kssdtree 2.0.2__tar.gz → 2.0.4__tar.gz

{kssdtree-2.0.2/kssdtree.egg-info → kssdtree-2.0.4}/PKG-INFO

@@ -1,8 +1,11 @@
-Metadata-Version: 2.1
+Metadata-Version: 1.1
 Name: kssdtree
-Version: 2.0.2
+Version: 2.0.4
 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/README.md

@@ -0,0 +1,8 @@
+Kssdtree is a versatile Python package for phylogenetic analysis, offering three distinct pipelines: the Routine Pipeline, the Reference Subtraction Pipeline, and the GTDB-based Phylogenetic Placement Pipeline.
+
+Routine Pipeline: A general-purpose tool for phylogenetic analysis of user genomic data.
+Reference Subtraction Pipeline: Designed for intra-species phylogenomic analysis.
+GTDB-based Phylogenetic Placement Pipeline: Facilitates the search for similar genomes in the Genome Taxonomy Database (GTDB), conducting phylogenetic analysis alongside these genomes and positioning the input genomes within the entire prokaryotic tree of life.
+Kssdtree also provides one-stop tree construction and visualization. It can handle DNA sequences in both fasta and fastq formats, whether gzipped or not. Additionally, Kssdtree is compatible with multiple platforms (Linux, MacOS, and Windows) and can be run using Jupyter notebooks.
+
+More usages about Kssdtree, please see Kssdtree documentation (https://kssdtree.readthedocs.io/en/latest).

{kssdtree-2.0.2 → kssdtree-2.0.4}/command_set.c

@@ -25,7 +25,6 @@
 #include <errno.h>
 #include <math.h>
 #include <unistd.h>
-
 const char skch_prefix[]="combco";
 const char idx_prefix[]="combco.index";
 const char pan_prefix[]="pan";

{kssdtree-2.0.2 → kssdtree-2.0.4/kssdtree.egg-info}/PKG-INFO

@@ -1,8 +1,11 @@
-Metadata-Version: 2.1
+Metadata-Version: 1.1
 Name: kssdtree
-Version: 2.0.2
+Version: 2.0.4
 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-2.0.2 → kssdtree-2.0.4}/kssdtree.py

@@ -28,23 +28,18 @@ 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)
-                import http.client
-                http.client.HTTPConnection._http_vsn = 10
-                http.client.HTTPConnection._http_vsn_str = 'HTTP/1.0'
                 if shuf_file == 'L3K9.shuf' or shuf_file == './L3K9.shuf':
                     url = 'https://zenodo.org/records/12699159/files/L3K9.shuf?download=1'
                 else:
                     url = 'https://zenodo.org/records/12699159/files/L3K10.shuf?download=1'
-                start_time = time.time()
-                response = requests.get(url, stream=True)
-                with open(shuf_file, 'wb') as file:
-                    for chunk in response.iter_content(chunk_size=1024):
-                        if chunk:
-                            file.write(chunk)
+                headers = {'Accept-Encoding': 'gzip, deflate'}
+                response = requests.get(url, headers=headers, stream=True)
+                with open(shuf_file, 'wb') as f:
+                    for chunk in response.iter_content(chunk_size=8192):
+                        f.write(chunk)
                 end_time = time.time()
-                if end_time - start_time > 120:
-                    print(
-                        "Network timeout, please manually download from https://zenodo.org/records/12699159")
+                if end_time - start_time > 200:
+                    print("Network timeout, please manually download from https://zenodo.org/records/12699159")
                     return False
                 print('Download finished: ', shuf_file)
             elif shuf_file in ['L2K8.shuf', 'L2K9.shuf', 'L3K11.shuf', './L2K8.shuf', './L2K9.shuf', './L3K11.shuf']:
@@ -64,9 +59,9 @@ 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!')
@@ -76,7 +71,7 @@ def sketch(shuf_file=None, genome_files=None, output=None, set_opt=None):
         return False
 
