PyamilySeq 0.5.0__py3-none-any.whl → 0.5.2__py3-none-any.whl

PyamilySeq/Constants.py

@@ -1,2 +1,2 @@
-PyamilySeq_Version = 'v0.5.0'
+PyamilySeq_Version = 'v0.5.2'
 

PyamilySeq/PyamilySeq.py

@@ -3,7 +3,7 @@ import collections
 import os
 import glob
 import subprocess
-from PyamilySeq_Species import *
+
 
 
 try:
@@ -25,7 +25,8 @@ def run_cd_hit(input_file, clustering_output, options):
         '-o', clustering_output,
         '-c', str(options.pident),
         '-s', str(options.len_diff),
-        '-T', "20",
+        '-T', str(options.clustering_threads),
+        '-M', str(options.clustering_memory),
         '-d', "0",
         '-sc', "1",
         '-sf', "1"
@@ -43,8 +44,8 @@ def main():
     required.add_argument('-run_mode', action='store', dest='run_mode', choices=['Full','Partial'],
                           help='Run Mode: Should PyamilySeq be run in "Full" or "Partial" mode?',
                           required=True)
-    required.add_argument('-group_mode', action='store', dest='group_type', choices=['Species','Genus'],
-                          help='Group Mode: Should PyamilySeq be run in "Species" or "Genus" mode?',
+    required.add_argument('-group_mode', action='store', dest='group_type', choices=['Species'],
+                          help='Group Mode: Should PyamilySeq be run in "Species" or "Genus" mode? - Genus mode not currently functioning',
                           required=True)
     required.add_argument("-clust_tool", action="store", dest="clust_tool", choices=['CD-HIT'],
                           help="Clustering tool to use: CD-HIT, DIAMOND, BLAST or MMseqs2.",
@@ -70,7 +71,14 @@ def main():
     full_mode_args.add_argument("-len_diff", action="store", dest="len_diff", type=float, default=0.80,
                           help="Default 0.80: Minimum length difference between clustered sequences - (-s) threshold for CD-HIT clustering.",
                           required=False)
-
+    ###Clustering Arguments
+    clustering_args = parser.add_argument_group('Clustering Runtime Arguments - Optional when "-run_mode Full" is used')
+    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.",
+                          required=False)
 
     ###Partial-Mode Arguments
     partial_mode_args = parser.add_argument_group('Partial-Mode Arguments - Required when "-run_mode Partial" is used')

{PyamilySeq-0.5.0.dist-info → PyamilySeq-0.5.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: PyamilySeq
-Version: 0.5.0
+Version: 0.5.2
 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
@@ -34,107 +34,88 @@ 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 v0.5.0: PyamilySeq Run Parameters.
+usage: PyamilySeq.py [-h] -run_mode {Full,Partial} -group_mode {Species} -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] [-groups CORE_GROUPS] [-w WRITE_FAMILIES] [-con CON_CORE] [-original_fasta ORIGINAL_FASTA] [-gpa GENE_PRESENCE_ABSENCE_OUT] [-verbose {True,False}] [-v]
+
+PyamilySeq v0.5.2: 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,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.
+                        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.
   -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
+                        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
+                        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
 
 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}
                         Default - False: Print out runtime messages
   -v                    Default - False: Print out version number and exit
 
-```
 
-### 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 -id .../genomes -it combined -ns _combined.gff3 -pid 0.90 -ld 0.60 -co testing_cd-hit -ct CD-HIT -od .../testing
-```
-#### '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
 ```
 
-```Calculating Groups
-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 +126,7 @@ 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 v0.5.0: Seq-Combiner Run Parameters.
+Seq-Combiner v0.5.2: Seq-Combiner Run Parameters.
 
 options:
   -h, --help            show this help message and exit

{PyamilySeq-0.5.0.dist-info → PyamilySeq-0.5.2.dist-info}/RECORD

@@ -1,14 +1,14 @@
 PyamilySeq/CD-Hit_StORF-Reporter_Cross-Genera_Builder.py,sha256=UzQ5iOKCNfurxmj1pnkowF11YfWBO5vnBCKxQK6goB8,26538
-PyamilySeq/Constants.py,sha256=H1GMMb0WK68bphZPfzCvdvvSi5BeQc80QL4igt17S94,31
-PyamilySeq/PyamilySeq.py,sha256=ONDjQZoR4YCdAoDq2Ufv8mcY_1ek1LPJF-OtS4gzXDs,11276
+PyamilySeq/Constants.py,sha256=A5pJCs_7qkEiazEOqQCfsvlKVh1Ba8EkEQfOJ24_Q2A,31
+PyamilySeq/PyamilySeq.py,sha256=eOiWW3jIUWFID28ljyYFyB8Nnnuays5glpA5K8qYXGc,11971
 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-0.5.0.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-PyamilySeq-0.5.0.dist-info/METADATA,sha256=II_Elm1hg0nTXjmnEnsct2e4l2KQ1xR2hcXgp1wEiJA,7649
-PyamilySeq-0.5.0.dist-info/WHEEL,sha256=Wyh-_nZ0DJYolHNn1_hMa4lM7uDedD_RGVwbmTjyItk,91
-PyamilySeq-0.5.0.dist-info/entry_points.txt,sha256=QtXD1tmnLvRAkIpGWZgXm1lfLH8GGeCwxmgoHZaTp98,102
-PyamilySeq-0.5.0.dist-info/top_level.txt,sha256=J6JhugUQTq4rq96yibAlQu3o4KCM9WuYfqr3w1r119M,11
-PyamilySeq-0.5.0.dist-info/RECORD,,
+PyamilySeq-0.5.2.dist-info/LICENSE,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+PyamilySeq-0.5.2.dist-info/METADATA,sha256=GEgsSru0ojf-SePFSocGGUuGKWGHE7mJ2oHOy9m3tBI,7471
+PyamilySeq-0.5.2.dist-info/WHEEL,sha256=Wyh-_nZ0DJYolHNn1_hMa4lM7uDedD_RGVwbmTjyItk,91
+PyamilySeq-0.5.2.dist-info/entry_points.txt,sha256=QtXD1tmnLvRAkIpGWZgXm1lfLH8GGeCwxmgoHZaTp98,102
+PyamilySeq-0.5.2.dist-info/top_level.txt,sha256=J6JhugUQTq4rq96yibAlQu3o4KCM9WuYfqr3w1r119M,11
+PyamilySeq-0.5.2.dist-info/RECORD,,