Merge pull request #100 from IAlibay/rm-propkainput

Removal of PROPKA input

docs/source/command.rst

@@ -12,8 +12,7 @@ protein-ligand complexes based in the 3D structure. The
 	   
   propka3 [-h] [-f FILENAMES] [-r REFERENCE] [-c CHAINS] [-i TITRATE_ONLY] [-t THERMOPHILES] [-a ALIGNMENT] [-m MUTATIONS]
          [-v VERSION_LABEL] [-p PARAMETERS] [--log-level {DEBUG,INFO,WARNING,ERROR,CRITICAL}] [-o PH] [-w WINDOW WINDOW WINDOW]
-         [-g GRID GRID GRID] [--mutator MUTATOR] [--mutator-option MUTATOR_OPTIONS] [-d] [-l] [-k] [-q] [--generate-propka-input]
+         [-g GRID GRID GRID] [--mutator MUTATOR] [--mutator-option MUTATOR_OPTIONS] [-d] [-l] [-k] [-q] [--protonate-all]
-         [--protonate-all]
          input_pdb
 
 
@@ -120,10 +119,6 @@ protein-ligand complexes based in the 3D structure. The
 	     
              suppress non-warning messages (default: None)
 	     
-.. option::  --generate-propka-input
-	     
-             Generate a PROPKA input file (default: False)
-	     
 .. option::  --protonate-all
 
 	     Protonate all atoms (will not influence pKa calculation)

propka/atom.py

@@ -12,10 +12,6 @@ from . import hybrid36
 
 
 # Format strings that get used in multiple places (or are very complex)
-PKA_FMT = "{:6.2f}"
-INPUT_LINE_FMT = (
-    "{type:6s}{r.numb:>5d} {atom_label} {r.res_name}{r.chain_id:>2s}"
-    "{r.res_num:>4d}{r.x:>12.3f}{r.y:>8.3f}{r.z:>8.3f}{group:>6s}{pka:>6s} \n")
 PDB_LINE_FMT1 = (
     "{type:6s}{r.numb:>5d} {atom_label} {r.res_name}{r.chain_id:>2s}"
     "{r.res_num:>4d}{r.x:>12.3f}{r.y:>8.3f}{r.z:>8.3f}{r.occ:>6s}"
@@ -33,7 +29,13 @@ STR_FMT = (
 
 
 class Atom:
-    """Atom class - contains all atom information found in the PDB file"""
+    """Atom class - contains all atom information found in the PDB file
+
+
+    .. versionchanged:: 3.4.0
+       :meth:`make_input_line` and :meth:`get_input_parameters` have been
+       removed as reading/writing PROPKA input is no longer supported.
+    """
 
     def __init__(self, line=None):
         """Initialize Atom object.
@@ -56,9 +58,6 @@ class Atom:
         self.z = None
         self.group = None
         self.group_type = None
-        self.group_label = None
-        self.group_model_pka = None
-        self.group_model_pka_set = None
         self.number_of_bonded_elements = {}
         self.cysteine_bridge = False
         self.bonded_atoms = []
@@ -255,31 +254,6 @@ class Atom:
         new_atom.icode = self.icode
         return new_atom
 
-    def make_input_line(self):
-        """PDB line for this atom.
-
-        TODO - Could be @property method/attribute
-        TODO - figure out difference between make_pdb_line, make_input_line,
-               and make_pdb_line2
-
-        Returns:
-            String with PDB-format line.
-        """
-        group = '-'
-        model_pka = '-'
-        if self.group:
-            group = self.group.type
-            if self.terminal == 'C-':
-                group = 'C-' ## circumventing C-/COO parameter unification
-
-            if self.group.titratable:
-                model_pka = PKA_FMT.format(self.group.model_pka)
-        str_ = INPUT_LINE_FMT.format(
-            type=self.type.upper(), r=self,
-            atom_label=make_tidy_atom_label(self.name, self.element),
-            group=group, pka=model_pka)
-        return str_
-
     def make_conect_line(self):
         """PDB line for bonding within this molecule.
 
