o ॵiF @s|dZddlZddlZddlZddlZddlmZmZmZm Z m Z ddl m Z ddl mZddlmZddlmZeZeeefZejjZeZeee efZejdd Gd d d Zejdd Gd d d Zejdd GdddZejdd GdddZejdd GdddZejdd GdddZ Gddde!Z"dedede eeeffddZ#dedededeeeeefffddZ$ej%d d!d"dd#d$ed%ed&e&de fd'd(Z'ej%d d!d"dd#d$ed%ed&e&de fd)d*Z(d+edefd,d-Z)d.Z*dedefd/d0Z+dedefd1d2Z,dede efd3d4Z-deeefdeee effd5d6Z.d7ede&fd8d9Z/dS):zParses the mmCIF file format.N)AnyMappingOptionalSequenceTuple)logging)PDB)SCOPData) MMCIFParserT)frozenc@seZdZUeed<eed<dS)MonomeridnumN__name__ __module__ __qualname__str__annotations__intrr_/home/ubuntu/.local/lib/python3.10/site-packages/modelscope/models/science/unifold/msa/mmcif.pyr "s  r c@sNeZdZUeed<eed<eed<eed<eed<eed<eed<eed<d S) AtomSite residue_nameauthor_chain_idmmcif_chain_idauthor_seq_num mmcif_seq_numinsertion_code hetatm_atom model_numNrrrrrr*s  rc@s&eZdZUeed<eed<eed<dS)ResiduePositionchain_idresidue_numberrNrrrrrr!7s  r!c@s2eZdZUeeed<eed<eed<eed<dS)ResidueAtPositionpositionname is_missinghetflagN)rrrrr!rrboolrrrrr$>s  r$c@szeZdZUdZeed<eed<eed<ee e fed<ee ee e ffed<e ed<ee e fed<ee efed <d S) MmcifObjectapRepresentation of a parsed mmCIF file. Contains: file_id: A meaningful name, e.g. a pdb_id. Should be unique amongst all files being processed. header: Biopython header. structure: Biopython structure. chain_to_seqres: Dict mapping chain_id to 1 letter amino acid sequence. E.g. {'A': 'ABCDEFG'} seqres_to_structure: Dict; for each chain_id contains a mapping between SEQRES index and a ResidueAtPosition. e.g. {'A': {0: ResidueAtPosition, 1: ResidueAtPosition, ...}} raw_string: The raw string used to construct the MmcifObject. file_idheader structurechain_to_seqresseqres_to_structure raw_stringmmcif_to_author_chain_id valid_chainsN)rrr__doc__rr PdbHeader PdbStructurerChainIdSeqResrr$rrrrrr*Fs r*c@s6eZdZUdZeeed<eee e fe fed<dS) ParsingResultzReturned by the parse function. Contains: mmcif_object: A MmcifObject, may be None if no chain could be successfully parsed. errors: A dict mapping (file_id, chain_id) to any exception generated. mmcif_objecterrorsN) rrrr3rr*rrrrrrrrrr8`s  r8c@seZdZdZdS) ParseErrorz;An error indicating that an mmCIF file could not be parsed.N)rrrr3rrrrr;nsr;prefix parsed_inforeturncspgg|D]\}}||r||qtfddDs-JdfddtDS)anExtracts loop associated with a prefix from mmCIF data as a list. Reference for loop_ in mmCIF: http://mmcif.wwpdb.org/docs/tutorials/mechanics/pdbx-mmcif-syntax.html Args: prefix: Prefix shared by each of the data items in the loop. e.g. '_entity_poly_seq.', where the data items are _entity_poly_seq.num, _entity_poly_seq.mon_id. Should include the trailing period. parsed_info: A dict of parsed mmCIF data, e.g. _mmcif_dict from a Biopython parser. Returns: Returns a list of dicts; each dict represents 1 entry from an mmCIF loop. cs g|] }t|tdkqS)r)len.0xsdatarr sz&mmcif_loop_to_list..z2mmCIF error: Not all loops are the same length: %scsg|] }tt|qSr)dictzipr@)colsrrrEs)items startswithappendallrG)r<r=keyvaluer)rHrDrmmcif_loop_to_listrs     rOindexcst||}fdd|DS)agExtracts loop associated with a prefix from mmCIF data as a dictionary. Args: prefix: Prefix shared by each of the data items in the loop. e.g. '_entity_poly_seq.', where the data items are _entity_poly_seq.num, _entity_poly_seq.mon_id. Should include the trailing period. index: Which item of loop data should serve as the key. parsed_info: A dict of parsed mmCIF data, e.g. _mmcif_dict from a Biopython parser. Returns: Returns a dict of dicts; each dict represents 1 entry from an mmCIF loop, indexed by the index column. csi|]}||qSrr)rAentryrPrr sz&mmcif_loop_to_dict..)rO)r<rPr=entriesrrRrmmcif_loop_to_dicts rUF)typed)catch_all_errorsr+ mmcif_stringrXc Csi}zXtdd}|j}|D]\}}t|ts|g||<qt|}t|d} | s3td|dfdiWSi} t|D]} | j