PyamilySeq 0.8.0__py3-none-any.whl → 0.8.1__py3-none-any.whl

PyamilySeq/Constants.py

@@ -1,2 +1,2 @@
-PyamilySeq_Version = 'v0.8.0'
+PyamilySeq_Version = 'v0.8.1'
 

PyamilySeq/Group_Splitter.py

@@ -110,11 +110,13 @@ def read_cd_hit_output(clustering_output):
                     clustered_header = clustered_info.split('>')[1].split('...')[0]
                     clustered_header = '>' + clustered_header
 
-                    if 'at +' in clustered_info:
-                        percent_identity = float(clustered_info.split('at +/')[1].strip().replace('%', ''))
+                    if 'at' in clustered_info:
+                        percent_identity = extract_identity(line)
 
-                    if '*' in line:
+                    elif '*' in line:
                         percent_identity = 100.0
+                    else:
+                        raise ValueError("Percent identity not found in the string.")
 
                     clusters[current_cluster_id].append({
                         'header': clustered_header,
@@ -130,7 +132,6 @@ def separate_groups(input_fasta, options, clustering_mode):
 
     paralog_groups = defaultdict(int)  # To track number of paralog groups
 
-
     for group_header, sequences in groups.items():
         group_name = group_header.split('|')[0]  # Get the group part (e.g., '>Group_n')
 
@@ -149,11 +150,12 @@ def separate_groups(input_fasta, options, clustering_mode):
 
         group_file_name = group_name.replace('>','')
 
-        temp_fasta = f"{options.output_dir}{group_file_name}.fasta"
+        temp_fasta = f"{options.output_dir}/{group_file_name}.fasta"
         write_fasta(sequences, temp_fasta)
 
         # Run cd-hit on the individual group
         clustering_output = f"{options.output_dir}/{group_file_name}_clustering"
+
         run_cd_hit(options, temp_fasta, clustering_output, clustering_mode)
 
         # Read the clustering results to find subgroups
@@ -255,7 +257,7 @@ def separate_groups(input_fasta, options, clustering_mode):
 
                 # Determine the next subgroup for this genome
                 subgroup_id = genome_count[genome] % num_subgroups
-                new_header = f"{options.output_dir}/{group_file_name}_subgroup_{subgroup_id}|{genome}|{header.split('|')[2]}"
+                new_header = f"{group_file_name}_subgroup_{subgroup_id}|{genome}|{header.split('|')[2]}"
                 subgroup_sequences[subgroup_id].append((new_header, seq))
 
                 # Increment the count for this genome
@@ -266,6 +268,12 @@ def separate_groups(input_fasta, options, clustering_mode):
                 subgroup_file = f"{options.output_dir}/{group_file_name}_subgroup_{subgroup_id}.fasta"
                 write_fasta(seqs, subgroup_file)
 
+                # Increment subgroup ID globally for the next subgroup
+                subgroup_id += 1
+                paralog_groups[group_name] += 1  # Count this group as a paralog group
+
+
+
         # Clean up temporary fasta file if the option is set
         if options.delete_temp_files:
             if temp_fasta and os.path.exists(temp_fasta):
@@ -288,6 +296,9 @@ def main():
     required.add_argument('-input_fasta', action='store', dest='input_fasta',
                           help='Input FASTA file containing gene groups.',
                           required=True)
+    required.add_argument('-sequence_type', action='store', dest='sequence_type', default='DNA',choices=['AA', 'DNA'],
+                          help='Default - DNA: Are groups "DNA" or "AA" sequences?',
+                          required=False)
     required.add_argument('-output_dir', action='store', dest='output_dir',
                           help='Output directory.',
                           required=True)
@@ -305,8 +316,8 @@ def main():
     optional.add_argument('-percent_threshold', action='store', dest='percent_threshold', type=float, default=80,
                           help='Minimum percentage of genomes with paralogs (default: 80.0)')
     optional.add_argument('-verbose', action='store_true', dest='verbose', help='Print verbose output.')
-    optional.add_argument('-delete_temp_files', action='store_true', dest='delete_temp_files',
-                          help='Delete all temporary files after processing.')
+    optional.add_argument('-no_delete_temp_files', action='store_false', dest='delete_temp_files',
+                          help='Default: Delete all temporary files after processing.')
 
     misc = parser.add_argument_group('Misc Arguments')
     misc.add_argument('-v', action='store_true', dest='version',
@@ -325,7 +336,11 @@ def main():
     if not os.path.exists(options.output_dir):
         os.makedirs(options.output_dir)
 
-    clustering_mode = 'cd-hit-est'
+    if options.sequence_type == 'DNA':
+        clustering_mode = 'cd-hit-est'
+    else:
+        clustering_mode = 'cd-hit'
+
     separate_groups(options.input_fasta, options, clustering_mode)
 
     print("Done")

