MoleculeNet

MoleculeNet Benchmark (website) MoleculeNet is a benchmark specially designed for testing machine learning methods of molecular properties. As we aim to facilitate the development of molecular machine learning method, this work curates a number of dataset collections, creates a suite of software that implements many kn

Papers using MoleculeNet (14)

Aligning Molecular Graph Explanations with Chemical Identity via InChIfied Invariants2026Evaluating machine learning models for predicting pesticide toxicity to honey bees2025 · 1 citesBiScale-GTR: Fragment-Aware Graph Transformers for Multi-Scale Molecular Representation Learning2026Sheaf Neural Networks on SPD Manifolds: Second-Order Geometric Representation Learning2026Local-Global Multimodal Contrastive Learning for Molecular Property Prediction2026Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining2025Learning Hierarchical Interaction for Accurate Molecular Property Prediction2025MolGraph: a Python package for the implementation of molecular graphs and graph neural networks with TensorFlow and Keras2022 · 6 citesAdvancing Drug Discovery with Enhanced Chemical Understanding via Asymmetric Contrastive Multimodal Learning2023 · 2 citesPointGAT: A quantum chemical property prediction model integrating graph attention and 3D geometry2023 · 1 citesMolecular Topological Profile (MOLTOP) -- Simple and Strong Baseline for Molecular Graph Classification2024 · 1 citesExtracting Molecular Properties from Natural Language with Multimodal Contrastive Learning2023Synergistic Fusion of Graph and Transformer Features for Enhanced Molecular Property Prediction2023Automated Molecular Concept Generation and Labeling with Large Language Models2024