PyamilySeq 1.1.1__tar.gz → 1.2.0__tar.gz

{pyamilyseq-1.1.1 → pyamilyseq-1.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: PyamilySeq
-Version: 1.1.1
+Version: 1.2.0
 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
@@ -13,6 +13,7 @@ Requires-Python: >=3.6
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: levenshtein
+Dynamic: license-file
 
 # PyamilySeq 
 **PyamilySeq** is a Python tool for clustering gene sequences into groups based on sequence similarity identified by tools such as CD-HIT, BLAST, DIAMOND or MMseqs2.
@@ -45,7 +46,7 @@ To update to the newest version add '-U' to end of the pip install command.
 ```commandline
 usage: PyamilySeq.py [-h] {Full,Partial} ...
 
-PyamilySeq v1.1.1: A tool for gene clustering and analysis.
+PyamilySeq v1.2.0: A tool for gene clustering and analysis.
 
 positional arguments:
   {Full,Partial}  Choose a mode: 'Full' or 'Partial'.
@@ -75,7 +76,7 @@ Escherichia_coli_110957|ENSB_TIZS9kbTvShDvyX	Escherichia_coli_110957|ENSB_TIZS9k
 ```
 ### Example output:
 ```
-Running PyamilySeq v1.1.1
+Running PyamilySeq v1.2.0
 Calculating Groups
 Number of Genomes: 10
 Gene Groups
@@ -220,7 +221,7 @@ 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 v1.1.1: Seq-Combiner - A tool to extract sequences from GFF/FASTA files and prepare them for PyamilySeq.
+PyamilySeq v1.2.0: 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
@@ -263,7 +264,7 @@ usage: Group_Splitter.py [-h] -input_fasta INPUT_FASTA -sequence_type {AA,DNA}
                          [-M CLUSTERING_MEMORY] [-no_delete_temp_files]
                          [-verbose] [-v]
 
-PyamilySeq v1.1.1: Group-Splitter - A tool to split multi-copy gene groups
+PyamilySeq v1.2.0: Group-Splitter - A tool to split multi-copy gene groups
 identified by PyamilySeq.
 
 options:
@@ -316,7 +317,7 @@ 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 v1.1.1: Cluster-Summary - A tool to summarise CD-HIT clustering files.
+PyamilySeq v1.2.0: Cluster-Summary - A tool to summarise CD-HIT clustering files.
 
 options:
   -h, --help            show this help message and exit

{pyamilyseq-1.1.1 → pyamilyseq-1.2.0}/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 v1.1.1: A tool for gene clustering and analysis.
+PyamilySeq v1.2.0: 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 v1.1.1
+Running PyamilySeq v1.2.0
 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 v1.1.1: Seq-Combiner - A tool to extract sequences from GFF/FASTA files and prepare them for PyamilySeq.
+PyamilySeq v1.2.0: 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
@@ -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 v1.1.1: Group-Splitter - A tool to split multi-copy gene groups
+PyamilySeq v1.2.0: 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 v1.1.1: Cluster-Summary - A tool to summarise CD-HIT clustering files.
+PyamilySeq v1.2.0: Cluster-Summary - A tool to summarise CD-HIT clustering files.
 
 options:
   -h, --help            show this help message and exit

{pyamilyseq-1.1.1 → pyamilyseq-1.2.0}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = PyamilySeq
-version = v1.1.1
+version = v1.2.0
 license_files = LICENSE
 author = Nicholas Dimonaco
 author_email = nicholas@dimonaco.co.uk
@@ -37,10 +37,16 @@ console_scripts =
 	group-splitter = PyamilySeq.Group_Splitter:main
 	Cluster-Summary = PyamilySeq.Cluster_Summary:main
 	cluster-summary = PyamilySeq.Cluster_Summary:main
+	Cluster-Extractor = PyamilySeq.Cluster_Extractor:main
+	cluster-extractor = PyamilySeq.Cluster_Extractor:main
 	Seq-Finder = PyamilySeq.Seq_Finder:main
 	seq-finder = PyamilySeq.Seq_Finder:main
 	Seq-Extractor = PyamilySeq.Seq_Extractor:main
 	seq-extractor = PyamilySeq.Seq_Extractor:main
+	
+	compute-singletrees-rf = aux_tools.RF.Compute_SingleTree_RFs:main
+	compare-rf = aux_tools.RF.compare_RF:main
+	compare-contree-singletrees = aux_tools.RF.compare_contree_singletrees:main
 
 [egg_info]
 tag_build = 

{pyamilyseq-1.1.1 → pyamilyseq-1.2.0}/src/PyamilySeq/PyamilySeq.py

@@ -1,5 +1,5 @@
 import argparse
-
+#from config import config_params
 
 try:
     from .PyamilySeq_Species import cluster as species_cluster
