i I dZddlZddlZddlZddlmZddlmZddl m Z m Z ddl m Z dd lmZmZmZmZmZmZmZmZmZmZmZmZmZmZmZmZejd Z d Z!d Z"e"#Z$e%d e&e"e'dDZ(e%de&e$e'dDZ)dZ*dZ+Gdde Z,dZ-dS)a PDB Topology Parser ========================================================================= This topology parser uses a standard PDB file to build a minimum internal structure representation (list of atoms). The topology reader reads a PDB file line by line and ignores atom numbers but only reads residue numbers up to 9,999 correctly. If you have systems containing at least 10,000 residues then you need to use a different file format (e.g. the "extended" PDB, *XPDB* format, see :mod:`~MDAnalysis.topology.ExtendedPDBParser`) that can handle residue numbers up to 99,999. .. note:: Atomtypes will be created from elements if they are present and valid. Otherwise, they will be guessed on Universe creation. By default, masses will also be guessed on Universe creation. This may change in release 3.0. See :ref:`Guessers` for more information. .. Note:: The parser processes atoms and their names. Partial charges are not set. Elements are parsed if they are valid. If partially missing or incorrect, empty records are assigned. See Also -------- * :mod:`MDAnalysis.topology.ExtendedPDBParser` * :class:`MDAnalysis.coordinates.PDB.PDBReader` * :class:`MDAnalysis.core.universe.Universe` Classes ------- .. autoclass:: PDBParser :members: :inherited-members: N)SYMB2Z)util)TopologyReaderBase change_squash)Topology) AtomnamesAtomidsAltLocsBondsChainIDs AtomtypesElementsICodes Occupancies RecordTypesResidsResnamesResnumsSegids Tempfactors FormalChargeszMDAnalysis.topology.PDBParsercF t|S#t$r|cYSwxYwN)float ValueError)valdefaults g/srv/www/vhosts/g4struct/public_html/venv/lib/python3.11/site-packages/MDAnalysis/topology/PDBParser.pyfloat_or_defaultr!cs7Szz s   $0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZcg|]}|Sr$.0pairs r r(lJJJTDJJJ$cg|]}|Sr$r$r%s r r(r(mr)r*cRd}t|}|D]}||z}|||z }|S)aDecodes the string s using the digit, value associations for each character. Parameters ---------- digits_values: dict A dictionary containing the base-10 numbers that each hexadecimal number corresponds to. s: str The contents of the pdb index columns. Returns ------- The integer in base-10 corresponding to traditional base-36. r)len) digits_valuessresultncs r decode_purer4psD F MA ##! -"" Mr*cxt||kr|d}|dks|dks|rt|S|tvr(t t|dd|dz zzz d|zzS|t vr(t t |dd|dz zzzd|zzSt d ) aC Decodes base-10/upper-case base-36/lower-case base-36 hybrid. Parameters ---------- width: int The number of columns in the pdb file store atom index. s: str The contents of the pdb index columns. Returns ------- int Base-10 integer corresponding to hybrid36. r- )r/r0 r+rzinvalid number literal.)r.isdigitintDIGITS_UPPER_VALUESr4DIGITS_LOWER_VALUESr)widthr0fs r hy36decoder@s A% aD HHSAIIKKq66M&&&-@!"$$$&(2%!)+<&<=?AU{K K&&&-@!"$$$&(2%!)+<&<=?AU{K K . / //r*c,eZdZdZddgZdZdZdZdS) PDBParseraQParser that obtains a list of atoms from a standard PDB file. Creates the following Attributes (if present): - names - chainids - tempfactors - occupancies - record_types (ATOM/HETATM) - resids - resnames - segids - elements - bonds - formalcharges Note that `PDBParser` accepts an optional keyword argument ``force_chainids_to_segids``. If set to ``True``, the chain IDs (even if empty values are in the chain ID column in the file) will forcibly be used instead of the segment IDs for creating segments. See