster, First_taxa in pangenome_clusters_First.items():
+        rep = list_of_reps[int(cluster)]  # get the rep of the current pep cluster
+
+        try:  # get the cluster from the storf clusters which contains this rep
+            num_clustered_First[cluster].append(rep + '_' + str(len(First_taxa)))
+            size_of_First_clusters = []
+            Firsts = num_clustered_First[cluster]
+            for First in Firsts:
+                First = First.rsplit('_', 1)
+                size_of_First_clusters.append(int(First[1]))
+                recorded_First.append(First[0])
+            pangenome_clusters_Type[cluster] = [len(num_clustered_First[cluster]), sum(size_of_First_clusters),
+                                                size_of_First_clusters, 0, 0, 0]
+
+        except KeyError:
+            ###Singleton
+            num_First_taxa = [len(First_taxa)]
+            pangenome_clusters_Type[cluster] = [1, len(First_taxa), num_First_taxa, 0, 0, 0]
+
+    # pangenome_clusters_Type = [Number of First clustered genomes or genera, Size of the cluster, Ditto, 0,0,0 ]
+    return pangenome_clusters_Type
+
+
+
+#@profile
+def combined_clustering_CDHIT(options, taxa_dict, splitter):
+    Second_in = open(options.reclustered, 'r')
+    combined_pangenome_clusters_First = OrderedDict()
+    combined_pangenome_clusters_First_sequences = OrderedDict()
+    combined_pangenome_clusters_Second = OrderedDict()
+    combined_pangenome_clusters_Second_sequences = OrderedDict()
+    combined_pangenome_clusters_First_Second_clustered = OrderedDict()
+
+    not_Second_only_cluster_ids = []
+    already_seen_PEP = []
+    Combined_clusters = OrderedDict()
+    Combined_reps = OrderedDict()
+    first = True
+    for line in Second_in:
+        if line.startswith('>'):
+            if first == False:
+                cluster_size = len(Combined_clusters[cluster_id])
+                Combined_reps.update({rep: cluster_size})
+                for pep in combined_pangenome_clusters_First_sequences[cluster_id]:
+                    if pep != []:
+                        if pep in already_seen_PEP:
+                            continue
+                        else:
+                            already_seen_PEP.append(pep)
+                if len(combined_pangenome_clusters_Second_sequences[cluster_id]) > 0 and len(combined_pangenome_clusters_First_sequences[cluster_id]) > 0:
+                    if len(combined_pangenome_clusters_First_sequences[cluster_id]) > 1:  # If we have clustered >1 PEP family, we need to record 1 as key and all others are val
+                        all_but_first = combined_pangenome_clusters_First_sequences[cluster_id][1:]
+                        storfs_clustered = combined_pangenome_clusters_Second_sequences[cluster_id]
+                        VALUE = all_but_first + storfs_clustered
+                    else:
+                        VALUE = combined_pangenome_clusters_Second_sequences[cluster_id]
+                    KEY = combined_pangenome_clusters_First_sequences[cluster_id][0]
+                    combined_pangenome_clusters_First_Second_clustered.update({KEY: VALUE})
+            cluster_id = line.strip('>')
+            cluster_id = cluster_id.strip('\n')
+            cluster_id = cluster_id.split(' ')[1]
+            Combined_clusters.update({cluster_id: []})
+            combined_pangenome_clusters_First.update({cluster_id: []})
+            combined_pangenome_clusters_First_sequences.update({cluster_id: []})
+            combined_pangenome_clusters_Second.update({cluster_id: []})
+            combined_pangenome_clusters_Second_sequences.update({cluster_id: []})
+
+            first = False
+        else:
+            clustered = line.split('\t')[1]
+            clustered = clustered.split('>')[1]
+            clustered = clustered.split('...')[0]
+            genome = clustered.split(splitter)[0]
+            taxa_dict[genome] += 1
+            if '*' in line:
+                rep = clustered
+                Combined_reps.update({rep: 0})
+            if first == False:
+                Combined_clusters[cluster_id].append(clustered)
+                clustered_taxa = clustered.split(splitter)[0]
+                if options.sequence_tag in line:
+                    if clustered_taxa not in combined_pangenome_clusters_Second[cluster_id]:
+                        combined_pangenome_clusters_Second[cluster_id].append(clustered_taxa)
+                    combined_pangenome_clusters_Second_sequences[cluster_id].append(clustered)
+                else:
+                    if cluster_id not in not_Second_only_cluster_ids:
+                        not_Second_only_cluster_ids.append(cluster_id)  # Tell us which StORF_Reporter clustered are unmatched to a PEP
+                    if clustered_taxa not in combined_pangenome_clusters_First[cluster_id]:
+                        combined_pangenome_clusters_First[cluster_id].append(clustered_taxa)
+                    combined_pangenome_clusters_First_sequences[cluster_id].append(clustered)
+
+
+    return combined_pangenome_clusters_First_Second_clustered,not_Second_only_cluster_ids, combined_pangenome_clusters_Second
+
+
+def cluster_EdgeList(options,splitter):
+    if options.cluster_format == 'TSV':
+        separator = '\t'
+    elif options.cluster_format == 'CSV':
+        separator = ','
+    cluster_id = 0
+    last_rep = ''
+    first = True
+    First_in = open(options.clusters, 'r')
+    pangenome_clusters_First = OrderedDict()
+    pangenome_clusters_First_sequences = OrderedDict()
+    taxa_dict = defaultdict(int)
+    reps = OrderedDict()