@@ -67,7 +67,7 @@ def main():
     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,
+    full_parser.add_argument("-fast_mode", action="store_true",
                              help="Enable fast mode for CD-HIT (not recommended) - CD-HIT parameter '-g'.")
 
 
@@ -95,14 +95,14 @@ def main():
         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("-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 gene groups as a single FASTA file (e.g., '99,95'). Triggers writing individual groups.")
+        subparser.add_argument("-write_individual_groups", action="store_true", dest="write_individual_groups",
                                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 (those in 99-100% of genomes).")
-        subparser.add_argument("-align_aa", action="store_true", required=False,
+        subparser.add_argument("-align", action="store_true", dest="align_core",
+                               help="Align and concatenate sequences for 'core' groups (those in 99-100%% of genomes).")
+        subparser.add_argument("-align_aa", action="store_true",
                                help="Align sequences as amino acids.")
-        subparser.add_argument("-no_gpa", action="store_false", dest="gene_presence_absence_out", required=False,
+        subparser.add_argument("-no_gpa", action="store_false", dest="gene_presence_absence_out",
                                help="Skip creation of gene_presence_absence.csv.")
         subparser.add_argument("-M", type=int, default=4000, dest="mem", required=False,
                                  help="Memory allocation for clustering (MB) - CD-HIT parameter '-M'.")
@@ -110,13 +110,15 @@ def main():
                                  help="Number of threads for clustering/alignment - CD-HIT parameter '-T' | MAFFT parameter '--thread'.")
 
         # Miscellaneous Arguments
-        subparser.add_argument("-verbose", action="store_true", required=False,
+        subparser.add_argument("-verbose", action="store_true",
                             help="Print verbose output.")
         subparser.add_argument("-v", "--version", action="version",
-                            version=f"PyamilySeq {PyamilySeq_Version}: Exiting.", help="Print version number and exit.")
+                            version=f"PyamilySeq {PyamilySeq_Version}: Exiting.")
 
     # Parse Arguments
     options = parser.parse_args()
+    ## Configuration
+
 
     if options.write_groups != None and options.write_individual_groups == False:
         options.write_individual_groups = True
@@ -147,7 +149,7 @@ def main():
         if options.align_core:
             options.write_individual_groups = True
             if options.write_groups == None:
-                sys.exit('Must provide "-w" to output gene groups before alignment "-a" can be done.')
+                sys.exit('Must provide "-write_groups" to output gene groups before alignment "-align" can be done.')
     elif options.run_mode == 'Partial':
         required_partial_mode = [options.cluster_file, options.original_fasta]
         if all(required_partial_mode):

{pyamilyseq-1.1.1 → pyamilyseq-1.2.0}/src/PyamilySeq/PyamilySeq_Genus.py

@@ -17,7 +17,8 @@ def gene_presence_absence_output(options, genus_dict, pangenome_clusters_First_s
     #in_name = options.clusters.split('.')[0].split('/')[-1]
     gpa_outfile = os.path.join(output_dir, 'gene_presence_absence.csv')
     gpa_outfile = open(gpa_outfile, 'w')
-    gpa_outfile.write('"Gene","Non-unique Gene name","Annotation","No. isolates","No. sequences","Avg sequences per isolate","Genome Fragment","Order within Fragment","'
+    genus_dict = OrderedDict(sorted(genus_dict.items()))
+    gpa_outfile.write('"Gene","Non-unique Gene name","Annotation","No. isolates","No. sequences","Avg sequences per isolate","Genome Fragment","Order within Fragment",'
                      '"Accessory Fragment","Accessory Order with Fragment","QC","Min group size nuc","Max group size nuc","Avg group size nuc","')
     gpa_outfile.write('","'.join(genus_dict.keys()))
     gpa_outfile.write('"\n')

{pyamilyseq-1.1.1 → pyamilyseq-1.2.0}/src/PyamilySeq/PyamilySeq_Species.py

