--- id: mordredcommunity version: "2.0.7" license: BSD-3-Clause license_treatment: permissive maintenance: active --- # mordredcommunity — Community-Maintained Version of mordred License: permissive · Maintenance: active · Downloads: 125.2K/mo ## What it is and what it does Mordredcommunity is a community-maintained fork of an original molecular descriptor calculator that is no longer actively developed. It computes a large set of molecular descriptors—topological, geometric, and physicochemical properties—from chemical structures provided as SMILES strings, SDF, or MOL files. The package wraps rdkit for structure parsing and calculation, and exposes descriptors through both a command-line interface and a Python API. Typical use is to load molecules, instantiate a Calculator with a descriptor set, and compute properties either for single molecules or batches. It supports 2D and 3D descriptor modes, selective descriptor calculation, and optional pandas DataFrame output. The CLI supports streaming reads for low-memory processing and progress bars; the library API allows direct integration into cheminformatics pipelines. Use it for: - Extract molecular features for machine learning models predicting drug properties or toxicity. - Batch-compute descriptor tables from chemical libraries for structure-activity relationship analysis. - Generate 2D or 3D topological descriptors for molecular similarity and clustering workflows. - Command-line processing of SMILES or SDF files to produce CSV descriptor tables for downstream analysis. - Integrate descriptor calculation into Python cheminformatics pipelines alongside rdkit workflows. ## Worth the install? AI-flagged interpretation of the facts above — verify before relying. Calculates molecular descriptors from chemical structures, computing topological, geometric, and physicochemical properties for use in cheminformatics workflows. Yes. The package is actively maintained, has low install friction, carries no known vulnerabilities, and solves a specific cheminformatics need (descriptor calculation) that the original unmaintained version no longer addresses. Install it if you need molecular descriptors for machine learning, structure analysis, or chemical property prediction; the API is stable and the community fork is actively accepting contributions. ## Install pip install mordredcommunity uv add mordredcommunity poetry add mordredcommunity ## Installing mordredcommunity Before you install: Low install friction with a pure-wheel distribution. Active maintenance as of 2026-08-10 with recent releases; the project is community-maintained after the original was abandoned, and maintainers are actively seeking contributors. License in practice: BSD-3-Clause is permissive; you can use, modify, and distribute this package with minimal restrictions, provided you retain the license notice. Quickstart: pip install mordredcommunity from rdkit import Chem from mordredcommunity import Calculator, descriptors mol = Chem.MolFromSmiles('c1ccccc1') calc = Calculator(descriptors, ignore_3D=True) result = calc(mol) rdkit must be installed (a compiled cheminformatics library); the package supports Python 3.9 and newer. Verify before relying: - Whether the 1826 total descriptors (1613 2D, 213 3D) remain current in version 2.0.7 or have changed. - Performance characteristics when calculating descriptors on large molecule batches. - Compatibility with pandas integration mentioned in the description when using the [full] extra. ## Package facts - License: BSD-3-Clause (permissive) - Python support: supports_current - Install friction: low - Maintenance: active - Downloads: 125.2K/month (top 15,000 on PyPI) - Known vulnerabilities: none known ## Tags molecular descriptor calculator, cheminformatics properties, chemical structure analysis, molecular feature extraction, SMILES descriptor computation, chemical fingerprinting, molecular descriptor batch processing, cheminformatics, molecular-descriptors, rdkit-wrapper [View on SkillFed](https://skillfed.io/packages/mordredcommunity) · [View on PyPI](https://pypi.org/project/mordredcommunity/)