Skip to content

Commit

Permalink
update fingerprint tutorial notebook (rdkit#2130)
Browse files Browse the repository at this point in the history
  • Loading branch information
@greglandrum
greglandrum authored Oct 26, 2018
1 parent 04c1234 commit 70861d5
Showing 1 changed file with 61 additions and 61 deletions.
122 changes: 61 additions & 61 deletions Docs/Notebooks/FingerprintGenerators.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -18,14 +18,14 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{1592354: 1, 574497: 1, 574498: 1, 541731: 1, 590881: 1, 1590402: 1, 590945: 1, 1590401: 2, 1590370: 2, 590882: 1, 1590307: 3, 1590369: 1, 1590306: 3, 1592355: 2}\n"
"{541731: 1, 574497: 1, 574498: 1, 590881: 1, 590882: 1, 590945: 1, 1590306: 3, 1590307: 3, 1590369: 1, 1590370: 2, 1590401: 2, 1590402: 1, 1592354: 1, 1592355: 2}\n"
]
}
],
Expand All @@ -35,10 +35,10 @@
"\n",
"mol = Chem.MolFromSmiles('CC(O)C(O)(O)C')\n",
"generator = rdFingerprintGenerator.GetAtomPairGenerator()\n",
"fingerprint = generator.GetFingerprint(mol)\n",
"fingerprint = generator.GetSparseCountFingerprint(mol)\n",
"non_zero = fingerprint.GetNonzeroElements()\n",
"\n",
"print non_zero"
"print(non_zero)"
]
},
{
Expand All @@ -50,23 +50,23 @@
},
{
"cell_type": "code",
"execution_count": 2,
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{1592354: 1, 574497: 1, 574498: 1, 590882: 1, 590881: 1, 1590402: 1, 590945: 1, 1590401: 2, 1590370: 2, 1590306: 3, 1590369: 1}\n"
"{574497: 1, 574498: 1, 590881: 1, 590882: 1, 590945: 1, 1590306: 3, 1590369: 1, 1590370: 2, 1590401: 2, 1590402: 1, 1592354: 1}\n"
]
}
],
"source": [
"generator = rdFingerprintGenerator.GetAtomPairGenerator(minDistance = 1, maxDistance = 2, includeChirality = False)\n",
"fingerprint = generator.GetFingerprint(mol)\n",
"fingerprint = generator.GetSparseCountFingerprint(mol)\n",
"non_zero = fingerprint.GetNonzeroElements()\n",
"\n",
"print non_zero"
"print(non_zero)"
]
},
{
Expand All @@ -78,28 +78,28 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{574497: 1, 574498: 1, 1590370: 2, 1590369: 1, 590945: 1}\n",
"{590881: 1, 590882: 1, 1590306: 2, 1590402: 1, 1590401: 1}\n"
"{574497: 1, 574498: 1, 590945: 1, 1590369: 1, 1590370: 2}\n",
"{590881: 1, 590882: 1, 1590306: 2, 1590401: 1, 1590402: 1}\n"
]
}
],
"source": [
"fingerprint = generator.GetFingerprint(mol, fromAtoms = [1])\n",
"fingerprint = generator.GetSparseCountFingerprint(mol, fromAtoms = [1])\n",
"non_zero = fingerprint.GetNonzeroElements()\n",
"\n",
"print non_zero\n",
"print(non_zero)\n",
"\n",
"fingerprint = generator.GetFingerprint(mol, ignoreAtoms = [1, 5])\n",
"fingerprint = generator.GetSparseCountFingerprint(mol, ignoreAtoms = [1, 5])\n",
"non_zero = fingerprint.GetNonzeroElements()\n",
"\n",
"print non_zero"
"print(non_zero)"
]
},
{
Expand All @@ -113,44 +113,44 @@
},
{
"cell_type": "code",
"execution_count": 5,
"execution_count": 10,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Atom pair {1592354: 1, 574497: 1, 574498: 1, 541731: 1, 590881: 1, 1590402: 1, 590945: 1, 1590401: 2, 1590370: 2, 590882: 1, 1590307: 3, 1590369: 1, 1590306: 3, 1592355: 2}\n",
