molSimplify 1.7.4__py3-none-any.whl

docs/source/conf.py

@@ -0,0 +1,224 @@
+# -*- coding: utf-8 -*-
+#
+# Configuration file for the Sphinx documentation builder.
+#
+# This file does only contain a selection of the most common options. For a
+# full list see the documentation:
+# http://www.sphinx-doc.org/en/master/config
+
+# -- Path setup --------------------------------------------------------------
+
+# If extensions (or modules to document with autodoc) are in another directory,
+# add these directories to sys.path here. If the directory is relative to the
+# documentation root, use os.path.abspath to make it absolute, like shown here.
+#
+import os
+import sys
+molSimplify_path = os.path.join(os.path.dirname(__file__), '../../../molSimplify')
+sys.path.insert(0, os.path.abspath(molSimplify_path))
+
+
+# -- Project information -----------------------------------------------------
+
+project = u'molSimplify'
+copyright = u'2020, Heather J. Kulik Group'
+author = u'Heather J. Kulik Research Group'
+
+# The short X.Y version
+version = u''
+# The full version, including alpha/beta/rc tags
+release = u''
+
+
+# -- General configuration ---------------------------------------------------
+
+# If your documentation needs a minimal Sphinx version, state it here.
+#
+# needs_sphinx = '1.0'
+
+# Add any Sphinx extension module names here, as strings. They can be
+# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
+# ones.
+extensions = [
+    'sphinx.ext.autodoc',
+    'sphinx.ext.napoleon',
+    'sphinx.ext.autosummary',
+    'sphinx.ext.doctest',
+    'sphinx.ext.intersphinx',
+    'sphinx.ext.todo',
+    'sphinx.ext.coverage',
+    'sphinx.ext.mathjax',
+    'sphinx.ext.ifconfig',
+    'sphinx.ext.viewcode',
+    'sphinx.ext.githubpages',
+]
+
+# Automatically generate summaries
+autosummary_generate = True
+autodoc_default_flags = ['members',
+                         'undoc-members',
+                         'show-inheritance',
+                         'inherited-members']
+
+# Add any paths that contain templates here, relative to this directory.
+templates_path = ['_templates']
+
+# The suffix(es) of source filenames.
+# You can specify multiple suffix as a list of string:
+#
+# source_suffix = ['.rst', '.md']
+source_suffix = '.rst'
+
+# The master toctree document.
+master_doc = 'index'
+
+# The language for content autogenerated by Sphinx. Refer to documentation
+# for a list of supported languages.
+#
+# This is also used if you do content translation via gettext catalogs.
+# Usually you set "language" from the command line for these cases.
+language = 'en'
+
+# List of patterns, relative to source directory, that match files and
+# directories to ignore when looking for source files.
+# This pattern also affects html_static_path and html_extra_path.
+exclude_patterns = ['**.ipynb_checkpoints', '**.ipynb',
+                    '.DS_store', '_build']
+
+# The name of the Pygments (syntax highlighting) style to use.
+pygments_style = 'sphinx'
+
+
+# -- Options for HTML output -------------------------------------------------
+
+# The theme to use for HTML and HTML Help pages.  See the documentation for
+# a list of builtin themes.
+#
+html_theme = 'sphinx_rtd_theme'
+
+# Theme options are theme-specific and customize the look and feel of a theme
+# further.  For a list of options available for each theme, see the
+# documentation.
+#
+# html_theme_options = {}
+
+# Add any paths that contain custom static files (such as style sheets) here,
+# relative to this directory. They are copied after the builtin static files,
+# so a file named "default.css" will overwrite the builtin "default.css".
+html_static_path = []
+
+# Custom sidebar templates, must be a dictionary that maps document names
+# to template names.
+#
+# The default sidebars (for documents that don't match any pattern) are
+# defined by theme itself.  Builtin themes are using these templates by
+# default: ``['localtoc.html', 'relations.html', 'sourcelink.html',
+# 'searchbox.html']``.
