HerbGNN

Read full text Summarise with VIRAT
Authors: Tonatiu Campos-García
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Benchmark pipeline for evaluating classical machine learning baselines against the HerbGNN deep learning framework for herbicide virtual screening under extreme class imbalance. This repository contains the analysis pipeline used in the HerbGNN study, including dataset preprocessing, fingerprint generation, baseline model training, statistical evaluation, bootstrap analysis, and figure generation. The goal of this repository is to provide a reproducible benchmark comparing Directed Message Passing Neural Networks (HerbGNN) with classical machine learning approaches such as Random Forest and XGBoost under scaffold-based cross-validation conditions typical of cheminformatics virtual screening.

Fields of Study & Subjects

Computational Drug Discovery Methods Machine Learning in Materials Science Weed Control and Herbicide Applications

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
21 March 2026
Language
EN
Document type
Dataset