PyamilySeq/PyamilySeq.py

@@ -27,7 +27,7 @@ def run_cd_hit(options, input_file, clustering_output, clustering_mode):
         '-o', clustering_output,
         '-c', str(options.pident),
         '-s', str(options.len_diff),
-        '-T', str(options.clustering_threads),
+        '-T', str(options.threads),
         '-M', str(options.clustering_memory),
         '-d', "0",
         '-sc', "1",
@@ -84,8 +84,8 @@ def main():
     clustering_args.add_argument("-mem", action="store", dest="clustering_memory", type=int, default=4000,
                           help="Default 4000: Memory to be allocated for clustering (in MBs).",
                           required=False)
-    clustering_args.add_argument("-t", action="store", dest="clustering_threads", type=int, default=4,
-                          help="Default 4: Threads to be allocated for clustering.",
+    clustering_args.add_argument("-t", action="store", dest="threads", type=int, default=8,
+                          help="Default 8: Threads to be allocated for clustering and/or alignment.",
                           required=False)
 
     ###Partial-Mode Arguments
@@ -130,8 +130,9 @@ def main():
 
     ### Misc Arguments
     misc = parser.add_argument_group('Misc')
-    misc.add_argument('-verbose', action='store_true', dest='verbose', default=None,                        help='Default - False: Print out runtime messages',
-                        required = False)
+    misc.add_argument('-verbose', action='store_true', dest='verbose', default=None,
+                      help='Default - False: Print out runtime messages',
+                      required = False)
     misc.add_argument('-v', action='store_true', dest='version',
                         help='Default - False: Print out version number and exit',
                         required=False)
@@ -254,6 +255,7 @@ def main():
                 self.output_dir = options.output_dir
                 self.gene_presence_absence_out = options.gene_presence_absence_out
                 self.write_groups = options.write_groups
+                self.threads = options.threads
                 self.align_core = options.align_core
                 self.fasta = combined_out_file
                 self.verbose = options.verbose
@@ -272,6 +274,7 @@ def main():
                 self.output_dir = options.output_dir
                 self.gene_presence_absence_out = options.gene_presence_absence_out
                 self.write_groups = options.write_groups
+                self.threads = options.threads
                 self.align_core = options.align_core
                 self.fasta = options.original_fasta
                 self.verbose = options.verbose

PyamilySeq/utils.py

@@ -6,6 +6,7 @@ import collections
 from tempfile import NamedTemporaryFile
 import sys
 from line_profiler_pycharm import profile
+import re
 
 
 ################### We are currently fixed using Table 11
@@ -110,12 +111,23 @@ def reverse_complement(seq):
     complement = {'A': 'T', 'T': 'A', 'G': 'C', 'C': 'G', 'N': 'N'}
     return ''.join(complement[base] for base in reversed(seq))
 
+
 def fix_path(path):
     fixed_path = os.path.normpath(path)
     fixed_path = os.path.realpath(fixed_path)
     return fixed_path
 
 
+def extract_identity(clustered_info):
+    # Use regular expressions to capture the percentage value at the end of the line
+    match = re.search(r'at ([-+]*)(\d+\.\d+)%', clustered_info)
+
+    if match:
+        percent_identity = float(match.group(2))  # Extract the percentage value
+        return percent_identity
+    else:
+        raise ValueError("Percent identity not found in the string.")
+
 def wrap_sequence(sequence, width=60):
     wrapped_sequence = []
     for i in range(0, len(sequence), width):
@@ -172,14 +184,15 @@ def run_mafft_on_sequences(options, sequences, output_file):
         with open(output_file, 'w') as output_f:
             if options.verbose == True:
                 subprocess.run(
-                    ['mafft', '--auto', temp_input_file_path],
+                    ['mafft', '--auto', '--thread', str(options.threads), temp_input_file_path],
                     stdout=output_f,
                     stderr=sys.stderr,
                     check=True
                 )
+
             else:
                 subprocess.run(
-                    ['mafft', '--auto', temp_input_file_path],
+                    ['mafft', '--auto', '--thread', str(options.threads), temp_input_file_path],
                     stdout=output_f,
                     stderr=subprocess.DEVNULL,  # Suppress stderr
                     check=True
@@ -385,7 +398,7 @@ def process_gene_families(options, directory, output_file):
 
     # Iterate over each gene family file
     for gene_file in os.listdir(directory):
-        if gene_file.endswith('.fasta'):
+        if gene_file.endswith('.fasta') and not gene_file.endswith('combined_group_sequences.fasta'):
             gene_path = os.path.join(directory, gene_file)
 
             # Read sequences from the gene family file
@@ -395,13 +408,15 @@ def process_gene_families(options, directory, output_file):
             longest_sequences = select_longest_gene(sequences)
 
