o Rŀg<^@spdZddlZddlZddlmZddlmZddlm Z ddlm Z ddl m Z Gdd d Z Gd d d ZdS) zmmCIF parsers.N) as_handle) MMCIF2Dict)PDBConstructionException)PDBConstructionWarning)StructureBuilderc@sDeZdZdZ dddZddZd d Zd d Zd dZddZ dS) MMCIFParserz1Parse a mmCIF file and return a Structure object.NTFcCsL|dur||_nt|_d|_d|_d|_t||_t||_t||_dS)aCreate a PDBParser object. The mmCIF parser calls a number of standard methods in an aggregated StructureBuilder object. Normally this object is instantiated by the MMCIParser object itself, but if the user provides his/her own StructureBuilder object, the latter is used instead. Arguments: - structure_builder - an optional user implemented StructureBuilder class. - auth_chains - True by default. If true, use the author chain IDs. If false, use the re-assigned mmCIF chain IDs. - auth_residues - True by default. If true, use the author residue numbering. If false, use the mmCIF "label" residue numbering, which has no insertion codes, and strictly increments residue numbers. NOTE: Non-polymers such as water don't have a "label" residue number, and will be skipped. - QUIET - Evaluated as a Boolean. If true, warnings issued in constructing the SMCRA data will be suppressed. If false (DEFAULT), they will be shown. These warnings might be indicative of problems in the mmCIF file! Nr) _structure_builderrheader line_counterbuild_structurebool auth_chains auth_residuesQUIETselfstructure_builderr rrrG/var/www/html/myenv/lib/python3.10/site-packages/Bio/PDB/MMCIFParser.py__init__s  zMMCIFParser.__init__cCsjt$|jrtjdtdt||_|||j | Wdn1s+wY|j S)zReturn the structure. Arguments: - structure_id - string, the id that will be used for the structure - filename - name of mmCIF file, OR an open text mode file handle ignorecategoryN) warningscatch_warningsrfilterwarningsrr _mmcif_dict_build_structurer set_header _get_header get_structure)r structure_idfilenamerrrr =s    zMMCIFParser.get_structurecCs$||vr||d}d|kr|S|S)Nr?r)rkeydictdefltrsltrrr _mmcif_getPs  zMMCIFParser._mmcif_getc Csb|j}|D])}||}z|d}Wn ttfyYqw|dkr.|dkr.||j|<dSqdS)Nrr#.)rget TypeError IndexErrorr )r target_keykeysmdr$valitemrrr_update_header_entryWs   z MMCIFParser._update_header_entrycCsddddddd|_|dgd|ddg|ddd g|d d g|d d g|dgd|jddur]zt|jd|jd<W|jSty\d|jd<Y|jSw|jS)N)nameheadidcodedeposition_datestructure_method resolutionr6) _entry_idz_exptl.entry_idz_struct.entry_idr4z _struct.titler5z_struct_keywords.pdbx_keywordsz_struct_keywords.textr7z3_pdbx_database_status.recvd_initial_deposition_dater8z _exptl.methodr9)z_refine.ls_d_res_highz_refine_hist.d_res_highz _em_3d_reconstruction.resolution)r r2float ValueError)rrrrrcs>  zMMCIFParser._get_headerc@ Cspddh}|j}|d}|d}|d}z|d}Wn ty$d}Ynw|jr-|d}n|d}d d |d D} d d |d D} dd |dD} |d} |d} |d}|d}|d}z dd |dD}Wntyvd}Yn tytddwz|d}|d}|d}|d}|d}|d}d}Wn tyd}Ynw|jrd |vr|d }n |d!}n|d!}d}d}d}|j}|||d"d#}d#}t t |D]v} | | zt || }!Wnty|| }!t d$tYnw| | }"| | }#| | }$|| }%|| }&| | }'|'|vrd"}'|| }(|(dkrUz|d | })d%|&d&|)d'}*WnttfyKd%|&d'}*Ynwt d(|*tqt |(}+| | },|,|vrdd"},|| }-zt|| }.Wn ty}td)dwzt|| }/Wn tytd*dw|| }0|0d+kr|%d,ks|%d-krd.}1nd/}1nd"}1|1|+|,f}(|dur|| }2||2kr|2}|d7}|||d}d}d}n||||&kr|&}||d}d}||(ks||%kr|(}|%}||%|1|+|,t|"|#|$fd0}3|r|| nd}4|j|-|3|.|/|'|-|!|4d1|dkrS| t |krS|| || || || || || f}5d2d |5D}6t|6d0}7||7qzXt|d3d}8t|d4d}9t|d5d}:t|d6d};t|d7d}|d9d}?|?dd#}?|?durt||?|>WdStyYdSw):Nr)r# _atom_site.id_atom_site.label_atom_id_atom_site.label_comp_id_atom_site.type_symbol_atom_site.auth_asym_id_atom_site.label_asym_idcSg|]}t|qSrr;.0xrrr z0MMCIFParser._build_structure.._atom_site.Cartn_xcSrCrrDrErrrrHrI_atom_site.Cartn_ycSrCrrDrErrrrHrI_atom_site.Cartn_z_atom_site.label_alt_id_atom_site.pdbx_PDB_ins_code_atom_site.B_iso_or_equiv_atom_site.occupancy_atom_site.group_PDBcSrCrintrFnrrrrHrI_atom_site.pdbx_PDB_model_numInvalid model number_atom_site_anisotrop.U[1][1]_atom_site_anisotrop.U[1][2]_atom_site_anisotrop.U[1][3]_atom_site_anisotrop.U[2][2]_atom_site_anisotrop.U[2][3]_atom_site_anisotrop.U[3][3]r_atom_site.auth_seq_id_atom_site.label_seq_id zBPDBConstructionWarning: Some atom serial numbers are not numerical"Non-existing residue ID in