Also -------- :class:`MDAnalysis.coordinates.PDB.PDBReader` .. versionadded:: 0.8 .. versionchanged:: 0.18.0 Added parsing of Record types .. versionchanged:: 1.0.0 Added parsing of valid Elements .. versionchanged:: 2.0.0 Bonds attribute is not added if no bonds are present in PDB file. If elements are invalid or partially missing, empty elements records are now assigned (Issue #2422). Aliased ``bfactors`` topologyattribute to ``tempfactors``. ``bfactors`` is deprecated and will be removed in 3.0 (Issue #1901) .. versionchanged:: 2.3.0 Formal charges are now read from PDB files if present. No formalcharge attribute is created if no formal charges are present in the PDB file. Any formal charges not set are assumed to have a value of 0. Raise `UserWarning` instead `RuntimeError` when CONECT records are corrupt. .. versionchanged:: 2.5.0 Formal charges will not be populated if an unknown entry is encountered, instead a UserWarning is emitted. .. versionchanged:: 2.8.0 Removed type and mass guessing (attributes guessing takes place now through universe.guess_TopologyAttrs() API). .. versionchanged:: 2.10.0 segID is read from 73-76 instead of 67-76 and added the `force_chainids_to_segids` keyword argument. Some infos in logger will be generated if the segids is not present or if the chainids are not completely equal to segids. PDBENTc |jdi|} ||jj}|r||nC#t $rt jdYn#t$rt jdYnwxYw|S)zqParse atom information from PDB file Returns ------- MDAnalysis Topology object ;Invalid atom serials were present, bonds will not be parsedz4CONECT records was corrupt, bonds will not be parsedr$) _parseatoms _parsebondsidsvaluesadd_TopologyAttrAttributeErrorwarningswarn RuntimeError)selfkwargstopbondss r parsezPDBParser.parsesd(((( ,$$SW^44E ,$$U+++ 6 6 6 M5 6 6 6 6 6 6 6 6 M5 6 6 6 6 6 6 sAB&BBc Dd}g}g}g}g}g}g}g} g} g} g} g} g}g}d|_d}tj|j5}|D]}|}|s|drnw|dsH||dd t|dd}n?# td |dd}n#t$rd |_|}|d z }YnwxYwYnxYw||n#||wxYw||d d ||d d| |dd||dd||dd||dd |j dkrt|dd}n0t|dd}||z dkr|dz }||z dk|}n&#t$rtj dd }YnwxYw| |||ddnI#| |||ddwxYw| t|ddd| t|ddd| |dddddn #1swxYwY|jrtj d td!t| |Drt d"t| st d#|} |d$drt d%|} t)|}g}|t*t,f|t.t,f|t0t,f|t2t,f|t4t6jf| t:t6jf| t>t6jffD]8\}}}||t7j ||&9t|r|}|tCt7j |t,&g}|D]t}|"tFvr(||"Ed'|d(}tj ||d)u|tIt7j |t,&ntj d*t|r tK|D]G\}}|d)ks7|d+krd||<d,|vsd-|vrt|ddd.||<;td||<H |tMt7j |t&n*#t$rd/|d0}tj |YnwxYwt7j | t6j&} t7j | t,&} |j dkrd)g|z}t7j |t,&}| '} t7j | t,&} tQ| | || f| | || | f\}!\} } }} } t)| }"|tS| |tU| |tW||tY| |d$ds(t| rbtd1| DsItQ| f| f\}#\} t)| }$|t[| nZd }$|t[t7j d2gt,&d}#t d3t]||"|$||!|#4}%|%S)5z"Create the initial Topology objectrFiEND)ATOMHETATMN Tr r9LNPXPDBixi'z8PDB file is missing resid information. Defaulted to '1'6<gBg?HzCSerial numbers went over 100,000. Higher serials have been guessedc g|] \}}||k Sr$r$)r&abs r r(z)PDBParser._parseatoms..Gs 99941aQ999r*z3Segment IDs and Chain IDs are not completely equal.zESetting segids from chainIDs because no segids found in the PDB file.force_chainids_to_segidsz@force_chainids_to_segids is set. Using chain IDs as segment IDs.)dtypezUnknown element z found for some atoms. These have been given an empty element record. If needed they can be guessed using universe.guess_TopologyAttrs(context='default', to_guess=['elements']).zElement information is missing, elements attribute will not be populated. If needed these can be guessed using universe.guess_TopologyAttrs(context='default', to_guess=['elements']).0+r6zUnknown entry z encountered