FunVIP 0.3.23__tar.gz → 0.3.23.2__tar.gz

{funvip-0.3.23 → funvip-0.3.23.2}/FunVIP.egg-info/PKG-INFO

@@ -1,22 +1,22 @@
 Metadata-Version: 2.1
 Name: FunVIP
-Version: 0.3.23
+Version: 0.3.23.2
 Summary: Fungal Validation & Identification Pipeline
 Author-email: Changwan Seo <wan101010@snu.ac.kr>
 License: GPL-3.0
 Project-URL: Homepage, https://github.com/Changwanseo/FunVIP
-Requires-Python: <3.13,>3.8
+Requires-Python: <=3.12,>=3.9
 License-File: LICENSE
-Requires-Dist: biopython==1.78
+Requires-Dist: biopython==1.84
 Requires-Dist: ete3==3.1.3
 Requires-Dist: Cython
 Requires-Dist: dendropy
 Requires-Dist: GenMine<1.2.0,>=1.1.0
 Requires-Dist: lxml
 Requires-Dist: matplotlib
-Requires-Dist: numpy
-Requires-Dist: openpyxl==3.0.9
-Requires-Dist: pandas==1.4.2
+Requires-Dist: numpy<2.0.0
+Requires-Dist: openpyxl==3.1.0
+Requires-Dist: pandas==2.2.2
 Requires-Dist: plotly==5.9.0
 Requires-Dist: psutil
 Requires-Dist: pyyaml

{funvip-0.3.23 → funvip-0.3.23.2}/FunVIP.egg-info/requires.txt

@@ -1,13 +1,13 @@
-biopython==1.78
+biopython==1.84
 ete3==3.1.3
 Cython
 dendropy
 GenMine<1.2.0,>=1.1.0
 lxml
 matplotlib
-numpy
-openpyxl==3.0.9
-pandas==1.4.2
+numpy<2.0.0
+openpyxl==3.1.0
+pandas==2.2.2
 plotly==5.9.0
 psutil
 pyyaml

{funvip-0.3.23 → funvip-0.3.23.2}/PKG-INFO

@@ -1,22 +1,22 @@
 Metadata-Version: 2.1
 Name: FunVIP
-Version: 0.3.23
+Version: 0.3.23.2
 Summary: Fungal Validation & Identification Pipeline
 Author-email: Changwan Seo <wan101010@snu.ac.kr>
 License: GPL-3.0
 Project-URL: Homepage, https://github.com/Changwanseo/FunVIP
-Requires-Python: <3.13,>3.8
+Requires-Python: <=3.12,>=3.9
 License-File: LICENSE
-Requires-Dist: biopython==1.78
+Requires-Dist: biopython==1.84
 Requires-Dist: ete3==3.1.3
 Requires-Dist: Cython
 Requires-Dist: dendropy
 Requires-Dist: GenMine<1.2.0,>=1.1.0
 Requires-Dist: lxml
 Requires-Dist: matplotlib
-Requires-Dist: numpy
-Requires-Dist: openpyxl==3.0.9
-Requires-Dist: pandas==1.4.2
+Requires-Dist: numpy<2.0.0
+Requires-Dist: openpyxl==3.1.0
+Requires-Dist: pandas==2.2.2
 Requires-Dist: plotly==5.9.0
 Requires-Dist: psutil
 Requires-Dist: pyyaml

{funvip-0.3.23 → funvip-0.3.23.2}/README.md

@@ -22,11 +22,12 @@ An automatic tree-based sequence identification and validation pipeline for fung
 - Data validation algorithm implemented
 
 
-# See [tutorial](https://github.com/Changwanseo/FunVIP/blob/main/tutorial/tutorial.md) for detailed usage
+## See [tutorial](https://github.com/Changwanseo/FunVIP/blob/main/tutorial/tutorial.md) for step by step tutorial
+## See [documentation](https://github.com/Changwanseo/FunVIP/blob/main/Documentation.md) for advanced usage
 
