B bϓ@sdZddlmZmZddlZddlZddlZddl m Z m Z m Z ddl mZddlmZmZmZmZddlmZddlmZmZddlZd d d d d ddgZGdddeZed Zed Zed Zed Z Gdd d eZ!Gddde!Z"Gddde#Z$dS)zr This contains the basic residue template and residue building libraries typically used in modelling applications ) OrderedDict defaultdictN)AminoAcidResidue RNAResidue DNAResidue) Structure)AtomBondAtomList TrackedList) iteritems)IncompatiblePatchError MoleculeErrorPROTEINNUCLEICSOLVENTUNKNOWNResidueTemplateResidueTemplateContainer PatchTemplatec@s(eZdZdZddZddZddZdS) _ResidueTypez) Singleton for various types of residues cCs ||_dS)N)name)selfrr6lib/python3.7/site-packages/parmed/modeller/residue.py__init__sz_ResidueType.__init__cCs d|jS)Nz)r)rrrr__repr__sz_ResidueType.__repr__cCs|jS)N)r)rrrr__str__sz_ResidueType.__str__N)__name__ __module__ __qualname____doc__rrrrrrrrsrc@seZdZdZd6ddZddZeddZd d Zd d Z d7ddZ ddZ e ddZ eddZeddZeddZddZddZddZd d!Zd"d#Zd8d&d'Zd9d(d)Zd*d+Zd:d-d.Zd/d0Zd1d2Zd;d4d5Zd$S))r&rr'r)rlenr#r$)rr&r'rrrrbs    zResidueTemplate.__repr__cCs|jS)N)r.)rrrrmaposzResidueTemplate.mapcCs<|j|jkrtd|j||_|j|||j|j<dS)a Adds an atom to this residue template Parameters ---------- atom : :class:`Atom` The atom to add to this residue Raises ------ ValueError if ``atom`` has the same name as another atom in this residue already z!Residue already has atom named %sN)rr. ValueErrorresiduer#append)ratomrrradd_atomss  zResidueTemplate.add_atomcCst|tkr|}n|j}||jkrr3format)rr@rrrr=s zResidueTemplate.delete_bondc Cs4||jd}x|D]}|t|qWx|D]}x|jD]}y |j|j}|j|j}Wnt k r|j|kr|j}|j|j}n|j}|j|j}|j j |j dkr|j||_ nN|j j |j dkr|j||_ n.|j j |j krtdn|j|j|Yq>X|||q>Wq2W|S)z This constructor creates a ResidueTemplate from a particular Residue object Parameters ---------- residue : :class:`Residue` The residue from which to create a template )rz2Cannot determine head/tail for unordered residues.)rr7_copycopyr$r#indexr;r<r3r4idxr&r'warningswarnr(r5rG) clsr4instr6r@Zi1Zi2ZoatomrNrrr from_residues.      zResidueTemplate.from_residuecCs8y|jStk r0tdd|D|_YnX|jS)z@ Atomic coordinates, in Angstroms, of all atoms in the template cSsg|]}|j|j|jgqSr)xxxyxz).0arrr sz/ResidueTemplate.coordinates..)Z_crdAttributeErrornpZarray)rrrr coordinatess zResidueTemplate.coordinatescCstt}x |jD]}||jd7<qWd|kr<|ddd}d}d|krt|||d7}d|krt|||d7}t|}x|D]}||||7}qW|S)zj Return the empirical chemical formula (in Hill notation) as a string (e.g. 'H2O', 'C6H12'), omitting EPs rJZEPcSs"||}|dkr|S|t|S)NrJ)popr8) element_countelementcountrrrformat_and_pop_element*s zJResidueTemplate.empirical_chemical_formula..format_and_pop_elementr"CH)rintr#Z element_namer]sortedr:)rr^r6raZchemical_formulaZalphabetical_elementsr_rrrempirical_chemical_formulas    z*ResidueTemplate.empirical_chemical_formulacCstdd|DS)NcSsg|] }|jqSr)charge)rWrXrrrrY?sz.ResidueTemplate.net_charge..)sum)rrrr net_charge=szResidueTemplate.net_chargecCs t|jS)N)r1r#)rrrr__len__CszResidueTemplate.__len__cCs t|jS)N)iterr#)rrrr__iter__FszResidueTemplate.__iter__cCs4t|tr||jkSt|tr(||jkStddS)NzShould not be here!)rErr#r8r.AssertionError)rr6rrr __contains__Is     zResidueTemplate.__contains__cCst||jd}x|jD]}|t|qWx"|jD]}||jj |j j q8W|j|_|j dk rv|j|j j |_ |j dk r|j|j j |_ x"|j D]}|j |j|j qW|j|_|j|_|S)N)r)r)rr#r7rKrLr$rGr;rNr<r&r'r(r5r*r+)rotherr6r@Z connectionrrr__copy__Ps     zResidueTemplate.__copy__csjt|tr.)rEr8r#r IndexErrorr%tuple)rrNr6r)rr __getitem__ds   zResidueTemplate.