---
id: aimsim-core
version: "2.2.3"
license: MIT
license_treatment: permissive
maintenance: aging
---

# aimsim-core — Core AIMSim molecular featurization and comparison utilities.

License: permissive · Maintenance: aging · Downloads: 85.0K/mo

## What it is and what it does

AIMSim-core is the backend library for molecular diversity visualization and analysis. It provides fingerprinting, descriptor calculation, and similarity scoring for chemical structures—the computational engine behind the full AIMSim package without the graphical interface. The package wraps multiple cheminformatics tools (RDKit, PaDELPy, MHFP, Mordred) into a unified API for comparing molecular structures.

The library is designed for chemists and computational researchers who need to assess chemical diversity in datasets, find structurally similar molecules, or build training sets for machine learning. It supports Morgan fingerprints, RDKit topological and Daylight fingerprints, and can interface with additional descriptor libraries. The project is stable but no longer actively developed, with maintenance provided on an as-needed basis.

Use it for:

- Exploratory synthesis: check if newly proposed molecules are too similar to already-synthesized ones to avoid redundant synthesis effort.
- Virtual screening: find structurally similar molecules in a database to an active compound for lead optimization or drug discovery.
- Machine learning dataset assessment: evaluate training set diversity to ensure robust model generalization and identify clusters requiring separate models.
- Substrate scope verification: assess structural and chemical similarity across reaction substrates to ensure functional group tolerance coverage.
- Descriptor-based analysis: calculate molecular fingerprints and descriptors for downstream cheminformatics workflows without visualization overhead.

## Worth the install?

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

Provides core molecular featurization and similarity comparison utilities for analyzing chemical diversity and structure relationships in molecular datasets.

Yes, if you need programmatic molecular featurization and similarity scoring in Python. The core module offers low-friction installation and stable, permissive licensing. However, maintenance is aging—the project is no longer actively developed—so evaluate whether you need ongoing support or can work with a stable snapshot. No known security vulnerabilities.

## Install

pip install aimsim-core
uv add aimsim-core
poetry add aimsim-core

## Installing aimsim-core

Before you install: Low friction installation with a pure-Python wheel. Maintenance is aging—the project reached stable state but is no longer actively developed, with support provided as time allows. Nine runtime dependencies including scikit-learn, rdkit, and pandas are well-established libraries.

License in practice: MIT license is permissive, allowing use in commercial and proprietary projects with minimal restrictions.

Quickstart:

pip install aimsim-core

from aimsim_core import Molecule
mol = Molecule(smiles='CCO')
fingerprint = mol.get_fingerprint('morgan')

Requires Python 3.8 or later. RDKit and other cheminformatics dependencies may require system libraries for compilation.

Verify before relying:

- Whether the core module API is stable and documented for programmatic use outside the GUI
- Performance characteristics when processing large molecular datasets
- Whether all 44 similarity metrics are accessible via the core module or only through the CLI

## Package facts

- License: MIT (permissive)
- Python support: supports_current
- Install friction: low
- Maintenance: aging
- Downloads: 85.0K/month (top 15,000 on PyPI)
- Known vulnerabilities: none known

## Tags

molecular fingerprinting, chemical similarity scoring, molecular descriptor calculation, chemical diversity analysis, structure comparison library, molecular featurization tools, cheminformatics similarity metrics, cheminformatics, molecular-descriptors, chemistry-toolkit

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