"Morgan {1741045729: 1, 1542633699: 1, 2246728737: 2, 2245273601: 1, 3537123720: 1, 864662311: 3, 2927183216: 1, 2245277810: 1, 1542631284: 2, 2782665878: 1, 3537119515: 1}\n",
"RDKitFingerprint {1524090560: 6, 2911990635: 1, 1753257252: 1, 2332326087: 1, 4275705116: 3, 1636471275: 3, 4279989780: 2, 398441839: 4, 3743603664: 1, 3977409745: 3, 3768818763: 1, 3083228099: 1, 1606685044: 2, 1940446997: 2, 2880661462: 1, 3473416248: 3, 3060973103: 1, 623990427: 1, 561308092: 2, 4274652475: 3}\n",
"TopologicalTorsion {4303897120: 1, 12893570080: 1, 12893831776: 2, 12893831712: 2}\n"
"Atom pair {541731: 1, 574497: 1, 574498: 1, 590881: 1, 590882: 1, 590945: 1, 1590306: 3, 1590307: 3, 1590369: 1, 1590370: 2, 1590401: 2, 1590402: 1, 1592354: 1, 1592355: 2}\n",
"Morgan {864662311: 3, 1542631284: 2, 1542633699: 1, 1741045729: 1, 2245273601: 1, 2245277810: 1, 2246728737: 2, 2782665878: 1, 2927183216: 1, 3537119515: 1, 3537123720: 1}\n",
"RDKitFingerprint {398441839: 4, 561308092: 2, 623990427: 1, 1524090560: 6, 1606685044: 2, 1636471275: 3, 1753257252: 1, 1940446997: 2, 2332326087: 1, 2880661462: 1, 2911990635: 1, 3060973103: 1, 3083228099: 1, 3473416248: 3, 3743603664: 1, 3768818763: 1, 3977409745: 3, 4274652475: 3, 4275705116: 3, 4279989780: 2}\n",
"TopologicalTorsion {4303897120: 1, 12893570080: 1, 12893831712: 2, 12893831776: 2}\n"
]
}
],
"source": [
"generator = rdFingerprintGenerator.GetAtomPairGenerator()\n",
"fingerprint = generator.GetFingerprint(mol)\n",
"fingerprint = generator.GetSparseCountFingerprint(mol)\n",
"non_zero = fingerprint.GetNonzeroElements()\n",
"\n",
"print \"Atom pair\", non_zero\n",
"print(\"Atom pair\", non_zero)\n",
"\n",
"generator = rdFingerprintGenerator.GetMorganGenerator(radius = 3)\n",
"fingerprint = generator.GetFingerprint(mol)\n",
"fingerprint = generator.GetSparseCountFingerprint(mol)\n",
"non_zero = fingerprint.GetNonzeroElements()\n",
"\n",
"print \"Morgan\", non_zero\n",
"print(\"Morgan\", non_zero)\n",
"\n",
"generator = rdFingerprintGenerator.GetRDKitFPGenerator()\n",
"fingerprint = generator.GetFingerprint(mol)\n",
"fingerprint = generator.GetSparseCountFingerprint(mol)\n",
"non_zero = fingerprint.GetNonzeroElements()\n",
"\n",
"print \"RDKitFingerprint\", non_zero\n",
"print(\"RDKitFingerprint\", non_zero)\n",
"\n",
"generator = rdFingerprintGenerator.GetTopologicalTorsionGenerator()\n",
"fingerprint = generator.GetFingerprint(mol)\n",
"fingerprint = generator.GetSparseCountFingerprint(mol)\n",
"non_zero = fingerprint.GetNonzeroElements()\n",
"\n",
"print \"TopologicalTorsion\", non_zero"
"print(\"TopologicalTorsion\", non_zero)"
]
},
{
Expand All @@ -164,14 +164,14 @@
},
{
"cell_type": "code",
"execution_count": 6,
"execution_count": 11,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"RDKitFingerprint {4275705116: 2, 1940446997: 1}\n",
"RDKitFingerprint {1940446997: 1, 4275705116: 2}\n",
"RDKitFingerprint {578931652: 1, 2298572045: 2}\n"
]
}
Expand All @@ -180,18 +180,18 @@
"simpleMol = Chem.MolFromSmiles('CCC')\n",
"\n",
"generator = rdFingerprintGenerator.GetRDKitFPGenerator()\n",
"fingerprint = generator.GetFingerprint(simpleMol)\n",