+    for line in First_in:
+        rep, child = line.strip().split(separator)
+        child_taxa = child.split(splitter)[0]  # Extracting the genome identifier from the child sequence
+        # Counting occurrences of genomes
+        taxa_dict[child_taxa] += 1
+        if first == True:
+            pangenome_clusters_First[0] = []
+            pangenome_clusters_First_sequences[0] = []
+            first = False
+
+        if rep != last_rep and last_rep != '':
+            cluster_id +=1
+            pangenome_clusters_First[cluster_id] = []
+            pangenome_clusters_First_sequences[cluster_id] = []
+            cluster_size = len(pangenome_clusters_First_sequences[cluster_id-1])
+            reps.update({last_rep: [cluster_size, len(pangenome_clusters_First[cluster_id-1])]})
+            pangenome_clusters_First[cluster_id] = []
+            pangenome_clusters_First_sequences[cluster_id] = []
+        if child_taxa not in pangenome_clusters_First[cluster_id]:
+            pangenome_clusters_First[cluster_id].append(child_taxa)
+
+        pangenome_clusters_First_sequences[cluster_id].append(child)
+        last_rep = rep
+        cluster_size = len(pangenome_clusters_First_sequences[cluster_id])
+        reps.update({rep: [cluster_size, len(pangenome_clusters_First[cluster_id])]})
+
+
+    return taxa_dict, pangenome_clusters_First, pangenome_clusters_First_sequences, reps
+
+
+def combined_clustering_Edge_List(options, splitter):
+    if options.cluster_format == 'TSV':
+        separator = '\t'
+    elif options.cluster_format == 'CSV':
+        separator = ','
+
+    cluster_id = 0
+    last_rep = ''
+    Second_in = open(options.reclustered, 'r')
+    combined_pangenome_clusters_First = OrderedDict()
+    combined_pangenome_clusters_First_sequences = OrderedDict()
+    combined_pangenome_clusters_Second = OrderedDict()
+    combined_pangenome_clusters_Second_sequences = OrderedDict()
+    combined_pangenome_clusters_First_Second_clustered = OrderedDict()
+
+    not_Second_only_cluster_ids = []
+    already_seen_PEP = []
+    Combined_clusters = OrderedDict()
+    Combined_reps = OrderedDict()
+    first = True
+    for line in Second_in:
+        rep, child = line.strip().split(separator)
+        child_taxa = child.split(splitter)[0]  # Extracting the genome identifier from the child sequence
+
+        if first == True:
+            Combined_clusters.update({cluster_id: []})
+            combined_pangenome_clusters_First.update({cluster_id: []})
+            combined_pangenome_clusters_First_sequences.update({cluster_id: []})
+            combined_pangenome_clusters_Second.update({cluster_id: []})
+            combined_pangenome_clusters_Second_sequences.update({cluster_id: []})
+            Combined_reps.update({rep: 0})
+            first = False
+
+        if first == False:
+            if rep != last_rep and last_rep != '':
+                cluster_size = len(Combined_clusters[cluster_id])
+                Combined_reps.update({rep: cluster_size})
+                for pep in combined_pangenome_clusters_First_sequences[cluster_id]:
+                    if pep != []:
+                        if pep in already_seen_PEP:
+                            continue
+                        else:
+                            already_seen_PEP.append(pep)
+                if len(combined_pangenome_clusters_Second_sequences[cluster_id]) > 0 and len(combined_pangenome_clusters_First_sequences[cluster_id]) > 0:
+                    if len(combined_pangenome_clusters_First_sequences[cluster_id]) > 1:  # If we have clustered >1 PEP family, we need to record 1 as key and all others are val
+                        all_but_first = combined_pangenome_clusters_First_sequences[cluster_id][1:]
+                        storfs_clustered = combined_pangenome_clusters_Second_sequences[cluster_id]
+                        VALUE = all_but_first + storfs_clustered
+                    else:
+                        VALUE = combined_pangenome_clusters_Second_sequences[cluster_id]
+                    KEY = combined_pangenome_clusters_First_sequences[cluster_id][0]
+                    combined_pangenome_clusters_First_Second_clustered.update({KEY: VALUE})
+
+                cluster_id += 1
+                Combined_clusters.update({cluster_id: []})
+                combined_pangenome_clusters_First.update({cluster_id: []})
+                combined_pangenome_clusters_First_sequences.update({cluster_id: []})
+                combined_pangenome_clusters_Second.update({cluster_id: []})
+                combined_pangenome_clusters_Second_sequences.update({cluster_id: []})
+                Combined_reps.update({rep: 0})
+
+        Combined_clusters[cluster_id].append(child)
+        if options.sequence_tag in line:
+            if child_taxa not in combined_pangenome_clusters_Second[cluster_id]:
+                combined_pangenome_clusters_Second[cluster_id].append(child_taxa)
+            combined_pangenome_clusters_Second_sequences[cluster_id].append(child)
+        else:
+            if cluster_id not in not_Second_only_cluster_ids:
+                not_Second_only_cluster_ids.append(cluster_id)  # Tell us which StORF_Reporter clustered are unmatched to a PEP
+            if child_taxa not in combined_pangenome_clusters_First[cluster_id]:
+                combined_pangenome_clusters_First[cluster_id].append(child_taxa)
+            combined_pangenome_clusters_First_sequences[cluster_id].append(child)
+
+        last_rep = rep
+
+    return combined_pangenome_clusters_First_Second_clustered,not_Second_only_cluster_ids, combined_pangenome_clusters_Second

