datamol
Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery: SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters, use rdkit directly.
Profile →npx skills add majiayu000/claude-skill-registry --skill scientific-pkg-datamol --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
Datamol offers a Pythonic interface over RDKit to perform common cheminformatics tasks: convert between molecular representations (SMILES, InChI, SELFIES), sanitize and standardize molecules, compute descriptors and fingerprints, generate 3D conformers, perform clustering and diversity analysis, analyze scaffolds/fragments, apply reactions, visualize molecules, and read/write various file formats with optional cloud support. It emphasizes batch processing and parallelization, returning native rdkit.Chem.Mol objects.
How it works
The skill describes concrete workflows and code examples for:
- Creating molecules from SMILES and converting between representations (dm.to_mol, dm.to_smiles, dm.to_inchi, dm.to_inchikey, dm.to_selfies).
- Standardization and sanitization (dm.sanitize_mol, dm.standardize_mol, dm.standardize_smiles).
- File I/O (dm.read_sdf, dm.read_smi, dm.read_csv, dm.read_excel, dm.open_df; dm.to_sdf, dm.to_smi, dm.to_xlsx).
- Descriptors and batch calculations (dm.descriptors.compute_many_descriptors, dm.descriptors.batch_compute_many_descriptors, dm.descriptors.n_aromatic_atoms, etc.).
- Fingerprints and similarity (dm.to_fp, dm.pdist, dm.cdist, squareform usage).
- Clustering and diversity (dm.cluster_mols, dm.pick_diverse, dm.pick_centroids).
- Scaffold analysis and SAR workflows (dm.to_scaffold_murcko, grouping by scaffold, train/test split by scaffolds).
- Fragmentation (dm.fragment.brics, dm.fragment.recap) and fragment-based scoring.
- 3D conformers (dm.conformers.generate, cluster, sasa) and SASA access.
- Visualization (dm.viz.to_image, dm.viz.conformers) and SAR-aligned visuals.
- Reactions (rdChemReactions usage with dm.reactions.apply_reaction) and batch reaction application. All examples use function names, file names, and tool names exactly as shown in the skill.
When to use it
Use when you need a consolidated, parallelizable workflow for common cheminformatics tasks with RDKit compatibility, especially if you prefer a higher-level API over direct RDKit calls. It is suitable for standard drug-discovery pipelines, descriptor-driven filtering, clustering/diversity selection, scaffold-based analyses, and basic virtual screening workflows.
What it can touch
- Functions and namespaces: dm, datamol as dm, dm.read_sdf, dm.to_sdf, dm.descriptors, dm.cluster_mols, dm.pick_diverse, dm.to_fp, dm.pdist, dm.cdist, dm.conformers, dm.viz, dm.reactions, dm.fragment, dm.to_scaffold_murcko, etc.
- It references external libraries and formats (RDKit Mol objects, SMILES, SDF/CSV/XLSX, conda/pip installations), but the skill itself enumerates touching these APIs through explicit examples and does not introduce new external tools beyond those named.
Caveats
- The skill states that it returns native rdkit.Chem.Mol objects.
- It assumes parallelization via n_jobs with values like -1, 1, 4, and notes that some functions support progress bars.
- It includes cloud storage examples (S3, GCS, HTTP) via dm.read_sdf, dm.to_sdf, dm.open_df, but no licensing or usage caveats beyond standard library and container capabilities are stated.
- No explicit licensing text beyond overall MIT license in the repository metadata; operational usage relies on the underlying Datamol and RDKit licenses.
# Datamol Cheminformatics Skill ## Overview Datamol is a Python library that provides a lightweight, Pythonic abstraction layer over RDKit for molecular cheminformatics. Simplify complex molecular operations with sensible defaults, efficient parallelization, and modern I/O capabilities. All molecular objects are native `rdkit.Chem.Mol` instances, ensuring full compatibility with the RDKit ecosystem. **Key capabilities**: - Molecular format conversion (SMILES, SELFIES, InChI) - Structure standardization and sanitization - Molecular descriptors and fingerprints - 3D conformer generation and analysis - Clustering and diversity selection - Scaffold and fragment analysis - Chemical reaction application - Visualization and alignment - Batch processing with parallelization - Cloud storage support via fsspec ## Installation and Setup Guide users to install datamol: ```bash # Via conda/mamba (recommended) conda install -c conda-forge datamol # Via pip pip install datamol ``` **Import convention**: ```python import datamol as dm ``` ## Core Workflows ### 1. Basic Molecule Handling **Creating molecules from SMILES**: ```python import datamol as dm # Single molecule mol = dm.to_mol("CCO") # Et
- Overview
- Installation and Setup
- Core Workflows
- 1. Basic Molecule Handling
- 2. Reading and Writing Molecular Files
- 3. Molecular Descriptors and Properties
- 4. Molecular Fingerprints and Similarity
- 5. Clustering and Diversity Selection
- 6. Scaffold Analysis
- 7. Molecular Fragmentation
- 8. 3D Conformer Generation
- 9. Visualization
- 10. Chemical Reactions
- Parallelization
Via conda/mamba (recommended) conda install -c conda-forge datamol Via pip pip install datamol
What does the datamol skill do?
Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery: SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters, use rdkit directly.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill scientific-pkg-datamol --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.