a#nSc@sdZddlmZddlmZddlmZddlmZddlTddlTddl Tddl Tddl Tddl Tddl TddlTddlTddlTyddlTWnnXddlTddlTddlmZee_ee_ddlZddlZdd lmZeZded Zddd d ZddddZddedZ!ddZ"ddddZ#dZ$e%dde&dZ'dZ(dZ)e*dkrddl+Z+e)\Z,Z-e+j.e,ndS(s% Import all RDKit chemistry modules i(trdBase(tRDConfig(t DataStructs(t rdGeometry(t*(t ForceFieldN(tloggercCs|j|}t|||s|dkr7d}ng|jD]}|j^qD}x*|D]"}||ksc|j|qcqcW|j|jdndS(s Applies the transformation (usually a 4x4 double matrix) to a molecule if keepConfs is False then all but that conformer are removed iiN(t GetConformertTransformConformert GetConformerstGetIdtRemoveConformertSetId(tmolttformtconfIdt keepConfstrefConftct allConfIdstid((sT/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/AllChem.pyt TransformMol)s  %  ig?cKs>tj|d|d|dd|}t|||||S(s9 returns a grid representation of the molecule's shape iiitspacing(Rt UniformGrid3Dt EncodeShape(R RtboxDimRtkwargstres((sT/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/AllChem.pytComputeMolShape8s'g?g@c Cs#tj|}|j|}t|t|}|dj|djd||dj|djd||dj|djd|f}tj |d|d|dd|}t |||dt dd|d}|j } g| D]} | dkrd^q} |t | } | S( su Calculates the volume of a particular conformer of a molecule based on a grid-encoding of the molecular shape. iiiRtignoreHstvdwScaleg?i(trdchemtMolRtCanonicalizeConformertComputeConfBoxtxtytzRRRtFalsetGetOccupancyVecttlen( R Rt gridSpacingt boxMargintconftboxtsideLentshapetvoxelVoltoccVectR#tvoxelstvol((sT/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/AllChem.pytComputeMolVolume?s  #   %cKsD|r`|r`|jdt|jdtks<tdn|j|}|sxtdqxnt|jdt}|r|j|}n|j|}|s|stdq$i}nd|j} i}xOt|D]A\} } | j|| } tj | j | j } | || tappendtLengthtnumpytarraytCompute2DCoordsMimicDistmat( R RARRtnAtstdmR+RFtpitjtpj((sT/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/AllChem.pyt$GenerateDepictionMatching3DStructures c Cs|sq|j|dt}|sItd|jd|jdfng|D]}tt|^qP}nd}xD|D]<}t||||d|} | |kr~| }|} q~q~W| |krt||||d| n|S(sK Returns the optimal RMS for aligning two molecules, taking symmetry into account. As a side-effect, the probe molecule is left in the aligned state. Arguments: - ref: the reference molecule - probe: the molecule to be aligned to the reference - refConfId: (optional) reference conformation to use - probeConfId: (optional) probe conformation to use - maps: (optional) a list of lists of (probeAtomId,refAtomId) tuples with the atom-atom mappings of the two molecules. If not provided, these will be generated using a substructure search. tuniquifysmol %s does not match mol %st_Nameg@@tatomMap(tGetSubstructMatchesR&R:tGetProptlistR=tAlignMol( treftprobet refConfIdt probeConfIdtmapstmatchesREtbestRMStamaptrmstbestMap((sT/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/AllChem.pyt GetBestRMSs(    c#st||jkr:tdt||jfndfdx9|D]+}|j|}x|D] }|VquWqYWdS(s Returns a generator for the virtual library defined by a reaction and a sequence of sidechain sets >>> from rdkit import Chem >>> from rdkit.Chem import AllChem >>> s1=[Chem.MolFromSmiles(x) for x in ('NC','NCC')] >>> s2=[Chem.MolFromSmiles(x) for x in ('OC=O','OC(=O)C')] >>> rxn = AllChem.ReactionFromSmarts('[O:2]=[C:1][OH].[N:3]>>[O:2]=[C:1][N:3]') >>> r = AllChem.EnumerateLibraryFromReaction(rxn,[s2,s1]) >>> [Chem.MolToSmiles(x[0]) for x in list(r)] ['CNC=O', 'CCNC=O', 'CNC(C)=O', 'CCNC(C)=O'] Note that this is all done in a lazy manner, so "infinitely" large libraries can be done without worrying about running out of memory. Your patience will run out first: Define a set of 10000 amines: >>> amines = (Chem.MolFromSmiles('N'+'C'*x) for x in range(10000)) ... a set of 10000 acids >>> acids = (Chem.MolFromSmiles('OC(=O)'+'C'*x) for x in range(10000)) ... now the virtual library (1e8 compounds in principle): >>> r = AllChem.EnumerateLibraryFromReaction(rxn,[acids,amines]) ... look at the first 4 compounds: >>> [Chem.MolToSmiles(r.next()[0]) for x in range(4)] ['NC=O', 'CNC=O', 'CCNC=O', 'CCCNC=O'] s#%d sidechains provided, %d requiredic3syxr||D]f}|dt|kri||d}x4|D]!