kssdtree 2.0.5__tar.gz → 2.0.6__tar.gz

{kssdtree-2.0.5/kssdtree.egg-info → kssdtree-2.0.6}/PKG-INFO

@@ -1,11 +1,8 @@
-Metadata-Version: 1.1
+Metadata-Version: 2.1
 Name: kssdtree
-Version: 2.0.5
+Version: 2.0.6
 Summary: Kssdtree is a versatile Python package for phylogenetic analysis. It also provides one-stop tree construction and visualization. It can handle DNA sequences of both fasta or fastq format, whether gzipped or not. 
 Home-page: https://github.com/yhlink/kssdtree
+Download-URL: https://pypi.org/project/kssdtree
 Author: Hang Yang
 Author-email: yhlink1207@gmail.com
-License: UNKNOWN
-Download-URL: https://pypi.org/project/kssdtree
-Description: UNKNOWN
-Platform: UNKNOWN

{kssdtree-2.0.5 → kssdtree-2.0.6/kssdtree.egg-info}/PKG-INFO

@@ -1,11 +1,8 @@
-Metadata-Version: 1.1
+Metadata-Version: 2.1
 Name: kssdtree
-Version: 2.0.5
+Version: 2.0.6
 Summary: Kssdtree is a versatile Python package for phylogenetic analysis. It also provides one-stop tree construction and visualization. It can handle DNA sequences of both fasta or fastq format, whether gzipped or not. 
 Home-page: https://github.com/yhlink/kssdtree
+Download-URL: https://pypi.org/project/kssdtree
 Author: Hang Yang
 Author-email: yhlink1207@gmail.com
-License: UNKNOWN
-Download-URL: https://pypi.org/project/kssdtree
-Description: UNKNOWN
-Platform: UNKNOWN

{kssdtree-2.0.5 → kssdtree-2.0.6}/kssdtree.py

@@ -336,7 +336,6 @@ def quick(shuf_file=None, genome_files=None, output=None, reference=None, databa
             if not s3:
                 return False
             print('Step4...')
-            print('Tree visualization finished!')
             visualize(newick=output, mode=mode)
             if platform.system() == 'Linux':
                 current_directory = os.getcwd()
@@ -367,7 +366,6 @@ def quick(shuf_file=None, genome_files=None, output=None, reference=None, databa
             s2 = retrieve(database=database, genome_sketch=qry_sketch, output=output, N=N, method=method)
             if not s2:
                 return False
-            print('Tree visualization finished!')
             visualize(newick=os.path.join(output, 'output.newick'),
                       taxonomy=os.path.join(output, 'output_accession_taxonomy.txt'), mode=None)
             if platform.system() == 'Linux':
@@ -434,7 +432,6 @@ def quick(shuf_file=None, genome_files=None, output=None, reference=None, databa
                 os.remove('ref.txt')
                 os.remove('qry.txt')
                 os.remove(temp_phy)
-                print('Tree visualization finished!')
                 visualize(newick=output, taxonomy='ref_qry.txt', mode='r')
                 if platform.system() == 'Linux':
                     current_directory = os.getcwd()
@@ -507,7 +504,6 @@ def quick(shuf_file=None, genome_files=None, output=None, reference=None, databa
             if not s6:
                 return False
             print('Step5...')
-            print('Tree visualization finished!')
             visualize(newick=output, mode=mode)
             if platform.system() == 'Linux':
                 current_directory = os.getcwd()

{kssdtree-2.0.5 → kssdtree-2.0.6}/setup.py

@@ -87,7 +87,7 @@ require_pakages = [
 
 setup(
     name='kssdtree',
-    version='2.0.5',
+    version='2.0.6',
     author='Hang Yang',
     author_email='yhlink1207@gmail.com',
     description="Kssdtree is a versatile Python package for phylogenetic analysis. It also provides one-stop tree construction and visualization. It can handle DNA sequences of both fasta or fastq format, whether gzipped or not. ",

{kssdtree-2.0.5 → kssdtree-2.0.6}/toolutils.py

@@ -1,6 +1,8 @@
 import random
 import operator
 import os
+import re
+
 import requests
 import json
 import zipfile
@@ -174,6 +176,7 @@ def view_tree(newick, taxonomy, mode):
             branch_name_face = TextFace(node.dist, fsize=8, fgcolor='black', tight_text=False,
                                         bold=False)
             node.add_face(branch_name_face, column=0, position='branch-top')
+        print('Tree visualization finished!')
         t.show(tree_style=ts)
     else:
         mode = 'r'
@@ -203,35 +206,43 @@ def view_tree(newick, taxonomy, mode):
         current_directory = os.getcwd()
         taxonomy_path = os.path.join(current_directory, taxonomy)
         if not os.path.exists(taxonomy_path):
-            print('"The file taxonomy txt does not exist."')
-            return
+            print('The file taxonomy txt does not exist!')
 
         all_accessions = []
         accession_taxonomy = {}
         with open(taxonomy_path, 'r') as file:
             for line in file:
                 columns = line.split()
-                column_1 = columns[0]
-                column_2 = columns[1:]
-                tempfile = ''
-                for x in column_2:
-                    tempfile = tempfile + x + ' '
-                tempfile = tempfile[:-1]
-                all_accessions.append(column_1)
-                accession_taxonomy[column_1] = tempfile
-
+                if len(columns) == 2:
+                    column_1 = columns[0]
+                    column_2 = columns[1:]
+                    tempfile = ''
+                    for x in column_2:
+                        tempfile = tempfile + x + ' '
+                    tempfile = tempfile[:-1]
+                    if column_1 in all_accessions:
+                        print('Tree visualization failed!')
+                        print('Tip: There are same genome names between the query genome and the reference genome.')
+                        return False
+                    all_accessions.append(column_1)
+                    accession_taxonomy[column_1] = tempfile
         known_species = []
         for x in all_accessions:
             if accession_taxonomy[x] != 'Unknown':
                 known_species.append(accession_taxonomy[x])
-
         temp_nwk = 'temp_kssdtree.newick'
 
         with open(newick, 'r') as f:
             lines = f.readlines()[0]
             for x in all_accessions:
+                # print(x)
+                pattern = r'\b{}\b'.format(re.escape(x))
+                # print(pattern)
+                match = re.search(pattern, lines)
+                if match:
+                    x_index = match.start()
                 x_len = len(x)
-                x_index = lines.index(x)
+                # print(x_index)
                 loc_index = x_index + x_len + 8
                 if x in accession_taxonomy.keys():
                     lines = str_insert(lines, loc_index, '[&&NHX:species=' + accession_taxonomy.get(x) + ']')
@@ -290,6 +301,7 @@ def view_tree(newick, taxonomy, mode):
                 node.img_style = nst
                 node.set_style(nst)
         # t.render("bubble_map.png", w=600, dpi=300, tree_style=ts)
+        print('Tree visualization finished!')
         t.show(tree_style=ts)
 
 def deal_gtdb_txt(temp_dist_output):