__getitem__NcCs|jstd|j}|dkr&t|}n t||}||kr<|S||t|}x|D]}t|j|||_qRW|jdj|tdd|jD7_|S)a Adjusts the partial charge of all atoms in the residue to match the requested target charge. The default target charge is the closest integer Parameters ---------- to : float, optional The desired net charge of this residue template. Default is the closest integer charge precision : int, optional The number of decimal places that each charge should be rounded to. Default is 4 Returns ------- self : :class:`ResidueTemplate` The current residue template whose charges are being modified Notes ----- This method modifies the atomic charges of this residue template in-place. Any residual charge (which is accumulated roundoff beyond the requested precision) is added to the first atom of the residue. This will typically be 10^-precision in magnitude, and should almost never be higher than 2*10^-precision. As long as a reasonable precision is chosen (no fewer than 3 or 4 decimal places), this will have only a negligible impact on a force field. If provided, "to" will be rounded to the ``precision``'th decimal place to make sure that the sum of the charges come out as close as possible to the target charge while still obeying the requested precision. Raises ------ ValueError If you try to call fix_charges on a residue template with no atoms z&Cannot fix charges on an empty residueNrcss|] }|jVqdS)N)rg)rWr6rrr sz.ResidueTemplate.fix_charges..)r#r3riroundr1rgrh)rto precisionriZsmearr6rrr fix_chargesos'   (zResidueTemplate.fix_chargesc Cst|}d}x|jD]}y||d}Wqttfk r}zR|drp|dd|krp|dd|jkrpn td|t|j t |fWdd}~XYqXqWxT|j D]J}|j |kr|j||j _|j||j _n|t|j |j|jdd}qWx|jD]\}} } ybxJ|| gD]>} |jr:| |jj kr:d|_|jr| |jj krd|_qW||| | d}WnJttfk r}z&td|| t|j t |fWdd}~XYnXqWxR|jD]H} y|j| Wn0tk r}ztd | Wdd}~XYnXqW|j} t| |t| d k}|sDtd | d dl}|d}||sd d| |D}tdt ||std|S)aC Apply the specified PatchTemplate to the ResidueTemplate. This only handles patches that affect a single residue. An exception is thrown if patch is incompatible because * The patch specifies that an atom is to be deleted that doesn't exist in the residue * A bond specified as being added in the patch does not have both atom names present after adding/deleting atoms from the patch * The new net charge is not integral to the specified precision * The residue is not modified in any way (no atoms or bonds added/changed/deleted) Parameters ---------- patch : PatchTemplate The patch to apply to this residue precision : int, optional Each valid patch should be produce a net charge that is integral to this many decimal places. Default is 4 Returns ------- residue : ResidueTemplate A new ResidueTemplate corresponding to the patched residue is returned. The original remains unmodified. FTDrJNzSAtom %s could not be deleted from the patched residue: atoms are %s (exception: %s))rr)rgzNBond %s-%s could not be added to patched residue: atoms are %s (exception: %s)z3Improper %s was not found in residue to be patched.gzPPatch is not compatible with residue due to non-integral charge (charge was %f).rcSsg|]}|qSrr)rWcrrrrYsz/ResidueTemplate.apply_patch..z7Patched residue bond graph is not a connected graph: %szPatch did not modify residue.)!rKrL delete_atomsrBr9r startswithr r%r.r:r8r#rr)rgr7r add_bondsr&r'rGrrdelete_impropersr/r>r3rirwnetworkx to_networkxZ is_connectedZconnected_components)rpatchryr4Zmodifications_mader?er6Z atom1_nameZ atom2_namerDrrAriZ is_integralZnxGZ componentsrrr apply_patchsX!   ,6   : $   zResidueTemplate.apply_patchcCs(y||dStk r"dSXdS)aDetermine whether a specified patch is compatible with this residue. Compatibility is determined by whether Residue.Template.apply_patch(patch) raises as exception or not. Parameters ---------- patch : PatchTemplate The patch to be applied to this residue. Returns ------- is_compatible : bool True if patch is compatible with the residue; False if not. TFN)rr )rrrrrpatch_is_compatibles  z#ResidueTemplate.patch_is_compatibleTcCsddl}|}x2|jD](}|jdks*|r|j|j|j|jdqWx>|jD]4}|j jdkrh|j jdksl|rL| |j j|j jqLW|S)ad Create a NetworkX graph of atoms and bonds Parameters ---------- include_extra_particles : bool Whether to include "atoms" that actually represent extra particles (atomic_number == 0). Returns ------- G : :class:`networkx.Graph` A NetworkX Graph representing the molecule rN)rgr)) rZGraphr# atomic_numberZadd_noderrgr)r$r;r<Zadd_edge)rZinclude_extra_particlesrrr6r@rrrrs  zResidueTemplate.to_networkxcCs0ddl}|}dd|jD|d<dd|jD|d<dd|jD|d <d d|jD|d <d d|jD|d <dd|jD|d<dd|jD|d<dd|jD|d<dd|jD|d<dd|jD|d<dd|jD|d<dd|jD|d<dd|jD|d<dd|jD|d<d d|jD|d!<d"d|jD|d#<d$d|jD|d%<d&d|jD|d'<d(d|jD|d)<d*d|jD|d+<y$|jd,d|jDd-d.d/gd0}Wntk rYn X||}y$|jd1d|jDd2d3d4gd0}Wntk r Yn X||}|S)5aB Create a pandas dataframe from the atom information Returns ------- df : :class:`pandas.DataFrame` The pandas DataFrame with all of the atomic properties Notes ----- The DataFrame will be over all atoms. The columns will be the attributes of the atom (as well as its containing residue). Some columns will *always* exist. Others will only exist if those attributes have been set on the Atom instances (see the :class:`Atom` docs for possible attributes and their meaning). The columns that will always be present are: - number : int - name : str - type : str - atomic_number : int - charge : float - mass : float - nb_idx : int - solvent_radius : float - screen : float - occupancy : float - bfactor : float - altloc : str - tree : str - join : int - irotat : int - rmin : float - epsilon : float - rmin_14 : float - epsilon_14 : float The following attributes are optionally present if they were present in the original file defining the structure: - xx : float (x-coordinate position) - xy : float (y-coordinate position) - xz : float (z-coordinate position) - vx : float (x-coordinate velocity) - vy : float (y-coordinate velocity) - vz : float (z-coordinate velocity) rNcSsg|] }|jqSr)number)rWr6rrrrYisz0ResidueTemplate.to_dataframe..rcSsg|] }|jqSr)r)rWr6rrrrYjsrcSsg|] }|jqSr)r))rWr6rrrrYksr)cSsg|] }|jqSr)r)rWr6rrrrYlsrcSsg|] }|jqSr)rg)rWr6rrrrYmsrgcSsg|] }|jqSr)mass)rWr6rrrrYnsrcSsg|] }|jqSr)nb_idx)rWr6rrrrYosrcSsg|] }|jqSr)solvent_radius)rWr6rrrrYpsrcSsg|] }|jqSr)screen)rWr6rrrrYqsrcSsg|] }|jqSr) occupancy)rWr6rrrrYrsrcSsg|] }|jqSr)bfactor)rWr6rrrrYssrcSsg|] }|jqSr)altloc)rWr6rrrrYtsrcSsg|] }|jqSr)tree)rWr6rrrrYusrcSsg|] }|jqSr)join)rWr6rrrrYvsrcSsg|] }|jqSr)irotat)rWr6rrrrYwsrcSsg|] }|jqSr)rmin)rWr6rrrrYxsrcSsg|] }|jqSr)epsilon)rWr6rrrrYysrcSsg|] }|jqSr)rmin_14)rWr6rrrrYzsrcSsg|] }|jqSr) epsilon_14)rWr6rrrrY{srcSsg|] }|jjqSr)r4r)rWr6rrrrY|sZresnamecSsg|]}|j|j|jgqSr)rTrUrV)rWr6rrrrYsrTrUrV)columnscSsg|]}|j|j|jgqSr)vxvyvz)rWr6rrrrYsrrr)ZpandasZ DataFramer#rZr)rZpdretZcoordsZvelsrrr to_dataframe7sJ/  zResidueTemplate.to_dataframecCsdt}x"|D]}|t||jdq Wx4|jD]*}|jt|j|j j |j|j j q2W|S)a Generates a Structure instance with a single residue from this ResidueTemplate Returns ------- struct : :class:`parmed.structure.Structure` The Structure with all of the bonds and connectivity of this template r) rr7rKrLrr$r5r r#r;rNr<)rstructr6r@rrr to_structures   zResidueTemplate.to_structureFc Ksddlm}ddlm}ddddddd }|d k r<|}nFtj|\}} | d krdtj|d } | |krv|| }n td ||dkr|j ||fddi|nr|dkr|j ||fddi|nP|dkr|j |j |i|f|n0|dkr| j |f||d|ntdd S)a Saves the current ResidueTemplate in the requested file format. Supported formats can be specified explicitly or determined by file-name extension. The following formats are supported, with the recognized suffix shown in parentheses: - MOL2 (.mol2) - MOL3 (.mol3) - OFF (.lib/.off) - PDB (.pdb) - PQR (.pqr) Parameters ---------- fname : str Name of the file to save. If ``format`` is ``None`` (see below), the file type will be determined based on the filename extension. If the type cannot be determined, a ValueError is raised. format : str, optional The case-insensitive keyword specifying what type of file ``fname`` should be saved as. If ``None`` (default), the file type will be determined from filename extension of ``fname`` overwrite : bool, optional If True, allow the target file to be overwritten. Otherwise, an IOError is raised if the file exists. Default is False kwargs : keyword-arguments Remaining arguments are passed on to the file writing routines that are called by this function Raises ------ ValueError if either filename extension or ``format`` are not recognized TypeError if the structure cannot be converted to the desired format for whatever reason r)AmberOFFLibrary)Mol2FileMOL2MOL3OFFLIBPDBPQR)z.mol2z.mol3z.offz.libz.pdbz.pqrN)z.bz2z.gzrJz#Could not determine file type of %smol3FT)rOFF)rr)rI overwritez,Unrecognized format for ResidueTemplate save) parmed.amber.offlibrparmed.formats.mol2rupperospathsplitextr3writerrsave) rfnamerIrkwargsrrextmapbaseextrrrrs4$       zResidueTemplate.save)r")rC)Nru)ru)T)NF)rrr r!rrpropertyr2r7rBrGr= classmethodrSr\rfrirjrlrnrprtrzrrrrrrrrrrr(s0'  * . (   ; ^ ^cs"eZdZdZdfdd ZZS)ra A residue patch (typically used for CHARMM) that is used to modify existing residues in some way (e.g., terminal patches, disulfide bridges, etc.) Parameters ---------- name : str, optional If provided, this is the name of the residue Attributes ---------- add_bonds : list of (str, str, order) List of bonds that need to be added in applying the patch delete_atoms : list of str List of atom names that need to be deleted in applying the patch delete_impropers : list of tuple of str List of impropers (tuple of atom names) that need to be deleted in applying the patch See Also -------- :class:`ResidueTemplate` Notes ----- This class basically just provides an additional list of atoms that need to be deleted when applying this patch -- something that does not apply to standard Residues r"cs&tt||g|_g|_g|_dS)N)superrrrr}r)rr) __class__rrr szPatchTemplate.__init__)r")rrr r!r __classcell__rr)rrrsc@sZeZdZdZdddZedddZdd Zdd d Zd dZ edddZ dddZ dS)rz A container of ResidueTemplate objects representing a unit with multiple residues Parameters ---------- name : str, optional The name of the residue container r"cCsd|_||_dS)N)boxr)rrrrrrsz!ResidueTemplateContainer.__init__TcCsH|}x2|jD]&}t|}|jdkr|jdk r|rt|jrnt|jdks`|jddkrd|j|_n2t |jst |jr|jddkrd|j|_n|jdkr.|jdk r.|r.t|jrt|jdks|jdd krd |j|_n8t |jst |jr.|jdd kr.d |j|_| |qW|j |_ |S) a< Instantiates a ResidueTemplateContainer from a Structure instance filled with residues Parameters ---------- struct : :class:`parmed.structure.Structure` The structure from which to generate the ResidueTemplateContainer from term_decorate : bool, optional If True, terminal amino and nucleic acid residues will be adorned as follows: * N-prepended if it is an N-terminal amino acid * C-prepended if it is a C-terminal amino acid * 5-appended if it is a 5'-terminal nucleic acid * 3-appended if it is a 3'-terminal nucleic acid For example, an N-terminal GLY will become NGLY, while a 5'-terminal DA will become DA5. Default is True NrurNzN%s5z%s5rbzC%s3z%s3) ZresiduesrrSr&r'rZhasrr1rrr5r)rQrZ term_decoraterRresZrtrrrfrom_structure"s(    z'ResidueTemplateContainer.from_structurecCs2t|tr&x|D]}|j|kr|SqWt||S)N)rEr8rr%rt)rvaluerrrrrtOs    z$ResidueTemplateContainer.