pdb-tools 2.4.12__tar.gz → 2.5.1__tar.gz

{pdb-tools-2.4.12 → pdb_tools-2.5.1}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: pdb-tools
-Version: 2.4.12
+Version: 2.5.1
 Summary: A swiss army knife for PDB files.
 Home-page: http://bonvinlab.org/pdb-tools
 Author: Joao Rodrigues
@@ -9,20 +9,30 @@ License: Apache Software License, version 2
 Project-URL: Bug Reports, https://github.com/haddocking/pdb-tools/issues
 Project-URL: Source, https://github.com/haddocking/pdb-tools
 Keywords: bioinformatics protein structural-biology pdb
-Platform: UNKNOWN
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Intended Audience :: Science/Research
 Classifier: Topic :: Scientific/Engineering
 Classifier: Topic :: Scientific/Engineering :: Chemistry
 Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
-Classifier: License :: OSI Approved :: Apache Software License
-Classifier: Programming Language :: Python :: 2
-Classifier: Programming Language :: Python :: 2.7
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.6
-Classifier: Programming Language :: Python :: 3.7
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
 Description-Content-Type: text/markdown
 License-File: LICENSE
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: keywords
+Dynamic: license
+Dynamic: license-file
+Dynamic: project-url
+Dynamic: summary
 
 # pdb-tools
 
@@ -176,5 +186,3 @@ or a new tools, read our `CONTRIBUTING` instructions [here](https://github.com/h
 ## License
 `pdb-tools` are open-source and licensed under the Apache License, version 2.0.
 For details, see the LICENSE file.
-
-

{pdb-tools-2.4.12 → pdb_tools-2.5.1}/pdb_tools.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: pdb-tools
-Version: 2.4.12
+Version: 2.5.1
 Summary: A swiss army knife for PDB files.
 Home-page: http://bonvinlab.org/pdb-tools
 Author: Joao Rodrigues
@@ -9,20 +9,30 @@ License: Apache Software License, version 2
 Project-URL: Bug Reports, https://github.com/haddocking/pdb-tools/issues
 Project-URL: Source, https://github.com/haddocking/pdb-tools
 Keywords: bioinformatics protein structural-biology pdb
-Platform: UNKNOWN
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Intended Audience :: Science/Research
 Classifier: Topic :: Scientific/Engineering
 Classifier: Topic :: Scientific/Engineering :: Chemistry
 Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
-Classifier: License :: OSI Approved :: Apache Software License
-Classifier: Programming Language :: Python :: 2
-Classifier: Programming Language :: Python :: 2.7
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.6
-Classifier: Programming Language :: Python :: 3.7
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
 Description-Content-Type: text/markdown
 License-File: LICENSE
+Dynamic: author
+Dynamic: author-email
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: home-page
+Dynamic: keywords
+Dynamic: license
+Dynamic: license-file
+Dynamic: project-url
+Dynamic: summary
 
 # pdb-tools
 
@@ -176,5 +186,3 @@ or a new tools, read our `CONTRIBUTING` instructions [here](https://github.com/h
 ## License
 `pdb-tools` are open-source and licensed under the Apache License, version 2.0.
 For details, see the LICENSE file.
-
-

{pdb-tools-2.4.12 → pdb_tools-2.5.1}/pdb_tools.egg-info/SOURCES.txt

@@ -42,6 +42,7 @@ pdbtools/pdb_selatom.py
 pdbtools/pdb_selchain.py
 pdbtools/pdb_selelem.py
 pdbtools/pdb_selhetatm.py
+pdbtools/pdb_selmodel.py
 pdbtools/pdb_selres.py
 pdbtools/pdb_selresname.py
 pdbtools/pdb_selseg.py

{pdb-tools-2.4.12 → pdb_tools-2.5.1}/pdb_tools.egg-info/entry_points.txt

@@ -33,6 +33,7 @@ pdb_selatom = pdbtools.pdb_selatom:main
 pdb_selchain = pdbtools.pdb_selchain:main
 pdb_selelem = pdbtools.pdb_selelem:main
 pdb_selhetatm = pdbtools.pdb_selhetatm:main
+pdb_selmodel = pdbtools.pdb_selmodel:main
 pdb_selres = pdbtools.pdb_selres:main
 pdb_selresname = pdbtools.pdb_selresname:main
 pdb_selseg = pdbtools.pdb_selseg:main
@@ -47,4 +48,3 @@ pdb_tofasta = pdbtools.pdb_tofasta:main
 pdb_uniqname = pdbtools.pdb_uniqname:main
 pdb_validate = pdbtools.pdb_validate:main
 pdb_wc = pdbtools.pdb_wc:main
-

