kssdtree 2.0.4__tar.gz → 2.0.6__tar.gz

{kssdtree-2.0.4/kssdtree.egg-info → kssdtree-2.0.6}/PKG-INFO

@@ -1,11 +1,8 @@
-Metadata-Version: 1.1
+Metadata-Version: 2.1
 Name: kssdtree
-Version: 2.0.4
+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-2.0.4 → kssdtree-2.0.6/kssdtree.egg-info}/PKG-INFO

@@ -1,11 +1,8 @@
-Metadata-Version: 1.1
+Metadata-Version: 2.1
 Name: kssdtree
-Version: 2.0.4
+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-2.0.4 → kssdtree-2.0.6}/kssdtree.py

@@ -28,6 +28,7 @@ def sketch(shuf_file=None, genome_files=None, output=None, set_opt=None):
         if not os.path.exists(shuf_file):
             if shuf_file in ['L3K9.shuf', './L3K9.shuf', 'L3K10.shuf', './L3K10.shuf']:
                 print('Downloading...', shuf_file)
+                start_time = time.time()
                 if shuf_file == 'L3K9.shuf' or shuf_file == './L3K9.shuf':
                     url = 'https://zenodo.org/records/12699159/files/L3K9.shuf?download=1'
                 else:
@@ -59,9 +60,9 @@ def sketch(shuf_file=None, genome_files=None, output=None, set_opt=None):
         print('Sketching...')
         start = time.time()
         if set_opt:
-            kssd.dist_dispatch(shuf_file, genome_files, output, 1, 0, 0, '')
+            kssd.dist_dispatch(shuf_file, genome_files, output, 1, 0, 0, '', '')
         else:
-            kssd.dist_dispatch(shuf_file, genome_files, output, 0, 0, 0, '')
+            kssd.dist_dispatch(shuf_file, genome_files, output, 0, 0, 0, '', '')
         end = time.time()
         print('Sketch spend time：%.2fs' % (end - start))
         print('Sketch finished!')
@@ -71,19 +72,16 @@ def sketch(shuf_file=None, genome_files=None, output=None, set_opt=None):
         return False
 
 
-def dist(genome_sketch=None, output=None, metric = None, flag=None):
+def dist(genome_sketch=None, output=None, metric=None, flag=None):
     if genome_sketch is not None and output is not None:
         if not os.path.exists(genome_sketch):
             print('No such file or directory: ', genome_sketch)
             return False
-        # if not os.path.exists(qry_sketch):
-        #     print('No such file or directory: ', qry_sketch)
-        #     return False
         if flag is None:
             flag = 0
         if metric is None:
             metric = 'mash'
-        
+
         print('Disting...')
         start = time.time()
         if '/' in output:
@@ -99,7 +97,7 @@ def dist(genome_sketch=None, output=None, metric = None, flag=None):
                 print('Metric type error, only supports mash or aaf distance')
                 return False
             else:
-                kssd.dist_dispatch(genome_sketch, output, genome_sketch, 2, 0, flag, metric)
+                kssd.dist_dispatch(genome_sketch, output, genome_sketch, 2, 0, flag, metric, '')
                 end = time.time()
                 print('Dist spend time：%.2fs' % (end - start))
                 print('Dist finished!')
@@ -112,6 +110,27 @@ def dist(genome_sketch=None, output=None, metric = None, flag=None):
         return False
 
