PyamilySeq 1.1.2__tar.gz → 1.2.0__tar.gz

{pyamilyseq-1.1.2 → pyamilyseq-1.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: PyamilySeq
-Version: 1.1.2
+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
@@ -46,7 +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 v1.1.2: 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'.
@@ -76,7 +76,7 @@ Escherichia_coli_110957|ENSB_TIZS9kbTvShDvyX	Escherichia_coli_110957|ENSB_TIZS9k
 ```
 ### Example output:
 ```
-Running PyamilySeq v1.1.2
+Running PyamilySeq v1.2.0
 Calculating Groups
 Number of Genomes: 10
 Gene Groups
@@ -221,7 +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 v1.1.2: 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
@@ -264,7 +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 v1.1.2: 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:
@@ -317,7 +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 v1.1.2: 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-1.1.2 → 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 v1.1.2: 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 v1.1.2
+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 v1.1.2: 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 v1.1.2: 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 v1.1.2: 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-1.1.2 → pyamilyseq-1.2.0}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = PyamilySeq
-version = v1.1.2
+version = v1.2.0
 license_files = LICENSE
 author = Nicholas Dimonaco
 author_email = nicholas@dimonaco.co.uk
@@ -43,6 +43,10 @@ console_scripts =
 	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-1.1.2 → 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-1.1.2 → 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-1.1.2 → pyamilyseq-1.2.0}/src/PyamilySeq/utils.py

@@ -7,7 +7,6 @@ from tempfile import NamedTemporaryFile
 import sys
 import re
 import math
-#from config import config_params
 
 ####
 # Placeholder for the distance function
@@ -15,11 +14,10 @@ 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):
-    #if config_params.verbose == True: - Not implemented yet
     print("Levenshtein package not installed - Will fallback to slower Python implementation.")
     # Fallback implementation
     def levenshtein_distance_calc(seq1, seq2):

{pyamilyseq-1.1.2 → pyamilyseq-1.2.0}/src/PyamilySeq.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: PyamilySeq
-Version: 1.1.2
+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
@@ -46,7 +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 v1.1.2: 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'.
@@ -76,7 +76,7 @@ Escherichia_coli_110957|ENSB_TIZS9kbTvShDvyX	Escherichia_coli_110957|ENSB_TIZS9k
 ```
 ### Example output:
 ```
-Running PyamilySeq v1.1.2
+Running PyamilySeq v1.2.0
 Calculating Groups
 Number of Genomes: 10
 Gene Groups
@@ -221,7 +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 v1.1.2: 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
@@ -264,7 +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 v1.1.2: 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:
@@ -317,7 +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 v1.1.2: 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-1.1.2 → pyamilyseq-1.2.0}/src/PyamilySeq.egg-info/entry_points.txt

@@ -8,6 +8,9 @@ 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-1.1.2/src/PyamilySeq/constants.py

@@ -1,2 +0,0 @@
-PyamilySeq_Version = 'v1.1.2'
-