LiteGEM: Lite Geometry Enhanced Molecular Representation Learning for Quantum Property Prediction

2021/06/28 by Shanzhuo Zhang, Lihang Liu, Zhang, Shanzhuo +15 · 1 citation
Biochemistry, Genetics and Molecular Biology · Computer Science · Materials Science · Mathematics · Physics and Astronomy · #Chemical Physics (physics.chem-ph) #Computational Drug Discovery Methods #Computer science #Epistemology #FOS: Computer and information sciences #FOS: Physical sciences #Geometry #Machine Learning (cs.LG) #Machine Learning in Materials Science #Mathematics #Philosophy #Physics #Political science #Property (philosophy) #Protein Structure and Dynamics #Quantum #Quantum mechanics #Representation (politics) #cs.LG #physics.chem-ph

paper · pdf · doi:10.48550/arxiv.2106.14494

published in arXiv (Cornell University) (Cornell University)

arxiv created 2021/06/28 · openalex publication_date 2021/06/28 · arxiv updated 2021/06/29 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In this report, we (SuperHelix team) present our solution to KDD Cup 2021-PCQM4M-LSC, a large-scale quantum chemistry dataset on predicting HOMO-LUMO gap of molecules. Our solution, Lite Geometry Enhanced Molecular representation learning (LiteGEM) achieves a mean absolute error (MAE) of 0.1204 on the test set with the help of deep graph neural networks and various self-supervised learning tasks. The code of the framework can be found in https://github.com/PaddlePaddle/PaddleHelix/tree/dev/competition/kddcup2021-PCQM4M-LSC/.

Citations

• Molecular Graph Convolutions: Moving Beyond Fingerprints
• Neural Message Passing for Quantum Chemistry
• Recent developments in the PySCF program package
• DeeperGCN: All You Need to Train Deeper GCNs

Cited by

• Evaluating Effects of Augmented SELFIES for Molecular Understanding Using QK-LSTM

Related

• Selected Machine Learning of HOMO-LUMO gaps with Improved Data-Efficiency
• Fast Quantum Property Prediction via Deeper 2D and 3D Graph Networks
• An ensemble of VisNet, Transformer-M, and pretraining models for molecular property prediction in OGB Large-Scale Challenge @ NeurIPS 2022
• On Graph Neural Network Ensembles for Large-Scale Molecular Property Prediction
• PointGAT: A quantum chemical property prediction model integrating graph attention and 3D geometry