in formal charge field. This likely indicates that the PDB file is not fully standard compliant. The formalcharges attribute will not be populated.c3K|]}|duV dSrr$)r&rs r z(PDBParser._parseatoms..s&$C$CSSD[$C$C$C$C$C$Cr*SYSTEMzDSegment/chain ID is empty, setting segids to default value 'SYSTEM'.)attrs atom_resindexresidue_segindex)/_wrapped_serialsropenanyfilenamestrip startswithappendr;r@rformatrMrNr!anyziploggerdebuginfogetr.r objectr rrr npint32rfloat32rarrayr capitalizerr enumeratercopyrrrrrrr )&rPrQ resid_prev record_typesserialsnamesaltlocschainidsicodes tempfactors occupanciesresidsresnamessegidselements formalchargeslast_wrapped_serialr?lineserialresidn_atomsrvvalsAttrrn atomtypesvalidated_elementselemwmsgientryresnumsresidx n_residuessegidx n_segmentsrRs& r rGzPDBParser._parseatomss9      %$ \$- ( (5 3A4 34 3zz||??5))E'9::##D!HNN$4$4555 + ad__FF11!+AtAbDz!:!:%11104-!4+q0+++ 1 NN6****GNN6**** T"R%[..00111tBrE{0022333RU 1 1 3 3444RU 1 1 3 3444RU 1 1 3 3444$$T"R%[%6%6%8%89997{f,, #DBK 0 0 #DBK 0 0#j0588!UNE$j0588%* !M#5666EEE MM%(((MM$r"u+"3"3"5"56666MM%(((MM$r"u+"3"3"5"56666""#3DBK#E#EFFF""#3DBK#E#EFFF d2b5k//112222k5 35 35 35 35 35 35 35 35 35 35 35 35 35 35 3p   > M= > > > 993vx#8#8999 : : P LLN O O O6{{  KK1 2 2 2F ::0% 8 8  KK: ; ; ;Fg,, 6*'6*8V,{F3'28,k2:6k2:6" < < D$ LLbht5999:: ; ; ; ; x== H I LL28HF#C#C#CDD E E E!#  2 2??$$..&--doo.?.?@@@@7t777D M$'''&--b1111 LL"(+=V"L"L"LMM N N N N MG H H H }   P P )- 8 8 - -HAu B;; C<< 01M!,,!Ullu /252;/?/?M!,,",,+, a(( -* ]28M+M+M+MNNOOOO $ $ $;;;; d#####  $&1118HF333 ;& TG^F&///++--&///>K Xvv .67TZ0[?]?];;67F[[  WW%%&&& VF^^$$$ VF^^$$$ Xh''((( JJ15 9 9 E [[ E!$$C$CF$C$C$C!C!C E!.vi& C C FIVVJ LL ( ( ( (J LL(6 B B BCC D D DF KKD E E Ew J"%+(.000  sA:O7:CD'DC.-D.D DD D D'O7'D>>DO7AJ0/L0 KLKLAO7AM!!B O77O;>O;A\11$]]cp|jrtjdtt dt |D}t }tj|j 5}d|D}|D]}t| \}}|D]Y} t|||| g} | | 6#t$rtjdYVwxYw dddn #1swxYwYt|}t|S)NrFc3$K|] \}}||fV dSrr$)r&rr0s r rtz(PDBParser._parsebonds..s*==$!Q1v======r*c36K|]}|dddk|VdS)NrYCONECTr$)r&rs r rtz(PDBParser._parsebonds..s4@@d48x+?+?T+?+?+?+?@@r*zOPDB file contained CONECT record to TER entry. These are not included in bonds.)ryrMrNrLdictrsetrrzr{ _parse_conectr|tupleaddKeyErrorr ) rPrmappingrSr?linesratomatomsrkbonds r rHzPDBParser._parsebondss   ! M' ( ( ( ==)G*<*<===== \$- ( ( (A@@a@@@E ( (+DJJLL99 e ( (A ($gdmWQZ%@AA $$@@@! ?@@@@@@ ( ( ( ( ( ( ( ( ( ( ( ( ( ( ( ( ( e U||s609D*CDC> ;D=C> >DDDN)__name__ __module__ __qualname____doc__rrTrGrHr$r*r rBrBs[55lU^F0DDDL$$$$$r*rBcxtdd}tdddz} tdd|zdkr"tdn(#t$rt jd|gfcYSwxYwfdt|D}||fS) aWparse a CONECT record from pdbs Parameters ---------- conect : str white space striped CONECT record Returns ------- atom_id : int atom index of bond bonds : set atom ids of bonded atoms Raises ------ RuntimeError Raised if ``conect`` is not a valid CONECT record rYrZNr[rz8Bond atoms aren't aligned proberly for CONECT record: {}z4Found CONECT record with single entry, ignoring thisc3^K|]'}td|dzzd|dzzV(dS)rZr[r9N)r;)r&rconects r rtz _parse_conect..sU''!#fR!a%Za!e3455''''''r*)r;r.rOrZeroDivisionErrorrMrNrange)ratom_id n_bond_atoms bond_atomss` r rrs(&2,Gvbcc{##q(L vbcc{  l *a / / ,,2F6NN<< < 0  LMMM{ '''' %%'''J J sAA55"BB).rnumpyrrMloggingguesser.tablesrlibrbaserr core.topologyr core.topologyattrsr r r r rrrrrrrrrrrr getLoggerrr! DIGITS_UPPERlower DIGITS_LOWERrrrr<r=r4r@rBrr$r*r rs?0++X######33333333$$$$$$(  : ; ;6 !!## dJJSSuuRyy-I-IJJJKKdJJSSuuRyy-I-IJJJKK0000:{{{{{"{{{| """""r*