@@ -15,14 +15,15 @@ def gene_presence_absence_output(options, genome_dict, pangenome_clusters_First_
     #in_name = options.clusters.split('.')[0].split('/')[-1]
     gpa_outfile = os.path.join(output_dir, 'gene_presence_absence.csv')
     gpa_outfile = open(gpa_outfile, 'w')
-    gpa_outfile.write('"Gene","Non-unique Gene name","Annotation","No. isolates","No. sequences","Avg sequences per isolate","Genome Fragment","Order within Fragment","'
+    genome_dict = OrderedDict(sorted(genome_dict.items()))
+    gpa_outfile.write('"Gene","Non-unique Gene name","Annotation","No. isolates","No. sequences","Avg sequences per isolate","Genome Fragment","Order within Fragment",'
                      '"Accessory Fragment","Accessory Order with Fragment","QC","Min group size nuc","Max group size nuc","Avg group size nuc","')
     gpa_outfile.write('","'.join(genome_dict.keys()))
     gpa_outfile.write('"\n')
     for cluster, sequences in pangenome_clusters_First_sequences_sorted.items():
         average_sequences_per_genome = len(sequences) / len(pangenome_clusters_First_sorted[cluster])
         gpa_outfile.write('"group_'+str(cluster)+'","","","'+str(len(pangenome_clusters_First_sorted[cluster]))+'","'+str(len(sequences))+'","'+str(average_sequences_per_genome)+
-                         '","","","","","","","","",""')
+                         '","","","","","","","",""')
 
 
         for genome in genome_dict.keys():

{pyamilyseq-1.1.1 → pyamilyseq-1.2.0}/src/PyamilySeq/Seq_Combiner.py

@@ -59,7 +59,7 @@ def main():
         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
+        exit(1)
 
     output_path = os.path.abspath(options.output_dir)
     if not os.path.exists(output_path):
@@ -77,7 +77,7 @@ def main():
     elif options.input_type == 'combined':
         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)
+        read_fasta_files(options.input_dir, options.name_split_fasta, combined_out_file, options.translate, True)
 
 if __name__ == "__main__":
     main()

{pyamilyseq-1.1.1 → pyamilyseq-1.2.0}/src/PyamilySeq/Seq_Extractor.py

@@ -9,8 +9,13 @@ def find_gene_ids_in_csv(csv_file, group_name):
             cells = line.strip().split(',')
             if cells[0].replace('"','') == group_name:
                 # Collect gene IDs from column 14 onward
+                # for cell in cells[14:]:
+                #     gene_ids.extend(cell.strip().replace('"','').split())  # Splitting by spaces if there are multiple IDs in a cell                break
                 for cell in cells[14:]:
-                    gene_ids.extend(cell.strip().replace('"','').split())  # Splitting by spaces if there are multiple IDs in a cell                break
+                    for gene in cell.strip().replace('"', '').split(';'):
+                        if gene:
+                            gene_ids.append(gene)
+
     return gene_ids
 
 def extract_sequences(fasta_file, gene_ids):

pyamilyseq-1.2.0/src/PyamilySeq/constants.py

@@ -0,0 +1,2 @@
+PyamilySeq_Version = 'v1.2.0'
+

{pyamilyseq-1.1.1 → pyamilyseq-1.2.0}/src/PyamilySeq/utils.py

@@ -14,7 +14,7 @@ levenshtein_distance_cal = None
 # Check for Levenshtein library once
 try:
     import Levenshtein as LV
-    # Assign the optimized function
+    # Assign the optimised function
     def levenshtein_distance_calc(seq1, seq2):
         return LV.distance(seq1, seq2)
 except (ModuleNotFoundError, ImportError):

{pyamilyseq-1.1.1 → pyamilyseq-1.2.0}/src/PyamilySeq.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: PyamilySeq
-Version: 1.1.1
+Version: 1.2.0
 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
@@ -13,6 +13,7 @@ Requires-Python: >=3.6
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: levenshtein
+Dynamic: license-file
 
 # PyamilySeq 
 **PyamilySeq** is a Python tool for clustering gene sequences into groups based on sequence similarity identified by tools such as CD-HIT, BLAST, DIAMOND or MMseqs2.
@@ -45,7 +46,7 @@ To update to the newest version add '-U' to end of the pip install command.
 ```commandline
 usage: PyamilySeq.py [-h] {Full,Partial} ...
 
