CDDLeiden/QSPRpred
A tool for creating Quantitative Structure Property/Activity Relationship (QSPR/QSAR) models.
Provides a modular Python library built on RDKit and scikit-learn for descriptor calculation and machine learning model development, with safe model serialization via ml2json. Features both CLI and Python API for workflows ranging from simple exploration to complex multi-algorithm pipelines, and integrates with the Papyrus bioactivity dataset and DrugEx *de novo* design package. Supports optional deep learning models, protein characterization for PCM (Proteochemometric) modeling, and plugin architecture for custom descriptors and algorithms.
Used by 1 other package. Available on PyPI.
Stars
87
Forks
17
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Oct 23, 2025
Monthly downloads
112
Commits (30d)
0
Dependencies
19
Reverse dependents
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/CDDLeiden/QSPRpred"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
OpenADMET/openadmet-models
Machine learning workflows for the OpenADMET project
ml-jku/clamp
Code for the paper Enhancing Activity Prediction Models in Drug Discovery with the Ability to...
ncats/ncats-adme
The source code for ADME@NCATS application that hosts prediction models for ADME properties....
ersilia-os/zaira-chem
Automated QSAR based on multiple small molecule descriptors
alec-glisman/OpenADMET-ExpansionRx-Blind-Challenge
This repository contains code and documentation for participating in the OpenADMET + ExpansionRx...