 
 ## Requirements
-- Conda environment (See [https://www.anaconda.com/products/individual](https://conda.io/projects/conda/en/latest/user-guide/install/index.html) to how to install conda environment)
+- Conda environment (See [https://www.anaconda.com/products/individual](https://conda.io/projects/conda/en/latest/user-guide/install/index.html) for how to install conda environment)
 
 <!--
 ## Installation with conda (May not work with Linux or Mac)
@@ -37,7 +38,8 @@ An automatic tree-based sequence identification and validation pipeline for fung
 If this one fails, use next one
 -->
 
-## Windows
+## Installation
+### Windows
 1. Install visual c++ [here](https://visualstudio.microsoft.com/visual-cpp-build-tools/)
 2. ```conda create -n FunVIP python>=3.8```
 3. ```conda activate FunVIP```
@@ -47,17 +49,18 @@ If this one fails, use next one
 * For upgrade use this command
 ``` pip install FunVIP --upgrade ```
 
-## Linux
+### Linux
 1. ```conda create -n FunVIP python>=3.8```
 2. ```conda activate FunVIP```
 3. ```pip install FunVIP```
-4. ```conda install -c bioconda raxml iqtree modeltest-ng mmseqs2 "blast>=2.12" mafft trimal gblocks fasttree```
-5. run ```FunVIP --test Terrei --email [your email] ``` to check installation
+4. ```conda config --add channels conda-forge```
+5. ```conda install -c bioconda raxml iqtree "modeltest-ng>=0.1.7" mmseqs2 "blast>=2.12" mafft trimal gblocks fasttree```
+6. run ```FunVIP --test Terrei --email [your email] ``` to check installation
 
 
 * For intel mac system, this method probably work, but we couldn't test it because we don't have any intel mac device. We're looking for feedbacks in intel mac
 
-## Apple Silicon Mac
+### Apple Silicon Mac
 1. ```CONDA_SUBDIR=osx-64 conda create -n FunVIP python>=3.8```
 2. ```conda activate FunVIP```
 3. ```conda config --env --set subdir osx-64```
@@ -66,7 +69,7 @@ If this one fails, use next one
 6. ```conda install -c bioconda raxml iqtree mmseqs2 "blast>=2.12" mafft trimal gblocks fasttree```
 7. run ```FunVIP --test Terrei --email [your email] ``` to check installation
 
-## Installation from source (For developers and core users)
+### Installation from source (For developers and core users)
 * this is for developmental steps
 1. ```git clone https://github.com/Changwanseo/FunVIP.git```
 2. Move to ```~/FunVIP```

{funvip-0.3.23 → funvip-0.3.23.2}/funvip/external/BLAST_Windows/bin/cleanup-blastdb-volumes.py

@@ -1,162 +1,162 @@
-#!/usr/bin/env python3
-"""
-# $Id: cleanup-blastdb-volumes.py 590894 2019-08-07 14:59:53Z camacho $
-# ===========================================================================
-# 
-#                            PUBLIC DOMAIN NOTICE
-#               National Center for Biotechnology Information
-# 
-#  This software/database is a "United States Government Work" under the
-#  terms of the United States Copyright Act.  It was written as part of
-#  the author's official duties as a United States Government employee and
-#  thus cannot be copyrighted.  This software/database is freely available
-#  to the public for use. The National Library of Medicine and the U.S.
-#  Government have not placed any restriction on its use or reproduction.
-# 
-#  Although all reasonable efforts have been taken to ensure the accuracy
-#  and reliability of the software and data, the NLM and the U.S.
-#  Government do not and cannot warrant the performance or results that
-#  may be obtained by using this software or data. The NLM and the U.S.
-#  Government disclaim all warranties, express or implied, including
-#  warranties of performance, merchantability or fitness for any particular
-#  purpose.
-# 
-#  Please cite the author in any work or product based on this material.
-# 
-# ===========================================================================
