Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

T007/22: Switch to fingerpring generator #348

Merged
merged 13 commits into from
May 16, 2023
Merged

T007/22: Switch to fingerpring generator #348

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
13 commits
Select commit Hold shift + click to select a range
520e4fd
update to using fingerprint generator
greglandrum Apr 19, 2023
9829654
Start branch
hamzaibrahim21 May 4, 2023
0cb803a
switch to fp generator
hamzaibrahim21 May 4, 2023
5be358d
Add 07 and 22 only
hamzaibrahim21 May 11, 2023
ece48b5
Revert "Add 07 and 22 only"
hamzaibrahim21 May 11, 2023
62bdf97
add 07 and 22 only
hamzaibrahim21 May 11, 2023
9c381fe
merge dev to switch-to-fp
hamzaibrahim21 May 11, 2023
214d659
Reset T004
hamzaibrahim21 May 15, 2023
8c788fa
Merge branch 'switch-fp-generator' into dev/switch_to_fpgenerators
dominiquesydow May 15, 2023
6cd3519
Merge pull request #330 from greglandrum/dev/switch_to_fpgenerators
dominiquesydow May 15, 2023
07cc9b7
Merge branch 'dev' into switch-fp-generator
dominiquesydow May 15, 2023
db84ea1
Merge branch 'dev' into switch-fp-generator
dominiquesydow May 15, 2023
01057e2
black 7, 11, 19, 22, 17
mbackenkoehler May 16, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion teachopencadd/talktorials/T004_compound_similarity/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,7 +54,7 @@ In this talktorial, we get familiar with different approaches to encode (descrip

### References

* Review on "Molecular similarity in medicinal chemistry" ([<i>J. Med. Chem.</i> (2014), <b>57</b>, 3186-3204](https://pubmed.ncbi.nlm.nih.gov/24151987/))
* Review on "Molecular similarity in medicinal chemistry" ([<i>J. Med. Chem.</i> (2014), <b>57</b>, 3186-3204](https://pubmed.ncbi.nlm.nih.gov/24151987))
* [Morgan fingerprints](http://www.rdkit.org/docs/GettingStartedInPython.html#morgan-fingerprints-circular-fingerprints) with `rdkit`
* Description of the extended-connectivity fingerprint ECFP ([<i>J. Chem. Inf. Model.</i> (2010), <b>50</b>,742-754](https://pubs.acs.org/doi/abs/10.1021/ci100050t))
* What is the chemical space?
Expand Down
5,625 changes: 2,827 additions & 2,798 deletions teachopencadd/talktorials/T004_compound_similarity/talktorial.ipynb
View file
Open in desktop

Large diffs are not rendered by default.