@@ -298,45 +272,11 @@ class Atom:
         res += '\n'
         return res
 
-    def get_input_parameters(self):
-        """Extract the input parameters stored in the occupancy and b-factor
-        fields in input files"""
-        # Set the group type
-        if self.occ != '-':
-            # make sure to set the terminal
-            if self.occ in ['N+', 'C-']:
-                self.terminal = self.occ
-            # save the ligand group charge
-            if self.occ == 'BLG':
-                self.charge = +1
-            elif self.occ == 'ALG':
-                self.charge = -1
-            # generic ions
-            if self.occ in ['1P', '2P', '1N', '2N']:
-                self.res_name = self.occ
-                self.occ = 'Ion'
-            # correct the group type
-            self.occ = self.occ.replace('N+', 'Nterm')
-            self.occ = self.occ.replace('C-', 'Cterm')
-            self.occ = self.occ.replace('ION', 'Ion')
-            self.occ = self.occ.replace('ALG', 'titratable_ligand')
-            self.occ = self.occ.replace('BLG', 'titratable_ligand')
-            self.occ = self.occ.replace('LG', 'non_titratable_ligand')
-            self.group_label = "{0:s}_group".format(self.occ)
-        # set the model pKa value
-        if self.beta != '-':
-            self.group_model_pka = float(self.beta)
-            self.group_model_pka_set = True
-        # set occ and beta to standard values
-        self.occ = '1.00'
-        self.beta = '0.00'
-
     def make_pdb_line(self):
         """Create PDB line.
 
         TODO - this could/should be a @property method/attribute
-        TODO - figure out difference between make_pdb_line, make_input_line,
+        TODO - figure out difference between make_pdb_line, and make_pdb_line2
-               and make_pdb_line2
 
         Returns:
             String with PDB line.
@@ -367,8 +307,7 @@ class Atom:
         """Create a PDB line.
 
         TODO - this could/should be a @property method/attribute
-        TODO - figure out difference between make_pdb_line, make_input_line,
+        TODO - figure out difference between make_pdb_line, and make_pdb_line2
-               and make_pdb_line2
 
         Returns:
             String with PDB line.

propka/conformation_container.py

@@ -25,7 +25,13 @@ RESIDUE_MULTIPLIER = 1000
 
 
 class ConformationContainer:
-    """Container for molecular conformations"""
+    """Container for molecular conformations
+
+
+    .. versionchanged:: 3.4.0
+       Removed :meth:`additional_setup_when_reading_input_files` as reading
+       PROPKA inputs is no longer supported.
+    """
 
     def __init__(self, name='', parameters=None, molecular_container=None):
         """Initialize conformation container.
@@ -58,19 +64,6 @@ class ConformationContainer:
             if group:
                 self.setup_and_add_group(group)
 
-    def additional_setup_when_reading_input_file(self):
-        """Generate interaction map and charge centers."""
-        # if a group is coupled and we are reading a .propka_input file, then
-        # some more configuration might be needed
-        map_ = make_interaction_map(
-            'Covalent coupling map for {0:s}'.format(str(self)),
-            self.get_covalently_coupled_groups(),
-            lambda g1, g2: g1 in g2.covalently_coupled_groups)
-        info(map_)
-        # check if we should set a common charge centre as well
-        if self.parameters.common_charge_centre:
-            self.set_common_charge_centres()
-
     def set_common_charge_centres(self):
         """Assign charge centers to groups."""
         for system in self.get_coupled_systems(

propka/group.py

@@ -3,6 +3,11 @@ Data structures for groups
 ==========================
 
 Routines and classes for storing groups important to PROPKA calculations.
+
+
+.. versionchanged:: 3.4.0
+   Removed :func:`initialize_atom_group` as reading PROPKA inputs is no longer
+   supported.
 """
 import math
 import propka.ligand
@@ -40,7 +45,14 @@ EXPECTED_ATOMS_BASE_INTERACTIONS = {
 
 
 class Group:
-    """Class for storing groups important to pKa calculations."""
+    """Class for storing groups important to pKa calculations.
+
+
+    .. versionchanged:: 3.4.0
+       Removed :meth:`make_covalently_coupled_line` and
+       :meth:`make_non_covalently_coupled_line` as writing PROPKA inputs is no
+       longer supported.
+    """
 
     def __init__(self, atom):
         """Initialize with an atom.
@@ -178,48 +190,6 @@ class Group:
             self.determinants[type_].append(
                 Determinant(new_determinant.group, new_determinant.value))
 