-# 
-# Author:  Christiam Camacho
-# 
-# File Description:
-#   Script to remove needless BLAST database files.
-# 
-# ===========================================================================
-"""
-import argparse, os, configparser
-import unittest, tempfile
-from pathlib import Path
-from glob import glob
-
-VERSION = '1.0'
-DESC = r""" Remove needless BLAST database volumes.  """
-
-
-class Tester(unittest.TestCase):
-    """ Testing class for this script. """
-
-    def test_blastdb_config_invalid(self):
-        rv = get_blastdb_from_ncbi_config("/dev/null")
-        self.assertIsNone(rv)
-
-    def test_blastdb_config(self):
-        config = configparser.ConfigParser()
-        expected = "/blast/db/blast"
-        config['BLAST'] = {'BLASTDB': expected}
-        tf = tempfile.NamedTemporaryFile(mode="wt")
-        config.write(tf)
-        tf.flush()
-        rv = get_blastdb_from_ncbi_config(tf.name)
-        self.assertEqual(expected, rv)
-
-    def test_blastdb_finder(self):
-        tal = tempfile.NamedTemporaryFile(suffix=".pin")
-        dbname = find_blastdb(tal.name[:-4], True)
-        self.assertEqual(dbname, tal.name[:-4])
-
-
-def find_blastdb(name: str, is_prot: bool) -> str:
-    """ Returns full path to BLAST database or None. """
-    alias_file = "{}.{}al".format(name, "p" if is_prot else "n")
-    index_file = "{}.{}in".format(name, "p" if is_prot else "n")
-    if os.path.exists(alias_file) or os.path.exists(index_file):
-        return name
-
-    if "BLASTDB" in os.environ:
-        alf = os.path.join(os.environ["BLASTDB"], alias_file)
-        idxf = os.path.join(os.environ["BLASTDB"], index_file)
-        if os.path.exists(alf) or os.path.exists(idxf):
-            return os.path.join(os.environ["BLASTDB"], name)
-
-    paths = [ os.getcwd(), str(Path.home()) ]
-    if "NCBI" in os.environ:
-        paths.append(os.path.join(os.environ["NCBI"]))
-
-    for path in paths:
-        for fname in [ ".ncbirc", "ncbi.ini" ]:
-            ncbirc = os.path.join(path, fname)
-            if os.path.exists(ncbirc):
-                blastdb = get_blastdb_from_ncbi_config(ncbirc)
-                if blastdb is not None:
-                    alf = os.path.join(blastdb, alias_file)
-                    idxf = os.path.join(blastdb, index_file)
-                    if os.path.exists(alf) or os.path.exists(idxf):
-                        return os.path.join(blastdb, name)
-
-
-def get_blastdb_from_ncbi_config(config_file: str) -> str:
-    """ Return the BLASTDB setting from the NCBI configuration file or None. """
-    config = configparser.ConfigParser()
-    config.read(config_file)
-    if 'BLAST' in config and 'BLASTDB' in config['BLAST']:
-        return config['BLAST']['BLASTDB']
-
-
-def main():
-    """ Entry point into this program. """
-    parser = create_arg_parser()
-    args = parser.parse_args()
-
-    ext = args.dbtype[0]
-    db = find_blastdb(args.db, ext == 'p')
-    if db == None:
-        print("Cannot find {} {} BLAST database".
-              format("protein" if ext == 'p' else "nucleotide", args.db),
-              file=sys.stderr)
-        return 1
-
-    alias_file = "{}.{}al".format(db, ext)
-    if not os.path.exists(alias_file):
-        return 1
-
-    with open(alias_file, "rt") as al:
-        for line in al:
-            if not line.startswith("DBLIST"):
-                continue
-            vols = list(map(lambda x: x.replace('"', ''), line.split()[1:]))
-            for existing_vols in sorted(glob("{}.*.{}in".format(db, ext))):
-                vol_name = os.path.basename(existing_vols)[:-4]
-                if vol_name in vols:
-                    continue
-                if args.dry_run:
-                    print("Will remove extra volume {}".format(existing_vols[:-4]))
