public void TestGetFunctionalGroupSubstructureSet()
{
var smarts = StandardSubstructureSets.GetFunctionalGroupSMARTS();
Assert.IsNotNull(smarts);
Assert.AreEqual(307, smarts.Count());
}
public void TestGetCountableMACCSSMARTSSubstructureSet()
{
var smarts = StandardSubstructureSets.GetCountableMACCSSMARTS();
Assert.IsNotNull(smarts);
Assert.AreEqual(142, smarts.Count()); // currently fragment pattern is ignored
}
/// <summary>
/// Set up the fingerprinter to use the fragments from <see cref="StandardSubstructureSets"/>.
/// </summary>
public SubstructureFingerprinter()
{
try
{
SetSmarts(StandardSubstructureSets.GetFunctionalGroupSMARTS());
}
catch (Exception ex)
{
throw new InvalidOperationException("Could not load SMARTS patterns", ex);
}
}
public void TestSize()
{
SubstructureFingerprinter fp;
fp = new SubstructureFingerprinter();
Assert.AreEqual(307, fp.Length);
fp = new SubstructureFingerprinter(StandardSubstructureSets.GetFunctionalGroupSMARTS());
Assert.AreEqual(307, fp.Length);
fp = new SubstructureFingerprinter(StandardSubstructureSets.GetCountableMACCSSMARTS());
Assert.AreEqual(142, fp.Length);
}
public void TestCountableMACCSBinary_Rings()
{
var parser = CDK.SmilesParser;
var printer = new SubstructureFingerprinter(StandardSubstructureSets.GetCountableMACCSSMARTS());
IAtomContainer mol;
BitArray bs;
// Aromatic 6-rings
mol = parser.ParseSmiles("C1=CC=CC(=C1)CCCC2=CC=CC=C2");
AtomContainerManipulator.PercieveAtomTypesAndConfigureAtoms(mol);
Aromaticity.CDKLegacy.Apply(mol);
bs = printer.GetBitFingerprint(mol).AsBitSet();
Assert.IsTrue(bs[128]); // 6-ring
Assert.IsTrue(bs[111]); // aromaticity
Assert.IsFalse(bs[7]); // 7-ring
Assert.IsFalse(bs[82]); // 5-ring
// Non-aromatic 6-rings
mol = parser.ParseSmiles("C1CC(CCC1)CCCCC2CCCCC2");
AtomContainerManipulator.PercieveAtomTypesAndConfigureAtoms(mol);
Aromaticity.CDKLegacy.Apply(mol);
bs = printer.GetBitFingerprint(mol).AsBitSet();
Assert.IsTrue(bs[128]); // 6-ring
Assert.IsFalse(bs[111]); // aromaticity
Assert.IsFalse(bs[7]); // 7-ring
Assert.IsFalse(bs[82]); // 5-ring
// Aromatic 6-ring, 3-ring and 4-ring
mol = parser.ParseSmiles("C1CC1C(CCC2CCC2)CC3=CC=CC=C3");
AtomContainerManipulator.PercieveAtomTypesAndConfigureAtoms(mol);
Aromaticity.CDKLegacy.Apply(mol);
bs = printer.GetBitFingerprint(mol).AsBitSet();
Assert.IsTrue(bs[128]); // 6-ring
Assert.IsTrue(bs[111]); // aromaticity
Assert.IsTrue(bs[10]); // 3-ring
Assert.IsTrue(bs[1]); // 4-ring
Assert.IsFalse(bs[7]); // 7-ring
Assert.IsFalse(bs[82]); // 5-ring
// Aromatic 6-ring, 3-ring and 4-ring
mol = parser.ParseSmiles("C1(CC1C(CCC2CCC2)CC3=CC=CC=C3)C(C(C(C4CC4)C5CC5)C6CC6)C7CC7");
AtomContainerManipulator.PercieveAtomTypesAndConfigureAtoms(mol);
Aromaticity.CDKLegacy.Apply(mol);
bs = printer.GetBitFingerprint(mol).AsBitSet();
Assert.IsTrue(bs[128]); // 6-ring
Assert.IsTrue(bs[111]); // aromaticity
Assert.IsTrue(bs[10]); // 3-ring
Assert.IsTrue(bs[1]); // 4-ring
Assert.IsFalse(bs[7]); // 7-ring
Assert.IsFalse(bs[82]); // 5-ring
}
public void TestCountableMACCSCount_Rings()
{
var parser = CDK.SmilesParser;
var printer = new SubstructureFingerprinter(StandardSubstructureSets.GetCountableMACCSSMARTS());
IAtomContainer mol;
