parsertest.java

化学图形处理软件

    }
    public void testPattern184() throws Exception { // Generic amino acid: low specificity.
        parse("[NX3,NX4+][CX4H]([*])[CX3](=[OX1])[O,N]"); 
    }
    public void testPattern185() throws Exception { //Template for 20 standard a.a.s
        parse("[$([$([NX3H,NX4H2+]),$([NX3](C)(C)(C))]1[CX4H]([CH2][CH2][CH2]1)[CX3](=[OX1])[OX2H,OX1-,N])," +
        		"$([$([NX3H2,NX4H3+]),$([NX3H](C)(C))][CX" +
        		"4H2][CX3](=[OX1])[OX2H,OX1-,N]),$([$([NX3H2,NX4H3+]),$([NX3H](C)(C))][CX4H]([*])[CX3](=[OX1])[OX2H,OX1-,N])]");
    }
    public void testPattern186() throws Exception { // Proline
        parse("[$([NX3H,NX4H2+]),$([NX3](C)(C)(C))]1[CX4H]([CH2][CH2][CH2]1)[CX3](=[OX1])[OX2H,OX1-,N]");
    }
    public void testPattern187() throws Exception { // Glycine
        parse("[$([$([NX3H2,NX4H3+]),$([NX3H](C)(C))][CX4H2][CX3](=[OX1])[OX2H,OX1-,N])]");
    }
    public void testPattern188() throws Exception {  // Alanine
        parse("[$([NX3H2,NX4H3+]),$([NX3H](C)(C))][CX4H]([CH3X4])[CX3](=[OX1])[OX2H,OX1-,N]");
    }
    public void testPattern189() throws Exception { //18_standard_aa_side_chains.
        parse("([$([CH3X4]),$([CH2X4][CH2X4][CH2X4][NHX3][CH0X3](=[NH2X3+,NHX2+0])[NH2X3])," + 
        		"$([CH2X4][CX3](=[OX1])[NX3H2]),$([CH2X4][CX3](=[OX1])[OH0-,OH])," + 
        		"$([CH2X4][SX2H,SX1H0-]),$([CH2X4][CH2X4][CX3](=[OX1])[OH0-,OH])," + 
        		"$([CH2X4][#6X3]1:[$([#7X3H+,#7X2H0+0]:[#6X3H]:[#7X3H]),$([#7X3H])]:" + 
        		"[#6X3H]:[$([#7X3H+,#7X2H0+0]:[#6X3H]:[#7X3H]),$([#7X3H])]:[#6X3H]1)," + 
        		"$([CHX4]([CH3X4])[CH2X4][CH3X4]),$([CH2X4][CHX4]([CH3X4])[CH3X4])," + 
        		"$([CH2X4][CH2X4][CH2X4][CH2X4][NX4+,NX3+0]),$([CH2X4][CH2X4][SX2][CH3X4])," + 
        		"$([CH2X4][cX3]1[cX3H][cX3H][cX3H][cX3H][cX3H]1),$([CH2X4][OX2H])," + 
        		"$([CHX4]([CH3X4])[OX2H]),$([CH2X4][cX3]1[cX3H][nX3H][cX3]2[cX3H][cX3H][cX3H][cX3H][cX3]12)," + 
        		"$([CH2X4][cX3]1[cX3H][cX3H][cX3]([OHX2,OH0X1-])[cX3H][cX3H]1),$([CHX4]([CH3X4])[CH3X4])])");
    }
    public void testPattern190() throws Exception { // N in Any_standard_amino_acid.
