a#nSc@sUdZddlmZddlmZddlmZddlmZddlmZddl Z ddl Z ddl m Z ej ae jd Zd Zd d Zd ZdZdZd dd dZde_dZdZdZdZeje_dZeje_dZ ej!e _dZ"ej#e"_dZ$de$_dZ%de%_dZ&ddZ'dZ(dZ)d d Z*d!Z+d"Z,d#Z-d$Z.d%Z/d d&Z0d'Z1d(Z2d)Z3d*Z4ej5e4_d+Z6ej7e6_d,Z8ej9e8_d-Z:ej;e:_d.Z<ej=e<_d/Z>ej?e>_d0Z@ejAe@_d1ZBejCeB_d2ZDejEeD_d3ZFejGeF_d4ZHejIeH_d5ZJejKeJ_dd d6ZLdeL_d7ZMd8ZNd9ZOd:ZPd;ddd<ZQd=eQ_dS(>s9 Calculation of topological/topochemical descriptors. i(tChem(tGraphs(trdchem(trdMolDescriptors(tpyPeriodicTableN(tentropyicCstj|tS(N(tmathtlogt_log2val(tx((s]/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/GraphDescriptors.pyt_log2sicCs1|st|}nttj|d}|S(sQ *Internal Use Only* this is just a row sum of the matrix... simple, neh? i(tsumtnumpytequal(tmattonlyOnestres((s]/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/GraphDescriptors.pyt_VertexDegrees scCs|j}|S(s *Internal Use Only* (t GetNumBonds(tmoltdMatR((s]/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/GraphDescriptors.pyt_NumAdjacencies,s cCs5i}x(|D] }|j|dd||R-R?R@((s]/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/GraphDescriptors.pyt _pyKappa2s  %cCsttj|d}|j}t|}||d}|r|ddkry||d||dd|}q||d||dd|}nd}|S(sq Hall-Kier Kappa3 value From equations (58), (61) and (62) of Rev. Comp. Chem. vol 2, 367-422, (1991) iiii(R#RRBR;R<(RtP3R>R-R?R@((s]/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/GraphDescriptors.pyt _pyKappa3s  %%cCs tj|S(N(RtCalcHallKierAlpha(R ((s]/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/GraphDescriptors.pytscCs tj|S(N(Rt CalcKappa1(R ((s]/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/GraphDescriptors.pyRHscCs tj|S(N(Rt CalcKappa2(R ((s]/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/GraphDescriptors.pyRHscCs tj|S(N(Rt CalcKappa3(R ((s]/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/GraphDescriptors.pyRHscCstg|jD]}|j^q }xd|krD|jdq(Wtj|d}ttjd|}|S(sR From equations (1),(9) and (10) of Rev. Comp. Chem. vol 2, 367-422, (1991) itdg?(Rt GetDegreetremoveR tarrayR tsqrt(RR tdeltasR((s]/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/GraphDescriptors.pytChi0s %cCsg|jD](}|jj|jj^q }xd|krZ|jdq>Wtj|d}ttjd|}|S(sS From equations (1),(11) and (12) of Rev. Comp. Chem. vol 2, 367-422, (1991) iRLg?( tGetBondst GetBeginAtomRMt GetEndAtomRNR ROR RP(RR tc1sR((s]/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/GraphDescriptors.pytChi1s ;cCstj|j|jS(N(t periodicTabletGetNOuterElecsRt GetTotalNumHs(R(((s]/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/GraphDescriptors.pyt_nValsicCsg}t|dr+|jdk r+|jSx|jD]}|j}|dkrtj|}|j}|dkr|jt ||q|jt ||t ||dq8|dkr|s|jdqq8|jdq8W||_|S(Nt _hkDeltasii g( thasattrR\R!RRRXRYRZtappendtfloat(RtskipHsRR(tntnVtnHs((s]/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/GraphDescriptors.pyR\s"    ,  cCs[t|}xd|kr+|jdqWd|_ttjdtj|}|S(sS From equations (5),(9) and (10) of Rev. Comp. Chem. vol 2, 367-422, (1991) ig?N(R\RNR!R R RPRO(RRQR((s]/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/GraphDescriptors.pyt_pyChi0vs   "cCstjt|dd}d}xX|jD]J}||j||j}|dkr.|tjd|7}q.q.W|S(sT From equations (5),(11) and (12) of Rev. Comp. Chem. vol 2, 367-422, (1991) R`igg?(R ROR\RStGetBeginAtomIdxt GetEndAtomIdxRP(RRQRtbondR((s]/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/GraphDescriptors.pyt_pyChi1vs cCstjgt|ddD]+}|dkr>dtj|nd^q}d}xDtj||dddD]&}|tj|tj|7}qpW|S(sq From equations (5),(15) and (16) of Rev. Comp. Chem. vol 2, 367-422, (1991) **NOTE**: because the current path finding code does, by design, detect rings as paths (e.g. in C1CC1 there is *1* atom path of length 3), values of ChiNv with N >= 3 may give results that differ from those provided by the old code in molecules that have rings of size 3. R`igg?ituseBonds(R