ICountFingerprint cfp;
// Aromatic 6-rings
mol = parser.ParseSmiles("C1=CC=CC(=C1)CCCC2=CC=CC=C2");
AtomContainerManipulator.PercieveAtomTypesAndConfigureAtoms(mol);
Aromaticity.CDKLegacy.Apply(mol);
cfp = printer.GetCountFingerprint(mol);
Assert.IsTrue(cfp.GetCountForHash(128) == 2); // 6-ring
Assert.IsTrue(cfp.GetCountForHash(111) == 2); // aromaticity
Assert.IsTrue(cfp.GetCountForHash(7) == 0); // 7-ring
Assert.IsTrue(cfp.GetCountForHash(82) == 0); // 5-ring
// Non-aromatic 6-rings
mol = parser.ParseSmiles("C1CC(CCC1)CCCCC2CCCCC2");
AtomContainerManipulator.PercieveAtomTypesAndConfigureAtoms(mol);
Aromaticity.CDKLegacy.Apply(mol);
cfp = printer.GetCountFingerprint(mol);
Assert.IsTrue(cfp.GetCountForHash(128) == 2); // 6-ring
Assert.IsTrue(cfp.GetCountForHash(111) == 0); // aromaticity
Assert.IsTrue(cfp.GetCountForHash(7) == 0); // 7-ring
Assert.IsTrue(cfp.GetCountForHash(82) == 0); // 5-ring
// Aromatic 6-ring, 3-ring and 4-ring
mol = parser.ParseSmiles("C1CC1C(CCC2CCC2)CC3=CC=CC=C3");
AtomContainerManipulator.PercieveAtomTypesAndConfigureAtoms(mol);
Aromaticity.CDKLegacy.Apply(mol);
cfp = printer.GetCountFingerprint(mol);
Assert.IsTrue(cfp.GetCountForHash(128) == 1); // 6-ring
Assert.IsTrue(cfp.GetCountForHash(111) == 1); // aromaticity
Assert.IsTrue(cfp.GetCountForHash(10) == 1); // 3-ring
Assert.IsTrue(cfp.GetCountForHash(1) == 1); // 4-ring
Assert.IsTrue(cfp.GetCountForHash(7) == 0); // 7-ring
Assert.IsTrue(cfp.GetCountForHash(82) == 0); // 5-ring
// Aromatic 6-ring, 3-ring and 4-ring
mol = parser.ParseSmiles("C1(CC1C(CCC2CCC2)CC3=CC=CC=C3)C(C(C(C4CC4)C5CC5)C6CC6)C7CC7");
AtomContainerManipulator.PercieveAtomTypesAndConfigureAtoms(mol);
Aromaticity.CDKLegacy.Apply(mol);
cfp = printer.GetCountFingerprint(mol);
Assert.IsTrue(cfp.GetCountForHash(128) == 1); // 6-ring
Assert.IsTrue(cfp.GetCountForHash(111) == 1); // aromaticity
Assert.IsTrue(cfp.GetCountForHash(10) == 5); // 3-ring
Assert.IsTrue(cfp.GetCountForHash(1) == 1); // 4-ring
Assert.IsTrue(cfp.GetCountForHash(7) == 0); // 7-ring
Assert.IsTrue(cfp.GetCountForHash(82) == 0); // 5-ring
}
public void TestCountableMACCSBinary()
{
// Tests are modified copy of the test included in the MACCS-FPs class
var parser = CDK.SmilesParser;
var printer = new SubstructureFingerprinter(StandardSubstructureSets.GetCountableMACCSSMARTS());
Assert.AreEqual(142, printer.Length);
var mol0 = parser.ParseSmiles("CC(N)CCCN");
var mol1 = parser.ParseSmiles("c1ccccc1CCc1ccccc1");
var mol2 = parser.ParseSmiles("c1ccccc1CC");
var mol3 = parser.ParseSmiles("CC(N)CCC");
var mol4 = parser.ParseSmiles("CCCC");
AtomContainerManipulator.PercieveAtomTypesAndConfigureAtoms(mol0);
AtomContainerManipulator.PercieveAtomTypesAndConfigureAtoms(mol1);
AtomContainerManipulator.PercieveAtomTypesAndConfigureAtoms(mol2);
AtomContainerManipulator.PercieveAtomTypesAndConfigureAtoms(mol3);
AtomContainerManipulator.PercieveAtomTypesAndConfigureAtoms(mol4);
Aromaticity.CDKLegacy.Apply(mol0);
Aromaticity.CDKLegacy.Apply(mol1);
Aromaticity.CDKLegacy.Apply(mol2);
Aromaticity.CDKLegacy.Apply(mol3);
Aromaticity.CDKLegacy.Apply(mol4);
var bs0 = printer.GetBitFingerprint(mol0).AsBitSet();
var bs1 = printer.GetBitFingerprint(mol1).AsBitSet();
