PyamilySeq 0.7.0__py3-none-any.whl → 0.7.1__py3-none-any.whl

PyamilySeq/Constants.py

@@ -1,2 +1,2 @@
-PyamilySeq_Version = 'v0.7.0'
+PyamilySeq_Version = 'v0.7.1'
 

PyamilySeq/PyamilySeq.py

@@ -41,6 +41,7 @@ def run_cd_hit(options, input_file, clustering_output, clustering_mode):
 
 def main():
     parser = argparse.ArgumentParser(description='PyamilySeq ' + PyamilySeq_Version + ': A tool that groups genes into unique clusters.')
+    vparser = argparse.ArgumentParser()
     ### Required Arguments
     required = parser.add_argument_group('Required Arguments')
     required.add_argument('-run_mode', action='store', dest='run_mode', choices=['Full','Partial'],
@@ -132,10 +133,20 @@ def main():
     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('-v', action='store_true', dest='version',
+
+    ### Version Arguments
+    version = vparser.add_argument_group('Version')
+    version.add_argument('-v', action='store_true', dest='version',
                         help='Default - False: Print out version number and exit',
                         required=False)
 
+
+
+    args, unknown = vparser.parse_known_args()
+
+    if args.version == True:
+        sys.exit("PyamilySeq version: "+PyamilySeq_Version)
+
     options = parser.parse_args()
 
     ### Checking all required parameters are provided by user #!!# Doesn't seem to work
@@ -288,5 +299,5 @@ def main():
           "Please report any issues to: https://github.com/NickJD/PyamilySeq/issues\n#####")
 
 if __name__ == "__main__":
-    print("Running PyamilySeq "+PyamilySeq_Version)
+    #print("Running PyamilySeq "+PyamilySeq_Version)
     main()