    	parse("[$([$([NX3H,NX4H2+]),$([NX3](C)(C)(C))]1[CX4H]([CH2][CH2][CH2]1)[CX3]" + 
    			"(=[OX1])[OX2H,OX1-,N]),$([$([NX3H2,NX4H3+]),$([NX3H](C)(C))][CX4H2][CX3]" + 
    			"(=[OX1])[OX2H,OX1-,N]),$([$([NX3H2,NX4H3+]),$([NX3H](C)(C))][CX4H]([$([CH3X4])," + 
    			"$([CH2X4][CH2X4][CH2X4][NHX3][CH0X3](=[NH2X3+,NHX2+0])[NH2X3]),$" +
    			"([CH2X4][CX3](=[OX1])[NX3H2]),$([CH2X4][CX3](=[OX1])[OH0-,OH])," +
    			"$([CH2X4][SX2H,SX1H0-]),$([CH2X4][CH2X4][CX3](=[OX1])[OH0-,OH])," +
    			"$([CH2X4][#6X3]1:[$([#7X3H+,#7X2H0+0]:[#6X3H]:[#7X3H]),$([#7X3H])]:" + 
    			"[#6X3H]:[$([#7X3H+,#7X2H0+0]:[#6X3H]:[#7X3H]),$([#7X3H])]:[#6X3H]1)," + 
    			"$([CHX4]([CH3X4])[CH2X4][CH3X4]),$([CH2X4][CHX4]([CH3X4])[CH3X4])," + 
    			"$([CH2X4][CH2X4][CH2X4][CH2X4][NX4+,NX3+0]),$([CH2X4][CH2X4][SX2][CH3X4])," +
    			"$([CH2X4][cX3]1[cX3H][cX3H][cX3H][cX3H][cX3H]1),$([CH2X4][OX2H])," +
    			"$([CHX4]([CH3X4])[OX2H]),$([CH2X4][cX3]1[cX3H][nX3H][cX3]2[cX3H][cX3H][cX3H][cX3H][cX3]12)," + 
    			"$([CH2X4][cX3]1[cX3H][cX3H][cX3]([OHX2,OH0X1-])[cX3H][cX3H]1)," +
    			"$([CHX4]([CH3X4])[CH3X4])])[CX3](=[OX1])[OX2H,OX1-,N])]"); 
    }
    public void testPattern191() throws Exception { // Non-standard amino acid.
        parse("[$([NX3,NX4+][CX4H]([*])[CX3](=[OX1])[O,N]);!$([$([$([NX3H,NX4H2+])," + 
        		"$([NX3](C)(C)(C))]1[CX4H]([CH2][CH2][CH2]1)[CX3](=[OX1])[OX2H,OX1-,N])," +
        		"$([$([NX3H2,NX4H3+]),$([NX3H](C)(C))][CX4H2][CX3](=[OX1])[OX2H,OX1-,N])," + 
        		"$([$([NX3H2,NX4H3+]),$([NX3H](C)(C))][CX4H]([$([CH3X4]),$([CH2X4][CH2X4][CH2X4][NHX3][CH0X3]" + 
        		"(=[NH2X3+,NHX2+0])[NH2X3]),$([CH2X4][CX3](=[OX1])[NX3H2]),$([CH2X4][CX3](=[OX1])[OH0-,OH])," +
        		"$([CH2X4][SX2H,SX1H0-]),$([CH2X4][CH2X4][CX3](=[OX1])[OH0-,OH]),$([CH2X4][#6X3]1:" + 
        		"[$([#7X3H+,#7X2H0+0]:[#6X3H]:[#7X3H]),$([#7X3H])]:" + 
        		"[#6X3H]:[$([#7X3H+,#7X2H0+0]:[#6X3H]:[#7X3H])," + 
        		"$([#7X3H])]:[#6X3H]1),$([CHX4]([CH3X4])[CH2X4][CH3X4]),$([CH2X4][CHX4]([CH3X4])[CH3X4])," +
        		"$([CH2X4][CH2X4][CH2X4][CH2X4][NX4+,NX3+0]),$([CH2X4][CH2X4][SX2][CH3X4])," +
        		"$([CH2X4][cX3]1[cX3H][cX3H][cX3H][cX3H][cX3H]1),$([CH2X4][OX2H]),$([CHX4]([CH3X4])[OX2H])," + 
        		"$([CH2X4][cX3]1[cX3H][nX3H][cX3]2[cX3H][cX3H][cX3H][cX3H][cX3]12)," + 
        		"$([CH2X4][cX3]1[cX3H][cX3H][cX3]([OHX2,OH0X1-])[cX3H][cX3H]1)," + 
        		"$([CHX4]([CH3X4])[CH3X4])])[CX3](=[OX1])[OX2H,OX1-,N])])]");
    }
    public void testPattern192() throws Exception { //Azide group
        parse("[$(*-[NX2-]-[NX2+]#[NX1]),$(*-[NX2]=[NX2+]=[NX1-])]");
    }
