R implementation of QSAR (Quantitative Structure-Activity Realtionship) trees to predict the bioconcentration of chemical compounds.

Wrapper to leverage cheminformatics tasks within scikit-learn workflows

Mechanistic QSAR models for key human health endpoints

Cheminformatics QSAR workflow for bioactivity prediction with RDKit, machine learning, and compound prioritization.

self learning and reference material on QSAR moleculear modelling

Some thoughts on building QSARModeling in Rust.

Conjuntos de dados públicos dos diversos trabalhos do LACC.

Classify acetylcholinesterase inhibitor with LightGBM

Bio-informed QSAR framework integrating P. falciparum transcriptomic signatures with molecular descriptors for enhanced antimalarial activity prediction (6.1% improvement, 98.3% feature reduction)

Reference implementation of the Vanishing Ranking Kernels (VRK) method

This project identifies potential EGFR inhibitors using a KNIME-based ML workflow and FBDD to discover key active fragments for lead optimization.

Pioneering Next-Generation AI for Scientific Breakthroughs. Starting with a JAK2 pIC50 Prediction Model.

ProtMetrics is a library to compute molecular descriptors that can be used for QSAR and machine learning modeling.

Predict Activity of Human Carbonic Anhydrase

Training data for "Prediction of clinically relevant drug-induced liver injury from structure using machine learning" (Hammann et al., J Appl Toxicol . 2019 Mar;39(3):412-419)

QSAR Project: CETP Inhibitor Discovery, Data Curation & Drug Repurposing Pipeline

A modern, reproducible pipeline for molecular bioactivity prediction built as a final year research project. This repository integrates cheminformatics, advanced machine learning, and interactive visualization to accelerate drug discovery.

Learning material derived from studies using the book 'Three Dimensional QSAR: Applications in Pharmacology and Toxicology (QSAR in Environmental and Health Sciences)'

SENDQSAR package enables researchers to build QSAR models from SEND datasets through streamlined data preprocessing, organ-wise toxicity scoring, descriptor calculation, and machine learning integration. The package supports automated workflows for model development and includes tools for visualization and performance evaluation.

pip install analoguesplit