-                to_rm = glob("{}??".format(existing_vols[:-2]))
-                to_rm += glob("{}.tar.gz.md5".format(existing_vols[:-4]))
-                for f in to_rm:
-                    if not args.dry_run:
-                        os.unlink(f)
-                        print("Removed {}".format(f))
-                    elif args.verbose > 0:
-                        print("Will remove {}".format(f))
-
-    return 0
-
-
-def create_arg_parser():
-    """ Create the command line options parser object for this script. """
-    parser = argparse.ArgumentParser(description=DESC)
-    parser.add_argument("-db", required=True, help="BLAST database name")
-    parser.add_argument("-dbtype", help="Molecule type", required=True,
-                        choices=["prot", "nucl"])
-    parser.add_argument("-dry-run", action='store_true',
-                        help="Do not delete any files, just list them")
-    parser.add_argument('-version', action='version',
-                        version='%(prog)s ' + VERSION)
-    parser.add_argument("-verbose", action="count", default=0,
-                        help="Increase output verbosity")
-    return parser
-
-
-if __name__ == "__main__":
-    import sys
-    sys.exit(main())
-
+#!/usr/bin/env python3
+"""
+# $Id: cleanup-blastdb-volumes.py 590894 2019-08-07 14:59:53Z camacho $
+# ===========================================================================
+# 
+#                            PUBLIC DOMAIN NOTICE
+#               National Center for Biotechnology Information
+# 
+#  This software/database is a "United States Government Work" under the
+#  terms of the United States Copyright Act.  It was written as part of
+#  the author's official duties as a United States Government employee and
+#  thus cannot be copyrighted.  This software/database is freely available
+#  to the public for use. The National Library of Medicine and the U.S.
+#  Government have not placed any restriction on its use or reproduction.
+# 
+#  Although all reasonable efforts have been taken to ensure the accuracy
+#  and reliability of the software and data, the NLM and the U.S.
+#  Government do not and cannot warrant the performance or results that
+#  may be obtained by using this software or data. The NLM and the U.S.
+#  Government disclaim all warranties, express or implied, including
+#  warranties of performance, merchantability or fitness for any particular
+#  purpose.
+# 
+#  Please cite the author in any work or product based on this material.
+# 
+# ===========================================================================
+# 
+# Author:  Christiam Camacho
+# 
+# File Description:
+#   Script to remove needless BLAST database files.
+# 
+# ===========================================================================
+"""
+import argparse, os, configparser
+import unittest, tempfile
+from pathlib import Path
+from glob import glob
+
+VERSION = '1.0'
+DESC = r""" Remove needless BLAST database volumes.  """
+
+
+class Tester(unittest.TestCase):
+    """ Testing class for this script. """
+
+    def test_blastdb_config_invalid(self):
+        rv = get_blastdb_from_ncbi_config("/dev/null")
+        self.assertIsNone(rv)
+
+    def test_blastdb_config(self):
+        config = configparser.ConfigParser()
+        expected = "/blast/db/blast"
+        config['BLAST'] = {'BLASTDB': expected}
+        tf = tempfile.NamedTemporaryFile(mode="wt")
+        config.write(tf)
+        tf.flush()
+        rv = get_blastdb_from_ncbi_config(tf.name)
+        self.assertEqual(expected, rv)
+
+    def test_blastdb_finder(self):
+        tal = tempfile.NamedTemporaryFile(suffix=".pin")
+        dbname = find_blastdb(tal.name[:-4], True)
+        self.assertEqual(dbname, tal.name[:-4])
+
+
+def find_blastdb(name: str, is_prot: bool) -> str:
