# Towards Rational Pesticide Design with Graph Machine Learning Models for Ecotoxicology

arXiv: https://arxiv.org/abs/2509.18703 · HTML: https://mlsanity.com/paper/2509.18703/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 25 references that are in the map.
- First posted on arXiv 23 Sep 2025.

## Builds on (most cited first, 9 of 9)

- [MoleculeNet: A Benchmark for Molecular Machine Learning](https://mlsanity.com/paper/1703.00564/) (2017)
- [Graph neural networks for materials science and chemistry](https://mlsanity.com/paper/2208.09481/) (2022)
- [A Survey on Graph Kernels](https://mlsanity.com/paper/1903.11835/) (2019)
- [ChemBERTa-2: Towards Chemical Foundation Models](https://mlsanity.com/paper/2209.01712/) (2022)
- [Relative Molecule Self-Attention Transformer](https://mlsanity.com/paper/2110.05841/) (2021)
- [Scikit-fingerprints: easy and efficient computation of molecular fingerprints in Python](https://mlsanity.com/paper/2407.13291/) (2024)
- [Strengthening structural baselines for graph classification using Local Topological Profile](https://mlsanity.com/paper/2305.00724/) (2023)
- [Molecular Topological Profile (MOLTOP) -- Simple and Strong Baseline for Molecular Graph Classification](https://mlsanity.com/paper/2407.12136/) (2024)
- [ApisTox: a new benchmark dataset for the classification of small molecules toxicity on honey bees](https://mlsanity.com/paper/2404.16196/) (2024)

## Built on by (most cited first, 1 of 1)

- [Scikit-fingerprints: Python library for scikit-learn compatible molecular fingerprints and chemoinformatics](https://mlsanity.com/paper/2608.02027/) (2026)

## Abstract (arXiv)

This research focuses on rational pesticide design, using graph machine learning to accelerate the development of safer, eco-friendly agrochemicals, inspired by in silico methods in drug discovery. With an emphasis on ecotoxicology, the initial contributions include the creation of ApisTox, the largest curated dataset on pesticide toxicity to honey bees. We conducted a broad evaluation of machine learning (ML) models for molecular graph classification, including molecular fingerprints, graph kernels, GNNs, and pretrained transformers. The results show that methods successful in medicinal chemistry often fail to generalize to agrochemicals, underscoring the need for domain-specific models and benchmarks. Future work will focus on developing a comprehensive benchmarking suite and designing ML models tailored to the unique challenges of pesticide discovery.