PyamilySeq/utils.py

@@ -3,6 +3,8 @@ import shutil
 import os
 import glob
 import collections
+from tempfile import NamedTemporaryFile
+import sys
 
 
 def is_tool_installed(tool_name):
@@ -30,7 +32,76 @@ def fix_path(path):
     return fixed_path
 
 
-
+def wrap_sequence(sequence, width=60):
+    wrapped_sequence = []
+    for i in range(0, len(sequence), width):
+        wrapped_sequence.append(sequence[i:i + width])
+    return "\n".join(wrapped_sequence)
+
+
+def read_fasta(fasta_file):
+    sequences = {}
+    current_sequence = None
+    with open(fasta_file, 'r') as file:
+        for line in file:
+            line = line.strip()
+            if not line:
+                continue  # Skip empty lines
+            if line.startswith('>'):
+                current_sequence = line[1:]  # Remove '>' character
+                sequences[current_sequence] = ''
+            else:
+                sequences[current_sequence] += line
+    return sequences
+
+
+def reorder_dict_by_keys(original_dict, sorted_keys):
+    return {k: original_dict[k] for k in sorted_keys}
+def custom_sort_key(k, dict1, dict2):
+    return (len(dict1[k]), len(dict2[k]))
+
+def sort_keys_by_values(dict1, dict2):
+    sorted_keys = sorted(dict1.keys(), key=lambda k: custom_sort_key(k, dict1, dict2), reverse=True)
+    return sorted_keys
+
+def select_longest_gene(sequences):
+    """Select the longest sequence for each genome."""
+    longest_sequences = {}
+    for seq_id, sequence in sequences.items():
+        genome = seq_id.split('|')[0]  # Assuming genome name can be derived from the sequence ID
+        if genome not in longest_sequences or len(sequence) > len(longest_sequences[genome][1]):
+            longest_sequences[genome] = (seq_id, sequence)
+    return longest_sequences
+
+
+def run_mafft_on_sequences(options, sequences, output_file):
+    print("Conducting MAFFT alignment.")
+    """Run mafft on the given sequences and write to output file."""
+    # Create a temporary input file for mafft
+    with NamedTemporaryFile('w', delete=False) as temp_input_file:
+        for header, sequence in sequences.items():
+            temp_input_file.write(f">{header}\n{sequence}\n")
+        temp_input_file_path = temp_input_file.name
+
+    # Run mafft
+    try:
+        with open(output_file, 'w') as output_f:
+            if options.verbose == True:
+                subprocess.run(
+                    ['mafft', '--auto', temp_input_file_path],
+                    stdout=output_f,
+                    stderr=sys.stderr,
+                    check=True
+                )
+            else:
+                subprocess.run(
+                    ['mafft', '--auto', temp_input_file_path],
+                    stdout=output_f,
+                    stderr=subprocess.DEVNULL,  # Suppress stderr
+                    check=True
+                )
+    finally:
+        os.remove(temp_input_file_path)  # Clean up the temporary file
 