 
-def dist(genome_sketch=None, output=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)
@@ -86,6 +81,9 @@ def dist(genome_sketch=None, output=None, flag=None):
         #     return False
         if flag is None:
             flag = 0
+        if metric is None:
+            metric = 'mash'
+        
         print('Disting...')
         start = time.time()
         if '/' in output:
@@ -97,11 +95,15 @@ def dist(genome_sketch=None, output=None, flag=None):
         else:
             output_name = output
         if output_name.endswith(".phy") or output_name.endswith(".phylip"):
-            kssd.dist_dispatch(genome_sketch, output, genome_sketch, 2, 0, flag)
-            end = time.time()
-            print('Dist spend time：%.2fs' % (end - start))
-            print('Dist finished!')
-            return True
+            if metric not in ['mash', 'aaf']:
+                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)
+                end = time.time()
+                print('Dist spend time：%.2fs' % (end - start))
+                print('Dist finished!')
+                return True
         else:
             print('Output type error, only supports .phylip (.phy) format:', output_name)
             return False

{kssdtree-2.0.2 → kssdtree-2.0.4}/mman.c

@@ -1,4 +1,3 @@
-
 #ifdef _WIN32
 #include <windows.h>
 #include <io.h>

{kssdtree-2.0.2 → kssdtree-2.0.4}/pykssd.c

@@ -121,12 +121,18 @@ int create_matrix(char *input_name, char *output_name, int flag) {
             for (int j = 0; j <= i; j++)
                 distances[i][j] = 0.0;
         }
-    } else {
+    } else if (flag == 1) {
         for (int i = 0; i < num_seqs; i++) {
             distances[i] = malloc(i * sizeof(double));
             for (int j = 0; j < i; j++)
                 distances[i][j] = 0.0;
         }
+    } else {
+        for (int i = 0; i < num_seqs; i++) {
+            distances[i] = malloc(num_seqs * sizeof(double));
+            for (int j = 0; j < num_seqs; j++)
+                distances[i][j] = 0.0;
+        }
     }
     rewind(fp);
     fgets(line, PATHLEN, fp);
@@ -144,7 +150,7 @@ int create_matrix(char *input_name, char *output_name, int flag) {
                 j += 1;
             }
         }
-    } else {
+    } else if (flag == 1) {
         while (fgets(line, PATHLEN, fp) != NULL) {
             sscanf(line, "%*s %*s %*s %*s %lf", &distance);
             if (j < i) {
@@ -156,6 +162,16 @@ int create_matrix(char *input_name, char *output_name, int flag) {
                 j += 1;
             }
         }
+    } else {
+        while (fgets(line, PATHLEN, fp) != NULL) {
+            sscanf(line, "%*s %*s %*s %*s %lf", &distance);
+            distances[i][j] = distance;
+            i += 1;
+            if (i == num_seqs && j < num_seqs) {
+                i = 0;
+                j += 1;
+            }
+        }
     }
 
     for (int i = 0; i < num_seqs; i++) {
@@ -187,7 +203,7 @@ int create_matrix(char *input_name, char *output_name, int flag) {
             }
             fprintf(fo, "\n");
         }
-    } else {
+    } else if (flag == 1) {
         for (int i = 0; i < num_seqs; i++) {
             fprintf(fo, "%s\t", seq_names[i]);
             for (int j = 0; j < num_seqs; j++) {
@@ -197,6 +213,14 @@ int create_matrix(char *input_name, char *output_name, int flag) {
             }
             fprintf(fo, "\n");
         }
+    } else {
+        for (int i = 0; i < num_seqs; i++) {
+            fprintf(fo, "%s\t", seq_names[i]);
+            for (int j = 0; j < num_seqs; j++) {
+                fprintf(fo, "%.6f\t", distances[i][j]);
+            }
+            fprintf(fo, "\n");
+        }
     }
     for (int i = 0; i < num_seqs; i++) {
         free(distances[i]);
@@ -235,8 +259,9 @@ static PyObject *py_dist_dispatch(PyObject *self, PyObject *args) {
     char *str3;
     int flag1;
     int flag2;
+    char *str4;
     int N;
-    if (!PyArg_ParseTuple(args, "sssiii", &str1, &str2, &str3, &flag1, &N, &flag2)) {
+    if (!PyArg_ParseTuple(args, "sssiiis", &str1, &str2, &str3, &flag1, &N, &flag2, &str4)) {
         return NULL;
     }
     if (flag1 == 0) {
@@ -394,6 +419,11 @@ static PyObject *py_dist_dispatch(PyObject *self, PyObject *args) {
         dist_opt_val3.num_remaining_args = 1;
         dist_opt_val3.remaining_args = &str3;
         dist_opt_val3.num_neigb = N;
+	if (strcmp(str4, "mash") == 0) {
+		dist_opt_val3.metric = 0;
+	} else {
+		dist_opt_val3.metric = 1;
+	}
 #ifdef _OPENMP
         if(dist_opt_val3.p == 0)
             dist_opt_val3.p = omp_get_num_procs();
@@ -628,4 +658,4 @@ static struct PyModuleDef kssdmodule = {
 