 
+def combine(genome_sketch1=None, genome_sketch2=None, output=None):
+    if genome_sketch1 is not None and genome_sketch2 is not None and output is not None:
+        if not os.path.exists(genome_sketch1):
+            print('No such file or directory: ', genome_sketch1)
+            return False
+        if not os.path.exists(genome_sketch2):
+            print('No such file or directory: ', genome_sketch2)
+            return False
+        kssd.dist_dispatch(output, genome_sketch1, genome_sketch2, 3, 0, 0, '', '')
+        return True
+
+
+def getlist(genome_sketch=None, output=None):
+    if genome_sketch is not None and output is not None:
+        if not os.path.exists(genome_sketch):
+            print('No such file or directory: ', genome_sketch)
+            return False
+        kssd.print_gnames(genome_sketch, output)
+        return True
+
+
 def retrieve(database=None, genome_sketch=None, output=None, N=None, method=None):
     if database is not None and genome_sketch is not None and output is not None:
         if method is None:
@@ -145,7 +164,7 @@ def retrieve(database=None, genome_sketch=None, output=None, N=None, method=None
             print('Retrieve finished!')
             return True
         else:
-            print("database only support 'gtdbr214'")
+            print('Only support gtdbr214 database!!!')
             return False
     else:
         print('Args error!!!')
@@ -317,7 +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()
@@ -348,7 +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':
@@ -362,6 +379,74 @@ def quick(shuf_file=None, genome_files=None, output=None, reference=None, databa
         else:
             print('Args error, please see https://kssdtree.readthedocs.io/en/latest!!!')
             return False
+    elif reference is None and database != 'gtdbr214':
+        if shuf_file is not None and genome_files is not None and output is not None:
+            if toolutils.is_positive_integer(N) or toolutils.is_negative_integer(N):
+                print("N must = 0 !!!")
+                return False
+            if not os.path.exists(database):
+                print('No such file or directory: ', database)
+                return False
+            if '/' in output:
+                output_dir = os.path.dirname(output)
+                output_name = output.split('/')[-1]
+                if not os.path.exists(output_dir):
+                    os.makedirs(output_dir)
+                    print("Created directory:", output_dir)
+            else:
+                output_name = output
+            if output_name.endswith(".newick"):
+                timeStamp = int(time.mktime(time.localtime(time.time())))
+                qry_sketch = toolutils.rs() + '_sketch_' + str(timeStamp)
+                temp_combine_sketch = toolutils.rs() + '_combine_sketch_' + str(timeStamp)
+                temp_phy = toolutils.rs() + '.phy'
+                s1 = sketch(shuf_file=shuf_file, genome_files=genome_files, output=qry_sketch, set_opt=True)
+                if not s1:
+                    return False
+                print('Step2...')
+                combine(genome_sketch1=database, genome_sketch2=qry_sketch, output=temp_combine_sketch)
+                if method == 'nj':
+                    s2 = dist(genome_sketch=temp_combine_sketch, output=temp_phy, flag=0)
+                else:
+                    s2 = dist(genome_sketch=temp_combine_sketch, output=temp_phy, flag=1)
+                if not s2:
+                    return False
+                print('Step3...')
+                s3 = build(phylip=temp_phy, output=output, method=method)
+                if not s3:
+                    return False
+                print('Step4...')
+                getlist(genome_sketch=database, output='ref.txt')
+                getlist(genome_sketch=qry_sketch, output='qry.txt')
+                with open('ref.txt', 'r') as ref_file:
+                    ref_lines = ref_file.readlines()
+                with open('qry.txt', 'r') as qry_file:
+                    qry_lines = qry_file.readlines()
+                with open('ref_qry.txt', 'w') as result_file:
+                    for line in ref_lines:
+                        new_name = toolutils.rename_genome(line.strip())
+                        result_file.write(new_name + '\tReference\n')
+                    for line in qry_lines:
+                        new_name = toolutils.rename_genome(line.strip())
+                        result_file.write(new_name + '\tUnknown\n')
+                os.remove('ref.txt')
+                os.remove('qry.txt')
+                os.remove(temp_phy)
+                visualize(newick=output, taxonomy='ref_qry.txt', mode='r')
+                if platform.system() == 'Linux':
+                    current_directory = os.getcwd()
+                    temp_dir1 = os.path.join(current_directory, qry_sketch)
+                    if os.path.exists(temp_dir1):
+                        shutil.rmtree(temp_dir1)
+                    temp_dir2 = os.path.join(current_directory, temp_combine_sketch)
+                    if os.path.exists(temp_dir2):
+                        shutil.rmtree(temp_dir2)
+            else:
+                print('Output type error, only supports .newick format:', output_name)
+                return False
+        else:
+            print('Args error, please see https://kssdtree.readthedocs.io/en/latest!!!')
+            return False
     elif reference is not None and database is None:
         if shuf_file is not None and genome_files is not None and output is not None and method in ['nj', 'dnj']:
             if toolutils.is_positive_integer(N) or toolutils.is_negative_integer(N):
@@ -419,7 +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-2.0.4 → kssdtree-2.0.6}/pykssd.c

@@ -252,7 +252,6 @@ static PyObject *py_write_dim_shuffle_file(PyObject *self, PyObject *args) {
     return Py_BuildValue("i", state);
 }
 