 
 
@@ -45,6 +116,7 @@ def read_separate_files(input_dir, name_split, combined_out):
 
             gff_features = []
             with open(gff_file, 'r') as file:
+                seen_seq_ids = collections.defaultdict(int)
                 lines = file.readlines()
                 for line in lines:
                     line_data = line.split('\t')
@@ -54,6 +126,11 @@ def read_separate_files(input_dir, name_split, combined_out):
                             feature = line_data[2]
                             strand = line_data[6]
                             start, end = int(line_data[3]), int(line_data[4])
+                            if seq_id in seen_seq_ids:
+                                seq_id += '_' + str(seen_seq_ids[seq_id])
+                                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)
@@ -93,6 +170,7 @@ def read_combined_files(input_dir, name_split, combined_out):
             fasta_dict = collections.defaultdict(str)
             gff_features = []
             with open(gff_file, 'r') as file:
+                seen_seq_ids = collections.defaultdict(int)
                 lines = file.readlines()
                 fasta_section = False
                 for line in lines:
@@ -114,6 +192,11 @@ def read_combined_files(input_dir, name_split, combined_out):
                                 strand = line_data[6]
                                 start, end = int(line_data[3]), int(line_data[4])
                                 seq_id = line_data[8].split('ID=')[1].split(';')[0]
+                                if seq_id in seen_seq_ids:
+                                    seq_id += '_' + str(seen_seq_ids[seq_id])
+                                    seen_seq_ids[seq_id] + 1
+                                else:
+                                    seen_seq_ids[seq_id] = 1
                                 gff_features.append((contig, start, end, strand, feature,  seq_id))
 
                 for contig, fasta in fasta_dict.items():

{PyamilySeq-0.5.1.dist-info → PyamilySeq-0.6.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: PyamilySeq
-Version: 0.5.1
+Version: 0.6.0
 Summary: PyamilySeq - A a tool to look for sequence-based gene families identified by clustering methods such as CD-HIT, DIAMOND, BLAST or MMseqs2.
 Home-page: https://github.com/NickJD/PyamilySeq
 Author: Nicholas Dimonaco
@@ -34,80 +34,83 @@ PyamilySeq requires Python 3.6 or higher. Install using pip:
 pip install PyamilySeq
 ```
 
+### Examples: Below are two examples of running PyamilySeq in its two main modes.
+#### 'Full Mode': Will conduct clustering of sequences as part of PyamilySeq run
+```bash 
+PyamilySeq -run_mode Full -group_mode Species -output_dir ../../test_data/testing -input_type combined -input_dir .../test_data/genomes -name_split _combined.gff3 -pid 0.99 -len_diff 0.99 -clust_tool CD-HIT -gpa True -con True -w 99 -verbose True
+```
+#### 'Partial Mode': Will take the output of a sequence clustering
+```bash
+PyamilySeq -run_mode Partial -group_mode Species -output_dir .../test_data/testing -cluster_file .../test_data/CD-HIT/combined_Ensmbl_pep_CD_90_60.clstr -clust_tool CD-HIT -original_fasta .../test_data/combined_Ensmbl_cds.fasta -gpa True -con True -w 99 -verbose True
+```
+
+```bash
+Calculating Groups
+Gene Groups:
+first_core_99: 3103
+first_core_95: 0
+first_core_15: 3217
+first_core_0: 4808
+Total Number of Gene Groups (Including Singletons): 11128
+```
+
+
 ## Usage - Menu
 ```
-usage: PyamilySeq.py [-h] -run_mode {Full,Partial} -group_mode {Species,Genus}
-                     -clust_tool {CD-HIT} -output_dir OUTPUT_DIR
-                     [-input_type {separate,combined}] [-input_dir INPUT_DIR]
-                     [-name_split NAME_SPLIT] [-pid PIDENT]
-                     [-len_diff LEN_DIFF] [-cluster_file CLUSTER_FILE]
-                     [-reclustered RECLUSTERED] [-seq_tag SEQUENCE_TAG]
-                     [-groups CORE_GROUPS] [-w WRITE_FAMILIES] [-con CON_CORE]
-                     [-original_fasta ORIGINAL_FASTA]
-                     [-gpa GENE_PRESENCE_ABSENCE_OUT] [-verbose {True,False}]
-                     [-v]
-
-PyamilySeq v0.5.1: PyamilySeq Run Parameters.
+usage: PyamilySeq.py [-h] -run_mode {Full,Partial} -group_mode {Species,Genus} -clust_tool {CD-HIT} -output_dir OUTPUT_DIR [-input_type {separate,combined}] [-input_dir INPUT_DIR] [-name_split NAME_SPLIT]
+                     [-pid PIDENT] [-len_diff LEN_DIFF] [-mem CLUSTERING_MEMORY] [-t CLUSTERING_THREADS] [-cluster_file CLUSTER_FILE] [-reclustered RECLUSTERED] [-seq_tag SEQUENCE_TAG]
+                     [-core_groups CORE_GROUPS] [-genus_groups GENUS_GROUPS] [-w WRITE_FAMILIES] [-con CON_CORE] [-original_fasta ORIGINAL_FASTA] [-gpa GENE_PRESENCE_ABSENCE_OUT] [-verbose {True,False}] [-v]
+
+PyamilySeq v0.6.0: PyamilySeq Run Parameters.
 