"fingerprint = generator.GetSparseCountFingerprint(simpleMol)\n",
"non_zero = fingerprint.GetNonzeroElements()\n",
"\n",
"print \"RDKitFingerprint\", non_zero\n",
"print(\"RDKitFingerprint\", non_zero)\n",
"\n",
"atomInvariantsGen = rdFingerprintGenerator.GetAtomPairAtomInvGen()\n",
"\n",
"generator = rdFingerprintGenerator.GetRDKitFPGenerator(atomInvariantsGenerator = atomInvariantsGen)\n",
"fingerprint = generator.GetFingerprint(simpleMol)\n",
"fingerprint = generator.GetSparseCountFingerprint(simpleMol)\n",
"non_zero = fingerprint.GetNonzeroElements()\n",
"\n",
"print \"RDKitFingerprint\", non_zero"
"print(\"RDKitFingerprint\", non_zero)"
]
},
{
Expand All @@ -203,63 +203,63 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": 12,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Morgan with AtomPairAtomInvGen {33: 2, 35: 1, 36: 1, 3205494725: 1, 2343097318: 1, 97: 3, 523835848: 1, 3205489706: 2, 3205489717: 1, 3205494778: 1, 618975071: 1}\n",
"Morgan with MorganAtomInvGen {1741045729: 1, 1542633699: 1, 2246728737: 2, 2245273601: 1, 3537123720: 1, 864662311: 3, 2927183216: 1, 2245277810: 1, 1542631284: 2, 2782665878: 1, 3537119515: 1}\n",
"Morgan with MorganFeatureAtomInvGen {0: 4, 3: 3, 3208860345: 1, 614176407: 1, 3205496825: 3, 792807483: 1, 3205495869: 2}\n",
"Morgan with RDKitAtomInvGen {12: 4, 2705297134: 1, 16: 3, 165450225: 1, 608338133: 1, 3205493174: 2, 3205492925: 3}\n",
"Morgan with MorganBondInvGen {1741045729: 1, 1542633699: 1, 2246728737: 2, 2245273601: 1, 3537123720: 1, 864662311: 3, 2927183216: 1, 2245277810: 1, 1542631284: 2, 2782665878: 1, 3537119515: 1}\n"
"Morgan with AtomPairAtomInvGen {33: 2, 35: 1, 36: 1, 97: 3, 523835848: 1, 618975071: 1, 2343097318: 1, 3205489706: 2, 3205489717: 1, 3205494725: 1, 3205494778: 1}\n",
"Morgan with MorganAtomInvGen {864662311: 3, 1542631284: 2, 1542633699: 1, 1741045729: 1, 2245273601: 1, 2245277810: 1, 2246728737: 2, 2782665878: 1, 2927183216: 1, 3537119515: 1, 3537123720: 1}\n",
"Morgan with MorganFeatureAtomInvGen {0: 4, 3: 3, 614176407: 1, 792807483: 1, 3205495869: 2, 3205496825: 3, 3208860345: 1}\n",
"Morgan with RDKitAtomInvGen {12: 4, 16: 3, 165450225: 1, 608338133: 1, 2705297134: 1, 3205492925: 3, 3205493174: 2}\n",
"Morgan with MorganBondInvGen {864662311: 3, 1542631284: 2, 1542633699: 1, 1741045729: 1, 2245273601: 1, 2245277810: 1, 2246728737: 2, 2782665878: 1, 2927183216: 1, 3537119515: 1, 3537123720: 1}\n"
]
}
],
"source": [
"atomInvariantsGen = rdFingerprintGenerator.GetAtomPairAtomInvGen()\n",
"\n",
"generator = rdFingerprintGenerator.GetMorganGenerator(radius = 3, atomInvariantsGenerator = atomInvariantsGen)\n",
"fingerprint = generator.GetFingerprint(mol)\n",
"fingerprint = generator.GetSparseCountFingerprint(mol)\n",
"non_zero = fingerprint.GetNonzeroElements()\n",
"\n",
"print \"Morgan with AtomPairAtomInvGen\", non_zero\n",
"print(\"Morgan with AtomPairAtomInvGen\", non_zero)\n",
"\n",
"atomInvariantsGen = rdFingerprintGenerator.GetMorganAtomInvGen()\n",
"\n",
"generator = rdFingerprintGenerator.GetMorganGenerator(radius = 3, atomInvariantsGenerator = atomInvariantsGen)\n",