-    def make_covalently_coupled_line(self):
-        """Create line for covalent coupling.
-
-        Returns:
-            string
-        """
-        # first check if there are any coupled groups at all
-        if len(self.covalently_coupled_groups) == 0:
-            return ''
-        line = 'CCOUPL{0:5d}'.format(self.atom.numb)
-        # extract and sort numbers of coupled groups
-        coupled = []
-        for group in self.covalently_coupled_groups:
-            coupled.append(group.atom.numb)
-        coupled.sort()
-        # write 'em out
-        for num in coupled:
-            line += '{0:5d}'.format(num)
-        line += '\n'
-        return line
-
-    def make_non_covalently_coupled_line(self):
-        """Create line for non-covalent coupling.
-
-        Returns:
-            string
-        """
-        # first check if there are any coupled groups at all
-        if len(self.non_covalently_coupled_groups) == 0:
-            return ''
-        line = 'NCOUPL{0:5d}'.format(self.atom.numb)
-        # extract and sort numbers of coupled groups
-        coupled = []
-        for group in self.non_covalently_coupled_groups:
-            coupled.append(group.atom.numb)
-        coupled.sort()
-        # write 'em out
-        for num in coupled:
-            line += '{0:5d}'.format(num)
-        line += '\n'
-        return line
-
     def __eq__(self, other):
         """Needed for creating sets of groups."""
         if self.atom.type == 'atom':
@@ -1425,15 +1395,3 @@ def is_ion_group(parameters, atom):
     if atom.res_name.strip() in parameters.ions.keys():
         return IonGroup(atom)
     return None
-
-def initialize_atom_group(atom):
-    """Initialize an atom group.
-
-    Args:
-        atom:  atom to initialize
-    """
-        # try to initialise the group
-    group_attr = globals()[atom.group_label]
-    atom.group = group_attr(atom)
-    atom.group.model_pka = atom.group_model_pka
-    atom.group.model_pka_set = atom.group_model_pka_set

propka/input.py

@@ -3,13 +3,17 @@ Input handling
 ==============
 
 Input routines.
+
+
+.. versionchanged:: 3.4.0
+   Methods to read PROPKA input files (:func:`read_propka` and
+   :func:`get_atom_lines_from_input`) have been removed.
 """
 from pathlib import Path
 from pkg_resources import resource_filename
 from propka.lib import protein_precheck
 from propka.atom import Atom
 from propka.conformation_container import ConformationContainer
-from propka.group import initialize_atom_group
 
 
 def open_file_for_reading(input_file):
@@ -67,14 +71,17 @@ def read_molecule_file(filename: str, mol_container, stream=None):
         usually have an associated file name, an appropirate file name should
         be passed to the ``filename`` argument. In this case, ``filename`` is
         not opened for reading, but instead is used to help recognise the file
-        type (based on the extension being either `.pdb` or `.propka_input`)
+        type (based on the extension being `.pdb`) and also uses that given
-        and also uses that given ``filename`` to assign a name to the input
+        ``filename`` to assign a name to the input
         :class:`~propka.molecular_container.MolecularContainer` object.
 
         >>> read_molecule_file('test.pdb', mol_container,
                                stream=string_io_object)
         <propka.molecular_container.MolecularContainer at 0x7f6e0c8f2310>
 
+
+    .. versionchanged:: 3.4.0
+       PROPKA input files (extension: `.propka_input`) are no longer read.
     """
     input_path = Path(filename)
     mol_container.name = input_path.stem
@@ -109,17 +116,6 @@ def read_molecule_file(filename: str, mol_container, stream=None):
             mol_container.conformations[name].sort_atoms()
         # find coupled groups
         mol_container.find_covalently_coupled_groups()
-    elif input_file_extension.lower() == '.propka_input':
-        # input is a propka_input file
-        conformations, conformation_names = read_propka(
-            input_file, mol_container.version.parameters, mol_container)
-        mol_container.conformations = conformations
-        mol_container.conformation_names = conformation_names
-        # Extract groups - this merely sets up the groups found in the
-        # input file
-        mol_container.extract_groups()
-        # do some additional set up
-        mol_container.additional_setup_when_reading_input_file()
     else:
         str_ = "Unknown input file type {0!s} for file {1!s}".format(
             input_file_extension, input_path)
@@ -220,94 +216,6 @@ def get_atom_lines_from_pdb(pdb_file, ignore_residues=[], keep_protons=False,
             terminal = None
 