 options:
   -h, --help            show this help message and exit
 
 Required Arguments:
   -run_mode {Full,Partial}
-                        Run Mode: Should PyamilySeq be run in "Full" or
-                        "Partial" mode?
-  -group_mode {Species}
-                        Group Mode: Should PyamilySeq be run in "Species" or
-                        "Genus" mode?  - Genus mode not currently functioning
-  -clust_tool {CD-HIT}  Clustering tool to use: CD-HIT, DIAMOND, BLAST or
-                        MMseqs2.
+                        Run Mode: Should PyamilySeq be run in "Full" or "Partial" mode?
+  -group_mode {Species,Genus}
+                        Group Mode: Should PyamilySeq be run in "Species" or "Genus" mode?
+  -clust_tool {CD-HIT}  Clustering tool to use: CD-HIT, DIAMOND, BLAST or MMseqs2.
   -output_dir OUTPUT_DIR
                         Directory for all output files.
 
 Full-Mode Arguments - Required when "-run_mode Full" is used:
   -input_type {separate,combined}
-                        Type of input files: 'separate' for separate FASTA and
-                        GFF files, 'combined' for GFF files with embedded
-                        FASTA sequences.
+                        Type of input files: 'separate' for separate FASTA and GFF files, 'combined' for GFF files with embedded FASTA sequences.
   -input_dir INPUT_DIR  Directory containing GFF/FASTA files.
   -name_split NAME_SPLIT
-                        substring used to split the filename and extract the
-                        genome name ('_combined.gff3' or '.gff').
+                        substring used to split the filename and extract the genome name ('_combined.gff3' or '.gff').
   -pid PIDENT           Default 0.95: Pident threshold for clustering.
-  -len_diff LEN_DIFF    Default 0.80: Minimum length difference between
-                        clustered sequences - (-s) threshold for CD-HIT
-                        clustering.
+  -len_diff LEN_DIFF    Default 0.80: Minimum length difference between clustered sequences - (-s) threshold for CD-HIT clustering.
+
+Clustering Runtime Arguments - Optional when "-run_mode Full" is used:
+  -mem CLUSTERING_MEMORY
+                        Default 4000: Memory to be allocated for clustering (in MBs).
+  -t CLUSTERING_THREADS
+                        Default 4: Threads to be allocated for clustering.
 
