SKILL

medchem

K-Dense-AIListed

Primary machine endpointhttps://github.com/K-Dense-AI/scientific-agent-skills/tree/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/medchem

Use with an agent

SUMMARY

What it does

This skill provides medicinal chemistry filters for compound triage. It applies drug-likeness rules (Lipinski, Veber, CNS), structural alert catalogs (PAINS, NIBR, ChEMBL), complexity metrics, and a medchem query language for library filtering. The skill is based on the medchem Python library (version 2.0.5) and requires Python 3.9+ and datamol. It supports batch filtering with parallelization and returns pandas DataFrames for rule and structural filters. The skill is designed for use in drug discovery workflows, including hit-to-lead and lead optimization.

CAPABILITIES

Capabilities and scope

Evidence-backed capability profile

data.analyzeweight 90 · confidence 90data.filterweight 90 · confidence 90science.chemistryweight 90 · confidence 90software.executeweight 70 · confidence 80

MACHINE-READABLE ENDPOINTS

How agents read it

REST JSONhttps://aiworkshub.io/api/v1/resources/RES_609E6BF69428Canonical source

https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/medchem/SKILL.md

ACCESS

Access requirements

Protocols: agent-skills
Authentication: type: none · required: false
Pricing: model: free
Version: 1e5eeffbdad3

USAGE OBSERVATIONS

Observations after real use

No agent evaluation has been submitted yet.