kssdtree 2.0.6__tar.gz → 2.0.8__tar.gz

{kssdtree-2.0.6/kssdtree.egg-info → kssdtree-2.0.8}/PKG-INFO

@@ -1,8 +1,12 @@
 Metadata-Version: 2.1
 Name: kssdtree
-Version: 2.0.6
+Version: 2.0.8
 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
+Requires-Dist: pyqt5
+Requires-Dist: ete3
+Requires-Dist: requests
+Requires-Dist: pandas

kssdtree-2.0.8/README.md

@@ -0,0 +1,66 @@
+#  Kssdtree: an interactive Python package for phylogenetic analysis based on sketching technique
+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.
+# 1. Installation 
+Kssdtree requires the Python 3 environment and the dependent packages pandas, pyqt5, ete3, and requests. If Kssdtree is installed using the pip command, these dependencies will be installed automatically. For MacOS, it requires Python 3.8 or higher version. For Windows, it requires Python 3.6 version and the installation of the gzip tool(https://gnuwin32.sourceforge.net/packages/gzip.htm) for sequence decompression.
+## 1.1 Linux
+
+```
+pip install kssdtree
+```
+## 1.2 MacOS
+
+```
+# (Optional) Install gcc (/opt/homebrew/bin/gcc-12) 
+brew install gcc@12
+
+# Create a virtual environment
+conda create --name=kssdtree python=3.10
+
+# Activate the virtual environment
+conda activate kssdtree
+
+# Install kssdtree
+pip install kssdtree
+```
+## 1.3 Windows
+
+```
+# Create a virtual environment
+conda create --name=kssdtree python=3.6.13
+
+# Activate the virtual environment
+conda activate kssdtree
+
+# (Optional) Install libpython and m2w64-toolchain
+conda install libpython m2w64-toolchain -c msys2
+
+# Install kssdtree
+pip install kssdtree
+```
+# 2. Quick-Tutorial 
+## 2.1 Routine Pipeline
+
+```
+import kssdtree
+kssdtree.quick(shuf_file='./shuf_files/L3K10.shuf', genome_files='your input genomes path', output='output.newick',  method='nj', mode='r')
+```
+## 2.2 Reference Subtraction Pipeline
+
+```
+import kssdtree
+kssdtree.quick(shuf_file='./shuf_files/L3K10.shuf', genome_files='your input genomes path', output='output.newick', reference='your reference genome path', method='nj', mode='r')
+```
+## 2.3 GTDB-based Phylogenetic Placement Pipeline
+
+```
+import kssdtree
+kssdtree.quick(shuf_file='./shuf_files/L3K9.shuf', genome_files='your input genomes path', output='your output path', database='gtdbr214', method='nj', mode='r', N=30)
+```
+More usages about Kssdtree, please see Kssdtree documentation (https://kssdtree.readthedocs.io/en/latest).
+# 3. How to cite
+Hang Yang, Xiaoxin Lu, Jiaxing Chang, Qing Chang, Wen Zheng, Zehua Chen, Huiguang Yi, Kssdtree: an interactive Python package for phylogenetic analysis based on sketching technique, Bioinformatics, Volume 40, Issue 10, October 2024, btae566, https://doi.org/10.1093/bioinformatics/btae566

{kssdtree-2.0.6 → kssdtree-2.0.8}/command_dist.c

@@ -309,7 +309,7 @@ const char *test_get_fullpath(const char *parent_path, const char *dstat_f) {
         return NULL;
 };
 
-const char gzpipe_cmc[] = "gzip -f";
+//const char gzpipe_cmc[] = "gzip -f";
 