    public void testPattern193() throws Exception { // Azide ion
        parse("[$([NX1-]=[NX2+]=[NX1-]),$([NX1]#[NX2+]-[NX1-2])]");
    }
    public void testPattern194() throws Exception { //Azide or azide ion
        parse("[$([$(*-[NX2-]-[NX2+]#[NX1]),$(*-[NX2]=[NX2+]=[NX1-])]),$([$([NX1-]=[NX2+]=[NX1-]),$([NX1]#[NX2+]-[NX1-2])])]");
    }

    public void testPattern195() throws Exception { // Sulfide
        parse("[#16X2H0]");
    }
    public void testPattern196() throws Exception { // Mono-sulfide
        parse("[#16X2H0][!#16]");
    }
    public void testPattern197() throws Exception { // Di-sulfide
        parse("[#16X2H0][#16X2H0]");
    }
    public void testPattern198() throws Exception { // Two sulfides
        parse("[#16X2H0][!#16].[#16X2H0][!#16]");
    }
    public void testPattern199() throws Exception { // Acid/conj-base
        parse("[OX2H,OX1H0-]");
    }
    public void testPattern200() throws Exception { // Non-acid Oxygen
        parse("[OX2H0]");
    }
    public void testPattern201() throws Exception { // Acid/base
        parse("[H1,H0-]");
    }
    public void testPattern202() throws Exception {
        parse("([Cl!$(Cl~c)].[c!$(c~Cl)])");
    }
    public void testPattern203() throws Exception {
        parse("([Cl]).([c])");
    }
    public void testPattern204() throws Exception {
        parse("([Cl].[c])");
    }
    public void testPattern205() throws Exception {
        parse("[NX3;H2,H1;!$(NC=O)].[NX3;H2,H1;!$(NC=O)]");
    }
    public void testPattern206() throws Exception {
        parse("[#0]");
    }
    public void testPattern207() throws Exception {
        parse("[*!H0,#1]");
    }
    public void testPattern208() throws Exception {
        parse("[#6!H0,#1]");
    }
    public void testPattern209() throws Exception {
        parse("[H,#1]");
    }
    public void testPattern210() throws Exception {
        parse("[!H0;F,Cl,Br,I,N+,$([OH]-*=[!#6]),+]");
    }
    public void testPattern211() throws Exception {
        parse("[CX3](=O)[OX2H1]");
    }
    public void testPattern212() throws Exception {
        parse("[CX3](=O)[OX1H0-,OX2H1]");
    }
    public void testPattern213() throws Exception {
        parse("[$([OH]-*=[!#6])]");
    }
    public void testPattern214() throws Exception { // Phosphoric_Acid 
        parse("[$(P(=[OX1])([$([OX2H]),$([OX1-]),$([OX2]P)])([$([OX2H]),$([OX1-]),$([OX2]P)])[$([OX2H]),$([OX1-]),$([OX2]P)]),$([P+]([OX1-])([$([OX" +
        		"2H]),$([OX1-]),$([OX2]P)])([$([OX2H]),$([OX1-]),$([OX2]P)])[$([OX2H]),$([OX1-]),$([OX2]P)])]");
    }
    public void testPattern215() throws Exception { // Sulfonic Acid. High specificity.