-
 static PyObject *py_dist_dispatch(PyObject *self, PyObject *args) {
     char *str1;
     char *str2;
@@ -260,8 +259,9 @@ static PyObject *py_dist_dispatch(PyObject *self, PyObject *args) {
     int flag1;
     int flag2;
     char *str4;
+    char *str5;
     int N;
-    if (!PyArg_ParseTuple(args, "sssiiis", &str1, &str2, &str3, &flag1, &N, &flag2, &str4)) {
+    if (!PyArg_ParseTuple(args, "sssiiiss", &str1, &str2, &str3, &flag1, &N, &flag2, &str4, &str5)) {
         return NULL;
     }
     if (flag1 == 0) {
@@ -308,6 +308,11 @@ static PyObject *py_dist_dispatch(PyObject *self, PyObject *args) {
         strcpy(dist_opt_val1.refpath, str2);
         strcpy(dist_opt_val1.outdir, str3);
         dist_opt_val1.num_remaining_args = 0;
+	if (strcmp(str5, "abundance") == 0) {
+                dist_opt_val1.abundance = true;
+        } else {
+                dist_opt_val1.abundance = false;
+        }
         dist_opt_val1.remaining_args = NULL;
 #ifdef _OPENMP
         if(dist_opt_val1.p == 0)
@@ -366,6 +371,11 @@ static PyObject *py_dist_dispatch(PyObject *self, PyObject *args) {
         strcpy(dist_opt_val2.outdir, str3);
         dist_opt_val2.num_remaining_args = 1;
         dist_opt_val2.remaining_args = &str2;
+	if (strcmp(str5, "abundance") == 0) {
+                dist_opt_val2.abundance = true;
+        } else {
+                dist_opt_val2.abundance = false;
+        }
 #ifdef _OPENMP
         if(dist_opt_val2.p == 0)
             dist_opt_val2.p = omp_get_num_procs();
@@ -424,6 +434,11 @@ static PyObject *py_dist_dispatch(PyObject *self, PyObject *args) {
 	} else {
 		dist_opt_val3.metric = 1;
 	}
+	if (strcmp(str5, "abundance") == 0) {
+                dist_opt_val3.abundance = true;
+        } else {
+                dist_opt_val3.abundance = false;
+        }
 #ifdef _OPENMP
         if(dist_opt_val3.p == 0)
             dist_opt_val3.p = omp_get_num_procs();
@@ -490,6 +505,11 @@ static PyObject *py_dist_dispatch(PyObject *self, PyObject *args) {
         dist_opt_val4.num_remaining_args = 2;
         dist_opt_val4.remaining_args[0] = str2;
         dist_opt_val4.remaining_args[1] = str3;
+	if (strcmp(str5, "abundance") == 0) {
+                dist_opt_val4.abundance = true;
+        } else {
+                dist_opt_val4.abundance = false;
+        }
 #ifdef _OPENMP
         if(dist_opt_val4.p == 0)
             dist_opt_val4.p = omp_get_num_procs();
@@ -515,7 +535,6 @@ static PyObject *py_dist_dispatch(PyObject *self, PyObject *args) {
     return Py_BuildValue("i", 1);
 }
 
-
 static PyObject *py_sketch_union(PyObject *self, PyObject *args) {
     char *i;
     char *o;

{kssdtree-2.0.4 → kssdtree-2.0.6}/setup.py

@@ -87,7 +87,7 @@ require_pakages = [
 
 setup(
     name='kssdtree',
-    version='2.0.4',
+    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-2.0.4 → kssdtree-2.0.6}/toolutils.py

@@ -1,6 +1,8 @@
 import random
 import operator
 import os
+import re
+
 import requests
 import json
 import zipfile
@@ -91,6 +93,62 @@ def upload_request(qry_sketch, method, N):
     else:
         return None, None
 
+
+def rename_genome(name):
+    if '.fq' in name:
+        if '/' in name:
+            qry = name.split('/')[-1].split('.fq')[0]
+        else:
+            qry = name.split('.fq')[0]
+    elif '.fastq' in name:
+        if '/' in name:
+            qry = name.split('/')[-1].split('.fastq')[0]
+        else:
+            qry = name.split('.fastq')[0]
+    elif '.fq.gz' in name:
+        if '/' in name:
+            qry = name.split('/')[-1].split('.fq.gz')[0]
+        else:
+            qry = name.split('.fq.gz')[0]
+    elif '.fastq.gz' in name:
+        if '/' in name:
+            qry = name.split('/')[-1].split('.fastq.gz')[0]
+        else:
+            qry = name.split('.fastq.gz')[0]
+    elif '.fa' in name:
+        if '/' in name:
+            qry = name.split('/')[-1].split('.fa')[0]
+        else:
+            qry = name.split('.fa')[0]
+    elif '.fna' in name:
+        if '/' in name:
+            qry = name.split('/')[-1].split('.fna')[0]
+        else:
+            qry = name.split('.fna')[0]
+    elif '.fasta' in name:
+        if '/' in name:
+            qry = name.split('/')[-1].split('.fasta')[0]
+        else:
+            qry = name.split('.fasta')[0]
+    elif '.fa.gz' in name:
+        if '/' in name:
+            qry = name.split('/')[-1].split('.fa.gz')[0]
+        else:
+            qry = name.split('.fa.gz')[0]
+    elif '.fna.gz' in name:
+        if '/' in name:
+            qry = name.split('/')[-1].split('.fna.gz')[0]
+        else:
+            qry = name.split('.fna.gz')[0]
+    elif '.fasta.gz' in name:
+        if '/' in name:
+            qry = name.split('/')[-1].split('.fasta.gz')[0]
+        else:
+            qry = name.split('.fasta.gz')[0]
+    else:
+        qry = name
+    return qry
+
 def view_tree(newick, taxonomy, mode):
     if taxonomy is None:
         from ete3 import PhyloTree, TreeStyle, NodeStyle, TextFace
@@ -118,6 +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'
@@ -147,35 +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) + ']')
@@ -234,6 +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):