}|g}|j||VqAWq |gVq WdS(Ni(R(textend(titemstdepthtitemtvtentrytl(t_combiEnumerator(sT/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/AllChem.pyRos    N(R(tGetNumReactantTemplatesR:t RunReactants(treactiont sidechainSetstchainstprodSetstprods((RosT/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/AllChem.pytEnumerateLibraryFromReactions"  i& cKs|j|}|s!tdni}|j|} x3t|D]%\} } | j| } | || >> from rdkit.Chem import AllChem >>> template = AllChem.MolFromSmiles("c1nn(Cc2ccccc2)cc1") >>> AllChem.EmbedMolecule(template) 0 >>> AllChem.UFFOptimizeMolecule(template) 0 Here's a molecule: >>> mol = AllChem.MolFromSmiles("c1nn(Cc2ccccc2)cc1-c3ccccc3") Now do the constrained embedding >>> newmol=AllChem.ConstrainedEmbed(mol, template) Demonstrate that the positions are the same: >>> newp=newmol.GetConformer().GetAtomPosition(0) >>> molp=mol.GetConformer().GetAtomPosition(0) >>> list(newp-molp)==[0.0,0.0,0.0] True >>> newp=newmol.GetConformer().GetAtomPosition(1) >>> molp=mol.GetConformer().GetAtomPosition(1) >>> list(newp-molp)==[0.0,0.0,0.0] True smolecule doesn't match the coreR6t randomSeedisCould not embed molecule.RigY@iRXtfixedt energyTolg-C6?tforceTolgMbP?tEmbedRMS(R;R:RR=R>t EmbedMoleculeR<R(tDistancetAddDistanceConstraintt InitializetMinimizeR\R8t AddExtraPointR#R$R%R9tSetProptstr(R tcoret useTetherst coreConfIdt randomseedt getForceFieldRRER6tcoreConfRFtidxItcorePtItciRStalgMaptfftidxJtdtntmoreReR+tptpIdx((sT/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/AllChem.pytConstrainedEmbedsT*   +  !    (! c Cshtj|}tj|}|j|}|sdxI|jD];}|jtjkr@|jtj|jt q@q@Wx1|jD]#}|jtj|jt qWx!|j D]}|j dqWx!|j D]}|j dqW|j |dt }|rUt |dkr8tjdn|d}xl|jD]^}||j}||j}|j||} | j|j| j|jqOWxy|j D]k}|j||j} | j|j| j|j| j|j| j |jqWt|t|drad|_qaqdtdn|S(sF assigns bond orders to a molecule based on the bond orders in a template molecule Arguments - refmol: the template molecule - mol: the molecule to assign bond orders to An example, start by generating a template from a SMILES and read in the PDB structure of the molecule >>> from rdkit.Chem import AllChem >>> template = AllChem.MolFromSmiles("CN1C(=NC(C1=O)(c2ccccc2)c3ccccc3)N") >>> mol = AllChem.MolFromPDBFile(os.path.join(RDConfig.RDCodeDir, 'Chem', 'test_data', '4DJU_lig.pdb')) >>> print len([1 for b in template.GetBonds() if b.GetBondTypeAsDouble() == 1.0]) 8 >>> print len([1 for b in mol.GetBonds() if b.GetBondTypeAsDouble() == 1.0]) 22 Now assign the bond orders based on the template molecule >>> newMol = AllChem.AssignBondOrdersFromTemplate(template, mol) >>> print len([1 for b in newMol.GetBonds() if b.GetBondTypeAsDouble() == 1.0]) 8 Note that the template molecule should have no explicit hydrogens else the algorithm will fail. It also works if there are different formal charges (this was github issue 235): >>> template=AllChem.MolFromSmiles('CN(C)C(=O)Cc1ccc2c(c1)NC(=O)c3ccc(cc3N2)c4ccc(c(c4)OC)[N+](=O)[O-]') >>> mol = AllChem.MolFromMolFile(os.path.join(RDConfig.RDCodeDir, 'Chem', 'test_data', '4FTR_lig.mol')) >>> AllChem.MolToSmiles(mol) 'COC1CC(C2CCC3C(C2)NC2CCC(CC(O)N(C)C)CC2NC3O)CCC1N(O)O' >>> newMol = AllChem.AssignBondOrdersFromTemplate(template, mol) >>> AllChem.MolToSmiles(newMol) 'COc1cc(-c2ccc3c(c2)Nc2ccc(CC(=O)N(C)C)cc2NC3=O)ccc1[N+](=O)[O-]' iRVis2More than one matching pattern found - picking onet __sssAtomssNo matching foundN( RR R;tGetBondst GetBondTypetBondTypetSINGLEt SetBondTypet SetIsAromaticR&tGetAtomstSetFormalChargeRYR(RtwarningtGetBeginAtomIdxt GetEndAtomIdxtGetBondBetweenAtomst GetIsAromatictGetAtomWithIdxtGetIdxtSetHybridizationtGetHybridizationtSetNumExplicitHstGetNumExplicitHstGetFormalCharget SanitizeMolthasattrtNoneRR:( trefmolR trefmol2tmol2tmatchingtbtatatom1tatom2tb2ta2((sT/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/AllChem.pytAssignBondOrdersFromTemplateSsJ$  cCs,ddl}ddl}|j|jdS(Nit__main__(tdoctesttsysttestmodtmodules(RR((sT/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/AllChem.pyt_testsR(iii(/t__doc__trdkitRRRtrdkit.GeometryRt rdkit.Chemtrdkit.Chem.rdPartialChargestrdkit.Chem.rdDepictortrdkit.Chem.rdForceFieldHelperstrdkit.Chem.ChemicalFeaturestrdkit.Chem.rdDistGeomtrdkit.Chem.rdMolAligntrdkit.Chem.rdMolTransformstrdkit.Chem.rdShapeHelperstrdkit.Chem.rdChemReactionstrdkit.Chem.rdSLNParsetrdkit.Chem.rdMolDescriptorstrdkit.Chem.rdqueriesRR@R tComputeGasteigerChargesRMtostrdkit.RDLoggerRR&RRR3RRJRURgRwR9tUFFGetMoleculeForceFieldRRRt__name__Rtfailedttriedtexit(((sT/public2/ftp/pub/ccp4/6.5/ccp4-6.5/lib/python2.7/site-packages/rdkit/Chem/AllChem.pyt sV                2 " 1\ X