B ž3Rc&/ã@sJddlZddlmZddlmZdd„Zdd„Zdadd „Zd d d „Z dS) éN)ÚChem)ÚAllChemc&Cst dddddddg¡}|dd d d d d ƒ|dd ddddƒ|dd ddddƒ|dd ddd dƒ|dd ddd dƒ|dd dd d d!ƒ|d"d dd#d$d%ƒ|d&d d'd(d)d*ƒ|d+d dd,d d-ƒ|d.d d/d0d1d2ƒ|d3d d4d5d6d7ƒ|d8d d9d:d d;ƒ|dd?d@ƒ|dAd dBdCd dDƒ|dEdFdGdHdIdJƒ|dKdFdLdMdNdOƒ|d dFdPd d dQƒ|dRdFdLdSd dTƒ|dUdFdLdVd dWƒ|d dFdPd d dXƒ|dYdFdLdZd d[ƒ|d\dFdLd]d d^ƒ|d dFdPd d d_ƒ|d`dadbdcd ddƒ|dedfdgdhd diƒ|djdkdldmdndoƒ|dpdkdqdrd dsƒ|dtdadbdud dvƒ|dwdfdgdxd dyƒ|dzdad{d|d d}ƒ|d~dfdd€d dƒ|d‚dfdƒd„d d…ƒg S)†aF Return a list of the individual patterns for mutating individual atoms in aromatic rings to generate a new aromatic ring. The elements are collections.namedtuple objects with the following fields: SMARTS - the left side of the reaction SMARTS pattern, matches the atom to mutate CONVERT_FROM - the element type being converted: c, n, o, s CONVERT_TO - the right side of the reaction SMARTS pattern, there can be multiple destination types separated with a comma, these should map to multiple actual reaction objects EXAMPLE - an example aromatic ring system that SMARTS should match against, used in test cases NEGATIVE_EXAMPLE - an example aromatic ring system that SMART should NOT match against, used in test cases DESCRIPTION - a human readable description of the SMARTS pattern matching ÚHeteroAtomReactionÚSMARTSZ CONVERT_FROMÚ CONVERT_TOZEXAMPLEZNEGATIVE_EXAMPLEZ DESCRIPTIONz&[c;x2;D2;r5:1]([n;x2;r5:2])[n;x2;r5:3]Úcz[n:1]([n:2])[n:3]z$c1nc[nH]c1,c1ncn([*])c1,c1nncn([*])1Úz9aromatic carbon in 5 membered ring, bonded to 2 nitrogenszj[c;x2;D2;r5:1]([n;h1;!+;!-;x2;r5;!$(*=*);!$(*[*;r5]=*):2])[n;x2;r5;!$(*=*);!$(*[*;r5]=*);!$(*[*;r5;x3]):3]z/[o:1]([n;H0:2])[n;H0:3],[s:1]([n;H0:2])[n;H0:3]zc1nc[nH]c1,[*]c1nc[nH]c1zk[*]c1ncno1,[*]n1[nH]cnc1=O,[*]c1nc2[nH]cnn2c(=O)c1[*],c1nc2cscc2[nH]1,c1c[nH]c2c1[nH]cn2,c1ccc2c(c1)[nH]cn2z‘aromatic carbon in 5 membered ring, bonded to 1 nitrogen not bonded to another atom that is in 2 rings, bonded to 1 nitrogen with H and no chargez[c;x2;D2;r5:1]([n;h1;!+;!-;x2;r5;!$(*=*);!$(*[*;r5]=*):2])[n;x2;r5;!$(*=*);!$(*[*;r5]=*);!$(*[n;r5;x3]);$(*[c;x3;$(*[*;r6])]):3] zc1ccc2c(c1)[nH]cn2zX[*]c1ncno1,[*]n1[nH]cnc1=O,[*]c1nc2[nH]cnn2c(=O)c1[*],c1nc2cscc2[nH]1,c1c[nH]c2c1[nH]cn2z’aromatic carbon in 5 membered ring, bonded to 1 nitrogen bonded to a bridgehead carbon in 6-member ring, bonded to 1 nitrogen with H and no chargez([c;x2;D2;r5:1]([c;x2;r5:2])[o,s;x2;r5:3]z[n:1]([c:2])[*:3]z [*]c1ccoc1,c1ccoc1[*],n1ccoc1[*]zMaromatic carbon in 5 membered ring, bonded to 1 carbon and 1 oxygen or sulfurz)[c;x2;D2;r5:1]([c;r5:2])[n;r5;h0;!