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.
8.3
Rating
0
Installs
Machine Learning
Category
Exceptional skill for molecular machine learning with DeepChem. The description is crystal clear about when to use this skill vs alternatives (torchdrug, pytdc). SKILL.md provides comprehensive coverage with decision trees for featurizer/model selection, critical warnings about scaffold splitting for drug discovery, and clear guidance scaling from simple to complex approaches. Three production-ready scripts cover solubility prediction, GNNs, and transfer learning. Structure is excellent with concise overview in SKILL.md and detailed references separated into api_reference.md and workflows.md. The skill addresses a highly specialized domain (molecular ML with 30+ featurizers, 50+ models, MoleculeNet benchmarks) that would require a CLI agent extensive domain knowledge and many tokens to replicate. Minor deduction in taskKnowledge for assuming some external dependency knowledge, but referenced files are comprehensive. Very high novelty score due to specialized chemistry/ML intersection and extensive pre-built capabilities.
K-Dense-AI
Skill Author
Loading SKILL.md…