 PyMODINIT_FUNC PyInit_kssd(void) {
     return PyModule_Create(&kssdmodule);
-}
+}

{kssdtree-2.0.2 → kssdtree-2.0.4}/setup.py

@@ -3,11 +3,6 @@ from setuptools import setup, Extension, find_packages
 from os import environ
 import os
 
-# def get_gcc_version():
-#     gcc_version = subprocess.check_output(['gcc', '--version']).decode('utf-8')
-#     version_line = gcc_version.split('\n', 1)[0]
-#     version_str = version_line.split()[-1]
-#     return version_str
 extra_compile_args = []
 extra_link_args = []
 if 'darwin' in sys.platform:
@@ -24,12 +19,12 @@ if 'darwin' in sys.platform:
             gcc_path = "/opt/homebrew/bin/gcc-11"
         elif 'gcc-12' == gcc_version:
             gcc_path = "/opt/homebrew/bin/gcc-12"
+        elif 'gcc-13' == gcc_version:
+            gcc_path = "/opt/homebrew/bin/gcc-13"
         elif 'gcc-14' == gcc_version:
             gcc_path = "/opt/homebrew/bin/gcc-14"
-        elif 'gcc-15' == gcc_version:
-            gcc_path = "/opt/homebrew/bin/gcc-15"
         else:
-            gcc_path = "/opt/homebrew/bin/gcc-13"
+            gcc_path = ""
         extra_compile_args = ['-fopenmp']
         extra_link_args = ['-fopenmp']
         os.environ["CC"] = gcc_path
@@ -92,7 +87,7 @@ require_pakages = [
 
 setup(
     name='kssdtree',
-    version='2.0.2',
+    version='2.0.4',
     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. ",
@@ -114,3 +109,4 @@ setup(
     zip_safe=False,
     include_package_data=True
 )
+

{kssdtree-2.0.2 → kssdtree-2.0.4}/toolutils.py

@@ -8,7 +8,7 @@ import pandas as pd
 import string
 
 def allowed_file(filename):
-    allowed_extensions = ['.fa', '.fa.gz', '.fasta', '.fasta.gz', '.fna', '.fna.gz', '.fastq', '.fastq.gz']
+    allowed_extensions = ['.fa', '.fa.gz', '.fasta', '.fasta.gz', '.fna', '.fna.gz', '.fastq', '.fastq.gz', '.fq', '.fq.gz']
     return any(filename.endswith(ext) for ext in allowed_extensions)
 
 def rs():

kssdtree-2.0.2/README.md

@@ -1,12 +0,0 @@
-# Kssdree: an interactive Python package for phylogenetic analysis based on sketching technique
-
-Kssdtree is a versatile Python package for phylogenetic analysis, including three different pipelines: routine pipeline, reference subtraction pipeline and phylogenetic placement pipeline. The routine pipeline serves as a versatile tool for general-purpose phylogenetic analysis of users' genomic data.  The reference subtraction pipeline designs for population-level phylogenetic analysis. The phylogenetic placement pipeline facilitates the search for similar genomes in the Genome Taxonomy Database (GTDB). It conducts phylogenetic analysis alongside these similar genomes and positions the input genomes within the entire prokaryotic tree of life. 
-
-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 can run on multiple platforms (Linux, Windows, and MacOS) with Jupyter notebooks.
-
-More usages about Kssdtree, please see Kssdtree documentation (https://kssdtree.readthedocs.io/en/latest).
- 
-
-
-
-