 
-def read_propka(input_file, parameters, molecule):
-    """Read PROPKA input file for molecular container.
-
-    Args:
-        input_file:  input file
-        parameters:  parameters for parsing/setup
-        molecule:  molecular container
-    Returns:
-        list with [conformations, names of conformations]
-    """
-    conformations = {}
-    # read in all atoms in the input file
-    lines = get_atom_lines_from_input(input_file)
-    for (name, atom) in lines:
-        if not name in conformations.keys():
-            conformations[name] = ConformationContainer(
-                name=name, parameters=parameters,
-                molecular_container=molecule)
-        conformations[name].add_atom(atom)
-    # make a sorted list of conformation names
-    names = sorted(conformations.keys(), key=conformation_sorter)
-    return [conformations, names]
-
-
-def get_atom_lines_from_input(input_file, tags=['ATOM  ', 'HETATM']):
-    """Get atom lines from a PROPKA input file.
-
-    Args:
-        input_file:  input file
-        tags:  tags defining atom lines
-    Yields:
-        conformation container, list of atoms
-    """
-    lines = open_file_for_reading(input_file).readlines()
-    conformation = ''
-    atoms = {}
-    numbers = []
-    for line in lines:
-        tag = line[0:6]
-        # set the conformation
-        if tag == 'MODEL ':
-            conformation = line[6:].strip()
-        # found an atom - save it
-        if tag in tags:
-            atom = Atom(line=line)
-            atom.get_input_parameters()
-            initialize_atom_group(atom)
-            atom.groups_extracted = 1
-            atom.is_protonated = True
-            atoms[atom.numb] = atom
-            numbers.append(atom.numb)
-        # found bonding information - apply it
-        if tag == 'CONECT' and len(line) > 14:
-            conect_numbers = [line[i:i+5] for i in range(6, len(line)-1, 5)]
-            center_atom = atoms[int(conect_numbers[0])]
-            for num in conect_numbers[1:]:
-                bond_atom = atoms[int(num)]
-                # remember to check for cysteine bridges
-                if center_atom.element == 'S' and bond_atom.element == 'S':
-                    center_atom.cysteine_bridge = True
-                    bond_atom.cysteine_bridge = True
-                # set up bonding
-                if not bond_atom in center_atom.bonded_atoms:
-                    center_atom.bonded_atoms.append(bond_atom)
-                if not center_atom in bond_atom.bonded_atoms:
-                    bond_atom.bonded_atoms.append(center_atom)
-        # found info on covalent coupling
-        if tag == 'CCOUPL' and len(line) > 14:
-            conect_numbers = [line[i:i+5] for i in range(6, len(line)-1, 5)]
-            center_atom = atoms[int(conect_numbers[0])]
-            for num in conect_numbers[1:]:
-                cov_atom = atoms[int(num)]
-                center_atom.group.couple_covalently(cov_atom.group)
-        # found info on non-covalent coupling
-        if tag == 'NCOUPL' and len(line) > 14:
-            conect_numbers = [line[i:i+5] for i in range(6, len(line)-1, 5)]
-            center_atom = atoms[int(conect_numbers[0])]
-            for num in conect_numbers[1:]:
-                cov_atom = atoms[int(num)]
-                center_atom.group.couple_non_covalently(cov_atom.group)
-        # this conformation is done - yield the atoms
-        if tag == 'ENDMDL':
-            for num in numbers:
-                yield (conformation, atoms[num])
-            # prepare for next conformation
-            atoms = {}
-            numbers = []
-
 def read_pdb(pdb_file, parameters, molecule):
     """Parse a PDB file.
 

