Skip to content

Ligand graph fix #39

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

Open
t-kimber wants to merge 6 commits into
base: master
Choose a base branch
from
Open

Ligand graph fix #39

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
20cb432
update ligand experiments.
t-kimber Sep 2, 2021
2308bea
update generated notebooks.
t-kimber Sep 2, 2021
99dc690
resolve conflicts from master.
t-kimber Sep 2, 2021
f0a4c42
test graph experiment
t-kimber Sep 2, 2021
20629b4
test for ligand graph training (failing).
t-kimber Sep 10, 2021
4034009
add EGFR subsample scripts for graph.
t-kimber Sep 10, 2021
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
4 changes: 2 additions & 2 deletions ...s/001_example-ligand-only-graph-subset.py → ..._example-ligand-only-graph-EGFR-subset.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@

# DATA -- Glob paths must be relative to the root of the repository: REPO / features
PARQUET_FILES = [
"ligand-only-graph-subsample/_output/ligand__SmilesToLigandFeaturizer__GraphLigandFeaturizer/ChEMBLDatasetProvider/*.parquet",
"ligand-only-graph-EGFR-subsample/_output/ligand__SmilesToLigandFeaturizer__GraphLigandFeaturizer/ChEMBLDatasetProvider/*.parquet",
]

# Model -- specified with the full import path to the class object
Expand Down Expand Up @@ -38,4 +38,4 @@
BOOTSTRAP_SAMPLE_RATIO = 1

# Output
VERBOSE = False
VERBOSE = False
8 changes: 2 additions & 6 deletions features/ligand-only-graph-subsample.py → features/ligand-only-graph-EGFR-subsample.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@

DATASET_CLS = "kinoml.datasets.chembl.ChEMBLDatasetProvider"
DATASET_KWARGS = {
"path_or_url": "https://github.com/openkinome/kinodata/releases/download/v0.2/activities-chembl28-sample100_v0.2.zip",
"path_or_url": "https://github.com/openkinome/kinodata/releases/download/v0.3/EGFR-activities-chembl29-sample.zip",
}

PIPELINES = {
Expand All @@ -24,14 +24,10 @@
FEATURIZE_KWARGS = {"keep": False}

GROUPS = [
[
"kinoml.datasets.groups.CallableGrouper",
{"function": "lambda measurement: measurement.system.protein.name"},
], # by kinase
[
"kinoml.datasets.groups.CallableGrouper",
{"function": "lambda measurement: type(measurement).__name__"},
], # by measurement type
]

TRAIN_TEST_VAL_KWARGS = {"idx_train": 0.8, "idx_test": 0.1, "idx_val": 0.1}
TRAIN_TEST_VAL_KWARGS = {"idx_train": 0.8, "idx_test": 0.1, "idx_val": 0.1}
9 changes: 6 additions & 3 deletions tests/experiments/test_model_ligand_only.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,8 +6,11 @@ echo "Models"

echo "Ligand only"

echo "Running model for '001_example-ligand-only-morgan1024-EGFR-subset'"
python run_notebook.py experiments/torch-train-test-debug-template.ipynb experiments/001_example-ligand-only-morgan1024-EGFR-subset.py --overwrite
echo "Running model for '001_example-ligand-only-graph-EGFR-subset'"
python run_notebook.py experiments/torch-train-test-debug-template.ipynb experiments/001_example-ligand-only-graph-EGFR-subset.py --overwrite

# echo "Running model for '001_example-ligand-only-morgan1024-EGFR-subset'"
# python run_notebook.py experiments/torch-train-test-debug-template.ipynb experiments/001_example-ligand-only-morgan1024-EGFR-subset.py --overwrite

# These won't run because there are not enough data points for each kinase on the sample data.

Expand All @@ -18,4 +21,4 @@ python run_notebook.py experiments/torch-train-test-debug-template.ipynb experim
# python run_notebook.py experiments/torch-train-test-debug-template.ipynb experiments/001_example-ligand-only-smiles-subset.py --overwrite

# echo "Running model for '001_example-ligand-only-graph-subset'"
# python run_notebook.py experiments/torch-train-test-debug-template.ipynb experiments/001_example-ligand-only-graph-subset.py --overwrite
# python run_notebook.py experiments/torch-train-test-debug-template.ipynb experiments/001_example-ligand-only-graph-subset.py --overwrite
11 changes: 5 additions & 6 deletions tests/features/test_featurization_ligand_only.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,14 +7,13 @@ echo "Featurization"
echo "Ligand only"

echo "Running featurization for 'ligand-only-morgan1024-EGFR-subsample'"
python run_notebook.py features/featurize-template.ipynb features/ligand-only-morgan1024-EGFR-subsample.py --overwrite
# python run_notebook.py features/featurize-template.ipynb features/ligand-only-morgan1024-EGFR-subsample.py --overwrite

echo "Running featurization for 'ligand-only-morgan1024-subsample'"
python run_notebook.py features/featurize-template.ipynb features/ligand-only-morgan1024-subsample.py --overwrite
# python run_notebook.py features/featurize-template.ipynb features/ligand-only-morgan1024-subsample.py --overwrite

echo "Running featurization for 'ligand-only-onehotsmiles-subsample'"
python run_notebook.py features/featurize-template.ipynb features/ligand-only-onehotsmiles-subsample.py --overwrite

echo "Running featurization for 'ligand-only-graph-subsample'"
python run_notebook.py features/featurize-template.ipynb features/ligand-only-graph-subsample.py --overwrite
# python run_notebook.py features/featurize-template.ipynb features/ligand-only-onehotsmiles-subsample.py --overwrite

echo "Running featurization for 'ligand-only-graph-EGFR-subsample'"
python run_notebook.py features/featurize-template.ipynb features/ligand-only-graph-EGFR-subsample.py --overwrite