             # Run mafft on the longest sequences
-            aligned_file = f"{gene_file}_aligned.fasta"
+            aligned_file = f"{directory}/{gene_file}_aligned.fasta.tmp"
             run_mafft_on_sequences(options, {seq_id: seq for seq_id, seq in longest_sequences.values()}, aligned_file)
 
             # Read aligned sequences and concatenate them
             aligned_sequences = read_fasta(aligned_file)
             for genome, aligned_seq in aligned_sequences.items():
                 genome_name = genome.split('|')[0]
+                if 'Group' in genome_name:
+                    print(2)
                 if genome_name not in concatenated_sequences:
                     concatenated_sequences[genome_name] = ""
                 concatenated_sequences[genome_name] += aligned_seq

{PyamilySeq-0.8.0.dist-info → PyamilySeq-0.8.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: PyamilySeq
-Version: 0.8.0
+Version: 0.8.1
 Summary: PyamilySeq - A a tool to look for 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
@@ -58,7 +58,7 @@ Escherichia_coli_110957|ENSB:TIZS9kbTvShDvyX	Escherichia_coli_110957|ENSB:TIZS9k
 ```
 ### Example output:
 ```
-Running PyamilySeq v0.8.0
+Running PyamilySeq v0.8.1
 Calculating Groups
 Gene Groups:
 First_core_99: 2682
@@ -80,7 +80,7 @@ PyamilySeq -run_mode Partial -group_mode Genus -clustering_format CD-HIT -output
  -cluster_file .../test_data/genus/CD-HIT/combined_cds_cd-hit_80_60.clstr -gpa 
 ```
 ```commandline
-Running PyamilySeq v0.8.0
+Running PyamilySeq v0.8.1
 Calculating Groups
 Genus Groups:
 First_genera_1:	28549
@@ -137,14 +137,14 @@ Please report any issues to: https://github.com/NickJD/PyamilySeq/issues
 ## PyamilySeq - Menu: 
 ### PyamilySeq is separated into two main 'run modes', Full and Partial. They each have their own set of required and optional arguments. 
 ```
-Running PyamilySeq v0.8.0
+Running PyamilySeq v0.8.1
 usage: PyamilySeq.py [-h] -run_mode {Full,Partial} -group_mode {Species,Genus} -clustering_format {CD-HIT,TSV,CSV} -output_dir OUTPUT_DIR
                      [-input_type {separate,combined}] [-input_dir INPUT_DIR] [-name_split NAME_SPLIT] [-sequence_type {AA,DNA}] [-gene_ident GENE_IDENT]
                      [-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_GROUPS] [-a]
                      [-original_fasta ORIGINAL_FASTA] [-gpa] [-verbose] [-v]
 
-PyamilySeq v0.8.0: A tool that groups genes into unique clusters.
+PyamilySeq v0.8.1: A tool that groups genes into unique clusters.
 
 options:
   -h, --help            show this help message and exit
@@ -176,8 +176,9 @@ Full-Mode Arguments - Required when "-run_mode Full" is used:
 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.
+  -t THREADS            Default 8: Threads to be allocated for clustering
+                        and/or alignment.
+
 
 Partial-Mode Arguments - Required when "-run_mode Partial" is used:
   -cluster_file CLUSTER_FILE
@@ -221,7 +222,7 @@ Seq-Combiner -input_dir .../test_data/genomes -name_split _combined.gff3 -output
 ```
 usage: Seq_Combiner.py [-h] -input_dir INPUT_DIR -input_type {separate,combined,fasta} -name_split NAME_SPLIT -output_dir OUTPUT_DIR -output_name OUTPUT_FILE [-gene_ident GENE_IDENT] [-translate] [-v]
 
-Seq-Combiner v0.8.0: A tool to extract sequences from GFF/FASTA files.
+Seq-Combiner v0.8.1: A tool to extract sequences from GFF/FASTA files.
 
 options:
   -h, --help            show this help message and exit
@@ -254,7 +255,7 @@ Misc Arguments:
 usage: Group_Splitter.py [-h] -input_fasta INPUT_FASTA -output_dir OUTPUT_DIR [-pident PIDENT] [-len_diff LEN_DIFF] [-clustering_threads CLUSTERING_THREADS]
                          [-clustering_memory CLUSTERING_MEMORY] [-percent_threshold PERCENT_THRESHOLD] [-verbose] [-delete_temp_files] [-v]
 
-Group-Splitter: v0.8.0: A tool to split "paralogous" groups identified by PyamilySeq.
+Group-Splitter: v0.8.1: A tool to split "paralogous" groups identified by PyamilySeq.
 
 options:
   -h, --help            show this help message and exit
@@ -262,6 +263,8 @@ options:
 Required Arguments:
   -input_fasta INPUT_FASTA
                         Input FASTA file containing gene groups.
+  -sequence_type {AA,DNA}
+                        Default - DNA: Are groups "DNA" or "AA" sequences?
   -output_dir OUTPUT_DIR
                         Output directory.
 