 Partial-Mode Arguments - Required when "-run_mode Partial" is used:
   -cluster_file CLUSTER_FILE
-                        Clustering output file containing CD-HIT, TSV or CSV
-                        Edge List
+                        Clustering output file containing CD-HIT, TSV or CSV Edge List
 
 Grouping Arguments - Use to fine-tune grouping of genes after clustering:
   -reclustered RECLUSTERED
-                        Clustering output file from secondary round of
-                        clustering
+                        Currently only works on Partial Mode: Clustering output file from secondary round of clustering.
   -seq_tag SEQUENCE_TAG
-                        Default - "StORF": Unique identifier to be used to
-                        distinguish the second of two rounds of clustered
-                        sequences
-  -groups CORE_GROUPS   Default - ('99,95,15'): Gene family groups to use
+                        Default - "StORF": Unique identifier to be used to distinguish the second of two rounds of clustered sequences
+  -core_groups CORE_GROUPS
+                        Default - ('99,95,15'): Gene family groups to use for "Species" mode
+  -genus_groups GENUS_GROUPS
+                        Default - ('1,2,3,4,5,6'): Gene family groups to use for "Genus" mode
 
 Output Parameters:
-  -w WRITE_FAMILIES     Default - No output: Output sequences of identified
-                        families (provide levels at which to output "-w 99,95"
-                        - Must provide FASTA file with -fasta
-  -con CON_CORE         Default - No output: Output aligned and concatinated
-                        sequences of identified families - used for MSA
-                        (provide levels at which to output "-w 99,95" - Must
-                        provide FASTA file with -fasta
+  -w WRITE_FAMILIES     Default - No output: Output sequences of identified families (provide levels at which to output "-w 99,95" - Must provide FASTA file with -fasta
+  -con CON_CORE         Default - No output: Output aligned and concatinated sequences of identified families - used for MSA (provide levels at which to output "-w 99,95" - Must provide FASTA file with -fasta
   -original_fasta ORIGINAL_FASTA
-                        FASTA file to use in conjunction with "-w" or "-con"
-                        when running in Partial Mode.
+                        FASTA file to use in conjunction with "-w" or "-con" when running in Partial Mode.
   -gpa GENE_PRESENCE_ABSENCE_OUT
-                        Default - False: If selected, a Roary formatted
-                        gene_presence_absence.csv will be created - Required
-                        for Coinfinder and other downstream tools
+                        Default - False: If selected, a Roary formatted gene_presence_absence.csv will be created - Required for Coinfinder and other downstream tools
 
 Misc:
   -verbose {True,False}
@@ -116,25 +119,6 @@ Misc:
 
 ```
 
-### Examples: Below are two examples of running PyamilySeq in its two main modes.
-#### 'Full Mode': Will conduct clustering of sequences as part of PyamilySeq run
-```bash 
-PyamilySeq -run_mode Full -group_mode Species -output_dir ../../test_data/testing -input_type combined -input_dir .../test_data/genomes -name_split _combined.gff3 -pid 0.99 -len_diff 0.99 -clust_tool CD-HIT -gpa True -con True -w 99 -verbose True
-```
-#### 'Partial Mode': Will take the output of a sequence clustering
-```bash
-PyamilySeq -run_mode Partial -group_mode Species -output_dir .../test_data/testing -cluster_file .../test_data/CD-HIT/combined_Ensmbl_pep_CD_90_60.clstr -clust_tool CD-HIT -original_fasta .../test_data/combined_Ensmbl_cds.fasta -gpa True -con True -w 99 -verbose True
-```
-
-```bash
-Calculating Groups
-Gene Groups:
-first_core_99: 3103
-first_core_95: 0
-first_core_15: 3217
-first_core_0: 4808
-Total Number of Gene Groups (Including Singletons): 11128
-```
 
 ## 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:
@@ -145,7 +129,7 @@ Seq-Combiner -input_dir .../test_data/genomes -name_split _combined.gff3 -output
 ```bash
 usage: Seq_Combiner.py [-h] -input_dir INPUT_DIR -input_type {separate,combined} -name_split NAME_SPLIT -output_dir OUTPUT_DIR -output_name OUTPUT_FILE
 
-Seq-Combiner v0.5.1: Seq-Combiner Run Parameters.
+Seq-Combiner v0.6.0: Seq-Combiner Run Parameters.
 