dkrAq9| j | | j <q9t ||ddd|| | d} t| |d WSt y{} z| ||df<|sktd|d WYd} ~ Sd} ~ ww) Entry point, parses an mmcif_string. Args: file_id: A string identifier for this file. Should be unique within the collection of files being processed. mmcif_string: Contents of an mmCIF file. catch_all_errors: If True, all exceptions are caught and error messages are returned as part of the ParsingResult. If False exceptions will be allowed to propagate. Returns: A ParsingResult. TQUIETr=N%No protein chains found in this file.1r+r,r-r.r/r0r1r2r9r:)r _mmcif_dictrI isinstancelist _get_header_get_protein_chainsr8_get_atom_site_listr rrr* Exception)r+rYrXr:parserr=rMrNr,r2r1atomr9errr fast_parsesP         rmc! Csi}z tjdd}t|}|d|}t|}|j}|D]\} } t| t s.| g|| <q t |} t |d} | sDt d|dfdiWSdd| D} i}i}t |D]]}|jd kr]qU|j||j<|j| vrd }|jd kr||jd vrwd }nd|j}|j}t|jsd }t|jt|j|d}t|j| |j}||ji}t||jd|d||<|||j<qU| D]$\}}||}||}t|D]\}}||vrtd|jdd d||<qqi}| D].\}}||}g}|D]}tj|jd}|t |dkr|ndqd!|}|||<qt"|| |||||| d}t ||dWSt#yF} z| ||df<|s6t d|dWYd} ~ Sd} ~ ww)rZTr[r^r]Nr_cSs$i|]\}}|tdd|DqS)cSsg|]}|jqSr)rrAmonomerrrrrEsz$parse...min)rAr"seqrrrrSszparse..r` HETATM)HOHWATWH_)r"r#rF)r%r&r'r(Xrarb)$rr ioStringIO get_structure_get_first_modelrcrIrdrerfrgr8rhr rrrrr_is_setr!rrrgetr$ enumerater r protein_letters_3to1rKr?joinr*ri)!r+rYrXr:rjhandlefull_structurefirst_model_structurer=rMrNr,r2 seq_start_numr1seq_to_structure_mappingsrkr(rr%seq_idxcurrentr"seq_info author_chaincurrent_mappingidxroauthor_chain_to_sequencerrcoder9rlrrrparses                     rr-cCs t|S)z1Returns the first model in a Biopython structure.)next get_models)r-rrrr~ns r~cCs|d}t|S)z!Returns the oldest revision date.*_pdbx_audit_revision_history.revision_daterp)r=revision_datesrrrget_release_datevsrc Csi}td|}ddd|D|d<d|vrt||d<ntd|d d |d <d D]&}||vrRz||d }t||d <Wq,tyQtd||Yq,wq,|S)zFReturns a basic header containing method, release date and resolution.z_exptl.,cSsg|]}|dqS)z _exptl.method)lower)rA experimentrrrrEsz_get_header..structure_methodr release_datez$Could not determine release_date: %sz _entry.idg resolution)z_refine.ls_d_res_highz _em_3d_reconstruction.resolutionz_reflns.d_resolution_highrzInvalid resolution format: %s)rOrrrwarningfloat ValueErrordebug)r=r, experimentsres_keyraw_resolutionrrrrf|s.    rfc Cs@ddt|d|d|d|d|d|d|d |d DS) zGReturns list of atom sites; contains data not present in the structure.cSsg|]}t|qSr)r)rAsiterrrrEsz'_get_atom_site_list..z_atom_site.label_comp_idz_atom_site.auth_asym_idz_atom_site.label_asym_idz_atom_site.auth_seq_idz_atom_site.label_seq_idz_atom_site.pdbx_PDB_ins_codez_atom_site.group_PDBz_atom_site.pdbx_PDB_model_num)rGr]rrrrhsrhc std|}tt}|D]}||dt|dt|ddq tdd|td|}tt}|D]}|d }|d }|||q4i} |D]\}} ||} t fd d | Drh| D]}| | |<qaqL| S) zExtracts polymer information for protein chains only. Args: parsed_info: _mmcif_dict produced by the Biopython parser. Returns: A dict mapping mmcif chain id to a list of Monomers. z_entity_poly_seq.z_entity_poly_seq.entity_idz_entity_poly_seq.mon_idz_entity_poly_seq.num)r rz _chem_comp.z _chem_comp.idz _struct_asym.z_struct_asym.idz_struct_asym.entity_idcsg|] }d|jdvqS)peptidez_chem_comp.type)r rn chem_compsrrrEsz'_get_protein_chains..) rO collections defaultdictrerKr rrUrIany) r=entity_poly_seqspolymersentity_poly_seq struct_asymsentity_to_mmcif_chains struct_asymr" entity_idr2r chain_idsrrrrgs8       rgrDcCs|dvS)zFReturns False if data is a special mmCIF character indicating 'unset'.).?rrCrrrrsr)0r3r dataclasses functoolsr{typingrrrrrabslrBiorBio.Datar Bio.PDB.MMCIFParserr rr6r4 Structurer5r7 MmCIFDict dataclassr rr!r$r*r8rir;rOrU lru_cacher)rmrr~-_MIN_LENGTH_OF_CHAIN_TO_BE_COUNTED_AS_PEPTIDErrfrhrgrrrrrs                B ! 4