 const char *run_stageI(dist_opt_val_t *opt_val, infile_tab_t *seqfile_stat,
                        int *shuffled_seqfname_ind, const char *co_dir, int p_fit_mem) {
@@ -327,18 +327,18 @@ const char *run_stageI(dist_opt_val_t *opt_val, infile_tab_t *seqfile_stat,
         }
     } else {
         int num_threads = seqfile_stat->infile_num > p_fit_mem ? p_fit_mem : 1;
-#ifdef _WIN32
-//        printf("Windows\n");
-        for (int i = 0; i < seqfile_stat->infile_num; i++) {
-            char fas_fname[PATHLEN];
-            char *seqfname = seqfile_stat->organized_infile_tab[shuffled_seqfname_ind[i]].fpath;
-            if (strstr(seqfname, ".gz") == NULL) {
-                sprintf(fas_fname, "%s %s", gzpipe_cmc, seqfname);
-                popen(fas_fname, "r");
-                seqfile_stat->organized_infile_tab[shuffled_seqfname_ind[i]].fpath = strcat(seqfname, ".gz");
-            }
-        }
-#endif
+//#ifdef _WIN32
+//      printf("Windows\n");
+//        for (int i = 0; i < seqfile_stat->infile_num; i++) {
+//            char fas_fname[PATHLEN];
+//            char *seqfname = seqfile_stat->organized_infile_tab[shuffled_seqfname_ind[i]].fpath;
+//            if (strstr(seqfname, ".gz") == NULL) {
+//                sprintf(fas_fname, "%s %s", gzpipe_cmc, seqfname);
+//                popen(fas_fname, "r");
+//                seqfile_stat->organized_infile_tab[shuffled_seqfname_ind[i]].fpath = strcat(seqfname, ".gz");
+//            }
+//        }
+//#endif
 #pragma omp parallel for num_threads(num_threads) reduction(+:all_ctx_ct) schedule(guided)
         for (int i = 0; i < seqfile_stat->infile_num; i++) {
             int tid = 0;

{kssdtree-2.0.6 → kssdtree-2.0.8}/iseq2comem.c

@@ -180,12 +180,23 @@ int reads2mco(char *seqfname, const char *co_dir, char *pipecmd) {
     printf("decomposing %s by reads is complete!\n", seqfname);
     return 1;
 }
+
+int is_gz_file(const char *seqfname) {
+    if (seqfname == NULL) return 0;
+
+    size_t len = strlen(seqfname);
+    if (len < 3) return 0;
+
+    return strcmp(seqfname + len - 3, ".gz") == 0;
+}
+
 #ifdef _WIN32
 const char gzpipe_cmd[] = "gzip -dc";
 #else
 const char gzpipe_cmd[] = "zcat -fc";
 #endif
 llong *fasta2co(char *seqfname, llong *co, char *pipecmd) {
+    printf("The fasta2co seqfname is: %s\n", seqfname);
     llong tuple = 0LLU, crvstuple = 0LLU,
             unituple, drtuple, pfilter;
     memset(co, 0LLU, hashsize * sizeof(llong));
@@ -196,7 +207,18 @@ llong *fasta2co(char *seqfname, llong *co, char *pipecmd) {
         sprintf(fas_fname, "%s %s", pipecmd, seqfname);
     else
         sprintf(fas_fname, "%s %s", gzpipe_cmd, seqfname);
-    if ((infp = popen(fas_fname, "r")) == NULL) fprintf(stderr, "fasta2co():%s", fas_fname);
+    printf("The fasta2co fas_fname is: %s\n", fas_fname);
+    if (is_gz_file(seqfname)){
+        printf(".gz format\n");
+        if ((infp = popen(fas_fname, "r")) == NULL) fprintf(stderr, "fasta2co():%s", fas_fname, "\n");
+    }else{
+        printf("not .gz format\n");
+        #ifdef _WIN32
+        if ((infp = fopen(seqfname, "r")) == NULL) fprintf(stderr, "fasta2co():%s", fas_fname, "\n");
+        #else
+        if ((infp = popen(fas_fname, "r")) == NULL) fprintf(stderr, "fasta2co():%s", fas_fname, "\n");
+        #endif
+    }
     int newLen = fread(seqin_buff, sizeof(char), READSEQ_BUFFSZ, infp);
     if (!(newLen > 0)) fprintf(stderr, "fastco():eof or fread error file=%s", seqfname);
     llong base = 1;
@@ -269,6 +291,7 @@ llong *fasta2co(char *seqfname, llong *co, char *pipecmd) {
 #define CT_MAX 0xfLLU
 
