qspr

A tool for creating Quantitative Structure Property/Activity Relationship (QSPR/QSAR) models.

Fast Molecular Property Prediction with mordredcommunity

ChemBFN: Bayesian Flow Network Framework for Chemistry Tasks. Developed in Hiroshima University.

A high-quality hand-curated logD7.4 dataset of 1,130 compounds

QSPR-based PyTorch models for fuel property prediction, with bundled datasets and analytical blend rules

Application for detecting functional groups of a molecules.

A new python package to visualize molecules in dots hover

A package to perform fingerprints from spectroscopy datas.

Raw quantum-chemical data as molecular graphs for graph neural networks

Prediction of CHI logD from ¹H/¹³C NMR spectra and molecular fingerprints using ML and deep learning.

demo electron-desktop

A Materials Informatics project to predict key polymer properties using XGBoost. Includes an end-to-end MLOps pipeline and a live interactive demo deployed on Hugging Face Spaces.

P2MAT - A python based user interface to predict melting point and boiling point of chemical compounds.

Two-paper package: Wuzi parametric topological-index family (graph theory) + reproducible orthogonality-screening pipeline for QSPR (methodology)

<It's part of the Lubricant Brain project.> Multimodal Attention Network for MOLecular property prediction (MANmol); 2) Adsorption energy dataset of 13320 organic compounds(AEdata); 3) 376 million Organic Compounds SMILES dataset(OCSmi).

KNIME cohesive workflows

Rust reimplementation of prodes — computes isoelectric point and surface electrostatic potential from protein structures for ion-exchange chromatography QSPR modeling.

Protein Descriptors Calculation - Surface Properties for ML/QSPR. Fork of tneijenhuis/prodes with improvements yielding 170× faster calculation. Cite the original publication: Neijenhuis et al. (2024) Biotechnology Journal 19, e2300708.

Workflows for prediction of inhalation toxicokinetics from chemical structure including the individual steps in the training and optimization of QSPR models, model selection and prediction of partition coefficients, applicability domain and toxicokinetics profile.