deepchem
Molecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization options and MoleculeNet benchmarks. Best for quick experiments with pre-trained models, diverse molecular representations. For graph-first PyTorch workflows use torchdrug; for benchmark datasets use pytdc.
npx skills add majiayu000/claude-skill-registry --skill deepchem-hxk622-tokendance --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
DeepChem skill enables molecular machine learning workflows, including loading molecular data (SMILES, SDF, FASTA), converting to ML-ready features, and training models across traditional ML, deep learning, and graph neural networks. It includes support for MoleculeNet benchmarks, transfer learning with pretrained models, and evaluation/prediction workflows.
How it works
- Provides data loading options via loaders (CSVLoader, SDFLoader, FASTALoader, ImageLoader, JsonLoader) and featurizers (e.g., CircularFingerprint, RDKitDescriptors, MolGraphConvFeaturizer).
- Guides featurization decisions based on model type (graph neural networks use graph featurizers; traditional ML use fingerprints/descriptors; sequence models use sequence-featurizers).
- Demonstrates data splitting strategies (ScaffoldSplitter, ButinaSplitter, MaxMinSplitter, RandomSplitter, RandomStratifiedSplitter) with ScaffoldSplitter emphasized for molecules to prevent data leakage.
- Shows model selection and training examples for traditional ML (RandomForest), deep learning (MultitaskRegressor), and graph neural networks (GCNModel, GATModel, AttentiveFPModel).
- Includes workflows for MoleculeNet benchmarks, transfer learning (ChemBERTa, GROVER), and evaluation/prediction patterns.
- Provides example scripts for solubility prediction, graph neural networks, and transfer learning in the scripts/ directory.
When to use it
- When loading and processing molecular data (SMILES, SDF, protein sequences)
- When predicting molecular properties (solubility, toxicity, ADMET) or pursuing drug discovery tasks
- When working with MoleculeNet benchmark datasets or transferring pretrained model knowledge to new data
- When choosing between graph-based vs traditional featurization approaches and needing a practical workflow with scaffold-aware splitting
What it can touch
- Tools: code_execute
- Files and code examples include imports and pipelines from DeepChem (e.g., dc.feat, dc.data, dc.models, dc.molnet, dc.metrics, dc.splits, dc.trans, dc.trans normalization, and pretrained model classes like HuggingFaceModel, GroverModel)
Caveats
- License: MIT
- Requires alignment with DeepChem APIs and corresponding dependencies; examples assume availability of datasets and pretrained models as shown
- Some configurations depend on dataset size and model type (e.g., GNNs may require larger datasets and longer training)
# DeepChem ## Overview DeepChem is a comprehensive Python library for applying machine learning to chemistry, materials science, and biology. Enable molecular property prediction, drug discovery, materials design, and biomolecule analysis through specialized neural networks, molecular featurization methods, and pretrained models. ## When to Use This Skill This skill should be used when: - Loading and processing molecular data (SMILES strings, SDF files, protein sequences) - Predicting molecular properties (solubility, toxicity, binding affinity, ADMET properties) - Training models on chemical/biological datasets - Using MoleculeNet benchmark datasets (Tox21, BBBP, Delaney, etc.) - Converting molecules to ML-ready features (fingerprints, graph representations, descriptors) - Implementing graph neural networks for molecules (GCN, GAT, MPNN, AttentiveFP) - Applying transfer learning with pretrained models (ChemBERTa, GROVER, MolFormer) - Predicting crystal/materials properties (bandgap, formation energy) - Analyzing protein or DNA sequences ## Core Capabilities ### 1. Molecular Data Loading and Processing DeepChem provides specialized loaders for various chemical data formats: ```pyth
- Overview
- When to Use This Skill
- Core Capabilities
- 1. Molecular Data Loading and Processing
- 2. Molecular Featurization
- 3. Data Splitting
- 4. Model Selection and Training
- 5. MoleculeNet Benchmarks
- 6. Transfer Learning
- 7. Model Evaluation
- 8. Making Predictions
- Typical Workflows
- Workflow A: Quick Benchmark Evaluation
- Workflow B: Custom Data Prediction
Use Delaney benchmark python scripts/predict_solubility.py Use custom data python scripts/predict_solubility.py \ Train GCN on Tox21 python scripts/graph_neural_network.py --model gcn --dataset tox21 Train AttentiveFP on custom data python scripts/graph_neural_network.py \ Fine-tune ChemBERTa on BBBP python scripts/transfer_learning.py --model chemberta --dataset bbbp
What does the deepchem skill do?
Molecular ML with diverse featurizers and pre-built datasets. Use for property prediction (ADMET, toxicity) with traditional ML or GNNs when you want extensive featurization options and MoleculeNet benchmarks. Best for quick experiments with pre-trained models, diverse molecular representations. For graph-first PyTorch workflows use torchdrug; for benchmark datasets use pytdc.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill deepchem-hxk622-tokendance --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.