propka/lib.py

@@ -195,9 +195,14 @@ def build_parser(parser=None):
                  new parser will be created.
     Returns:
         ArgumentParser object.
+
+
+    .. versionchanged:: 3.4.0
+       Argument `--generate-propka-input` has been removed as writing PROPKA
+       input files is no longer supported.
     """
     if parser is not None:
-        group = parser.add_argument_group(title="PROPKA invoation options")
+        group = parser.add_argument_group(title="PROPKA invocation options")
     else:
         parser = argparse.ArgumentParser(
             description=("PROPKA predicts the pKa values of ionizable "
@@ -285,9 +290,6 @@ def build_parser(parser=None):
     group.add_argument(
         "-q", "--quiet", action="store_const", const="WARNING",
         dest="log_level", help="suppress non-warning messages")
-    group.add_argument(
-        "--generate-propka-input", action="store_true",
-        help="Generate a PROPKA input file")
     group.add_argument(
         "--protonate-all", dest="protonate_all", action="store_true",
         help="Protonate all atoms (will not influence pKa calculation)",

propka/molecular_container.py

@@ -6,7 +6,7 @@ Molecular container for storing all contents of PDB files.
 """
 import os
 import propka.version
-from propka.output import write_propka, write_pka, print_header, print_result
+from propka.output import write_pka, print_header, print_result
 from propka.conformation_container import ConformationContainer
 from propka.lib import info, warning, make_grid
 
@@ -22,6 +22,12 @@ class MolecularContainer:
 
     TODO - this class name does not conform to PEP8 but has external use.
     We should deprecate and change eventually.
+
+
+    .. versionchanged:: 3.4.0
+       Removed :meth:`write_propka` and
+       :meth:`additional_setup_when_reading_input_file` as reading and writing
+       PROPKA input files is no longer supported.
     """
 
     def __init__(self, parameters, options=None):
@@ -72,11 +78,6 @@ class MolecularContainer:
         for name in self.conformation_names:
             self.conformations[name].extract_groups()
 
-    def additional_setup_when_reading_input_file(self):
-        """Additional setup."""
-        for name in self.conformation_names:
-            self.conformations[name].additional_setup_when_reading_input_file()
-
     def calculate_pka(self):
         """Calculate pKa values."""
         # calculate for each conformation
@@ -123,16 +124,6 @@ class MolecularContainer:
             self.conformation_names[0]].chains
         self.conformations['AVR'] = avr_conformation
 
-    def write_propka(self, filename=None):
-        """Write PROPKA input file.
-
-        Args:
-            filename:  file to write to
-        """
-        if filename is None:
-            filename = os.path.join('{0:s}.propka_input'.format(self.name))
-        write_propka(self, filename)
-
     def write_pka(self, filename=None, reference="neutral",
                   direction="folding", options=None):
         """Write pKa information to a file.

propka/output.py

@@ -3,6 +3,11 @@ Output
 ======
 
 Output routines.
+
+
+.. versionchanged::3.4.0
+   Removed :func:`write_proka` as writing PROPKA input files is no longer
+   supported.
 """
 from datetime import date
 from propka.lib import info
@@ -589,30 +594,3 @@ def write_mol2_for_atoms(atoms, filename):
     out.write(bonds_section)
     out.write(substructure_section)
     out.close()
-
-def write_propka(molecular_container, filename):
-    """Write PROPKA input file for molecular container.
-
-    Args:
-        molecular_container:  molecular container
-        filename:  output file name
-    """
-    out = open_file_for_writing(filename)
-    for conformation_name in molecular_container.conformation_names:
-        out.write('MODEL {0:s}\n'.format(conformation_name))
-        # write atoms
-        for atom in molecular_container.conformations[conformation_name].atoms:
-            out.write(atom.make_input_line())
-        # write bonds
-        for atom in molecular_container.conformations[conformation_name].atoms:
-            out.write(atom.make_conect_line())
-        # write covalently coupled groups
-        for group in (
-                molecular_container.conformations[conformation_name].groups):
-            out.write(group.make_covalently_coupled_line())
-        # write non-covalently coupled groups
-        for group in (
-                molecular_container.conformations[conformation_name].groups):
-            out.write(group.make_non_covalently_coupled_line())
-        out.write('ENDMDL\n')
-    out.close()

