{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/chemrl-gem-geometry-enhanced-molecular","title":"ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction","arxiv_id":"2106.06130","date":"2021-06-11","proceeding":null,"authors":["Xiaomin Fang","Lihang Liu","Jieqiong Lei","Donglong He","Shanzhuo Zhang","Jingbo Zhou","Fan Wang","Hua Wu","Haifeng Wang"],"abstract":"Effective molecular representation learning is of great importance to facilitate molecular property prediction, which is a fundamental task for the drug and material industry. Recent advances in graph neural networks (GNNs) have shown great promise in applying GNNs for molecular representation learning. Moreover, a few recent studies have also demonstrated successful applications of self-supervised learning methods to pre-train the GNNs to overcome the problem of insufficient labeled molecules. However, existing GNNs and pre-training strategies usually treat molecules as topological graph data without fully utilizing the molecular geometry information. Whereas, the three-dimensional (3D) spatial structure of a molecule, a.k.a molecular geometry, is one of the most critical factors for determining molecular physical, chemical, and biological properties. To this end, we propose a novel Geometry Enhanced Molecular representation learning method (GEM) for Chemical Representation Learning (ChemRL). At first, we design a geometry-based GNN architecture that simultaneously models atoms, bonds, and bond angles in a molecule. To be specific, we devised double graphs for a molecule: The first one encodes the atom-bond relations; The second one encodes bond-angle relations. Moreover, on top of the devised GNN architecture, we propose several novel geometry-level self-supervised learning strategies to learn spatial knowledge by utilizing the local and global molecular 3D structures. We compare ChemRL-GEM with various state-of-the-art (SOTA) baselines on different molecular benchmarks and exhibit that ChemRL-GEM can significantly outperform all baselines in both regression and classification tasks. For example, the experimental results show an overall improvement of 8.8% on average compared to SOTA baselines on the regression tasks, demonstrating the superiority of the proposed method.","url_abs":"https://arxiv.org/abs/2106.06130v4","url_pdf":"https://arxiv.org/pdf/2106.06130v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"molecular-property-prediction","task_name":"Molecular Property Prediction"},{"task_slug":"property-prediction","task_name":"Property Prediction"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"molecular-representation","task_name":"molecular representation"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/molecular-property-prediction-on-bace-1","task":"Molecular Property Prediction","dataset":"BACE","model":"ChemRL-GEM","rank_in_archive_order":4,"of":20,"metrics":{"ROC-AUC":"85.6"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-bbbp-1","task":"Molecular Property Prediction","dataset":"BBBP","model":"ChemRL-GEM","rank_in_archive_order":18,"of":29,"metrics":{"ROC-AUC":"72.4"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-esol","task":"Molecular Property Prediction","dataset":"ESOL","model":"ChemRL-GEM","rank_in_archive_order":14,"of":20,"metrics":{"RMSE":"0.798"},"uses_additional_data":true},{"leaderboard":"/sota/molecular-property-prediction-on-freesolv","task":"Molecular Property Prediction","dataset":"FreeSolv","model":"ChemRL-GEM","rank_in_archive_order":16,"of":22,"metrics":{"RMSE":"1.877"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on","task":"Molecular Property Prediction","dataset":"Lipophilicity","model":"ChemRL-GEM","rank_in_archive_order":3,"of":13,"metrics":{"RMSE":"0.66"},"uses_additional_data":true},{"leaderboard":"/sota/molecular-property-prediction-on-qm7","task":"Molecular Property Prediction","dataset":"QM7","model":"ChemRL-GEM","rank_in_archive_order":2,"of":8,"metrics":{"MAE":"58.9"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-qm8","task":"Molecular Property Prediction","dataset":"QM8","model":"ChemRL-GEM","rank_in_archive_order":2,"of":8,"metrics":{"MAE":"0.0171"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-qm9","task":"Molecular Property Prediction","dataset":"QM9","model":"ChemRL-GEM","rank_in_archive_order":2,"of":8,"metrics":{"MAE":"0.00746"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-sider-1","task":"Molecular Property Prediction","dataset":"SIDER","model":"ChemRL-GEM","rank_in_archive_order":5,"of":19,"metrics":{"ROC-AUC":"67.2"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-tox21-1","task":"Molecular Property Prediction","dataset":"Tox21","model":"ChemRL-GEM","rank_in_archive_order":7,"of":20,"metrics":{"ROC-AUC":"78.1"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-toxcast-1","task":"Molecular Property Prediction","dataset":"ToxCast","model":"ChemRL-GEM","rank_in_archive_order":4,"of":8,"metrics":{"ROC-AUC":"69.2"},"uses_additional_data":false},{"leaderboard":"/sota/molecular-property-prediction-on-clintox-1","task":"Molecular Property Prediction","dataset":"clintox","model":"ChemRL-GEM","rank_in_archive_order":8,"of":20,"metrics":{"Molecules (M)":"20","ROC-AUC":"90.1"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2106.06130","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}