o Rŀg@sJdZddlZddlmZddlmZddlmZddZ Gdd d Z dS) uProtein Structural Alignment using Combinatorial Extension. Python code written by Joao Rodrigues. C++ code and Python/C++ interface adapted from open-source Pymol and originally written by Jason Vertrees. The original license and notices are available in `cealign` folder. Reference --------- Shindyalov, I.N., Bourne P.E. (1998). "Protein structure alignment by incremental combinatorial extension (CE) of the optimal path". Protein Engineering. 11 (9): 739–747. PMID 9796821. N) run_cealign) PDBException)QCPSuperimposercCs |jdS)N)id)rrC/var/www/html/myenv/lib/python3.10/site-packages/Bio/PDB/cealign.pys r c@s4eZdZdZdddZddZdd Zdd d Zd S) CEAlignerz7Protein Structure Alignment by Combinatorial Extension.cCs6|dksJd|dksJd||_||_d|_dS)aSuperimpose one set of atoms onto another using structural data. Structures are superimposed using guide atoms, CA and C4', for protein and nucleic acid molecules respectively. Parameters ---------- window_size : float, optional CE algorithm parameter. Used to define paths when building the CE similarity matrix. Default is 8. max_gap : float, optional CE algorithm parameter. Maximum gap size. Default is 30. rz"window_size must be greater than 0z"max_gap must be positive (or zero)N) window_sizemax_gaprms)selfrrrrr __init__!s  zCEAligner.__init__cCsg}t|D](}t|tdD]}d|vr!||djqd|vr/||djqq|s>d|jd}t||S)zReturn the coordinates of guide atoms in the structure. We use guide atoms (C-alpha and C4' atoms) since it is much faster than using all atoms in the calculation without a significant loss in accuracy. )keyCAzC4'z Structure z does not have any guide atoms.)sorted get_chains _RESID_SORTERappendcoordtolistrr)r structurecoordschainresidmsgrrr get_guide_coord_from_structure7sz(CEAligner.get_guide_coord_from_structurecCsB|||_t|j|jdkrt|j}d|d}t|dS)zCDefine a reference structure onto which all others will be aligned.z*Too few atoms in the reference structure (*). Try reducing the window_size parameter.N)r refcoordlenrr)rrn_atomsrrrr set_referenceLs   zCEAligner.set_referenceTcsPd_|tjdkrt}d|d}t|tjjj}t|ddfdd|D}d\}}|D]9} | \} } t fd d| D} t fd d| D} t }| | | | |j|kry|j}|j |jf}q@|durtd |r|\}}|D]}|D]}|D]}|||qqq|_dS) aAlign the input structure onto the reference structure. Parameters ---------- transform: bool, optional If True (default), apply the rotation/translation that minimizes the RMSD between the two structures to the input structure. If False, the structure is not modified but the optimal RMSD will still be calculated. Nr!z'Too few atoms in the mobile structure (r"rcs,g|]\}}t|krt|t|fqSr)r$tuple).0pApB)longest_lengthrr ts&z#CEAligner.align..)g.ANcsg|]}j|qSr)r#r(i)rrr r,~scsg|]}|qSrrr-)rrr r,sz$Failed to find a suitable alignment.)rr r$rrrr#rnparrayrsetrunrottran RuntimeErrorrget_unpacked_list transform)rrr7r%rpaths longest_paths best_rmsdbest_upathidxAidxBcoordsAcoordsBalnrotmtxtrvecrratomr)rr+rr alignXsF          zCEAligner.alignN)r r )T)__name__ __module__ __qualname____doc__rr r&rErrrr r s   r ) rInumpyr/Bio.PDB.ccealignrBio.PDB.PDBExceptionsrBio.PDB.qcprotrrr rrrr s