pdb_tools-2.5.1/pdbtools/pdb_selmodel.py

@@ -0,0 +1,194 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+#
+# Copyright 2022 João Pedro Rodrigues
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+"""
+Extracts one or more models from a PDB file.
+
+If the PDB file has no MODEL records, returns the entire file.
+
+Usage:
+    python pdb_selmodel.py -<model id> <pdb file>
+
+Example:
+    python pdb_selmodel.py -1 1GGR.pdb  # selects model 1
+    python pdb_selmodel.py -1,3 1GGR.pdb  # selects models 1 and 3
+
+This program is part of the `pdb-tools` suite of utilities and should not be
+distributed isolatedly. The `pdb-tools` were created to quickly manipulate PDB
+files using the terminal, and can be used sequentially, with one tool streaming
+data to another. They are based on old FORTRAN77 code that was taking too much
+effort to maintain and compile. RIP.
+"""
+
+import os
+import sys
+
+__author__ = "Joao Rodrigues"
+__email__ = "j.p.g.l.m.rodrigues@gmail.com"
+
+
+def check_input(args):
+    """Checks whether to read from stdin/file and validates user input/options.
+    """
+
+    # Defaults
+    option = ''
+    fh = sys.stdin  # file handle
+
+    if not len(args):
+        # Reading from pipe with default option
+        if sys.stdin.isatty():
+            sys.stderr.write(__doc__)
+            sys.exit(1)
+
+    elif len(args) == 1:
+        # One of two options: option & Pipe OR file & default option
+        if args[0].startswith('-'):
+            option = args[0][1:]
+            if sys.stdin.isatty():  # ensure the PDB data is streamed in
+                emsg = 'ERROR!! No data to process!\n'
+                sys.stderr.write(emsg)
+                sys.stderr.write(__doc__)
+                sys.exit(1)
+
+        else:
+            if not os.path.isfile(args[0]):
+                emsg = 'ERROR!! File not found or not readable: \'{}\'\n'
+                sys.stderr.write(emsg.format(args[0]))
+                sys.stderr.write(__doc__)
+                sys.exit(1)
+
+            fh = open(args[0], 'r')
+
+    elif len(args) == 2:
+        # Two options: option & File
+        if not args[0].startswith('-'):
+            emsg = 'ERROR! First argument is not an option: \'{}\'\n'
+            sys.stderr.write(emsg.format(args[0]))
+            sys.stderr.write(__doc__)
+            sys.exit(1)
+
+        if not os.path.isfile(args[1]):
+            emsg = 'ERROR!! File not found or not readable: \'{}\'\n'
+            sys.stderr.write(emsg.format(args[1]))
+            sys.stderr.write(__doc__)
+            sys.exit(1)
+
+        option = args[0][1:]
+        fh = open(args[1], 'r')
+
+    else:  # Whatever ...
+        sys.stderr.write(__doc__)
+        sys.exit(1)
+
+    # Validate option
+    option_set = set()
+    for opt in option.split(','):
+        opt = opt.strip()
+        if not opt:
+            continue
+        try:
+            opt = int(opt)
+        except ValueError:
+            emsg = 'ERROR!! Model identifier is invalid: \'{}\'\n'
+            sys.stderr.write(emsg.format(opt))
+            sys.stderr.write(__doc__)
+            sys.exit(1)
+        option_set.add(opt)
+
+    if not option_set:
+        emsg = 'ERROR!! You must provide at least one model identifier\n'
+        sys.stderr.write(emsg)
+        sys.stderr.write(__doc__)
+        sys.exit(1)
+
+    return (fh, option_set)
+
+
+def run(fhandle, model_set):
+    """
+    Filter the PDB file for specific model identifiers.
+
+    This function is a generator.
+
+    Parameters
+    ----------
+    fhandle : a line-by-line iterator of the original PDB file.
+
+    model_set : set, or list, or tuple
+        The group of models to kepp.
+        Example: (1, 3), keeps only atoms from models 1 and 3
+
+    Yields
+    ------
+    str (line-by-line)
+        The PDB lines for those matching the selected chains.
+    """
+    records = ('ATOM', 'HETATM', 'TER', 'ANISOU')
+    ignore_model = False
+    for line in fhandle:
+        if line.startswith('MODEL'):
+            model_id = int(line[10:14])
+            if model_id not in model_set:
+                ignore_model = True
+                continue
+
+        elif line.startswith('ENDMDL'):
+            if ignore_model:
+                ignore_model = False
+                continue
+
+        elif ignore_model and line.startswith(records):
+            continue
+        yield line
+
+
+select_model = run
+
+
+def main():
+    # Check Input
+    pdbfh, models = check_input(sys.argv[1:])
+
+    # Do the job
+    new_pdb = run(pdbfh, models)
+
+    try:
+        _buffer = []
+        _buffer_size = 5000  # write N lines at a time
+        for lineno, line in enumerate(new_pdb):
+            if not (lineno % _buffer_size):
+                sys.stdout.write(''.join(_buffer))
+                _buffer = []
+            _buffer.append(line)
+
+        sys.stdout.write(''.join(_buffer))
+        sys.stdout.flush()
+    except IOError:
+        # This is here to catch Broken Pipes
+        # for example to use 'head' or 'tail' without
+        # the error message showing up
+        pass
+
+    # last line of the script
+    # We can close it even if it is sys.stdin
+    pdbfh.close()
+    sys.exit(0)
+
+
+if __name__ == '__main__':
+    main()

