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.
K-Dense-AI · 已有 AI 审核记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add K-Dense-AI/scientific-agent-skills --skill deepchem技能说明
name: deepchem description: 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. license: MIT license allowed-tools: Read Write Edit Bash compatibility: Requires Python 3.7–3.11 (PyPI 2.8.0 caps at <3.12). Install PyTorch, TensorFlow, or JAX before the matching deepchem extra. RDKit is a core dependency. metadata: version: "1.5" skill-author: K-Dense Inc.
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.
Version note: Examples target deepchem 2.8.0 (PyPI stable, Apr 2024). Requires Python 3.7–3.11 (<3.12 on PyPI). Core utilities (loaders, featurizers, MoleculeNet) work without a DL backend; GNN and transformer models need the matching extra (torch, tensorflow, or jax). Install the backend framework first when using GPU builds.
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
Eight capability areas, each with worked code, are in references/core_capabilities.md:
- Molecular data loading and processing — loaders,
NumpyDataset/DiskDataset. - Molecular featurization — circular fingerprints, graph convolution, and descriptors.
- Data splitting — random, scaffold, stratified, and butina splitters, and why scaffold splitting is the honest default for molecules.
- Model selection and training — the model families and how to fit them.
- MoleculeNet benchmarks — loading standard datasets and their published splits.
- Transfer learning — pretraining and fine-tuning.
- Model evaluation — metrics appropriate to regression and classification tasks.
- Making predictions — applying a trained model to new molecules.
Three end-to-end workflows are in references/typical_workflows.md.
Example Scripts
This skill includes three production-ready scripts in the scripts/ directory:
1. predict_solubility.py
Train and evaluate solubility prediction models. Works with Delaney benchmark or custom CSV data.
# Use Delaney benchmark
python scripts/predict_solubility.py
# Use custom data
python scripts/predict_solubility.py \
--data my_data.csv \
--smiles-col smiles \
--target-col solubility \
--predict "CCO" "c1ccccc1"
2. graph_neural_network.py
Train various graph neural network architectures on molecular data.
# 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 \
--model attentivefp \
--data molecules.csv \
--task-type regression \
--targets activity \
--epochs 100
3. transfer_learning.py
Fine-tune pretrained models (ChemBERTa, GROVER, MolFormer) on molecular property prediction tasks.
# Fine-tune ChemBERTa on BBBP
python scripts/transfer_learning.py --model chemberta --dataset bbbp
# Fine-tune GROVER on custom data
python scripts/transfer_learning.py \
--model grover \
--data small_dataset.csv \
--target activity \
--task-type classification \
--epochs 20
Common Patterns and Best Practices
Pattern 1: Always Use Scaffold Splitting for Molecules
# GOOD: Prevents data leakage
splitter = dc.splits.ScaffoldSplitter()
train, test = splitter.train_test_split(dataset)
# BAD: Similar molecules in train and test
splitter = dc.splits.RandomSplitter()
train, test = splitter.train_test_split(dataset)
Pattern 2: Normalize Features and Targets
transformers = [
dc.trans.NormalizationTransformer(
transform_y=True, # Also normalize target values
dataset=train
)
]
for transformer in transformers:
train = transformer.transform(train)
test = transformer.transform(test)
Pattern 3: Start Simple, Then Scale
- Start with Random Forest + CircularFingerprint (fast baseline)
- Try XGBoost/LightGBM if RF works well
- Move to deep learning (MultitaskRegressor) if you have >5K samples
- Try GNNs if you have >10K samples
- Use transfer learning for small datasets or novel scaffolds
Pattern 4: Handle Imbalanced Data
# Option 1: Balancing transformer
transformer = dc.trans.BalancingTransformer(dataset=train)
train = transformer.transform(train)
# Option 2: Use balanced metrics
metric = dc.metrics.Metric(dc.metrics.balanced_accuracy_score)
Pattern 5: Avoid Memory Issues
# Use DiskDataset for large datasets
dataset = dc.data.DiskDataset.from_numpy(X, y, w, ids)
# Use smaller batch sizes
model = dc.models.GCNModel(batch_size=32) # Instead of 128
Common Pitfalls
Issue 1: Data Leakage in Drug Discovery
Problem: Using random splitting allows similar mo
阅读完整来源 ↗