43 changes: 22 additions & 21 deletions teachopencadd/talktorials/T007_compound_activity_machine_learning/talktorial.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -210,7 +210,7 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": 32,
"metadata": {},
"outputs": [],
"source": [
Expand All @@ -228,8 +228,7 @@
"from sklearn.metrics import roc_curve, roc_auc_score\n",
"import matplotlib.pyplot as plt\n",
"from rdkit import Chem\n",
"from rdkit.Chem import MACCSkeys\n",
"from rdkit.Chem.AllChem import GetMorganFingerprintAsBitVect\n",
"from rdkit.Chem import MACCSkeys, rdFingerprintGenerator\n",
"\n",
"from teachopencadd.utils import seed_everything\n",
"\n",
Expand All @@ -242,7 +241,7 @@
},
{
"cell_type": "code",
"execution_count": 2,
"execution_count": 33,
"metadata": {},
"outputs": [],
"source": [
Expand All @@ -266,7 +265,7 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": 34,
"metadata": {},
"outputs": [
{
Expand Down Expand Up @@ -380,8 +379,8 @@
"</div>"
],
"text/plain": [
" molecule_chembl_id IC50 units smiles \n",
"0 CHEMBL63786 0.003 nM Brc1cccc(Nc2ncnc3cc4ccccc4cc23)c1 \\\n",
" molecule_chembl_id IC50 units smiles \\\n",
"0 CHEMBL63786 0.003 nM Brc1cccc(Nc2ncnc3cc4ccccc4cc23)c1 \n",
"1 CHEMBL35820 0.006 nM CCOc1cc2ncnc(Nc3cccc(Br)c3)c2cc1OCC \n",
"2 CHEMBL53711 0.006 nM CN(C)c1cc2c(Nc3cccc(Br)c3)ncnc2cn1 \n",
"3 CHEMBL66031 0.008 nM Brc1cccc(Nc2ncnc3cc4[nH]cnc4cc23)c1 \n",
Expand All @@ -395,7 +394,7 @@
"4 11.096910 329.027607 5 2 3.5726 True "
]
},
"execution_count": 3,
"execution_count": 34,
"metadata": {},
"output_type": "execute_result"
}
Expand All @@ -415,7 +414,7 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": 35,
"metadata": {},
"outputs": [
{
Expand Down Expand Up @@ -488,7 +487,7 @@
"4 CHEMBL53753 CNc1cc2c(Nc3cccc(Br)c3)ncnc2cn1 11.096910"
]
},
"execution_count": 4,
"execution_count": 35,
"metadata": {},
"output_type": "execute_result"
}
Expand Down Expand Up @@ -523,7 +522,7 @@
},
{
"cell_type": "code",
"execution_count": 5,
"execution_count": 36,
"metadata": {},
"outputs": [
{
Expand All @@ -549,7 +548,7 @@
},
{
"cell_type": "code",
"execution_count": 6,
"execution_count": 37,
"metadata": {},
"outputs": [
{
Expand Down Expand Up @@ -628,7 +627,7 @@
"4 CHEMBL53753 CNc1cc2c(Nc3cccc(Br)c3)ncnc2cn1 11.096910 1.0"
]
},
"execution_count": 6,
"execution_count": 37,
"metadata": {},
"output_type": "execute_result"
}
Expand All @@ -653,7 +652,7 @@
},
{
"cell_type": "code",
"execution_count": 7,
"execution_count": 38,
"metadata": {},
"outputs": [],
"source": [
Expand Down Expand Up @@ -685,9 +684,11 @@
" if method == \"maccs\":\n",
" return np.array(MACCSkeys.GenMACCSKeys(mol))\n",
" if method == \"morgan2\":\n",
" return np.array(GetMorganFingerprintAsBitVect(mol, 2, nBits=n_bits))\n",
" fpg = rdFingerprintGenerator.GetMorganGenerator(radius=2, fpSize=n_bits)\n",
" return np.array(fpg.GetCountFingerprint(mol))\n",
" if method == \"morgan3\":\n",
" return np.array(GetMorganFingerprintAsBitVect(mol, 3, nBits=n_bits))\n",
" fpg = rdFingerprintGenerator.GetMorganGenerator(radius=3, fpSize=n_bits)\n",
" return np.array(fpg.GetCountFingerprint(mol))\n",
" else:\n",
" # NBVAL_CHECK_OUTPUT\n",
" print(f\"Warning: Wrong method specified: {method}. Default will be used instead.\")\n",
Expand All @@ -696,7 +697,7 @@
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": 39,
"metadata": {},
"outputs": [],
"source": [
Expand All @@ -705,7 +706,7 @@
},
{
"cell_type": "code",
"execution_count": 9,
"execution_count": 40,
"metadata": {},
"outputs": [
{
Expand Down Expand Up @@ -766,8 +767,8 @@
"</div>"
],
"text/plain": [
" molecule_chembl_id smiles pIC50 active \n",
"0 CHEMBL63786 Brc1cccc(Nc2ncnc3cc4ccccc4cc23)c1 11.522879 1.0 \\\n",
" molecule_chembl_id smiles pIC50 active \\\n",