propka/run.py

@@ -21,7 +21,12 @@ _LOGGER = logging.getLogger("PROPKA")
 
 
 def main(optargs=None):
-    """Read in structure files, calculate pKa values, and print pKa files."""
+    """Read in structure files, calculate pKa values, and print pKa files.
+
+
+    .. versionchanged:: 3.4.0
+       Removed ability to write out PROPKA input files.
+    """
     # loading options, flags and arguments
     optargs = optargs if optargs is not None else []
     options = loadOptions(*optargs)
@@ -32,8 +37,6 @@ def main(optargs=None):
         my_molecule = read_molecule_file(pdbfile, my_molecule)
         my_molecule.calculate_pka()
         my_molecule.write_pka()
-        if options.generate_propka_input:
-            my_molecule.write_propka()
 
 
 def single(filename: str, optargs: tuple = (), stream=None,
@@ -93,6 +96,9 @@ def single(filename: str, optargs: tuple = (), stream=None,
 
         :func:`propka.input.read_molecule_file`
 
+
+    .. versionchanged:: 3.4.0
+       Removed ability to write out PROPKA input files.
     """
     # Deal with input optarg options
     optargs = tuple(optargs)
@@ -113,8 +119,6 @@ def single(filename: str, optargs: tuple = (), stream=None,
     my_molecule.calculate_pka()
 
     # write outputs
-    if options.generate_propka_input:
-        my_molecule.write_propka()
     if write_pka:
         my_molecule.write_pka()
 

tests/test_basic_regression.py

@@ -78,8 +78,6 @@ def run_propka(options, pdb_path, tmp_path):
         molecule = read_molecule_file(str(pdb_path), molecule)
         molecule.calculate_pka()
         molecule.write_pka()
-        if args.generate_propka_input:
-            molecule.write_propka()
     finally:
         os.chdir(cwd)
 

tests/test_run.py

@@ -30,6 +30,7 @@ def test_single_file(tmpdir, pdb, options):
     with tmpdir.as_cwd():
         pkrun.single(filename, options)
         compare_output(pdb, Path.cwd(), ref_path)
+        assert os.path.isfile(f'{pdb}.pka')
 
 
 @pytest.mark.parametrize("pdb, options", [
@@ -51,6 +52,7 @@ def test_single_filestream(tmpdir, pdb, options):
     with tmpdir.as_cwd():
         pkrun.single(filename, options, stream=filestream)
         compare_output(pdb, Path.cwd(), ref_path)
+        assert os.path.isfile(f'{pdb}.pka')
 
     filestream.close()
 
@@ -69,27 +71,10 @@ def test_single_nopka(tmpdir):
     assert not os.path.isfile(f"{pdb}.pka")
 
 
-def test_single_propka_input(tmpdir):
-    """Basic test to check that the propka_input file is written when
-    `--generate-propka-input` is passed"""
-    pdb = "1FTJ-Chain-A"
-    options = ('--generate-propka-input',)
-    ref_path, pdb_path = get_paths(pdb)
-    filename = f"{pdb}.pdb"
-
-    with open(pdb_path, 'r') as writer:
-        filestream = StringIO(writer.read())
-
-    with tmpdir.as_cwd():
-        pkrun.single(filename, options, stream=filestream)
-        assert os.path.isfile(f"{pdb}.propka_input")
-
-
 def test_single_extra_files_logwarn(tmpdir, caplog):
     """Tests that a logging warning is thrown if passing files via optargs"""
     pdb = "1FTJ-Chain-A"
-    options = ('-f foo.pdb bar.pdb', '-f test.pdb test2.pdb',
+    options = ('-f foo.pdb bar.pdb', '-f test.pdb test2.pdb')
-               '--generate-propka-input')
     ref_path, pdb_path = get_paths(pdb)
     filename = str(pdb_path)
 

tests/test_streamio.py

@@ -38,8 +38,6 @@ def run_propka_stream(options, input_file, filename):
     molecule = read_molecule_file(filename, molecule, stream=input_file)
     molecule.calculate_pka()
     molecule.write_pka()
-    if args.generate_propka_input:
-        molecule.write_propka()
 
 
 @pytest.mark.parametrize("pdb, options", [