{PyamilySeq-0.7.0.dist-info → PyamilySeq-0.7.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: PyamilySeq
-Version: 0.7.0
+Version: 0.7.1
 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 v0.7.0
+Running PyamilySeq v0.7.1
 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 v0.7.0
+Running PyamilySeq v0.7.1
 Calculating Groups
 Genus Groups:
 First_genera_1:	28549
@@ -98,37 +98,36 @@ Please report any issues to: https://github.com/NickJD/PyamilySeq/issues
 ### Reclustering can be used to see where additional sequences/genes lay in relation to a contemporary pangenome/gene grouping.
 ```
 PyamilySeq -run_mode Partial -group_mode Species -clustering_format CD-HIT -output_dir .../test_data/species/CD-HIT/testing 
--cluster_file .../test_data/species/CD-HIT/E-coli_extracted_cds_cd-hit_90_60.clstr -gpa 
--reclustered .../test_data/species/CD-HIT/E-coli_extracted_cds_cd-hit_90_60_And_StORFs_cds_90_60.clstr
+-cluster_file .../test_data/species/CD-HIT/E-coli_extracted_cds_cd-hit_80_60.clstr -gpa 
+-reclustered .../test_data/species/CD-HIT/E-coli_extracted_cds_cd-hit_80_60_And_StORFs_cds_80_60.clstr
 ```
 #### As can be seen below, the additional sequences recovered by the StORF-Reporter annotation tool have 'extended' contemporary or created entirely new gene groups. 'First' corresponds to the groups identified from the first clustering round and 'Second' for the second. In 'reclustering' mode, First_core_# groups are unaffected thus retaining the initial grouping information. 
 ```commandline
-Running PyamilySeq v0.7.0
 Calculating Groups
 Gene Groups:
-First_core_99: 69
-First_core_95: 1002
-First_core_15: 4716
-First_core_0: 37960
-extended_core_99: 6
-extended_core_95: 73
-extended_core_15: 331
-extended_core_0: 582
-combined_core_99: 4
-combined_core_95: 88
-combined_core_15: 455
-combined_core_0: 228
+First_core_99: 587
+First_core_95: 1529
+First_core_15: 3708
+First_core_0: 29992
+extended_core_99: 29
+extended_core_95: 67
+extended_core_15: 431
+extended_core_0: 1331
+combined_core_99: 2
+combined_core_95: 4
+combined_core_15: 5
+combined_core_0: 4
 Second_core_99: 0
-Second_core_95: 5
-Second_core_15: 254
-Second_core_0: 3714
-only_Second_core_99: 6
-only_Second_core_95: 364
-only_Second_core_15: 3950
-only_Second_core_0: 31269
-Total Number of First Gene Groups (Including Singletons): 43747
-Total Number of Second Gene Groups (Including Singletons): 66525
-Total Number of First Gene Groups That Had Additional Second Sequences But Not New Genomes: 9593
+Second_core_95: 6
+Second_core_15: 172
+Second_core_0: 1825
+only_Second_core_99: 53
+only_Second_core_95: 493
+only_Second_core_15: 3806
+only_Second_core_0: 27569
+Total Number of First Gene Groups (Including Singletons): 35816
+Total Number of Second Gene Groups (Including Singletons): 67728
+Total Number of First Gene Groups That Had Additional Second Sequences But Not New Genomes: 136
 Outputting gene_presence_absence file
 Thank you for using PyamilySeq -- A detailed user manual can be found at https://github.com/NickJD/PyamilySeq
 Please report any issues to: https://github.com/NickJD/PyamilySeq/issues
@@ -138,14 +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 v0.7.0
+Running PyamilySeq v0.7.1
 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 v0.7.0: A tool that groups genes into unique clusters.
+PyamilySeq v0.7.1: A tool that groups genes into unique clusters.
 
 options:
   -h, --help            show this help message and exit
@@ -198,9 +197,9 @@ Output Parameters:
   -w WRITE_GROUPS       Default - No output: Output sequences of identified groups (provide levels at which to output - Species "-w 99,95" Genus "-w 2,3" -
                         Must provide FASTA file with -original_fasta if in Partial run mode.
   -a                    Default - No output: SLOW! (Only works for Species mode) Output aligned and concatinated sequences of identified groups -provide
-                        group levels at which to output "-w 99,95" - Must provide FASTA file with -original_fasta in Partialrun mode.
+                        group levels at which to output "-w 99,95" - Must provide FASTA file with -original_fasta in Partial run mode.
   -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 "-a" when running in Partial Mode.
   -gpa                  Default - False: If selected, a Roary/Panaroo formatted gene_presence_absence.csv will be created - Required for Coinfinder and
                         other downstream tools
 
@@ -222,7 +221,7 @@ 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 v0.7.0: A tool to extract sequences from GFF/FASTA files.
+Seq-Combiner v0.7.1: A tool to extract sequences from GFF/FASTA files.
 
 options:
   -h, --help            show this help message and exit

{PyamilySeq-0.7.0.dist-info → PyamilySeq-0.7.1.dist-info}/RECORD

@@ -1,14 +1,14 @@
-PyamilySeq/Constants.py,sha256=RSX5-UuBXOrbEv3ETN415RwqoB6WmNe5eD-p7L15CJA,31
-PyamilySeq/PyamilySeq.py,sha256=wmdOVxxRKqsamsEWgnVVCYETUaYOEQQVYERpClrg4Zw,15203
+PyamilySeq/Constants.py,sha256=4MNcQLwJguoC9fHBLbreAe-GNgNvtzYrF0MBM6BFY_s,31
+PyamilySeq/PyamilySeq.py,sha256=RbM6G1yU64jlb9r7QRry1vw5mQsxndM6TrvMvq3BVik,15466
 PyamilySeq/PyamilySeq_Genus.py,sha256=ZjD61mTW7NgmsfGfFVEXeIZoSCha9PaLtMPnqdTtacU,12413
 PyamilySeq/PyamilySeq_Species.py,sha256=WL6pu8hlGpnemcpu1tLFmlUlPd4vJpQSW4Om5Hclu_k,14438
 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=-0OZxmX96kOTzms8gnbFBvc5DL6NsqNHNpLpQ4UjNk8,15726
-PyamilySeq-0.7.0.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-PyamilySeq-0.7.0.dist-info/METADATA,sha256=JDhA1JdFaESNwtqzWjRgaA92lrmVFNJWQZUonHgJuvA,13105
-PyamilySeq-0.7.0.dist-info/WHEEL,sha256=R0nc6qTxuoLk7ShA2_Y-UWkN8ZdfDBG2B6Eqpz2WXbs,91
-PyamilySeq-0.7.0.dist-info/entry_points.txt,sha256=QtXD1tmnLvRAkIpGWZgXm1lfLH8GGeCwxmgoHZaTp98,102
-PyamilySeq-0.7.0.dist-info/top_level.txt,sha256=J6JhugUQTq4rq96yibAlQu3o4KCM9WuYfqr3w1r119M,11
-PyamilySeq-0.7.0.dist-info/RECORD,,
+PyamilySeq-0.7.1.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+PyamilySeq-0.7.1.dist-info/METADATA,sha256=IpbThlfEmO-S8Nl617eQB64Xzu9GJDz19L4Jhx7lwGY,13076
+PyamilySeq-0.7.1.dist-info/WHEEL,sha256=HiCZjzuy6Dw0hdX5R3LCFPDmFS4BWl8H-8W39XfmgX4,91
+PyamilySeq-0.7.1.dist-info/entry_points.txt,sha256=QtXD1tmnLvRAkIpGWZgXm1lfLH8GGeCwxmgoHZaTp98,102
+PyamilySeq-0.7.1.dist-info/top_level.txt,sha256=J6JhugUQTq4rq96yibAlQu3o4KCM9WuYfqr3w1r119M,11
+PyamilySeq-0.7.1.dist-info/RECORD,,

{PyamilySeq-0.7.0.dist-info → PyamilySeq-0.7.1.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (72.1.0)
+Generator: setuptools (72.2.0)
 Root-Is-Purelib: true
 Tag: py3-none-any