+#
+# html_sidebars = {}
+
+
+# -- Options for HTMLHelp output ---------------------------------------------
+
+# Output file base name for HTML help builder.
+htmlhelp_basename = 'molSimplifydoc'
+
+
+# -- Options for LaTeX output ------------------------------------------------
+
+latex_elements = {
+    # The paper size ('letterpaper' or 'a4paper').
+    #
+    # 'papersize': 'letterpaper',
+
+    # The font size ('10pt', '11pt' or '12pt').
+    #
+    # 'pointsize': '10pt',
+
+    # Additional stuff for the LaTeX preamble.
+    #
+    # 'preamble': '',
+
+    # Latex figure (float) alignment
+    #
+    # 'figure_align': 'htbp',
+}
+
+# Grouping the document tree into LaTeX files. List of tuples
+# (source start file, target name, title,
+#  author, documentclass [howto, manual, or own class]).
+latex_documents = [
+    (master_doc, 'molSimplify.tex', u'molSimplify Documentation',
+     u'Heather J. Kulik Group', 'manual'),
+]
+
+
+# -- Options for manual page output ------------------------------------------
+
+# One entry per manual page. List of tuples
+# (source start file, name, description, authors, manual section).
+man_pages = [
+    (master_doc, 'molsimplify', u'molSimplify Documentation',
+     [author], 1)
+]
+
+
+# -- Options for Texinfo output ----------------------------------------------
+
+# Grouping the document tree into Texinfo files. List of tuples
+# (source start file, target name, title, author,
+#  dir menu entry, description, category)
+texinfo_documents = [
+    (master_doc, 'molSimplify', u'molSimplify Documentation',
+     author, 'molSimplify', 'Inorganic structure building.',
+     'Miscellaneous'),
+]
+
+
+# -- Options for Epub output -------------------------------------------------
+
+# Bibliographic Dublin Core info.
+epub_title = project
+
+# The unique identifier of the text. This can be a ISBN number
+# or the project homepage.
+#
+# epub_identifier = ''
+
+# A unique identification for the text.
+#
+# epub_uid = ''
+
+# A list of files that should not be packed into the epub file.
+epub_exclude_files = ['search.html']
+
+
+# -- Extension configuration -------------------------------------------------
+
+# -- Options for intersphinx extension ---------------------------------------
+
+# Example configuration for intersphinx: refer to the Python standard library.
+intersphinx_mapping = {'python': ('https://docs.python.org/3', None)}
+
+# -- Options for todo extension ----------------------------------------------
+
+# If true, `todo` and `todoList` produce output, else they produce nothing.
+todo_include_todos = True
+
+# Napoleon settings
+napoleon_google_docstring = True
+napoleon_numpy_docstring = True
+napoleon_include_init_with_doc = False
+napoleon_include_private_with_doc = False
+napoleon_include_special_with_doc = True
+napoleon_use_admonition_for_examples = False
+napoleon_use_admonition_for_notes = False
+napoleon_use_admonition_for_references = False
+napoleon_use_ivar = False
+napoleon_use_param = True
+napoleon_use_rtype = True
+napoleon_type_aliases = None
+
+# Latex equations options
+imgmath_image_format = 'svg'
+imgmath_font_size = 18

molSimplify/Classes/__init__.py

@@ -0,0 +1,6 @@
+from .atom3D import atom3D
+from .globalvars import globalvars
+from .mol3D import mol3D
+from .rundiag import run_diag
+
+__all__ = ["atom3D", "globalvars", "mol3D", "run_diag"]

molSimplify/Classes/atom3D.py

@@ -0,0 +1,235 @@
+# @file atom3D.py
+#  Defines atom3D class and contains useful manipulation/retrieval routines.
+#
+#  Written by Kulik Group
+#
+#  Department of Chemical Engineering, MIT
+
+from math import sqrt
+from typing import List, Optional
+from molSimplify.Classes.globalvars import globalvars
+
+
+class atom3D:
+    """ atom3D class. Base class in molSimplify for representing an element.
