cheminformatics

Execute RDKit pipelines for property calculation, library filtering, and similarity analysis.

13|5|Updated May 4, 2026

Search Tags:#cheminformatics #drug-discovery #smiles #rdkit #molecular-descriptors #mmpdb

Ready to run

npx skills add https://github.com/awslabs/hcls-agent-skills --skill cheminformatics-awslabs

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: cheminformatics
Source: https://github.com/awslabs/hcls-agent-skills/tree/main/skills/cheminformatics
Command: npx skills add https://github.com/awslabs/hcls-agent-skills --skill cheminformatics-awslabs

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires rdkit, mmpdb.

What problem does it solve?

This skill eliminates manual errors and parameter mismatches in chemical data processing, ensuring that molecular property calculations and library filtering follow industry-standard best practices.

Core Features & Use Cases

Compound Filtering: Automatically apply Lipinski, Veber, and PAINS filters to identify drug-like candidates.
Similarity Analysis: Perform high-accuracy fingerprint similarity searches and clustering using modern RDKit generators.
Matched Molecular Pair Analysis: Identify structural transformations and SAR trends using mmpdb integration.

Quick Start

Use the cheminformatics skill to filter the provided SMILES list for Lipinski compliance and calculate Morgan fingerprint similarity against the reference compound.

Frequently Asked Questions about cheminformatics

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I filter compound libraries using Lipinski and PAINS filters?▼

Filter compound libraries by applying Lipinski, Veber, and PAINS filters to SMILES lists to automatically identify drug-like candidates. This eliminates manual parameter mismatches and ensures industry-standard best practices in chemical data processing for drug discovery.

What is the best way to run matched molecular pair analysis for SAR trends?▼

Run matched molecular pair analysis by integrating mmpdb to identify structural transformations and SAR trends. This approach ensures accurate molecular parsing and canonicalization to reveal meaningful chemical relationships in your compound data for drug discovery.

How do I calculate molecular fingerprint similarity against a reference compound?▼

Calculate molecular fingerprint similarity by generating Morgan fingerprints using modern RDKit generators. This ensures high-accuracy similarity searches and clustering for comparing target compounds against a reference molecule in chemical data analysis.

Do I need RDKit and mmpdb installed for cheminformatics pipelines?▼

Yes, you need RDKit and mmpdb packages installed to execute cheminformatics pipelines. These dependencies are required to ensure accurate molecular parsing, canonicalization, fingerprint generation, and matched molecular pair analysis.

Can I use this approach for small-molecule property calculation in drug discovery?▼

Yes, you can use this approach for small-molecule property calculation in drug discovery. It executes RDKit-based workflows to calculate molecular descriptors and evaluate drug-like properties such as Lipinski rule compliance for compound libraries.

Why does manual chemical data processing cause parameter mismatches?▼

Manual chemical data processing causes parameter mismatches due to inconsistent molecular parsing and canonicalization settings. Automating pipelines with RDKit ensures standardized property calculations and library filtering for drug discovery.