+    """ Returns full path to BLAST database or None. """
+    alias_file = "{}.{}al".format(name, "p" if is_prot else "n")
+    index_file = "{}.{}in".format(name, "p" if is_prot else "n")
+    if os.path.exists(alias_file) or os.path.exists(index_file):
+        return name
+
+    if "BLASTDB" in os.environ:
+        alf = os.path.join(os.environ["BLASTDB"], alias_file)
+        idxf = os.path.join(os.environ["BLASTDB"], index_file)
+        if os.path.exists(alf) or os.path.exists(idxf):
+            return os.path.join(os.environ["BLASTDB"], name)
+
+    paths = [ os.getcwd(), str(Path.home()) ]
+    if "NCBI" in os.environ:
+        paths.append(os.path.join(os.environ["NCBI"]))
+
+    for path in paths:
+        for fname in [ ".ncbirc", "ncbi.ini" ]:
+            ncbirc = os.path.join(path, fname)
+            if os.path.exists(ncbirc):
+                blastdb = get_blastdb_from_ncbi_config(ncbirc)
+                if blastdb is not None:
+                    alf = os.path.join(blastdb, alias_file)
+                    idxf = os.path.join(blastdb, index_file)
+                    if os.path.exists(alf) or os.path.exists(idxf):
+                        return os.path.join(blastdb, name)
+
+
+def get_blastdb_from_ncbi_config(config_file: str) -> str:
+    """ Return the BLASTDB setting from the NCBI configuration file or None. """
+    config = configparser.ConfigParser()
+    config.read(config_file)
+    if 'BLAST' in config and 'BLASTDB' in config['BLAST']:
+        return config['BLAST']['BLASTDB']
+
+
+def main():
+    """ Entry point into this program. """
+    parser = create_arg_parser()
+    args = parser.parse_args()
+
+    ext = args.dbtype[0]
+    db = find_blastdb(args.db, ext == 'p')
+    if db == None:
+        print("Cannot find {} {} BLAST database".
+              format("protein" if ext == 'p' else "nucleotide", args.db),
+              file=sys.stderr)
+        return 1
+
+    alias_file = "{}.{}al".format(db, ext)
+    if not os.path.exists(alias_file):
+        return 1
+
+    with open(alias_file, "rt") as al:
+        for line in al:
+            if not line.startswith("DBLIST"):
+                continue
+            vols = list(map(lambda x: x.replace('"', ''), line.split()[1:]))
+            for existing_vols in sorted(glob("{}.*.{}in".format(db, ext))):
+                vol_name = os.path.basename(existing_vols)[:-4]
+                if vol_name in vols:
+                    continue
+                if args.dry_run:
+                    print("Will remove extra volume {}".format(existing_vols[:-4]))
+                to_rm = glob("{}??".format(existing_vols[:-2]))
+                to_rm += glob("{}.tar.gz.md5".format(existing_vols[:-4]))
+                for f in to_rm:
+                    if not args.dry_run:
+                        os.unlink(f)
+                        print("Removed {}".format(f))
+                    elif args.verbose > 0:
+                        print("Will remove {}".format(f))
+
+    return 0
+
+
+def create_arg_parser():
+    """ Create the command line options parser object for this script. """
+    parser = argparse.ArgumentParser(description=DESC)
+    parser.add_argument("-db", required=True, help="BLAST database name")
+    parser.add_argument("-dbtype", help="Molecule type", required=True,
+                        choices=["prot", "nucl"])
+    parser.add_argument("-dry-run", action='store_true',
+                        help="Do not delete any files, just list them")
+    parser.add_argument('-version', action='version',
+                        version='%(prog)s ' + VERSION)
+    parser.add_argument("-verbose", action="count", default=0,
+                        help="Increase output verbosity")
+    return parser
+
+
+if __name__ == "__main__":
+    import sys
+    sys.exit(main())
+