"fingerprint = generator.GetFingerprint(mol)\n",
"fingerprint = generator.GetSparseCountFingerprint(mol)\n",
"non_zero = fingerprint.GetNonzeroElements()\n",
"\n",
"# Default for Morgan FP\n",
"print \"Morgan with MorganAtomInvGen\", non_zero\n",
"print(\"Morgan with MorganAtomInvGen\", non_zero)\n",
"\n",
"atomInvariantsGen = rdFingerprintGenerator.GetMorganFeatureAtomInvGen()\n",
"\n",
"generator = rdFingerprintGenerator.GetMorganGenerator(radius = 3, atomInvariantsGenerator = atomInvariantsGen)\n",
"fingerprint = generator.GetFingerprint(mol)\n",
"fingerprint = generator.GetSparseCountFingerprint(mol)\n",
"non_zero = fingerprint.GetNonzeroElements()\n",
"\n",
"print \"Morgan with MorganFeatureAtomInvGen\", non_zero\n",
"print(\"Morgan with MorganFeatureAtomInvGen\", non_zero)\n",
"\n",
"atomInvariantsGen = rdFingerprintGenerator.GetRDKitAtomInvGen()\n",
"\n",
"generator = rdFingerprintGenerator.GetMorganGenerator(radius = 3, atomInvariantsGenerator = atomInvariantsGen)\n",
"fingerprint = generator.GetFingerprint(mol)\n",
"fingerprint = generator.GetSparseCountFingerprint(mol)\n",
"non_zero = fingerprint.GetNonzeroElements()\n",
"\n",
"print \"Morgan with RDKitAtomInvGen\", non_zero\n",
"print(\"Morgan with RDKitAtomInvGen\", non_zero)\n",
"\n",
"bondInvariantsGen = rdFingerprintGenerator.GetMorganBondInvGen()\n",
"\n",
"generator = rdFingerprintGenerator.GetMorganGenerator(radius = 3, bondInvariantsGenerator = bondInvariantsGen)\n",
"fingerprint = generator.GetFingerprint(mol)\n",
"fingerprint = generator.GetSparseCountFingerprint(mol)\n",
"non_zero = fingerprint.GetNonzeroElements()\n",
"\n",
"# Default for Morgan FP\n",
"print \"Morgan with MorganBondInvGen\", non_zero"
"print(\"Morgan with MorganBondInvGen\", non_zero)"
]
},
{
Expand All @@ -273,31 +273,31 @@
},
{
"cell_type": "code",
"execution_count": 7,
"execution_count": 13,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{558113: 2, 541730: 1}\n",
"{541730: 1, 558113: 2}\n",
"{16417: 2, 16418: 1}\n"
]
}
],
"source": [
"\n",
"generator = rdFingerprintGenerator.GetAtomPairGenerator()\n",
"fingerprint = generator.GetFingerprint(simpleMol)\n",
"fingerprint = generator.GetSparseCountFingerprint(simpleMol)\n",
"non_zero = fingerprint.GetNonzeroElements()\n",
"\n",
"print non_zero\n",
"print(non_zero)\n",
"\n",
"customAtomInvariants = [1, 1, 1]\n",
"fingerprint = generator.GetFingerprint(simpleMol, customAtomInvariants = customAtomInvariants)\n",
"fingerprint = generator.GetSparseCountFingerprint(simpleMol, customAtomInvariants = customAtomInvariants)\n",
"non_zero = fingerprint.GetNonzeroElements()\n",
"\n",
"print non_zero\n"
"print(non_zero)\n"
]
},
{
Expand All @@ -317,21 +317,21 @@
],
"metadata": {
"kernelspec": {
"display_name": "Python 2",
"display_name": "Python 3",
"language": "python",
"name": "python2"
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 2
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython2",
"version": "2.7.14"
"pygments_lexer": "ipython3",
"version": "3.6.5"
}
},
"nbformat": 4,
Expand Down

0 comments on commit 70861d5

Please sign in to comment.