        parse("[$([#16X4](=[OX1])(=[OX1])([#6])[OX2H,OX1H0-]),$([#16X4+2]([OX1-])([OX1-])([#6])[OX2H,OX1H0-])]");
    }
    public void testPattern216() throws Exception { // Acyl Halide
        parse("[CX3](=[OX1])[F,Cl,Br,I]");
    }
    public void testPattern217() throws Exception {
        parse("[NX2-]");
    }
    public void testPattern218() throws Exception {
        parse("[OX2H+]=*");
    }
    public void testPattern219() throws Exception {
        parse("[OX3H2+]");
    }
    public void testPattern220() throws Exception {
        parse("[#6+]");
    }
    public void testPattern221() throws Exception {
        parse("[$([cX2+](:*):*)]");
    }
    public void testPattern222() throws Exception {
        parse("[$([NX1-]=[NX2+]=[NX1-]),$([NX1]#[NX2+]-[NX1-2])]");
    }
    public void testPattern223() throws Exception {
        parse("[+1]~*~*~[-1]");
    }
    public void testPattern224() throws Exception {
        parse("[$([!-0!-1!-2!-3!-4]~*~[!+0!+1!+2!+3!+4]),$([!-0!-1!-2!-3!-4]~*~*~[!+0!+1!+2!+3!+4]),$([!-0!-1!-2!-3!-4]~*~*~*~[!+0!+1!+2!+3!+4]),$([!-0!-1!-2!-3!-4]~*~*~*~*~[!+0!+1!+2!+3!+4]),$([!-0!-1!-2!-3!-4]~*~*~*~*~*~[!+0!+1!+2!+3!+4]),$([!-0!-1!-2!-3!-4]~*~*~*~*~*~*~[!+0!+1!+2!+3!+4]),$([!-0!-1!-2!-3!-4]~*~*~*~*~*~*~*~[!+0!+1!+2!+3!+4]),$([!-0!-1!-2!-3!-4]~*~*~*~*~*~*~*~*~[!+0!+1!+2!+3!+4]),$([!-0!-1!-2!-3!-4]~*~*~*~*~*~*~*~*~*~[!+0!+1!+2!+3!+4])]");
    }
    public void testPattern225() throws Exception {
        parse("([!-0!-1!-2!-3!-4].[!+0!+1!+2!+3!+4])");
    }
    public void testPattern226() throws Exception { // Hydrogen-bond acceptor, Only hits carbonyl and nitroso
        parse("[#6,#7;R0]=[#8]");
    }
    public void testPattern227() throws Exception { // Hydrogen-bond acceptor
        parse("[!$([#6,F,Cl,Br,I,o,s,nX3,#7v5,#15v5,#16v4,#16v6,*+1,*+2,*+3])]");
    }
    public void testPattern228() throws Exception {
        parse("[!$([#6,H0,-,-2,-3])]");
    }
    public void testPattern229() throws Exception {
        parse("[!H0;#7,#8,#9]");
    }
    public void testPattern230() throws Exception {
        parse("[O,N;!H0]-*~*-*=[$([C,N;R0]=O)]");
    }
    public void testPattern231() throws Exception {
        parse("[#6;X3v3+0]");
    }
    public void testPattern232() throws Exception {
        parse("[#7;X2v4+0]");
    }
    public void testPattern233() throws Exception { // Amino Acid
        parse("[$([$([NX3H,NX4H2+]),$([NX3](C)(C)(C))]1[CX4H]([CH2][CH2][CH2]1)[CX3](=[OX1])[OX2H,OX1-,N]),$([$([NX3H2,NX4H3+]),$([NX3H](C)(C))][CX4H2][" + 
        		"CX3](=[OX1])[OX2H,OX1-,N]),$([$([NX3H2,NX4H3+]),$([NX3H](C)(C))][CX4H]([*])[CX3](=[OX1])[OX2H,OX1-,N])]");
    }
    public void testPattern234() throws Exception {
        parse("[#6][CX3](=O)[$([OX2H0]([#6])[#6]),$([#7])]");
    }
    public void testPattern235() throws Exception {
        parse("[#8]=[C,N]-aaa[F,Cl,Br,I]");
    }
    public void testPattern236() throws Exception {
        parse("[O,N;!H0;R0]");
    }
    public void testPattern237() throws Exception {
        parse("[#8]=[C,N]");
    }
    public void testPattern238() throws Exception { // PCB
        parse("[$(c:cCl),$(c:c:cCl),$(c:c:c:cCl)]-[$(c:cCl),$(c:c:cCl),$(c:c:c:cCl)]");
    }
    public void testPattern239() throws Exception { // Imidazolium Nitrogen
        parse("[nX3r5+]:c:n");
    }
    public void testPattern240() throws Exception { // 1-methyl-2-hydroxy benzene with either a Cl or H at the 5 position.
