aimsim-core
Core AIMSim molecular featurization and comparison utilities.
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 on this page — 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
aimsim-core on PyPI
pip
pip install aimsim-coreuv
uv add aimsim-corepoetry
poetry add aimsim-coreInstalling 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 the current Python release (>=3.8) |
| Install friction | low — pure-Python wheel |
| Runtime dependencies | 9 — psutil, scikit_learn, rdkit, numpy, pandas, padelpy, mhfp, mordredcommunity, multiprocess |
| Maintenance | aging — 339 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 85,046/month — #13,958 on PyPI (30-day window, as of 2026-08-14) |
| Known vulnerabilities | none known (OSV.dev, checked 2026-08-14) |
Evidence: aimsim_core-2.2.3-py3-none-any.whl
Tags
More Scientific/Engineering packages
NumPy provides an N-dimensional array object…
permissive · top 100 on PyPI
pandaspandas provides fast, flexible data structures…
permissive · top 100 on PyPI
scipyscipy provides numerical algorithms for…
permissive · top 100 on PyPI
scikit-learnscikit-learn provides a comprehensive Python…
permissive · top 1,000 on PyPI
dilldill extends Python's pickle module to…
permissive · top 1,000 on PyPI
multiprocessMultiprocess is an enhanced fork of Python's…
permissive · top 1,000 on PyPI
mhfpEncodes molecular structures as MinHash…
unclear · top 15,000 on PyPI
mordredcommunityCalculates molecular descriptors from chemical…
permissive · top 15,000 on PyPI
selfiesConverts between SELFIES (Self-Referencing…
permissive · top 15,000 on PyPI
padelpyPaDELPy wraps the PaDEL-Descriptor Java engine…
permissive · top 15,000 on PyPI
chempropChemprop trains and deploys message passing…
permissive · top 15,000 on PyPI
dscribeDScribe transforms atomic structures into…
permissive · top 15,000 on PyPI
rdkitRDKit is a chemoinformatics toolkit providing…
permissive · top 5,000 on PyPI
prolifProLIF generates interaction fingerprints from…
permissive · top 15,000 on PyPI
chembl-structure-pipelineStandardizes and salt-strips molecular…
permissive · top 15,000 on PyPI
princePrince implements multivariate exploratory data…
permissive · top 15,000 on PyPI