chain ' ', residue ''PDBConstructionWarning: Invalid or missing B factorInvalid or missing occupancyHETATMHOHWATWHf serial_numberelementcSrCrrDrF_rrrrH8rIz_cell.length_az_cell.length_bz_cell.length_cz_cell.angle_alphaz_cell.angle_betaz_cell.angle_gammaz_symmetry.space_group_name_H-M)rKeyErrorr r<rrrinit_structureinit_segrangelenset_line_counterrSrwarnrr,r; init_model init_chain init_residuenparrayupper init_atom set_anisou Exception set_symmetry)@rr! _unassigned mmcif_dictatom_serial_list atom_id_listresidue_id_list element_list chain_id_listx_listy_listz_listalt_list icode_list b_factor_listoccupancy_listfieldname_list serial_list aniso_u11 aniso_u12 aniso_u13 aniso_u22 aniso_u23 aniso_u33 aniso_flag seq_id_listcurrent_chain_idcurrent_residue_idcurrent_resnamercurrent_model_idcurrent_serial_idiserialrGyzresnamechainidaltlocresseq msg_resseqmsg int_resseqicoder4 tempfactor occupancy fieldname hetatm_flag serial_idcoordrqu mapped_anisou anisou_arrayabcalphabetagammacell spacegrouprrrrsL                                 zMMCIFParser._build_structureNTTF) __name__ __module__ __qualname____doc__rr r(r2rrrrrrrs ' %rc@s,eZdZdZ d ddZddZd d ZdS) FastMMCIFParserz2Parse an MMCIF file and return a Structure object.NTFcCsF|dur||_nt|_d|_d|_t||_t||_t||_dS)aRCreate a FastMMCIFParser object. The mmCIF parser calls a number of standard methods in an aggregated StructureBuilder object. Normally this object is instantiated by the parser object itself, but if the user provides his/her own StructureBuilder object, the latter is used instead. The main difference between this class and the regular MMCIFParser is that only 'ATOM' and 'HETATM' lines are parsed here. Use if you are interested only in coordinate information. Arguments: - structure_builder - an optional user implemented StructureBuilder class. - auth_chains - True by default. If true, use the author chain IDs. If false, use the re-assigned mmCIF chain IDs. - auth_residues - True by default. If true, use the author residue numbering. If false, use the mmCIF "label" residue numbering, which has no insertion codes, and strictly increments residue numbers. NOTE: Non-polymers such as water don't have a "label" residue number, and will be skipped. - QUIET - Evaluated as a Boolean. If true, warnings issued in constructing the SMCRA data will be suppressed. If false (DEFAULT), they will be shown. These warnings might be indicative of problems in the mmCIF file! Nr)rrr r r r rrrrrrrPs  zFastMMCIFParser.__init__c Cszt,|jrtjdtdt|}|||Wdn1s$wYWdn1s3wY|jS)zReturn the structure. Arguments: - structure_id - string, the id that will be used for the structure - filename - name of the mmCIF file OR an open filehandle rrN) rrrrrrrrr )rr!r"handlerrrr zs   zFastMMCIFParser.get_structurecB CsZddh}d\}}gg}}gg}} |D]G} | dr%d}|| q| dr4d}|| q|r>| dr>d}q|rH| drHd}q|rR|| q|r[| | qtttj|} tttj| } tt|| } | tt|| | d }| d }| d }z| d }Wn t yd}Ynw|j r| d }n| d}dd| dD}dd| dD}dd| dD}| d}| d}| d}| d}| d}z dd| dD}Wnt yd}Yn t yt ddwz| d}| d}| d }| d!}| d"} | d#}!d$}"Wn t y d%}"Ynw|j r4d&| vr/| d&}#n | d'}#n| d'}#d}$d}%d}&|j}'|'||'d(d)}(d)})tt|D]T}*|'|*||*}+||*},||*}-||*}.||*}/||*}0||*}1|1|vrd(}1|#|*}2|2dkrz| d&|*}3d*|0d+|3d,}4Wnt tfyd*|0d,}4Ynwtd-|4tqUt|2}5||*}6|6|vrd(}6||*d.}7zt||*}8Wn t yt d/dwzt||*}9Wn t yt d0dw||*}:|:d1krd2};nd(};|;|5|6f}2|dur-||*}<|)||'j|7|=|8|9|1|7|+|>d4|"d$kr|*t|kr||*||*||*||*| |*|!|*f}?d5d|?D}@t|@d3}A|' |AqUdS)6Nr)r#)FFz _atom_site.Tz_atom_site_anisotrop.#Fr=r>r?r@rArBcSrCrrDrErrrrHrIz4FastMMCIFParser._build_structure..rJcSrCrrDrErrrrHrIrKcSrCrrDrErrrrHrIrLrMrNrOrPrQcSrCrrRrTrrrrHrIrVrWrXrYrZr[r\r]r^rr_r`rarbrcrdrerf"rgrhrirmrnrocSrCrrDrrrrrrHWrI)! startswithappendstripzipmapstrsplitr%updatertr r<rrrrurvrwrxryr,rrzrrSr;r{r|r}r~rrr)Brr! filehandler read_atom read_aniso_fields_records_anisof_anisorsline _record_tbl _anisob_tblrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrGrrrrrrrrrrr4rrrrrrrqrrrrrrrsF                                 z FastMMCIFParser._build_structurer)rrrrrr rrrrrrMs  * r)rrnumpyr~Bio.FilerBio.PDB.MMCIF2DictrBio.PDB.PDBExceptionsrrBio.PDB.StructureBuilderrrrrrrrs     <