        parse("[c;$([*Cl]),$([*H1])]1ccc(O)c(C)c1");
        parse("Cc1:c(O):c:c:[$(cCl),$([cH])]:c1");
    }
    public void testPattern241() throws Exception { // Nonstandard atom groups.
        parse("[!#1;!#2;!#3;!#5;!#6;!#7;!#8;!#9;!#11;!#12;!#15;!#16;!#17;!#19;!#20;!#35;!#53]");
    }    
    /**
     * From http://www.daylight.com/dayhtml_tutorials/languages/smarts/index.html
     */
    public void testPropertyCharge1() throws Exception {
    	assertEquals(0, match("[+1]", "[OH-].[Mg+2]"));
    }
    public void testPropertyCharge2() throws Exception {
    	assertEquals(1, match("[+1]", "COCC(O)Cn1ccnc1[N+](=O)[O-]"));
    }
    public void testPropertyCharge3() throws Exception {
    	assertEquals(1, match("[+1]", "[NH4+]"));
    }
    public void testPropertyCharge4() throws Exception {
    	assertEquals(0, match("[+1]", "CN1C(=O)N(C)C(=O)C(N(C)C=N2)=C12"));
    }
    public void testPropertyCharge5() throws Exception {
    	assertEquals(2, match("[+1]", "[Cl-].[Cl-].NC(=O)c2cc[n+](COC[n+]1ccccc1C=NO)cc2"));
    }
    public void testPropertyAromatic1() throws Exception {
    	int m = match("[a]", "c1cc(C)c(N)cc1");
    	assertEquals(6, m);
    }
    public void testPropertyAromatic2() throws Exception {
    	int m = match("[a]", "c1c(C)c(N)cnc1");
    	assertEquals(6, m);
    }
    public void testPropertyAromatic3() throws Exception {
    	int m = match("[a]", "c1(C)c(N)cco1");
    	assertEquals(5, m);
    }
    public void testPropertyAromatic4() throws Exception {
    	int m = match("[a]", "c1c(C)c(N)c[nH]1");
    	assertEquals(5, m);
    }
    public void testPropertyAromatic5() throws Exception {
    	int m = match("[a]", "O=n1ccccc1");
    	assertEquals(6, m);
    }  
    public void testPropertyAromatic6() throws Exception {
    	int m = match("[a]", "[O-][n+]1ccccc1");
    	assertEquals(6, m);
    }  
    public void testPropertyAromatic7() throws Exception {
    	int m = match("[a]", "c1ncccc1C1CCCN1C");
    	assertEquals(6, m);
    }  
    public void testPropertyAromatic8() throws Exception {
    	int m = match("[a]", "c1ccccc1C(=O)OC2CC(N3C)CCC3C2C(=O)OC");
    	assertEquals(6, m);
    }
    public void testPropertyAliphatic1() throws Exception {
    	int m = match("[A]", "c1cc(C)c(N)cc1");
    	assertEquals(2, m);
    }
    public void testPropertyAliphatic2() throws Exception {
    	int m = match("[A]", "CCO");
    	assertEquals(3, m);
    }
    public void testPropertyAliphatic3() throws Exception {
    	int m = match("[A]", "C=CC=CC=C");
    	assertEquals(6, m);
    }
    public void testPropertyAliphatic4() throws Exception {
    	int m = match("[A]", "CC(C)(C)C");
    	assertEquals(5, m);
    }
    public void testPropertyAliphatic5() throws Exception {
    	int m = match("[A]", "CCN(CC)C(=O)C1CN(C)C2CC3=CNc(ccc4)c3c4C2=C1");