{pdb-tools-2.4.12 → pdb_tools-2.5.1}/pdbtools/pdb_tidy.py

@@ -44,6 +44,8 @@ effort to maintain and compile. RIP.
 
 import os
 import sys
+import re
+import textwrap
 
 __author__ = "Joao Rodrigues"
 __email__ = "j.p.g.l.m.rodrigues@gmail.com"
@@ -108,7 +110,7 @@ def check_input(args):
 
 def run(fhandle, strict=False):
     """
-    Add TER/END statements and pads all lines to 80 characters.
+    Add TER/END statements and truncates/pads all lines to 80 characters.
 
     This function is a generator.
 
@@ -161,8 +163,14 @@ def run(fhandle, strict=False):
         if line.startswith(ignored):  # to avoid matching END _and_ ENDMDL
             continue
 
-        # Check line length
-        line = "{:<80}\n".format(line)
+        # Check line length, wrapping and padding as necessary
+        # preserve the line prefix for wrapping
+        prefix = re.match(r"\S+\s*", line).group(0)
+        content = line[len(prefix):].lstrip()
+
+        line = "".join(
+            f"{prefix}{part:<{80 - len(prefix)}}\n"
+            for part in textwrap.wrap(content, width=80 - len(prefix)))
 
         yield line
 
@@ -214,9 +222,9 @@ def run(fhandle, strict=False):
             if atom_section:
                 atom_section = False
                 yield make_TER(prev_line)
-                if in_model:
-                    yield "{:<80}\n".format("ENDMDL")
-                    in_model = False
+            if in_model:
+                yield "{:<80}\n".format("ENDMDL")
+                in_model = False
 
             if line.startswith('MODEL'):
                 line = "MODEL " + "    " + str(num_models).rjust(4)
@@ -240,9 +248,9 @@ def run(fhandle, strict=False):
             # Add last TER statement
             atom_section = False
             yield make_TER(prev_line)
-            if in_model:
-                yield "{:<80}\n".format("ENDMDL")
-                in_model = False
+        if in_model:
+            yield "{:<80}\n".format("ENDMDL")
+            in_model = False
 
     # Add END statement
     yield "{:<80}\n".format("END")

{pdb-tools-2.4.12 → pdb_tools-2.5.1}/setup.py

@@ -8,6 +8,7 @@ https://github.com/pypa/sampleproject
 # Always prefer setuptools over distutils
 from setuptools import setup, find_packages
 from os import listdir, path
+
 # io.open is needed for projects that support Python 2.7
 # It ensures open() defaults to text mode with universal newlines,
 # and accepts an argument to specify the text encoding
@@ -17,54 +18,40 @@ from io import open
 here = path.abspath(path.dirname(__file__))
 
 # Get the long description from the README file
-with open(path.join(here, 'README.md'), encoding='utf-8') as f:
+with open(path.join(here, "README.md"), encoding="utf-8") as f:
     long_description = f.read()
 