-;!+:3]z[n:1]([c:2])[n:3]zc1nc[nH]c1[*],n1cc[nH]c1[*],n1cc[nH][n+]1[*],[*]n1cc2c(c1)CCCC2,[*]N1Cc2cn([*])cc2C1,[*]c1c2c(cn1[*])CCCC2,[*]c1cn2c(c1[*])CCC2z`aromatic carbon in 5 membered ring, bonded to 1 carbon, bonded to 1 nitrogen with no H no chargez+[c;x2;D2;r5:1]([c;x2;r5:2])[n;x2;r5;h1;+:3]z!c1c([*])sc[nH+]1,c1csc([*])[nH+]1z^aromatic carbon in 5 membered ring, bonded to 1 carbon, bonded to 1 nitrogen with H and chargez)[c;x2;D2;r5:1]([c:2])[n;x2;r5;h1;!+;!-:3]z‹[*]n1[nH]ccc1=O,[*]n1cc[nH]c1=O,[*]c1nc2[nH]ccn2c(=O)c1[*],[*]c1ccc[nH]1,[*]c1ncc[nH]1,[*][n+]1ccc[nH]1,[*][n+]1cc[nH]c1,c1ccc2c(c1)cc[nH]2z[*]c1cn2ccnc2nc1[*]zaaromatic carbon in 5 membered ring, bonded to 1 carbon, bonded to 1 nitrogen with H and no chargezy[c;x2;D2;r5:1]([c;x2;r5;!$(*=*);!$(*[*;r5]=*);!$(*[*;r5;x3]):2])[n;x2;r5;!$(*=*);!$(*[*;r5]=*);!$(*[*;r5;x3]);h1;!+;!-:3]z)[o:1]([c:2])[n;H0:3],[s:1]([c:2])[n;H0:3]z=[*]c1ccc[nH]1,[*]c1ncc[nH]1,[*][n+]1ccc[nH]1,[*][n+]1cc[nH]c1zac1ccc2c(c1)cc[nH]2,[*]n1[nH]ccc1=O,[*]n1cc[nH]c1=O,[*]c1nc2[nH]ccn2c(=O)c1[*],[*]c1cn2ccnc2nc1[*]z‹aromatic carbon in 5 membered ring, bonded to 1 carbon, bonded to 1 nitrogen with H and no charge, no exocyclic double bonds or fused ringsz+[c;x2;D2;r5:1]([c;x2;r5:2])[n;h0;+;x2;r5:3]z+CC[n+]1ccco1,[*][n+]1ccco1,[*][n+]1ccc[nH]1zfaromatic carbon in 5 membered ring, bonded to 1 carbon, bonded to 1 nitrogen with no H and with chargez9[c;x2;D2;r5:1]([c;x2;r5:2])[n;h0;+;x2;r5:3][n;x2;r5;h1:4]z3[o:1]([c:2])[n:3][n;H0:4],[s:1]([c:2])[n:3][n;H0:4]z[*][n+]1ccc[nH]1zCC[n+]1ccco1,[*][n+]1ccco1z¢aromatic carbon in 5 membered ring, bonded to 1 carbon, bonded to 1 nitrogen with no H and with charge, that nitrogen is then bonded to a nitrogen with a hydrogenz3[c;x2;D2;r5:1]([c;x2;r5:2])[c;x2;r5:3][o,s;x2;r5:4]z[n:1]([c:2])[c:3][*:4]zs1cccn1,o1c([*])ccn1z s1cc([*])cn1zQaromatic carbon in 5 membered ring, bonded to 2 carbons, oxygen or sulfur in ringz=[!o;!s;r5:1]1~[c;r5:2]~[c;x2;D2;r5:3]~[c;r5:4]~[!o;!s;r5:5]~1z [*:1]1~[c:2]~[n:3]~[c:4]~[*:5]~1z*[*]c1cc[nH]c1,[*]n1cccc1,[*]n1ccc2nccc-2c1zTaromatic carbon in 5 membered ring, bonded to 2 carbons, no oxygen or sulfur in ringzR[n;h1;!+;!-;r5:1]1~[c;!$(*=*);r5:2]~[c;x2;D2;r5:3]~[c;!