    	assertEquals(15, m);
    }
    public void testPropertyAliphatic6() throws Exception {
    	int m = match("[A]", "N12CCC36C1CC(C(C2)=CCOC4CC5=O)C4C3N5c7ccccc76");
    	assertEquals(19, m);
    }
    //TODO: atomicnumber always 0 in smiles parsed atomcontainer
    public void testPropertyAtomicNumber1() throws Exception {
    	int m = match("[#6]", "c1cc(C)c(N)cc1");
    	assertEquals(7, m);    	
    }
    public void testPropertyAtomicNumber2() throws Exception {
    	int m = match("[#6]", "CCO");
    	assertEquals(2, m);    	
    }
    public void testPropertyAtomicNumber3() throws Exception {
    	int m = match("[#6]", "C=CC=CC=C-O");
    	assertEquals(6, m);    	
    }
    public void testPropertyAtomicNumber4() throws Exception {
    	int m = match("[#6]", "CC(C)(C)C");
    	assertEquals(5, m);    	
    }
    public void testPropertyAtomicNumber5() throws Exception {
    	int m = match("[#6]", "COc1cc2c(ccnc2cc1)C(O)C4CC(CC3)C(C=C)CN34");
    	assertEquals(20, m);    	
    }
    public void testPropertyAtomicNumber6() throws Exception {
    	int m = match("[#6]", "C123C5C(O)C=CC2C(N(C)CC1)Cc(ccc4O)c3c4O5");
    	assertEquals(17, m);    	
    }
    public void testPropertyAtomicNumber7() throws Exception {
    	int m = match("[#6]", "C123C5C(OC(=O)C)C=CC2C(N(C)CC1)Cc(ccc4OC(=O)C)c3c4O5");
    	assertEquals(21, m);    	
    }
    public void testPropertyR1() throws Exception {
    	int m = match("[R2]", "N12CCC36C1CC(C(C2)=CCOC4CC5=O)C4C3N5c7ccccc76");
    	assertEquals(7, m);     	
    }
    public void testPropertyR2() throws Exception {
    	int m = match("[R2]", "COc1cc2c(ccnc2cc1)C(O)C4CC(CC3)C(C=C)CN34");
    	assertEquals(6, m);     	
    }
    public void testPropertyR3() throws Exception {
    	int m = match("[R2]", "C123C5C(O)C=CC2C(N(C)CC1)Cc(ccc4O)c3c4O5");
    	assertEquals(4, m);     	
    }
    public void testPropertyR4() throws Exception {
    	int m = match("[R2]", "C123C5C(OC(=O)C)C=CC2C(N(C)CC1)Cc(ccc4OC(=O)C)c3c4O5");
    	assertEquals(4, m);     	
    }
    public void testPropertyR5() throws Exception {
    	int m = match("[R2]", "C1C(C)=C(C=CC(C)=CC=CC(C)=CCO)C(C)(C)C1");
    	assertEquals(0, m);
    }
    public void testPropertyr1() throws Exception {
    	int m = match("[r5]", "N12CCC36C1CC(C(C2)=CCOC4CC5=O)C4C3N5c7ccccc76");
    	assertEquals(9, m);
    }
    public void testPropertyr2() throws Exception {
    	int m = match("[r5]", "COc1cc2c(ccnc2cc1)C(O)C4CC(CC3)C(C=C)CN34");
    	assertEquals(0, m);
    }
    public void testPropertyr3() throws Exception {
    	int m = match("[r5]", "C123C5C(O)C=CC2C(N(C)CC1)Cc(ccc4O)c3c4O5");
    	assertEquals(5, m);
    }
    public void testPropertyr4() throws Exception {
    	int m = match("[r5]", "C123C5C(OC(=O)C)C=CC2C(N(C)CC1)Cc(ccc4OC(=O)C)c3c4O5");