var bs2 = printer.GetBitFingerprint(mol2).AsBitSet();
var bs3 = printer.GetBitFingerprint(mol3).AsBitSet();
var bs4 = printer.GetBitFingerprint(mol4).AsBitSet();
// Check for the aromatic 6M rings
Assert.IsFalse(bs0[111]);
Assert.IsTrue(bs1[111]);
Assert.IsTrue(bs2[111]);
Assert.IsFalse(bs3[111]);
Assert.IsFalse(bs4[111]);
// Check for the fingerprints being subsets
Assert.IsFalse(FingerprinterTool.IsSubset(bs1, bs2));
Assert.IsFalse(FingerprinterTool.IsSubset(bs0, bs3));
Assert.IsTrue(FingerprinterTool.IsSubset(bs3, bs4));
}
public void TestCountableMACCSCount2()
{
var parser = CDK.SmilesParser;
var printer = new SubstructureFingerprinter(StandardSubstructureSets.GetCountableMACCSSMARTS());
IAtomContainer mol;
ICountFingerprint cfp;
// Test molecule 1
mol = parser.ParseSmiles("C([S](O)(=O)=O)C1=C(C=CC=C1)CCCC[N+](=O)[O-]");
AtomContainerManipulator.PercieveAtomTypesAndConfigureAtoms(mol);
Aromaticity.CDKLegacy.Apply(mol);
cfp = printer.GetCountFingerprint(mol);
Assert.IsTrue(cfp.GetCountForHash(46) == 2);
Assert.IsTrue(cfp.GetCountForHash(27) == 1);
Assert.IsTrue(cfp.GetCountForHash(59) == 2);
Assert.IsTrue(cfp.GetCountForHash(49) == 1);
Assert.IsTrue(cfp.GetCountForHash(111) == 1);
Assert.IsTrue(cfp.GetCountForHash(129) == 3);
Assert.IsTrue(cfp.GetCountForHash(115) == 2);
Assert.IsTrue(cfp.GetCountForHash(120) == 3);
Assert.IsTrue(cfp.GetCountForHash(41) == 3);
Assert.IsTrue(cfp.GetCountForHash(93) == 0);
Assert.IsTrue(cfp.GetCountForHash(91) == 0);
Assert.IsTrue(cfp.GetCountForHash(24) == 0);
// Test molecule 2: Diatrizoic acid
mol = parser.ParseSmiles("CC(=O)NC1=C(C(=C(C(=C1I)C(=O)O)I)NC(=O)C)I");
AtomContainerManipulator.PercieveAtomTypesAndConfigureAtoms(mol);
Aromaticity.CDKLegacy.Apply(mol);
cfp = printer.GetCountFingerprint(mol);
Assert.IsTrue(cfp.GetCountForHash(15) == 3);
Assert.IsTrue(cfp.GetCountForHash(135) == 3);
Assert.IsTrue(cfp.GetCountForHash(139) == 4);
Assert.IsTrue(cfp.GetCountForHash(93) == 3);
Assert.IsTrue(cfp.GetCountForHash(73) == 6);
Assert.IsTrue(cfp.GetCountForHash(91) == 0);
}
public void TestCountableMACCSBinary2()
{
var parser = CDK.SmilesParser;
var printer = new SubstructureFingerprinter(StandardSubstructureSets.GetCountableMACCSSMARTS());
IAtomContainer mol;
BitArray bs;
// Test molecule 1
mol = parser.ParseSmiles("C([S](O)(=O)=O)C1=C(C=CC=C1)CCCC[N+](=O)[O-]");
AtomContainerManipulator.PercieveAtomTypesAndConfigureAtoms(mol);
Aromaticity.CDKLegacy.Apply(mol);
bs = printer.GetBitFingerprint(mol).AsBitSet();
Assert.IsTrue(bs[46]);
Assert.IsTrue(bs[27]);
Assert.IsTrue(bs[59]);
Assert.IsTrue(bs[49]);
Assert.IsTrue(bs[111]);
Assert.IsTrue(bs[129]);
Assert.IsTrue(bs[115]);
Assert.IsTrue(bs[120]);
Assert.IsTrue(bs[41]);
Assert.IsFalse(bs[93]);
Assert.IsFalse(bs[91]);
Assert.IsFalse(bs[24]);
// Test molecule 2: Diatrizoic acid
mol = parser.ParseSmiles("CC(=O)NC1=C(C(=C(C(=C1I)C(=O)O)I)NC(=O)C)I");
AtomContainerManipulator.PercieveAtomTypesAndConfigureAtoms(mol);
Aromaticity.CDKLegacy.Apply(mol);
bs = printer.GetBitFingerprint(mol).AsBitSet();
Assert.IsTrue(bs[15]);
Assert.IsTrue(bs[135]);
Assert.IsTrue(bs[139]);
Assert.IsTrue(bs[93]);
Assert.IsTrue(bs[73]);
Assert.IsFalse(bs[91]);
}