Deepchem
Builds molecular property prediction and MoleculeNet workflows with DeepChem, including...
Install
npx skills add K-Dense-AI/scientific-agent-skills --skill deepchem -g -a claude-code -y- Repository
- K-Dense-AI/scientific-agent-skills55.7k
- Category
- Data and ML
- Updated
- 9d ago
- License
- MIT license
- Context cost
- Mediumabout 2,049 tokens
- Runs scripts
- Yes, review before use
What it does
Builds molecular property prediction and MoleculeNet workflows with DeepChem, including SMILES featurization, scaffold or grouped holdouts, masked labels, graph models and explicit pretrained encoder transfer. Used for ADMET, toxicity, solubility and chemistry ML when DeepChem data/model contracts and scientific validation are needed.
DeepChem
When to use
Use for molecular property prediction, SMILES/graph featurization, MoleculeNet benchmarks and explicitly configured encoder transfer. The workflow also covers DeepChem materials and sequence adapters when their data/model contracts are met.
Targets DeepChem 2.8.0, still the stable PyPI release at review. Nightly 2.8.1
builds have additional APIs and different constraints; do not mix latest docs
with a stable installation. The tested CPU stack and optional-backend limitations
are in references/review.md.
Workflow
- Define compound identity, assay conditions, target units and missing labels. Parse SMILES and retain a record of rejected rows. Audit duplicate structures and repeated measurements before splitting.
- Match the representation to the model using the table below. Fit a numeric baseline first; dataset size alone does not select the best architecture.
- Choose a scaffold, temporal or grouped holdout for the deployment question. Preserve exact split IDs, inspect scaffold overlap and per-task class support, and reject empty splits. Scaffold splitting does not eliminate all leakage.
- Fit preprocessing on training data only. Preserve
dataset.wmasks. Normalize continuous targets only, and invert those transforms for metrics/predictions. - Select model settings/epochs on validation data and evaluate the final holdout once. Report per-task support, uncertainty across planned repeats and baseline comparisons. AUC requires both observed classes.
- Predict using the training representation and transforms. Preserve identifiers, original target units and applicability limits. Successful fitting is not evidence of prospective scientific performance.
