ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction

ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction Xiaomin Fang, Lihang Liu, Jieqiong Lei, Donglong He, Shanzhuo Zhang, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-670872/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 07 Feb, 2022 Read the published version in Nature Machine Intelligence → Version 1 posted You are reading this latest preprint version 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. Drug Delivery Biological Chemistry molecular property prediction drug development GNN ChemRL Full Text Additional Declarations There is NO Competing Interest. Cite Share Download PDF Status: Published Journal Publication published 07 Feb, 2022 Read the published version in Nature Machine Intelligence → Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-670872","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":41229332,"identity":"71c4316b-86a1-469c-81b4-c9e3b3e265ee","order_by":0,"name":"Xiaomin Fang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA+ElEQVRIiWNgGAWjYBAC9gYQaQDEzAwMBxIqDjCwMSTg18JzAKGF8cGDM0RrgQBmw4dtIC4hLexnD7/mKbCT023nPSaROO+OPB97jgHDj4ptuLXw5KVZzjBINjY7zJcmkbjtmWEbzxsDxp4zt3FqsWfIMTP4YMCcuO0wjxlQy2HGNokcA2bGNtxaePjfmBkkGNRDtcw5bE9Yi0SO8YMPBodBWowNEhsOJxKh5Y0Z4wyD40C/8Bg+SDj2LLmN51nBQXx+4eHPMf7M86dazuz8GYODP2ru2M5vT9744EcFbi1AwCaBIXQAn3ogYP5AQMEoGAWjYBSMdAAAowRYgNqGOeAAAAAASUVORK5CYII=","orcid":"","institution":"Baidu Inc.","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Xiaomin","middleName":"","lastName":"Fang","suffix":""},{"id":41229333,"identity":"80911465-05fb-485d-a9ff-dec9b385dd5c","order_by":1,"name":"Lihang Liu","email":"","orcid":"","institution":"Baidu Inc.","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Lihang","middleName":"","lastName":"Liu","suffix":""},{"id":41229334,"identity":"1ec98b3f-c460-4baf-8266-5f2c74701e6a","order_by":2,"name":"Jieqiong Lei","email":"","orcid":"","institution":"Tsinghua University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Jieqiong","middleName":"","lastName":"Lei","suffix":""},{"id":41229335,"identity":"2da23d12-05c1-43dd-80df-8c1b96dc1edc","order_by":3,"name":"Donglong He","email":"","orcid":"","institution":"Baidu Inc.","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Donglong","middleName":"","lastName":"He","suffix":""},{"id":41229336,"identity":"fe203184-e9bb-421f-ad76-09340cec2743","order_by":4,"name":"Shanzhuo Zhang","email":"","orcid":"","institution":"Baidu Inc.","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Shanzhuo","middleName":"","lastName":"Zhang","suffix":""},{"id":41229337,"identity":"c600f9d8-0225-4ddd-9f5d-ef3103698b3e","order_by":5,"name":"Jingbo Zhou","email":"","orcid":"","institution":"Baidu Inc.","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Jingbo","middleName":"","lastName":"Zhou","suffix":""},{"id":41229338,"identity":"331bb813-ac71-461e-9c69-42b49d8741f8","order_by":6,"name":"Fan Wang","email":"","orcid":"","institution":"Baidu Inc.","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Fan","middleName":"","lastName":"Wang","suffix":""},{"id":41229339,"identity":"065cf797-d5ed-452d-a597-885605b57044","order_by":7,"name":"Hua Wu","email":"","orcid":"","institution":"Baidu","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Hua","middleName":"","lastName":"Wu","suffix":""},{"id":41229340,"identity":"a60ffd87-184f-472e-af94-e05c1df424d7","order_by":8,"name":"Haifeng Wang","email":"","orcid":"","institution":"Baidu","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Haifeng","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2021-06-30 11:50:33","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-670872/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-670872/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s42256-021-00438-4","type":"published","date":"2022-02-07T05:00:00+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":19034844,"identity":"182d6299-8654-4fb0-8434-eb61f2bacc7c","added_by":"auto","created_at":"2022-03-09 18:49:44","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":498605,"visible":true,"origin":"","legend":"","description":"","filename":"ChemRLGEM.pdf","url":"https://assets-eu.researchsquare.com/files/rs-670872/v1_covered.pdf"},{"id":13670499,"identity":"d9bdeb99-7183-494b-990e-da9eb8506c5d","added_by":"auto","created_at":"2021-09-17 11:05:32","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":493405,"visible":true,"origin":"","legend":"","description":"","filename":"ChemRLGEM.pdf","url":"https://assets-eu.researchsquare.com/files/rs-670872/v1_covered.pdf"},{"id":12718841,"identity":"e114fa90-b289-40fa-883d-4f2bf4df2ef1","added_by":"auto","created_at":"2021-08-24 16:10:10","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":489876,"visible":true,"origin":"","legend":"","description":"","filename":"ChemRLGEM.pdf","url":"https://assets-eu.researchsquare.com/files/rs-670872/v1_covered.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction","fulltext":[{"header":"Full Text","content":"This preprint is available for \u003ca href='/article/rs-670872/latest.pdf' target='_blank'\u003edownload as a PDF\u003c/a\u003e."}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"nature-portfolio","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Nature Portfolio","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"ejp","reportingPortfolio":"","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"molecular property prediction, drug development, GNN, ChemRL","lastPublishedDoi":"10.21203/rs.3.rs-670872/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-670872/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"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.","manuscriptTitle":"ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2021-08-24 16:09:59","doi":"10.21203/rs.3.rs-670872/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-machine-intelligence","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"natmachintell","sideBox":"Learn more about [Nature Machine Intelligence](http://www.nature.com/natmachintell/)","snPcode":"","submissionUrl":"","title":"Nature Machine Intelligence","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Research","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"818d812d-0de5-4179-84bd-f94aef9183fb","owner":[],"postedDate":"August 24th, 2021","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":6677046,"name":"Drug Delivery"},{"id":6677047,"name":"Biological Chemistry"}],"tags":[],"updatedAt":"2022-03-09T18:49:39+00:00","versionOfRecord":{"articleIdentity":"rs-670872","link":"https://doi.org/10.1038/s42256-021-00438-4","journal":{"identity":"nature-machine-intelligence","isVorOnly":false,"title":"Nature Machine Intelligence"},"publishedOn":"2022-02-07 05:00:00","publishedOnDateReadable":"February 7th, 2022"},"versionCreatedAt":"2021-08-24 16:09:59","video":"","vorDoi":"10.1038/s42256-021-00438-4","vorDoiUrl":"https://doi.org/10.1038/s42256-021-00438-4","workflowStages":[]},"version":"v1","identity":"rs-670872","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-670872","identity":"rs-670872","version":["v1"]},"buildId":"7rjqhiLT3MXkJMwkYKINL","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}