PyamilySeq-0.8.1.dist-info/RECORD

@@ -0,0 +1,15 @@
+PyamilySeq/Constants.py,sha256=J_jZheqHCbmFVCLrY8nMe4T5VZQOQ7PbT_HmYSi58WM,31
+PyamilySeq/Group_Splitter.py,sha256=wrz-vcQ2gJ40MLLczFY8te35_uYrOBuh2v-fJSIVsWo,15578
+PyamilySeq/PyamilySeq.py,sha256=OAtz6b7dnvA-Qg0dnf2JXImiOtsDrDfVit7Q6DFbuPU,15265
+PyamilySeq/PyamilySeq_Genus.py,sha256=hC34cHIFu8YaXXgcPyVwuWENlsxx-7mT-Qr6PAdio4U,12414
+PyamilySeq/PyamilySeq_Species.py,sha256=spgS-h-lrySZBiOiB6jX6pPRaL5j8f5V1Hq3XOjBOko,14404
+PyamilySeq/Seq_Combiner.py,sha256=dPDu6LlT3B-ZDn3wKZ3AeWraDgv2Tub_16l9CLc3tQ0,3353
+PyamilySeq/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+PyamilySeq/clusterings.py,sha256=rcWFv0IiWoS4aUNRjDDwNEL86l1wIKa4vK4htAxy8Hg,18787
+PyamilySeq/utils.py,sha256=vjPSIua4E72JTWlzH4CUaRcR-Z6Nr-RQ9N_92tfZI_w,19686
+PyamilySeq-0.8.1.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+PyamilySeq-0.8.1.dist-info/METADATA,sha256=weIjFQkc7ggqkPlPkSA5an8eFiUzhDyxGl9t7-rJPsA,14555
+PyamilySeq-0.8.1.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
+PyamilySeq-0.8.1.dist-info/entry_points.txt,sha256=15BsozBN6vRWvZeQon05dY4YQT7DqP5i2TUqFWRGCvc,150
+PyamilySeq-0.8.1.dist-info/top_level.txt,sha256=J6JhugUQTq4rq96yibAlQu3o4KCM9WuYfqr3w1r119M,11
+PyamilySeq-0.8.1.dist-info/RECORD,,

PyamilySeq-0.8.0.dist-info/RECORD

@@ -1,15 +0,0 @@
-PyamilySeq/Constants.py,sha256=lbVZv4vDHroA83KCDTIGuVb6bubKYZbwLmhYHxedXQc,31
-PyamilySeq/Group_Splitter.py,sha256=raZMV9SN7Qqw5Hci5qpkaahR66JMQf6dX8TvThjh3kU,14986
-PyamilySeq/PyamilySeq.py,sha256=0607A9nqafoQ8IhBxGgGJ-v3DVV6C6-LgzdDIXb2C-c,15179
-PyamilySeq/PyamilySeq_Genus.py,sha256=hC34cHIFu8YaXXgcPyVwuWENlsxx-7mT-Qr6PAdio4U,12414
-PyamilySeq/PyamilySeq_Species.py,sha256=spgS-h-lrySZBiOiB6jX6pPRaL5j8f5V1Hq3XOjBOko,14404
-PyamilySeq/Seq_Combiner.py,sha256=dPDu6LlT3B-ZDn3wKZ3AeWraDgv2Tub_16l9CLc3tQ0,3353
-PyamilySeq/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-PyamilySeq/clusterings.py,sha256=rcWFv0IiWoS4aUNRjDDwNEL86l1wIKa4vK4htAxy8Hg,18787
-PyamilySeq/utils.py,sha256=6UtYJW3_0rDhEhvrJi6R3smvKu2n_bjqUkuzr5DcJM4,19061
-PyamilySeq-0.8.0.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-PyamilySeq-0.8.0.dist-info/METADATA,sha256=ZnpQvAQy5EXGrzS0G9y5qH2Rhmb0LW2HvOT-b5WJLoo,14436
-PyamilySeq-0.8.0.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
-PyamilySeq-0.8.0.dist-info/entry_points.txt,sha256=15BsozBN6vRWvZeQon05dY4YQT7DqP5i2TUqFWRGCvc,150
-PyamilySeq-0.8.0.dist-info/top_level.txt,sha256=J6JhugUQTq4rq96yibAlQu3o4KCM9WuYfqr3w1r119M,11
-PyamilySeq-0.8.0.dist-info/RECORD,,