PyamilySeq 0.5.1__py3-none-any.whl → 0.6.0__py3-none-any.whl

PyamilySeq/Constants.py

@@ -1,2 +1,2 @@
-PyamilySeq_Version = 'v0.5.1'
+PyamilySeq_Version = 'v0.6.0'
 

PyamilySeq/PyamilySeq.py

@@ -7,11 +7,13 @@ import subprocess
 
 
 try:
-    from .PyamilySeq_Species import cluster
+    from .PyamilySeq_Species import cluster as species_cluster
+    from .PyamilySeq_Genus import cluster as genus_cluster
     from .Constants import *
     from .utils import *
 except (ModuleNotFoundError, ImportError, NameError, TypeError) as error:
-    from PyamilySeq_Species import cluster
+    from PyamilySeq_Species import cluster as species_cluster
+    from PyamilySeq_Genus import cluster as genus_cluster
     from Constants import *
     from utils import *
 
@@ -25,7 +27,8 @@ 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 +46,8 @@ 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'],
-                          help='Group Mode: Should PyamilySeq be run in "Species" or "Genus" mode? - Genus mode not currently functioning',
+    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=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 +73,14 @@ 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')
@@ -80,13 +90,17 @@ def main():
 
     ###Grouping Arguments
     grouping_args = parser.add_argument_group('Grouping Arguments - Use to fine-tune grouping of genes after clustering')
-    grouping_args.add_argument('-reclustered', action='store', dest='reclustered', help='Clustering output file from secondary round of clustering',
+    grouping_args.add_argument('-reclustered', action='store', dest='reclustered',
+                        help='Currently only works on Partial Mode: Clustering output file from secondary round of clustering.',
                         required=False)
     grouping_args.add_argument('-seq_tag', action='store', dest='sequence_tag', default='StORF',
                         help='Default - "StORF": Unique identifier to be used to distinguish the second of two rounds of clustered sequences',
                         required=False)
-    grouping_args.add_argument('-groups', action="store", dest='core_groups', default="99,95,15",
-                        help='Default - (\'99,95,15\'): Gene family groups to use',
+    grouping_args.add_argument('-core_groups', action="store", dest='core_groups', default="99,95,15",
+                        help='Default - (\'99,95,15\'): Gene family groups to use for "Species" mode',
+                        required=False)
+    grouping_args.add_argument('-genus_groups', action="store", dest='genus_groups', default="1,2,3,4,5,6",
+                        help='Default - (\'1,2,3,4,5,6\'): Gene family groups to use for "Genus" mode',
                         required=False)
 
     ###Output Arguments
@@ -118,6 +132,8 @@ def main():
 
     ### Checking all required parameters are provided by user
     if options.run_mode == 'Full':
+        if options.reclustered != None:
+            sys.exit("Currently reclustering only works on Partial Mode.")
         required_full_mode = [options.input_type, options.input_dir, options.name_split, options.clust_tool,
                               options.pident, options.len_diff]
         if all(required_full_mode):
@@ -157,7 +173,7 @@ def main():
         else:
             exit("mafft is not installed. Please install mafft to proceed.")
     ##CD-HIT
-    if options.clust_tool == 'CD-HIT':
+    if options.clust_tool == 'CD-HIT' and options.run_mode == 'Full':
         if is_tool_installed('cd-hit'):
             if options.verbose == True:
                 print("cd-hit is installed. Proceeding with clustering.")
@@ -167,7 +183,7 @@ def main():
     if options.write_families != None and options.original_fasta == False:
         exit("-fasta must br provided if -w is used")
 
-    options.core_groups = options.core_groups + ',0'
+
 
 
     if options.cluster_file:
@@ -183,24 +199,30 @@ def main():
     combined_out_file = os.path.join(output_path, "combined_sequences.fasta")
     clustering_output = os.path.join(output_path, 'clustering_' + options.clust_tool)
 
-
-    if options.run_mode == 'Full':
-
+    if options.group_type == 'Species':
+        options.core_groups = options.core_groups + ',0'
+        groups_to_use = options.core_groups
+    else:
+        options.genus_groups = options.genus_groups + ',>'
+        groups_to_use = options.genus_groups
 
 
+    if options.run_mode == 'Full':
         if options.input_type == 'separate':
             read_separate_files(options.input_dir, options.name_split, combined_out_file)
         else:
             read_combined_files(options.input_dir, options.name_split, combined_out_file)
 
         run_cd_hit(combined_out_file, clustering_output, options)
+
         class clustering_options:
             def __init__(self):
                 self.cluster_format = options.clust_tool
                 self.reclustered = options.reclustered
                 self.sequence_tag = options.sequence_tag
-                self.core_groups = '99,95,15,0'
+                self.core_groups = groups_to_use
                 self.clusters = clustering_output + clust_affix
+                self.output_dir = options.output_dir
                 self.gene_presence_absence_out = options.gene_presence_absence_out
                 self.write_families = options.write_families
                 self.con_core = options.con_core
@@ -215,8 +237,9 @@ def main():
                 self.cluster_format = options.clust_tool
                 self.reclustered = options.reclustered
                 self.sequence_tag = options.sequence_tag
-                self.core_groups = '99,95,15,0'
+                self.core_groups = groups_to_use
                 self.clusters = options.cluster_file
+                self.output_dir = options.output_dir
                 self.gene_presence_absence_out = options.gene_presence_absence_out
                 self.write_families = options.write_families
                 self.con_core = options.con_core
@@ -226,9 +249,10 @@ def main():
         clustering_options = clustering_options()
 
 
-
-
-    cluster(clustering_options)
+    if options.group_type == 'Species':
+        species_cluster(clustering_options)
+    elif options.group_type == 'Genus':
+        genus_cluster((clustering_options))
 
     print("Thank you for using PyamilySeq -- A detailed user manual can be found at https://github.com/NickJD/PyamilySeq\n"
           "Please report any issues to: https://github.com/NickJD/PyamilySeq/issues\n#####")