datamol
Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including 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.
npx skills add majiayu000/claude-skill-registry --skill datamol-k-dense-ai-scientific-agent-ski-2 --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 provides a Pythonic wrapper around RDKit for tasks like SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, and cloud I/O support via fsspec. It returns native rdkit.Chem.Mol objects and aims to simplify standard cheminformatics workflows with sensible defaults and parallelization.
How it works
The skill exposes workflows and code examples to: create molecules from SMILES, convert between formats (SMILES, InChI, etc.), sanitize and standardize molecules, read and write molecular files (SDF, SMILES, CSV, Excel) with a universal reader/writer (dm.open_df, dm.save_df), and optionally use cloud storage paths via fsspec. It includes modules for descriptors, fingerprints (e.g., DM defaults to ECFP6), clustering (Butina), diversity selection, scaffold analysis, BRICS/RECAP fragmentation, 3D conformer generation and clustering, SASA calculations, visualization helpers, and applying chemical reactions via RDKit. It also documents parallelization through n_jobs and notes which functions support it (e.g., read_sdf, batch descriptor computation, clustering, pdist, conformers.sasa).
Key concrete operations include:
- Creating mol objects: dm.to_mol("CCO")
- Converting formats: dm.to_smiles(mol), dm.to_inchi(mol), dm.to_selfies(mol)
- Standardization: dm.standardize_mol(mol, disconnect_metals=True, normalize=True, reionize=True)
- Reading/writing: dm.read_sdf(...), dm.read_csv(...), dm.to_sdf(...), dm.to_smi(...), dm.to_xlsx(...)
- Descriptors: dm.descriptors.compute_many_descriptors(mol), dm.descriptors.batch_compute_many_descriptors(..., n_jobs=-1)
- Fingerprints: dm.to_fp(mol, fp_type='ecfp', radius=2, n_bits=2048)
- Clustering/diversity: dm.cluster_mols(...), dm.pick_diverse(...)
- Scaffolds/fragments: dm.to_scaffold_murcko(mol), dm.fragment.brics(mol), dm.fragment.recap(mol)
- 3D conformers: dm.conformers.generate(...), dm.conformers.cluster(...), dm.conformers.sasa(...)
- Visualization: dm.viz.to_image(...), dm.viz.conformers(...)
- Reactions: uses rdChemReactions to apply SMARTS-based reactions via dm.reactions.apply_reaction
When to use it
Use when performing standard drug-discovery cheminformatics tasks that can be expressed via the wrappers provided, especially if you want native RDKit Mol objects and parallelized batch operations. Cloud I/O can be used if remote paths are explicitly required.
What it can touch
- Functions and objects under the datamol namespace (e.g., dm.to_mol, dm.read_sdf, dm.descriptors, dm.cluster_mols, dm.viz, dm.reactions).
- External tools referenced by the library (RDKit via datamol dependency, fsspec for cloud I/O, and optional packages like s3fs/gcsfs if cloud paths are used).
Caveats
- Requires Python 3.8+ and datamol; RDKit is installed automatically as a datamol dependency (since 0.12.2).
- Cloud I/O via fsspec may require s3fs or gcsfs backend packages when using remote paths.
- Examples note that lazy-loading behavior and specific version details may apply (e.g., datamol 0.12.x specifics), and some features are dependent on Datamol defaults.
# 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. **Version note:** Examples target **datamol 0.12.x** (PyPI stable: **0.12.5**, June 2024). Since 0.10.0, modules are lazy-loaded by default (set `DATAMOL_DISABLE_LAZY_LOADING=1` to disable). Since 0.12.2, RDKit is a direct PyPI dependency of datamol. Fingerprints use RDKit's `rdFingerprintGenerator` API (0.12.5+). **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 uv pip
- 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
uv pip install datamol uv pip install s3fs # AWS S3 uv pip install gcsfs # Google Cloud Storage
What does the datamol skill do?
Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including 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 datamol-k-dense-ai-scientific-agent-ski-2 --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.