 # Collect names of bin/*py scripts
 # e.g. 'pdb_intersect=bin.pdb_intersect:main',
-binfiles = listdir(path.join(here, 'pdbtools'))
-bin_py = [f[:-3] + '=pdbtools.' + f[:-3] + ':main' for f in binfiles
-          if f.endswith('.py')]
+binfiles = listdir(path.join(here, "pdbtools"))
+bin_py = [
+    f[:-3] + "=pdbtools." + f[:-3] + ":main" for f in binfiles if f.endswith(".py")
+]
 
 setup(
-    name='pdb-tools',  # Required
-    version='2.4.12',  # Required
-    description='A swiss army knife for PDB files.',  # Optional
+    name="pdb-tools",  # Required
+    version="2.5.1",  # Required
+    description="A swiss army knife for PDB files.",  # Optional
     long_description=long_description,  # Optional
-    long_description_content_type='text/markdown',  # Optional (see note above)
-    url='http://bonvinlab.org/pdb-tools',  # Optional
-    author='Joao Rodrigues',  # Optional
-    author_email='j.p.g.l.m.rodrigues@gmail.com',  # Optional
-    license='Apache Software License, version 2',
-    classifiers=[  # Optional
-        # How mature is this project? Common values are
-        #   3 - Alpha
-        #   4 - Beta
-        #   5 - Production/Stable
-        'Development Status :: 5 - Production/Stable',
-        #'Development Status :: 4 - Beta',
-
-        # Indicate who your project is intended for
-        'Intended Audience :: Science/Research',
-        'Topic :: Scientific/Engineering',
-        'Topic :: Scientific/Engineering :: Chemistry',
-        'Topic :: Scientific/Engineering :: Bio-Informatics',
-
-
-        # Pick your license as you wish
-        'License :: OSI Approved :: Apache Software License',
-
-        # Specify the Python versions you support here. In particular, ensure
-        # that you indicate whether you support Python 2, Python 3 or both.
-        'Programming Language :: Python :: 2',
-        'Programming Language :: Python :: 2.7',
-        'Programming Language :: Python :: 3',
-        'Programming Language :: Python :: 3.6',
-        'Programming Language :: Python :: 3.7',
+    long_description_content_type="text/markdown",  # Optional (see note above)
+    url="http://bonvinlab.org/pdb-tools",  # Optional
+    author="Joao Rodrigues",  # Optional
+    author_email="j.p.g.l.m.rodrigues@gmail.com",  # Optional
+    license="Apache Software License, version 2",
+    classifiers=[
+        "Development Status :: 5 - Production/Stable",
+        "Intended Audience :: Science/Research",
+        "Topic :: Scientific/Engineering",
+        "Topic :: Scientific/Engineering :: Chemistry",
+        "Topic :: Scientific/Engineering :: Bio-Informatics",
+        "Programming Language :: Python :: 3.9",
+        "Programming Language :: Python :: 3.10",
+        "Programming Language :: Python :: 3.11",
+        "Programming Language :: Python :: 3.12",
+        "Programming Language :: Python :: 3.13",
+        "Programming Language :: Python :: 3.14",
     ],
-
-    keywords='bioinformatics protein structural-biology pdb',  # Optional
-
+    keywords="bioinformatics protein structural-biology pdb",  # Optional
     # You can just specify package directories manually here if your project is
     # simple. Or you can use find_packages().
     #
@@ -75,7 +62,6 @@ setup(
     #   py_modules=["my_module"],
     #
     packages=find_packages(),  # Required
-
     # To provide executable scripts, use entry points in preference to the
     # "scripts" keyword. Entry points provide cross-platform support and allow
     # `pip` to create the appropriate form of executable for the target
@@ -84,11 +70,9 @@ setup(
     # For example, the following would provide a command called `sample` which
     # executes the function `main` from this package when invoked:
     entry_points={  # Optional
-        'console_scripts': bin_py,
+        "console_scripts": bin_py,
     },
-
     # scripts=[path.join('bin', f) for f in listdir(path.join(here, 'bin'))],
-
     # List additional URLs that are relevant to your project as a dict.
     #
     # This field corresponds to the "Project-URL" metadata fields:
@@ -99,10 +83,9 @@ setup(
     # maintainers, and where to support the project financially. The key is
     # what's used to render the link text on PyPI.
     project_urls={  # Optional
-        'Bug Reports': 'https://github.com/haddocking/pdb-tools/issues',
-        'Source': 'https://github.com/haddocking/pdb-tools',
+        "Bug Reports": "https://github.com/haddocking/pdb-tools/issues",
+        "Source": "https://github.com/haddocking/pdb-tools",
     },
-
     # Test Suite
-    test_suite='tests.test_all',
+    test_suite="tests.test_all",
 )