ROR\RPRRBtprod(RtorderthkdRQtaccumtpath((s]/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/GraphDescriptors.pyt _pyChiNv_s M#$cCs t|dS(sS From equations (5),(15) and (16) of Rev. Comp. Chem. vol 2, 367-422, (1991) i(Ro(R((s]/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/GraphDescriptors.pyt_pyChi2vscCs t|dS(sS From equations (5),(15) and (16) of Rev. Comp. Chem. vol 2, 367-422, (1991) i(Ro(R((s]/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/GraphDescriptors.pyt_pyChi3vscCs t|dS(sZ From equations (5),(15) and (16) of Rev. Comp. Chem. vol 2, 367-422, (1991) **NOTE**: because the current path finding code does, by design, detect rings as paths (e.g. in C1CC1 there is *1* atom path of length 3), values of Chi4v may give results that differ from those provided by the old code in molecules that have 3 rings. i(Ro(R((s]/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/GraphDescriptors.pyt_pyChi4v s cCswg|jD]}t|^q }x |jdrG|jdq(Wtj|d}ttjd|}|S(s Similar to Hall Kier Chi0v, but uses nVal instead of valence This makes a big difference after we get out of the first row. iRLg?(RR[tcountRNR ROR RP(RR RQR((s]/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/GraphDescriptors.pyt_pyChi0n+s %cCstjg|jD]}t|^qd}d}xX|jD]J}||j||j}|dkrD|tjd|7}qDqDW|S(sE Similar to Hall Kier Chi1v, but uses nVal instead of valence RLgg?(R RORR[RSReRfRP(RR tdeltsRRgR((s]/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/GraphDescriptors.pyt_pyChi1n7s1 cCsg|jD]}t|^q }tjg|D]%}|rQdtj|nd^q2}d}xDtj||dddD]&}|tj|tj|7}qW|S(s Similar to Hall Kier ChiNv, but uses nVal instead of valence This makes a big difference after we get out of the first row. **NOTE**: because the current path finding code does, by design, detect rings as paths (e.g. in C1CC1 there is *1* atom path of length 3), values of ChiNn with N >= 3 may give results that differ from those provided by the old code in molecules that have rings of size 3. g?giRii(RR[R RORPRRBRj(RRkR tnvalRQRmRn((s]/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/GraphDescriptors.pyt _pyChiNn_Cs %;#$cCs t|dS(s Similar to Hall Kier Chi2v, but uses nVal instead of valence This makes a big difference after we get out of the first row. i(Rx(R((s]/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/GraphDescriptors.pyt_pyChi2nUscCs t|dS(s Similar to Hall Kier Chi3v, but uses nVal instead of valence This makes a big difference after we get out of the first row. i(Rx(R((s]/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/GraphDescriptors.pyt_pyChi3n\scCs t|dS(s Similar to Hall Kier Chi4v, but uses nVal instead of valence This makes a big difference after we get out of the first row. **NOTE**: because the current path finding code does, by design, detect rings as paths (e.g. in C1CC1 there is *1* atom path of length 3), values of Chi4n may give results that differ from those provided by the old code in molecules that have 3 rings. i(Rx(R((s]/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/GraphDescriptors.pyt_pyChi4ncs cCs tj|S(N(Rt CalcChi0v(R ((s]/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/GraphDescriptors.pyRHpscCs tj|S(N(Rt CalcChi1v(R ((s]/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/GraphDescriptors.pyRHrscCs tj|S(N(Rt CalcChi2v(R ((s]/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/GraphDescriptors.pyRHtscCs tj|S(N(Rt CalcChi3v(R ((s]/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/GraphDescriptors.pyRHvscCs tj|S(N(Rt CalcChi4v(R ((s]/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/GraphDescriptors.pyRHxscCstj||S(N(Rt CalcChiNv(R ty((s]/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/GraphDescriptors.pyRHzscCs tj|S(N(Rt CalcChi0n(R ((s]/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/GraphDescriptors.pyRH}scCs tj|S(N(Rt CalcChi1n(R ((s]/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/GraphDescriptors.pyRHscCs tj|S(N(Rt CalcChi2n(R ((s]/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/GraphDescriptors.pyRHscCs tj|S(N(Rt CalcChi3n(R ((s]/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/GraphDescriptors.pyRHscCs tj|S(N(Rt CalcChi4n(R ((s]/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/GraphDescriptors.pyRHscCstj||S(N(Rt CalcChiNn(R R((s]/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/GraphDescriptors.pyRHsc Cs6|s|d kr|rutj|dddddd}||_tj|dddddddd}||_qAy |j}WnAtk rtj|dddddddd }||_nXy |j}WqAtk rtj|dddddddd}||_qAXn'tj|dddddddd}t|}t||}|j }||d}d }t |} xpt | D]b} || } xOt | | D]>} || | fdkr|d t j | || 7}qqWqW|ddkr,t|t|d|} nd} | S( s Calculate Balaban's J value for a molecule **Arguments** - mol: a molecule - dMat: (optional) a distance/adjacency matrix for the molecule, if this is not provide, one will be calculated - forceDMat: (optional) if this is set, the distance/adjacency matrix will be recalculated regardless of whether or not _dMat_ is provided or the molecule already has one **Returns** - a float containing the J value We follow the notation of Balaban's paper: Chem. Phys. Lett. vol 89, 399-404, (1982) tuseBOit useAtomWtsitforcetemptyValtprefixtNoBOtBalabangg?N(R!RR0t _balabanMattGetAdjacencyMatrixR1R2RRt GetNumAtomsR#trangeR RPR_(RRR7R8tstqRatmuR tnStitsitjtJ((s]/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/GraphDescriptors.pytBalabanJs@! '   '   ''    *!c Cs|r9tj|dddddddd}||_nd}g}dg|}xt|D]} || j} | jtg| | D]} d| ^q} y|j| } Wn*tk rt |} |j | nX| d|| \}} y| j t | || this implementation treats aromatic rings as the > corresponding Kekule structure with alternating bonds, > for purposes of counting "connections". Upon further thought, this is the WRONG thing to do. It results in the possibility of a molecule giving two different CT values depending on the kekulization. For example, in the old implementation, these two SMILES: CC2=CN=C1C3=C(C(C)=C(C=N3)C)C=CC1=C2C CC3=CN=C2C1=NC=C(C)C(C)=C1C=CC2=C3C which correspond to differentk kekule forms, yield different values. The new implementation uses consistent (aromatic) bond orders for aromatic bonds. THIS MEANS THAT THIS IMPLEMENTATION IS NOT BACKWARDS COMPATIBLE. Any molecule containing aromatic rings will yield different values with this implementation. The new behavior is the correct one, so we're going to live with the breakage. **NOTE** this barfs if the molecule contains a second (or nth) fragment that is one atom. RiRRiitaN(RR!RR0R1R2RRRtGetAtomWithIdxRRRtmintmaxtkeysRR(RRRR7RRRRt neighborListRtsymmetryClassesRthingeAtomNumberthingeAtomClasst numNeighborsRt neighbor_iIdxtNiClasst bond_i_ordertnumConnectionst connectionKeyRt neighbor_jIdxtNjClasst bond_j_ordertks((s]/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/GraphDescriptors.pytBertzCT0sR( !   !      !&  s2.0.0(Rt__doc__trdkitRt rdkit.ChemRRRRRR Rtrdkit.ML.InfoTheoryRtGetPeriodicTableRXRRR RRRR/R!R:tversionRARDRFR<t_CalcHallKierAlpha_versiontKappa1t_CalcKappa1_versiontKappa2t_CalcKappa2_versiontKappa3t_CalcKappa3_versionRRRWR[R\RdRhRoRpRqRrRtRvRxRyRzR{tChi0vt_CalcChi0v_versiontChi1vt_CalcChi1v_versiontChi2vt_CalcChi2v_versiontChi3vt_CalcChi3v_versiontChi4vt_CalcChi4v_versiontChiNv_t_CalcChiNv_versiontChi0nt_CalcChi0n_versiontChi1nt_CalcChi1n_versiontChi2nt_CalcChi2n_versiontChi3nt_CalcChi3n_versiontChi4nt_CalcChi4n_versiontChiNn_t_CalcChiNn_versionRRRRRR(((s]/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/GraphDescriptors.pyts                                                    B   "[