+
+        Parameters
+        ----------
+            Sym : str, optional
+                Symbol for atom3D instantiation. Element symbol. Default is 'C'.
+            xyz : list, optional
+                List of coordinates for new atom. Default is [0.0, 0.0, 0.0].
+            name : str, optional
+                Unique identifier for atom 3D instantiation. Default is False.
+            partialcharge : int, optional
+                Charge assigned to atom when added to mol. Default is None.
+    """
+    def __init__(self,
+                 Sym: str = 'C',
+                 xyz: Optional[List[float]] = None,
+                 name: Optional[str] = None,
+                 partialcharge: Optional[float] = None,
+                 Tfactor=0,
+                 greek='',
+                 occup=1.00,
+                 loc='',
+                 line=""):
+
+        # Element symbol
+        self.sym = Sym
+        self.partialcharge = partialcharge
+        globs = globalvars()
+        amass = globs.amass()
+        if Sym not in amass:  # assign default values if not in dictionary
+            print(("We didn't find the atomic mass of %s in the dictionary. Assigning default value of 12!\n" % (Sym)))
+            # Atomic mass
+            self.mass = 12.0  # default atomic mass
+            # Atomic number
+            self.atno = 6  # default atomic number
+            # Covalent radius
+            self.rad = 0.75  # default atomic radius
+        else:
+            self.mass = amass[Sym][0]
+            self.atno = amass[Sym][1]
+            self.rad = amass[Sym][2]
+        # Flag for freezing in optimization
+        self.frozen = False
+        # Flag for atom name
+        # NOTE: does not compare to None because empty string would not be valid and
+        # some parts of molSimplify still instantiate atom3D with name=False
+        if name:
+            self.name = name
+        else:
+            self.name = Sym
+
+        # Coordinates
+        if xyz is None:
+            xyz = [0.0, 0.0, 0.0]
+        self.__xyz = xyz
+
+        # Temperature factor (only useful for proteins)
+        self.Tfactor = Tfactor
+
+        # Greek letter (e.g. alpha carbon - only useful for proteins)
+        if greek == '':
+            self.greek = Sym
+        else:
+            self.greek = greek
+
+        # Occupancy (only useful for proteins)
+        self.occup = occup
+
+        # EDIA score (only useful for proteins)
+        self.EDIA = 0
+
+        # Conformation (only useful for proteins)
+        self.loc = ""
+
+        # PDB line (only useful for proteins)
+        self.line = line
+
+    def __repr__(self):
+        return f"atom3D(Sym={self.sym}, xyz={self.__xyz})"
+
+    # TODO: uncomment this once protein3D has a better implementation than
+    # hashing of a mutable object!
+    # def __eq__(self, other):
+    #     if isinstance(other, self.__class__):
+    #         return self.__dict__ == other.__dict__
+    #     else:
+    #         return False
+
+    def coords(self):
+        """ Get coordinates of a given atom.
+
+        Returns
+        -------
+            coords : list
+                List of coordinates in X, Y, Z format.
+        """
+        x, y, z = self.__xyz
+        return [x, y, z]
+
+    def distance(self, atom2) -> float:
+        """ Get distance from one atom3D class to another.
+
+        Parameters
+        ----------
+            atom2 : atom3D
+                atom3D class of the atom to measure distance from.
+
+
+        Returns
+        -------
+            dist : float
+                Distance in angstroms.
+        """
+        xyz = self.coords()
+        point = atom2.coords()
+        dx = xyz[0]-point[0]
+        dy = xyz[1]-point[1]
+        dz = xyz[2]-point[2]
+        return sqrt(dx*dx+dy*dy+dz*dz)
+
+    def distancev(self, atom2):
+        """ Get distance vector from one atom3D class to another.
+
+        Parameters
+        ----------
+            atom2 : atom3D
+                atom3D class of the atom to measure distance from.
+
+
+        Returns
+        -------
+            dist_list : list
+                List of distances in vector form: [dx, dy, dz] with units of Angstroms.