"0 CHEMBL63786 Brc1cccc(Nc2ncnc3cc4ccccc4cc23)c1 11.522879 1.0 \n",
"1 CHEMBL35820 CCOc1cc2ncnc(Nc3cccc(Br)c3)c2cc1OCC 11.221849 1.0 \n",
"2 CHEMBL53711 CN(C)c1cc2c(Nc3cccc(Br)c3)ncnc2cn1 11.221849 1.0 \n",
"\n",
Expand All @@ -777,7 +778,7 @@
"2 [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ... "
]
},
"execution_count": 9,
"execution_count": 40,
"metadata": {},
"output_type": "execute_result"
}
Expand Down
2 changes: 1 addition & 1 deletion teachopencadd/talktorials/T011_query_online_api_webservices/talktorial.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1418,7 +1418,7 @@
}
],
"source": [
"client.Information.get_kinase_names?"
"?client.Information.get_kinase_names"
]
},
{
Expand Down
2 changes: 1 addition & 1 deletion teachopencadd/talktorials/T017_advanced_nglview_usage/talktorial.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1476,7 +1476,7 @@
}
],
"source": [
"view.shape.add_sphere?"
"?view.shape.add_sphere"
]
},
{
Expand Down
7 changes: 6 additions & 1 deletion teachopencadd/talktorials/T019_md_simulation/talktorial.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -292,8 +292,10 @@
"source": [
"try:\n",
" import google.colab\n",
"\n",
" !pip install condacolab\n",
" import condacolab\n",
"\n",
" condacolab.install()\n",
"except ModuleNotFoundError:\n",
" pass"
Expand All @@ -315,14 +317,16 @@
" import condacolab\n",
" from google.colab import files\n",
" from IPython.display import clear_output\n",
"\n",
" condacolab.check()\n",
" !conda install -q -y -c conda-forge mdtraj openmm openmmforcefields openff-toolkit pdbfixer pypdb rdkit\n",
"except ModuleNotFoundError:\n",
" on_colab = False\n",
"else:\n",
" #check if installation was succesful\n",
" # check if installation was succesful\n",
" try:\n",
" import rdkit\n",
"\n",
" on_colab = True\n",
" clear_output() # clear the excessive installation outputs\n",
" print(\"Dependencies successfully installed!\")\n",
Expand Down Expand Up @@ -352,6 +356,7 @@
],
"source": [
"import sys\n",
"\n",
"if not on_colab and sys.platform.startswith((\"linux\", \"darwin\")):\n",
" !mamba install -q -y -c conda-forge openmmforcefields\n",
" # Notes:\n",
Expand Down
13 changes: 7 additions & 6 deletions teachopencadd/talktorials/T022_ligand_based_screening_neural_network/talktorial.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -362,7 +362,7 @@
},
{
"cell_type": "code",
"execution_count": 1,
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
Expand All @@ -375,8 +375,7 @@
"import pandas as pd\n",
"import numpy as np\n",
"from rdkit import Chem\n",
"from rdkit.Chem import MACCSkeys, Draw\n",
"from rdkit.Chem.AllChem import GetMorganFingerprintAsBitVect\n",
"from rdkit.Chem import MACCSkeys, Draw, rdFingerprintGenerator\n",
"from sklearn.model_selection import train_test_split\n",
"import matplotlib.pyplot as plt\n",
"from sklearn import metrics\n",
Expand Down Expand Up @@ -690,9 +689,11 @@
" if method == \"maccs\":\n",
" return np.array(MACCSkeys.GenMACCSKeys(mol))\n",
" if method == \"morgan2\":\n",
" return np.array(GetMorganFingerprintAsBitVect(mol, 2, nBits=n_bits))\n",
" fpg = rdFingerprintGenerator.GetMorganGenerator(radius=2, fpSize=n_bits)\n",
" return np.array(fpg.GetCountFingerprint(mol))\n",
" if method == \"morgan3\":\n",
" return np.array(GetMorganFingerprintAsBitVect(mol, 3, nBits=n_bits))\n",
" fpg = rdFingerprintGenerator.GetMorganGenerator(radius=3, fpSize=n_bits)\n",
" return np.array(fpg.GetCountFingerprint(mol))\n",
" else:\n",
" print(f\"Warning: Wrong method specified: {method}.\" \" Default will be used instead.\")\n",
" return np.array(MACCSkeys.GenMACCSKeys(mol))"
Expand Down Expand Up @@ -1921,7 +1922,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.16"
"version": "3.7.8"
},
"toc-autonumbering": true,
"widgets": {
Expand Down