agentsclimarketplace

Rdkit scaffold analysis starter

Skill ma-compbio-lab/SkillFoundry/skills/drug-discovery-and-cheminformatics/rdkit-scaffold-analysis-starter

A framework for discovering, compiling, and validating reusable skills for scientific agents.

Install
npx -y skills add ma-compbio-lab/SkillFoundry --skill rdkit-scaffold-analysis-starter

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

What its author says it does

Copied from the file, not written here

Use this skill to compute Murcko scaffold summaries for a small local molecule set with RDKit. Prefer it for deterministic scaffold grouping and smoke-scale cheminformatics checks.

SKILL.md

2.3 KB, 502 tokens by cl100k_base, as published. Nobody here has run it

Purpose

Analyze a small local TSV of SMILES strings with RDKit Murcko scaffolds and emit a compact JSON summary that can feed later smoke integration or scaffold triage workflows.

When to use

  • You need a local scaffold grouping summary for a small curated molecule set.
  • You want canonical SMILES, Murcko scaffolds, generic scaffolds, and group counts from one deterministic run.

When not to use

  • You need large library clustering, matched molecular pair analysis, or SAR interpretation.
  • You need remote compound lookup or medicinal-chemistry recommendations.

Inputs

  • A TSV file with columns name and smiles
  • Optional JSON output path

Outputs

  • JSON with per-molecule canonical SMILES, Murcko scaffold, generic scaffold, scaffold groups, generic scaffold groups, and summary counts

Requirements

  • slurm/envs/chem-tools/bin/python
  • RDKit available in that environment

Procedure

  1. Inspect examples/molecules.tsv.
  2. Run slurm/envs/chem-tools/bin/python skills/drug-discovery-and-cheminformatics/rdkit-scaffold-analysis-starter/scripts/run_rdkit_scaffold_analysis.py --input skills/drug-discovery-and-cheminformatics/rdkit-scaffold-analysis-starter/examples/molecules.tsv.
  3. Review molecules, scaffold_groups, and summary.

Validation

  • The bundled example returns at least one scaffold group with count >= 2.
  • Invalid SMILES input returns a non-zero exit code with a clear error message.

Failure modes and fixes

  • Invalid SMILES: fix the offending row in the input TSV.
  • Missing RDKit environment: rerun with slurm/envs/chem-tools/bin/python.
  • Missing name or smiles columns: use a header row with exactly those field names.

Safety and limits

  • Local scaffold computation only.
  • No medicinal-chemistry conclusions are implied by the grouping.

Provenance

Related skills

  • rdkit-molecular-descriptors
  • rdkit-molecule-standardization

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.