 llong *fastq2co(char *seqfname, llong *co, char *pipecmd, int Q, int M) {
+    printf("The fastq2co seqfname is: %s\n", seqfname);
     if (M >= CT_MAX) fprintf(stderr, "fastq2co(): Occurence num should smaller than %d", (int) CT_MAX);
     llong tuple = 0LLU, crvstuple = 0LLU, unituple, drtuple, pfilter;
     memset(co, 0LLU, hashsize * sizeof(llong));
@@ -278,7 +301,18 @@ llong *fastq2co(char *seqfname, llong *co, char *pipecmd, int Q, int M) {
         sprintf(fq_fname, "%s %s", pipecmd, seqfname);
     else
         sprintf(fq_fname, "%s %s", gzpipe_cmd, seqfname);
-    if ((infp = popen(fq_fname, "r")) == NULL) fprintf(stderr, "fastq2co():%s", fq_fname);
+    printf("The fastq2co fq_fname is: %s\n", fq_fname);
+    if (is_gz_file(seqfname)){
+        printf(".gz format\n");
+        if ((infp = popen(fq_fname, "r")) == NULL) fprintf(stderr, "fastq2co():%s", fq_fname, "\n");
+    }else{
+        printf("not .gz format\n");
+        #ifdef _WIN32
+        if ((infp = fopen(seqfname, "r")) == NULL) fprintf(stderr, "fastq2co():%s", fq_fname, "\n");
+        #else
+        if ((infp = popen(fq_fname, "r")) == NULL) fprintf(stderr, "fastq2co():%s", fq_fname, "\n");
+        #endif
+    }
     char *seq = malloc(LEN + 10);
     char *qual = malloc(LEN + 10);
     fgets(seq, LEN, infp);
@@ -354,6 +388,7 @@ llong *fastq2co(char *seqfname, llong *co, char *pipecmd, int Q, int M) {
 #define OCCRC_MAX 0xffffLLU
 
 llong *fastq2koc(char *seqfname, llong *co, char *pipecmd, int Q) {
+    printf("The fastq2koc seqfname is: %s\n", seqfname);
     llong tuple = 0LLU, crvstuple = 0LLU, unituple, drtuple, pfilter;
     memset(co, 0LLU, hashsize * sizeof(llong));
     FILE *infp;
@@ -362,7 +397,18 @@ llong *fastq2koc(char *seqfname, llong *co, char *pipecmd, int Q) {
         sprintf(fq_fname, "%s %s", pipecmd, seqfname);
     else
         sprintf(fq_fname, "%s %s", gzpipe_cmd, seqfname);
-    if ((infp = popen(fq_fname, "r")) == NULL) fprintf(stderr, "fastq2koc():%s", fq_fname);
+    printf("The fastq2koc fq_fname is: %s\n", fq_fname);
+    if (is_gz_file(seqfname)){
+        printf(".gz format\n");
+        if ((infp = popen(fq_fname, "r")) == NULL) fprintf(stderr, "fastq2koc():%s", fq_fname, "\n");
+    }else{
+        printf("not .gz format\n");
+        #ifdef _WIN32
+        if ((infp = fopen(seqfname, "r")) == NULL) fprintf(stderr, "fastq2koc():%s", fq_fname, "\n");
+        #else
+        if ((infp = popen(fq_fname, "r")) == NULL) fprintf(stderr, "fastq2koc():%s", fq_fname, "\n");
+        #endif
+    }
     char *seq = malloc(LEN + 10);
     char *qual = malloc(LEN + 10);
     fgets(seq, LEN, infp);

{kssdtree-2.0.6 → kssdtree-2.0.8/kssdtree.egg-info}/PKG-INFO

@@ -1,8 +1,12 @@
 Metadata-Version: 2.1
 Name: kssdtree
-Version: 2.0.6
+Version: 2.0.8
 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
+Requires-Dist: pyqt5
+Requires-Dist: ete3
+Requires-Dist: requests
+Requires-Dist: pandas

{kssdtree-2.0.6 → kssdtree-2.0.8}/setup.py

@@ -87,7 +87,7 @@ require_pakages = [
 
 setup(
     name='kssdtree',
-    version='2.0.6',
+    version='2.0.8',
     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-2.0.6 → kssdtree-2.0.8}/toolutils.py

@@ -213,7 +213,7 @@ def view_tree(newick, taxonomy, mode):
         with open(taxonomy_path, 'r') as file:
             for line in file:
                 columns = line.split()
-                if len(columns) == 2:
+                if len(columns) > 1:
                     column_1 = columns[0]
                     column_2 = columns[1:]
                     tempfile = ''

kssdtree-2.0.6/README.md

@@ -1,8 +0,0 @@
-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).