-PyamilySeq v1.1.1: A tool for gene clustering and analysis.
+PyamilySeq v1.2.0: A tool for gene clustering and analysis.
 
 positional arguments:
   {Full,Partial}  Choose a mode: 'Full' or 'Partial'.
@@ -75,7 +76,7 @@ Escherichia_coli_110957|ENSB_TIZS9kbTvShDvyX	Escherichia_coli_110957|ENSB_TIZS9k
 ```
 ### Example output:
 ```
-Running PyamilySeq v1.1.1
+Running PyamilySeq v1.2.0
 Calculating Groups
 Number of Genomes: 10
 Gene Groups
@@ -220,7 +221,7 @@ 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 v1.1.1: Seq-Combiner - A tool to extract sequences from GFF/FASTA files and prepare them for PyamilySeq.
+PyamilySeq v1.2.0: 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
@@ -263,7 +264,7 @@ usage: Group_Splitter.py [-h] -input_fasta INPUT_FASTA -sequence_type {AA,DNA}
                          [-M CLUSTERING_MEMORY] [-no_delete_temp_files]
                          [-verbose] [-v]
 
-PyamilySeq v1.1.1: Group-Splitter - A tool to split multi-copy gene groups
+PyamilySeq v1.2.0: Group-Splitter - A tool to split multi-copy gene groups
 identified by PyamilySeq.
 
 options:
@@ -316,7 +317,7 @@ 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 v1.1.1: Cluster-Summary - A tool to summarise CD-HIT clustering files.
+PyamilySeq v1.2.0: Cluster-Summary - A tool to summarise CD-HIT clustering files.
 
 options:
   -h, --help            show this help message and exit

{pyamilyseq-1.1.1 → pyamilyseq-1.2.0}/src/PyamilySeq.egg-info/SOURCES.txt

@@ -15,6 +15,7 @@ src/PyamilySeq/Seq_Extractor.py
 src/PyamilySeq/Seq_Finder.py
 src/PyamilySeq/__init__.py
 src/PyamilySeq/clusterings.py
+src/PyamilySeq/config.py
 src/PyamilySeq/constants.py
 src/PyamilySeq/utils.py
 src/PyamilySeq.egg-info/PKG-INFO

{pyamilyseq-1.1.1 → pyamilyseq-1.2.0}/src/PyamilySeq.egg-info/entry_points.txt

@@ -1,11 +1,16 @@
 [console_scripts]
+Cluster-Extractor = PyamilySeq.Cluster_Extractor: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
+cluster-extractor = PyamilySeq.Cluster_Extractor:main
 cluster-summary = PyamilySeq.Cluster_Summary:main
+compare-contree-singletrees = aux_tools.RF.compare_contree_singletrees:main
+compare-rf = aux_tools.RF.compare_RF:main
+compute-singletrees-rf = aux_tools.RF.Compute_SingleTree_RFs:main
 group-splitter = PyamilySeq.Group_Splitter:main
 pyamilyseq = PyamilySeq.PyamilySeq:main
 seq-combiner = PyamilySeq.Seq_Combiner:main

pyamilyseq-1.1.1/src/PyamilySeq/constants.py

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