+        """
+        xyz = self.coords()
+        point = atom2.coords()
+        dx = xyz[0]-point[0]
+        dy = xyz[1]-point[1]
+        dz = xyz[2]-point[2]
+        return [dx, dy, dz]
+
+    def ismetal(self, transition_metals_only=True) -> bool:
+        """ Identify whether an atom is a metal.
+
+        Parameters
+        ----------
+            transition_metals_only : bool, optional
+                Identify only transition metals. Default is true.
+
+        Returns
+        -------
+            metal : bool
+                Bool for whether or not an atom is a metal.
+        """
+        return self.sym in globalvars().metalslist(transition_metals_only=transition_metals_only)
+
+    def setcoords(self, xyz):
+        """ Set coordinates of an atom3D class to a new location.
+
+        Parameters
+        ----------
+            xyz : list
+                List of coordinates, has length 3: [X, Y, Z]
+        """
+        self.__xyz[0] = xyz[0]
+        self.__xyz[1] = xyz[1]
+        self.__xyz[2] = xyz[2]
+
+    def symbol(self) -> str:
+        """ Return symbol of atom3D.
+
+        Returns
+        -------
+            symbol : str
+                Element symbol for atom3D class.
+        """
+        return self.sym
+
+    def mutate(self, newType='C'):
+        """ Mutate an element to another element in the atom3D.
+
+        Parameters
+        ----------
+            newType : str, optional
+                Element name for new element. Default is 'C'.
+
+        """
+        globs = globalvars()
+        amass = globs.amass()
+        if newType not in list(amass.keys()):
+            print(('Error, unknown atom atom type transformation to ' + str(newType)))
+            print('no changes made')
+        else:
+            self.mass = amass[newType][0]
+            self.atno = amass[newType][1]
+            self.rad = amass[newType][2]
+            self.name = newType
+            self.sym = newType
+
+    def translate(self, dxyz):
+        """ Move the atom3D by a displacement vector.
+
+        Parameters
+        ----------
+            dxyz : list
+                Displacement vector of length 3: [dx, dy, dz].
+
+        """
+        x, y, z = self.__xyz
+        self.__xyz[0] = x + dxyz[0]
+        self.__xyz[1] = y + dxyz[1]
+        self.__xyz[2] = z + dxyz[2]
+
+    def setEDIA(self, score):
+        """ Sets the EDIA score of an individual atom3D.
+
+        Parameters
+        ----------
+            score : float
+                Desired EDIA score of atom
+        """
+        self.EDIA = score

molSimplify/Classes/dft_obs.py

@@ -0,0 +1,130 @@
+# @file dft_obs.py
+#  Contains dft_observation class.
+#
+#  Written by JP Janet for HJK Group
+#
+#  Dpt of Chemical Engineering, MIT
+
+from molSimplify.Informatics.lacRACAssemble import (
+    generate_all_ligand_autocorrelations,
+    generate_all_ligand_deltametrics,
+    generate_full_complex_autocorrelations,
+    generate_metal_autocorrelations,
+    generate_metal_deltametrics,
+    generate_all_ligand_misc)
+from molSimplify.Classes.mol3D import mol3D
+
+# DFT observations used to postprocess DFT results by measuring ligand properties
+
+
+class dft_observation:
+    def __init__(self, name, geopath):
+        self.name = name
+        self.descriptors = list()
+        self.descriptor_names = list()
+        self.mol = False
+        self.health = False
+        self.comments = list()
+        self.geopath = geopath
+        self.coord = 'undef'
+
+    def sety(self, y_value):
+        self.yvalue = y_value
+
+    def obtain_mol3d(self):
+        this_mol = mol3D()
+        this_mol.readfromxyz(self.geopath)
+        if this_mol.natoms > 0:
+            self.mol = this_mol
+            self.natoms = this_mol.natoms
+            self.health = True
+        else:
+            self.comments.append('geo file appears empty')
+            self.health = False
+
+    def get_coord(self):
+        self.coord = len(self.mol.getBondedAtomsSmart(self.mol.findMetal()[0]))
+
+    def get_descriptor_vector(self, lig_only, simple, flag_name=False, loud=False):
+
+        self.get_coord()
