Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →mkurman/deepchem
Molecular ML with diverse featurizers and pre-built datasets.
Passed 22 of 22 test cases with the skill, and 12 of 22 without it.
and 11 more in the full report
10 fixed12 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
My Graph Convolutional Network model trained on 600 molecules for 5 epochs is performing worse than a basic Random Forest baseline. What are two changes to training parameters or dataset scale to address GNN underperformance?
| Checked | Without skill | With skill |
|---|---|---|
| Recommends increasing training epochs to between 50 and 100. | Missed | Passed |
| Notes that GNNs generally perform best on larger datasets exceeding 10,000 samples. | Missed | Passed |
The instructions your model reads when the skill loads.
-------|------|-------------------|------------| | < 1K samples | Any | SklearnModel (RandomForest) | CircularFingerprint | | 1K-100K | Classification/Regression | GBDTModel or MultitaskRegressor | CircularFingerprint | | > 100K | Molecular properties | GCNModel, AttentiveFPModel, DMPNNModel | MolGraphConvFeaturizer | | Any (small preferred) | Transfer learning | ChemBERTa, GROVER, MolFormer | Model-specific | | Crystal structures | Materials properties | CGCNNModel, MEGNetModel | Structure-based | | Protein sequences | Protein properties | ProtBERT | Sequence-based |
from sklearn.ensemble import RandomForestRegressor
# Wrap scikit-learn model
sklearn_model = RandomForestRegressor(n_estimators=100)
model = dc.models.SklearnModel(model=sklearn_model)
model.fit(train)
# Multitask regressor (for fingerprints)
model = dc.models.MultitaskRegressor(
n_tasks=2,
n_features=2048,
layer_sizes=[1000, 500],
dropouts=0.25,
learning_rate=0.001
)
model.fit(train, nb_epoch=50)
# Graph Convolutional Network
model = dc.models.GCNModel(
n_tasks=1,
mode='regression',
batch_size=128,
learning_rate=0.001
)
test cases passed, vs 12 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.