 options:
   -h, --help            show this help message and exit

PyamilySeq-0.6.0.dist-info/RECORD

@@ -0,0 +1,15 @@
+PyamilySeq/CD-Hit_StORF-Reporter_Cross-Genera_Builder.py,sha256=UzQ5iOKCNfurxmj1pnkowF11YfWBO5vnBCKxQK6goB8,26538
+PyamilySeq/Constants.py,sha256=LNbn_6kugNL3dl4HFDkq8ZC4cizcXy6MWRz3hP4QJGI,31
+PyamilySeq/PyamilySeq.py,sha256=_Lwk_NYUmOMzoJsCRpiMIx5CFuKYxnYBjZ6NhTdBiCE,13026
+PyamilySeq/PyamilySeq_Genus.py,sha256=dKSM4ZGrOzZPIMkDveyiWD4WqBeYjwAP3g1diR7-0rE,12107
+PyamilySeq/PyamilySeq_Species.py,sha256=urDUDkTu4-5L5rPlaWN2kicXOalqDDVK9lLOrOMdDUU,13219
+PyamilySeq/Seq_Combiner.py,sha256=bHEIR-MZODSGm8n69ZIN-XzEoct5WZ1kH5Xa6uKCu4Y,1972
+PyamilySeq/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+PyamilySeq/clusterings.py,sha256=Xa0YTvfmI0A8sPdaNHw3j2PVVvGR0JlrebUb_vP2kt8,16183
+PyamilySeq/utils.py,sha256=bC1fpJ8SS14oB4EHvsgZbR0ttn83BiBttlMYeD6IS3g,9863
+PyamilySeq-0.6.0.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+PyamilySeq-0.6.0.dist-info/METADATA,sha256=4O545LBKwlxMTj4q8kCth-IEYJW8Vz4YhaaJ5R3P9EE,7706
+PyamilySeq-0.6.0.dist-info/WHEEL,sha256=Wyh-_nZ0DJYolHNn1_hMa4lM7uDedD_RGVwbmTjyItk,91
+PyamilySeq-0.6.0.dist-info/entry_points.txt,sha256=QtXD1tmnLvRAkIpGWZgXm1lfLH8GGeCwxmgoHZaTp98,102
+PyamilySeq-0.6.0.dist-info/top_level.txt,sha256=J6JhugUQTq4rq96yibAlQu3o4KCM9WuYfqr3w1r119M,11
+PyamilySeq-0.6.0.dist-info/RECORD,,

PyamilySeq-0.5.1.dist-info/RECORD

@@ -1,14 +0,0 @@
-PyamilySeq/CD-Hit_StORF-Reporter_Cross-Genera_Builder.py,sha256=UzQ5iOKCNfurxmj1pnkowF11YfWBO5vnBCKxQK6goB8,26538
-PyamilySeq/Constants.py,sha256=mmMeeD5svOnN-Kn7LUd16DY8rWTcU2WajldKlNkuuWY,31
-PyamilySeq/PyamilySeq.py,sha256=7pyBujHmdYR6DVNlKQ2BqX9-AylTpNexrcWN-rtyauk,11275
-PyamilySeq/PyamilySeq_Genus.py,sha256=JpLLu3QaahUHBe7E80xVHtFORGuyeUMOt9eiLN5uazc,31286
-PyamilySeq/PyamilySeq_Species.py,sha256=6LHEdp6Vndoder8dlVSuyUKHdCbo5Rbxea1rnncrceY,35172
-PyamilySeq/Seq_Combiner.py,sha256=bHEIR-MZODSGm8n69ZIN-XzEoct5WZ1kH5Xa6uKCu4Y,1972
-PyamilySeq/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-PyamilySeq/utils.py,sha256=KhEnwzgVZyUu_Q92ukRPUrVD2505xSg9NY6e75nUmPQ,6487
-PyamilySeq-0.5.1.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-PyamilySeq-0.5.1.dist-info/METADATA,sha256=FJRNy2WTazUXemY4jHYPmpJEdq5JQMebhfeicagLTCA,7792
-PyamilySeq-0.5.1.dist-info/WHEEL,sha256=Wyh-_nZ0DJYolHNn1_hMa4lM7uDedD_RGVwbmTjyItk,91
-PyamilySeq-0.5.1.dist-info/entry_points.txt,sha256=QtXD1tmnLvRAkIpGWZgXm1lfLH8GGeCwxmgoHZaTp98,102
-PyamilySeq-0.5.1.dist-info/top_level.txt,sha256=J6JhugUQTq4rq96yibAlQu3o4KCM9WuYfqr3w1r119M,11
-PyamilySeq-0.5.1.dist-info/RECORD,,