$(*=*);r5:4]~[!o;!s;r5:5]~1zF[n;H0:1]1~[c:2]~[o:3]~[c:4]~[*:5]1,[n;H0:1]1~[c:2]~[s:3]~[c:4]~[*:5]~1zc1cc[nH]c1,c1ccc2c(c1)cc[nH]2z,[*]n1cccc1,[*]n1cc([*])cc1,[*]n1ccc(=O)[nH]1z’aromatic carbon in 5 membered ring, bonded to 2 carbons without carbonyls, no oxygen or sulfur in ring, and a nitrogen with a hydrogen in the ringzæ[c;h1;D2;r6;$(a1ccc[c,n,o][c,n,o]1),$(a1cc[c,n,o][c,n,o]c1),$(a1c[c,n,o][c,n,o]cc1),$(a1[c,n,o][c,n,o]ccc1),$(a1cc[n,o]c[n,o]1),$(a1c[n,o]c[n,o]c1),$(a1[n,o]c[n,o]cc1),$(a1[n,o]ccc[n,o]1),$(a1c[n,o]cc[n,o]1),$(a1[n,o]cc[n,o]c1):1]z[n:1]z\c1ccccc1,c1cccnc1,c1nccnc1,[*]c1cc(=O)cco1,c1c([*])[nH]c(=O)[nH]c1=O,[*]c1c[nH]c(=O)[nH]c1=OzJaromatic carbon in 6 membered ring, has 1H, ring has less than 3 nitrogensz[n;x2;r5;h1;!+;!-;!$(*[o,s]):1]Únz [o:1],[s:1]zc1n[nH]nn1,c1cc[nH]c1z!c1ccn([*])c1,[*]c1o[nH]c(=O)c1[*]zQaromatic nitrogen in 5 membered ring, 1H, no charge, not next to sulfur or oxygenz([n;x2;X2;r5;h0;!+;!-;$(*[a;r5][a;r5]):1]z[c:1]z c1cnc[nH]1z c1ccn([*])c1zNaromatic nitrogen in 5 membered ring, bonded to 2 heavy atoms, no H, no chargez No mutationszHaromatic nitrogen in 5 membered ring, bonded to 3 heavy atoms, no chargez![n;x2;X3;r5;+;$(*[a;r5][a;r5]):1]z c1coc[n+]1CzFaromatic nitrogen in 5 membered ring, bonded to 3 heavy atoms, chargedz([n;x2;X2;r6;h0;!+;!-;$(*[a;r6][a;r6]):1]zc1cccnc1,c1nccnc1zVaromatic nitrogen in 6 membered ring, bonded to 2 heavy atoms, no hydrogens, no chargezLaromatic nitrogen in 6 membered ring, bonded to 2 heavy atoms, 1H, no chargez![n;x2;r6;h1;+;$(*[a;r6][a;r6]):1]zc1ccc2c(c1)ccc[nH+]2zJaromatic nitrogen in 6 membered ring, bonded to 2 heavy atoms, 1H, chargedz![n;x2;r6;X3;+;$(*[a;r6][a;r6]):1]z[*][n+]1cccc2c1cccc2zFaromatic nitrogen in 6 membered ring, bonded to 3 heavy atoms, chargedzHaromatic nitrogen in 6 membered ring, bonded to 3 heavy atoms, no chargez$[s;x2;r5;!+;!-;$(*([c;r5])[c;r5]):1]Úsz[n;H1:1],[o:1]zc1ccsc1,c1ncsc1z7aromatic sulfur in 5 membered ring, bonded to 2 carbonsz$[o;x2;r5;!+;!-;$(*([c;r5])[c;r5]):1]Úoz[n;H1:1],[s:1]zc1ccoc1,c1ncoc1z7aromatic oxygen in 5 membered ring, bonded to 2 carbonsz?[o,s;x2;r5;!+;!-:1]([c;x2;r5;!$(*=*):2])[n;x2;r5;h0;D2;!+;!-:3]zo,sz[c:1]([c:2])[n;H1:3]zc1cnoc1,c1csnc1,c1c([*])snc1z=[*]n1occc1=O,[*][n+]1ccco1,[*]n1c(=O)[nH]sc1=O,[*]c1nsc(=O)o1z‡aromatic oxygen or sulfur in 5 membered ring, bonded to 1 carbon, 1 nitrogen with no charge with no hydrogen and only bonded to 2 atomsz-[o,s;x2;r5;!+;!