---
id: chembl-structure-pipeline
version: "1.2.4"
license: MIT
license_treatment: permissive
maintenance: aging
---

# chembl-structure-pipeline — ChEMBL Structure Pipeline

License: permissive · Maintenance: aging · Downloads: 194.4K/mo

## What it is and what it does

ChEMBL Structure Pipeline is a molecular curation toolkit that implements the standardization and quality-checking protocols used by the ChEMBL database. It wraps RDKit to perform three main tasks: standardize molecular structures (normalize charges, aromaticity, and stereochemistry), extract parent compounds by removing salts and counterions, and assess structure quality by identifying problematic features and assigning penalty scores. The package is used to prepare chemical data for database ingestion or downstream analysis.

It's a specialized tool for chemoinformatics workflows—useful when you're building a chemical database, cleaning scraped or legacy molecular data, or need to apply ChEMBL's curation rules to your own structures. The API is straightforward: pass a molblock (V2000 format) to one of three main functions and get back a standardized molblock, parent structure, or quality report.

Use it for:

- Standardize raw molecular structures before loading them into a chemical database or registry.
- Extract parent compounds from salt forms or multi-component mixtures for deduplication.
- Assess and flag problematic structures in a dataset with penalty scores to prioritize manual review.
- Prepare chemical data for machine learning pipelines that require consistent molecular representation.
- Validate chemical structures submitted by users in a web application or data portal.

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

Standardizes and salt-strips molecular structures using ChEMBL protocols, and assesses structure quality with penalty scoring.

Yes, if you work with chemical structures and need ChEMBL-compatible curation. Install friction is low and the license is permissive. The main caveat is aging maintenance (263 days since last release), so if you encounter issues or need active support, you may need to fork or patch it yourself. No known vulnerabilities.

## Install

pip install chembl-structure-pipeline
uv add chembl-structure-pipeline
poetry add chembl-structure-pipeline

## Installing chembl-structure-pipeline

Before you install: Low friction: pure Python wheel with just setuptools and rdkit as runtime dependencies. Maintenance status is aging—last release 263 days ago—so expect slower response to issues.

License in practice: MIT license is permissive; you can use, modify, and distribute this package with minimal legal friction.

Quickstart:

pip install chembl_structure_pipeline

from chembl_structure_pipeline import standardizer

molblock = """..."""
std_molblock = standardizer.standardize_molblock(molblock)

rdkit must be installed and functional; it may require compilation or conda on some platforms.

Verify before relying:

- Whether the package supports modern Python versions (requires_python is unspecified in the fact sheet)
- Whether rdkit is available as a pre-built wheel on all target platforms or requires compilation

## Package facts

- License: MIT (permissive)
- Python support: unspecified
- Install friction: low
- Maintenance: aging
- Downloads: 194.4K/month (top 15,000 on PyPI)
- Known vulnerabilities: none known

## Tags

molecule standardization pipeline, chemical structure curation, salt stripping molecules, structure quality assessment, chembl molecular processing, rdkit structure validation, parent compound extraction, chemoinformatics, molecular-curation, rdkit-wrapper

[View on SkillFed](https://skillfed.io/packages/chembl-structure-pipeline) · [View on PyPI](https://pypi.org/project/chembl-structure-pipeline/)