__getitem__rucCs2t|dkrtdx|D]}|j|dqW|S)a Adjusts the net charge of all residues in this ResidueContainer to match the closest integer charge Parameters ---------- precision : int, optional The number of decimal places that each charge should be rounded to. Default is 4 Returns ------- self : :class:`ResidueTemplateContainer` The current residue template container whose ResidueTemplates are being modified Notes ----- This method modifies everything in-place. Raises ------ ValueError If you try to call fix_charges on a container with no templates rz(Cannot fix charges on an empty container)ry)r1r3rz)rryrrrrrzVs   z$ResidueTemplateContainer.fix_chargescCs.t}x"|D]}|j|krq |||j<q W|S)a_ Converts the ResidueTemplateContainer instance to a library of unique :class:`ResidueTemplate` instances. The first of each kind of residue is taken Returns ------- residues : dict {str : :class:`ResidueTemplate`} The residue library with all residues from this residue collection )rr)rrrrrr to_libraryvs   z#ResidueTemplateContainer.to_libraryFcCsV|}xJt|D]>\}}t|ts.td||rD|t|q||qW|S)aT Converts a dictionary of ResidueTemplate items into a ResidueTemplateContainer. Parameters ---------- library : dict or OrderedDict The library of ResidueTemplate objects to add to this container copy : bool, optional If True, copies of each ResidueTemplate in library is added to the ResidueTemplateContainer. Default is False Returns ------- cont : ResidueTemplateContainer A ResidueTemplateContainer containing all of the residues defined in ``library`` Notes ----- If the library is ordered, that order is maintained Raises ------ TypeError if any of the items in the input library is not a ResidueTemplate instance (or an instance of a subclass) z$%r is not a ResidueTemplate instance)r rErr3r5rKrL)rQZlibraryrLZcont_rrrr from_librarys  z%ResidueTemplateContainer.from_libraryNc Ksddlm}ddlm}ddddd}|dk r8|}nFtj|\}}|d kr`tj|d }||krr||}n td ||dkr|j ||fd d d|nJ|dkr|j ||fd d d|n&|dkr|j | |f|ntddS)a  Saves the current ResidueTemplateContainer in the requested file format. Supported formats can be specified explicitly or determined by file-name extension. The following formats are supported, with the recognized suffix and ``format`` keyword shown in parentheses: - MOL2 (.mol2) - MOL3 (.mol3) - OFF (.lib/.off) Parameters ---------- fname : str Name of the file to save. If ``format`` is ``None`` (see below), the file type will be determined based on the filename extension. If the type cannot be determined, a ValueError is raised. format : str, optional The case-insensitive keyword specifying what type of file ``fname`` should be saved as. If ``None`` (default), the file type will be determined from filename extension of ``fname`` kwargs : keyword-arguments Remaining arguments are passed on to the file writing routines that are called by this function Raises ------ ValueError if either filename extension or ``format`` are not recognized TypeError if the structure cannot be converted to the desired format for whatever reason Notes ----- Mol2 and Mol3 files are saved as concatenated multiple @s. By contrast, ``Structure.save`` will save a single @ mol2 file with multiple residues if the mol2 format is requested. r)r)rrrr)z.mol2z.mol3z.offz.libN)z.bz2z.gzrJz#Could not determine file type of %sFT)rsplit)rrz,Unrecognized format for ResidueTemplate save) rrrrrrrrr3rr) rrrIrrrrrrrrrrs*%     zResidueTemplateContainer.save)r")T)ru)F)N) rrr r!rrrrtrzrrrrrrrrs   ,  &)%r! collectionsrrrLrKZnumpyr[rZparmed.residuerrrZparmed.structurerZparmed.topologyobjectsrr r r Zparmed.utils.sixr Zparmed.exceptionsr rrO__all__objectrrrrrrrr%rrrrrs2    L%