-:1]([c;x2;r5:2])[n;x2;r5;+:3]z[c:1]([c:2])[n;+0:3]z [*][n+]1ccco1zbaromatic oxygen or sulfur in 5 membered ring, bonded to 1 carbon, 1 nitrogen in ring with a chargez'[s;x2;r5;!+;!-;$(*([c;r5])[n;h1;r5]):1]z[*]c1s[nH]c(=O)c1[*]zRaromatic sulfur in 5 membered ring, bonded to 1 carbon, 1 nitrogen with a hydrogenz'[o;x2;r5;!+;!-;$(*([c;r5])[n;h1;r5]):1]z[*]c1o[nH]c(=O)c1[*]zRaromatic oxygen in 5 membered ring, bonded to 1 carbon, 1 nitrogen with a hydrogenz5[s;x2;r5;!+;!-:1]([c;x2;r5:2])[n;x2;r5;h0;D3;!+;!-:3]z&[n;H1:1]([c:2])[n:3],[o:1]([c:2])[n:3]z[*]n1sc(=O)n([*])c1=Ozdaromatic sulfur in 5 membered ring, bonded to 1 carbon, 1 nitrogen with no charge bonded to 3 atoms z5[o;x2;r5;!+;!-:1]([c;x2;r5:2])[n;x2;r5;h0;D3;!+;!-:3]z&[n;H1:1]([c:2])[n:3],[s:1]([c:2])[n:3]z[*]n1oc(=O)n([*])c1=Ozdaromatic oxygen in 5 membered ring, bonded to 1 carbon, 1 nitrogen with no charge bonded to 3 atoms z[o;r6:1]z[n;H1:1]z[*]c1cccc(=O)o1z"aromatic oxygen in 6 membered ring)Ú collectionsÚ namedtuple)r©rú?lib/python3.7/site-packages/rdkit/Chem/EnumerateHeterocycles.pyÚGetHeterocycleReactionSmarts sFrccsNxHtƒD]>}|j}|sqx,|j d¡D]}|d|}t |¡Vq&WqWdS)Nú,z>>)rrrÚsplitrZReactionFromSmarts)ÚrowZsmartsÚproductZreactionrrrÚ_ParseReactions?s  rcCstdkrttƒƒatS)zu Return RDKit ChemicalReaction objects of the reaction SMARTS returned from GetHeterocyleReactionSmarts. N)ÚREACTION_CACHEÚlistrrrrrÚGetHeterocycleReactionsJs rc cs²|dfg}tƒ}xœ|r¬| d¡\}}|dk r8||kr8dSxptƒD]f}x`| |f¡D]P}|d}t |¡tj|dd}||kr€qR| ||df¡| |¡|VqRWq@WqWdS)aH Enumerate possible relevant heterocycles on the given input molecule. >>> from rdkit.Chem.EnumerateHeterocycles import EnumerateHeterocycles >>> from rdkit import Chem >>> for smi in sorted(Chem.MolToSmiles(m) for m in EnumerateHeterocycles(Chem.MolFromSmiles('c1ccccc1'))): ... print(smi) c1ccccc1 c1ccncc1 c1ccnnc1 c1cnccn1 c1cncnc1 c1cnncn1 c1cnnnc1 c1ncncn1 The algorithm works by mutating only one atom at a time. The depth parameter can be used to control the level of this recursion. For example, only enumerating aromatic rings that are one atom different: >>> for smi in sorted(Chem.MolToSmiles(m) for m in EnumerateHeterocycles(Chem.MolFromSmiles('n1ccccc1'), depth=1)): ... print(smi) c1ccccc1 c1ccnnc1 c1cnccn1 c1cncnc1 rNT)ZisomericSmilesé) ÚsetÚpoprZ RunReactantsrZ SanitizeMolZ MolToSmilesÚappendÚadd) ZinputmolZdepthZstarting_pointsÚseenZcurmolZcurdepthZrxnZnewmolZ newmol_smilesrrrÚEnumerateHeterocyclesUs     r)N) r ZrdkitrZ rdkit.ChemrrrrrrrrrrÚs  3