+        if not lig_only and (self.coord == 6):
+            results_dictionary = generate_all_ligand_misc(self.mol, loud)
+            self.append_descriptors(
+                results_dictionary['colnames'], results_dictionary['result_ax'], 'misc', 'ax')
+            self.append_descriptors(
+                results_dictionary['colnames'], results_dictionary['result_eq'], 'misc', 'eq')
+        print(('after adding misc descriptors... ' +
+               str(len(self.descriptor_names))))
+        if self.coord == 6:  # oct only
+            results_dictionary = generate_all_ligand_autocorrelations(
+                self.mol, depth=3, loud=loud, flag_name=flag_name)
+            self.append_descriptors(
+                results_dictionary['colnames'], results_dictionary['result_ax_full'], 'f', 'ax')
+            self.append_descriptors(
+                results_dictionary['colnames'], results_dictionary['result_eq_full'], 'f', 'eq')
+            print(('after adding full ax/eq descriptors... ' +
+                   str(len(self.descriptor_names))))
+            if not simple and not lig_only:
+                self.append_descriptors(
+                    results_dictionary['colnames'], results_dictionary['result_ax_con'], 'lc', 'ax')
+                self.append_descriptors(
+                    results_dictionary['colnames'], results_dictionary['result_eq_con'], 'lc', 'eq')
+                results_dictionary = generate_all_ligand_deltametrics(
+                    self.mol, depth=3, loud=True, flag_name=flag_name)
+                self.append_descriptors(
+                    results_dictionary['colnames'], results_dictionary['result_ax_con'], 'D_lc', 'ax')
+                self.append_descriptors(
+                    results_dictionary['colnames'], results_dictionary['result_eq_con'], 'D_lc', 'eq')
+
+                print(('after adding lc ax/eq descriptors... ' +
+                       str(len(self.descriptor_names))))
+        if not lig_only:
+            if not simple:
+                results_dictionary = generate_metal_autocorrelations(
+                    self.mol, depth=3, loud=loud)
+                self.append_descriptors(
+                    results_dictionary['colnames'], results_dictionary['results'], 'mc', 'all')
+                results_dictionary = generate_metal_deltametrics(
+                    self.mol, depth=3, loud=loud)
+                self.append_descriptors(
+                    results_dictionary['colnames'], results_dictionary['results'], 'D_mc', 'all')
+            results_dictionary = generate_full_complex_autocorrelations(
+                self.mol, depth=3, loud=loud)
+            self.append_descriptors(
+                results_dictionary['colnames'], results_dictionary['results'], 'f', 'all')
+        print(('after adding full complex descriptors... ' +
+               str(len(self.descriptor_names))))
+
+    def append_descriptors(self, list_of_names, list_of_props, prefix, suffix):
+        for names in list_of_names:
+            if hasattr(names, '__iter__'):
+                names = ["-".join([prefix, str(i), suffix]) for i in names]
+                self.descriptor_names += names
+            else:
+                names = "-".join([prefix, str(names), suffix])
+                self.descriptor_names.append(names)
+        for values in list_of_props:
+            if hasattr(values, '__iter__'):
+                self.descriptors.extend(values)
+            else:
+                self.descriptors.append(values)
+
+
+def write_descriptor_csv(list_of_runs):
+    with open('descriptor_file.csv', 'w') as f:
+        f.write('runs,')
+        n_cols = len(list_of_runs[0].descriptor_names)
+        for i, names in enumerate(list_of_runs[0].descriptor_names):
+            if i < (n_cols-1):
+                f.write(names+',')
+            else:
+                f.write(names+'\n')
+        for runs in list_of_runs:
+            try:
+                f.write(runs.name)
+                for properties in runs.descriptors:
+                    f.write(','+str(properties))
+                f.write('\n')
+            except AttributeError:
+                pass