---
id: padelpy
version: "0.1.17"
license: MIT
license_treatment: permissive
maintenance: active
---

# padelpy — A Python wrapper for PaDEL-Descriptor software

License: permissive · Maintenance: active · Downloads: 92.2K/mo

## What it is and what it does

PaDELPy is a thin Python wrapper around the PaDEL-Descriptor Java engine, a well-established tool for computing molecular descriptors and fingerprints. It exposes PaDEL's command-line interface through Python functions, allowing you to calculate chemical features from SMILES strings, MDL MolFiles, and SDF files without needing to invoke the CLI directly.

The package bundles the PaDEL JAR and dependencies, so no separate download is needed. It provides high-level helpers (`from_smiles`, `from_mdl`, `from_sdf`) that return descriptor values as dictionaries or lists of dictionaries, plus a lower-level `padeldescriptor` function for direct CLI control. It has no Python dependencies beyond the standard library, but requires a Java 8+ runtime on your system PATH.

Use it for:

- Calculate molecular descriptors for machine learning pipelines in drug discovery or materials science
- Batch-process SMILES strings or structure files to extract chemical fingerprints for similarity searches
- Generate both 2D and 3D descriptors with optional tautomer standardization and aromaticity detection
- Export descriptor results to CSV for downstream analysis in data science workflows
- Parallelize descriptor computation across multiple molecules using the threads parameter

## Worth the install?

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

PaDELPy wraps the PaDEL-Descriptor Java engine to compute molecular descriptors and fingerprints from chemical structures in SMILES, MDL MolFile, and SDF formats.

Yes, if you need PaDEL-Descriptor's specific descriptor set and have Java 8+ available. The package is actively maintained, has no Python dependencies, and integrates cleanly into cheminformatics workflows. Install it if you're already committed to PaDEL's descriptor types; if you're exploring alternatives, consider RDKit or Mordred first, as they have different descriptor engines and dependency profiles.

## Install

pip install padelpy
uv add padelpy
poetry add padelpy

## Installing padelpy

Before you install: Low install friction: pure Python wheel with no runtime dependencies beyond the standard library. Wheels are large (20+ MB) because they bundle the PaDEL JAR and libraries, but installation is straightforward. Repository is active with recent releases.

License in practice: MIT license is permissive, allowing commercial and private use with minimal restrictions. You may use, modify, and distribute this package freely as long as you include the license notice.

Quickstart:

pip install padelpy

from padelpy import from_smiles

# Compute descriptors for a molecule
descriptors = from_smiles("CCC")

# Compute descriptors and fingerprints
desc_fp = from_smiles("CCC", fingerprints=True)

Requires Java Runtime Environment (JRE) 8+ on PATH; verify with `java -version`. Python 3.10 or later required.

Verify before relying:

- Performance characteristics and typical runtime for descriptor calculation on large molecule batches
- Specific descriptor and fingerprint types available beyond PubChem fingerprints mentioned
- Memory requirements for processing large SDF or MDL files

## Package facts

- License: MIT (permissive)
- Python support: supports_current
- Install friction: low
- Maintenance: active
- Downloads: 92.2K/month (top 15,000 on PyPI)
- Known vulnerabilities: none known

## Tags

molecular descriptor calculation, chemical fingerprints python, smiles to descriptors, padel descriptor wrapper, molecular feature extraction, cheminformatics descriptors, sdf mdl file processing, cheminformatics, molecular-descriptors, java-wrapper

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