Decoupled peak property learning for efficient and interpretable ECD spectra prediction

Decoupled peak property learning for efficient and interpretable ECD spectra 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 Decoupled peak property learning for efficient and interpretable ECD spectra prediction Hao Li, Da Long, Li Yuan, Yu Wang, Yonghong Tian, Xinchang Wang, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4470356/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 03 Jan, 2025 Read the published version in Nature Computational Science → Version 1 posted You are reading this latest preprint version Abstract Electronic circular dichroism (ECD) spectra contain key information about molecular chirality by discriminating the absolute configurations of chiral molecules, which is crucial in asymmetric organic synthesis and the drug industry. However, existing predictive approaches lack the consideration of ECD spectra due to the data scarcity, and the interpretability to achieve trust-worthy prediction. Here, we establish a large-scale dataset for Chiral Molecular ECD spectra~(CMCDS) and propose the ECDFormer for accurate and interpretable ECD spectra prediction. ECDFormer decomposes ECD spectra into peak entities, employs the QFormer architecture to learn peak properties, and renders peaks into spectra. Compared to spectra sequence prediction methods, our decoupled peak prediction approach significantly enhances both accuracy and efficiency, improving the peak symbol accuracy from 37.3% to 72.7% and dramatically decreasing the time cost from 2-10 CPU hours to 1.5 seconds. More significantly, ECDFormer demonstrated its ability to capture molecular orbital information directly from spectral data using the explainable peak-decoupling approach, showcasing its potential to uncover hidden correlations between molecular substructures and spectral features. Furthermore, ECDFormer proved to be equally proficient at predicting various types of spectra of complex natural products, highlighting its substantial generalization capabilities. Physical sciences/Chemistry/Theoretical chemistry/Computational chemistry Physical sciences/Chemistry/Cheminformatics ECD Spectra Molecular Chirality Automatic spectrum prediction Decoupled Peak Property Learning Full Text Additional Declarations There is NO Competing Interest. Supplementary Files ECDFormerNCS2024supple0524final.pdf Cite Share Download PDF Status: Published Journal Publication published 03 Jan, 2025 Read the published version in Nature Computational Science → 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-4470356","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":312838720,"identity":"25af0159-c03c-413f-b2f5-c2f62ac18fc0","order_by":0,"name":"Hao Li","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA4ElEQVRIiWNgGAWjYBACPmYeIGlgI8fY3sAMEmBsIKSFDaylIM2YuecAsVoYQFo+HE5sn5FArBZ23oMfPhgcNuad+fawMQ+DjeyGA8zPHuB3GF+y5AyDdDnJ2XnJyTwMacYbDrCZGxDwi4E0j4G1seHsHOPDPAyHEzcc4GGTIKDF+DePAXPi/ptnQFr+E6XFDGiLc2LjDB5joMMOEKfFcoZBmjFjT16y4RyDZOOZh9nM8Grh5z9jfOPDH1BUnj0s8abCTrbvePMzvFqQADgZADEzkeqhWkbBKBgFo2AUYAEAy68/fsKmbTMAAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0002-3200-0270","institution":"Peking University","correspondingAuthor":true,"prefix":"","firstName":"Hao","middleName":"","lastName":"Li","suffix":""},{"id":312838721,"identity":"ea94fea6-ed49-4028-bed8-0ea5b8d7a3a5","order_by":1,"name":"Da Long","email":"","orcid":"","institution":"Xiamen University","correspondingAuthor":false,"prefix":"","firstName":"Da","middleName":"","lastName":"Long","suffix":""},{"id":312838722,"identity":"011f30e3-8d99-49f6-9406-a909d07449c4","order_by":2,"name":"Li Yuan","email":"","orcid":"","institution":"School of Electronic and Computer Engineering, Peking University","correspondingAuthor":false,"prefix":"","firstName":"Li","middleName":"","lastName":"Yuan","suffix":""},{"id":312838723,"identity":"4bf57acc-b008-4d00-85fc-d9b2751a1fb2","order_by":3,"name":"Yu Wang","email":"","orcid":"","institution":"School of Computer Science, Peking University","correspondingAuthor":false,"prefix":"","firstName":"Yu","middleName":"","lastName":"Wang","suffix":""},{"id":312838724,"identity":"e139c857-4256-494c-8817-73e876c5928c","order_by":4,"name":"Yonghong Tian","email":"","orcid":"https://orcid.org/0000-0002-2978-5935","institution":"Peking University","correspondingAuthor":false,"prefix":"","firstName":"Yonghong","middleName":"","lastName":"Tian","suffix":""},{"id":312838725,"identity":"31d0cb40-9057-4845-9543-9f1f2f9d7dba","order_by":5,"name":"Xinchang Wang","email":"","orcid":"https://orcid.org/0000-0001-6260-9282","institution":"Xiamen University","correspondingAuthor":false,"prefix":"","firstName":"Xinchang","middleName":"","lastName":"Wang","suffix":""},{"id":312838726,"identity":"fcbb8cfc-4fa9-4528-bfd3-4b4036ee9016","order_by":6,"name":"Fanyang Mo","email":"","orcid":"","institution":"School of Materials Science and Engineering, Peking University","correspondingAuthor":false,"prefix":"","firstName":"Fanyang","middleName":"","lastName":"Mo","suffix":""}],"badges":[],"createdAt":"2024-05-24 06:20:08","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4470356/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4470356/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s43588-024-00757-7","type":"published","date":"2025-01-03T05:00:00+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":72949433,"identity":"95f05283-de33-4f87-b35e-bd94dc89fc75","added_by":"auto","created_at":"2025-01-04 08:06:20","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":6593118,"visible":true,"origin":"","legend":"","description":"","filename":"ECDFormerNCS20240524final.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4470356/v1_covered_e53d2f5d-4e38-47cc-accc-68d1c5041aa0.pdf"},{"id":58100545,"identity":"c8f8a302-1c75-48dd-83fc-d25e4dd20a6e","added_by":"auto","created_at":"2024-06-11 06:31:00","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":2476529,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cbr\u003e\u003c/p\u003e","description":"","filename":"ECDFormerNCS2024supple0524final.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4470356/v1/55c0ac34c98a9bb5bebc4dd6.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Decoupled peak property learning for efficient and interpretable ECD spectra prediction","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"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":"ECD Spectra, Molecular Chirality, Automatic spectrum prediction, Decoupled Peak Property Learning","lastPublishedDoi":"10.21203/rs.3.rs-4470356/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4470356/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Electronic circular dichroism (ECD) spectra contain key information about molecular chirality by discriminating the absolute configurations of chiral molecules, which is crucial in asymmetric organic synthesis and the drug industry. However, existing predictive approaches lack the consideration of ECD spectra due to the data scarcity, and the interpretability to achieve trust-worthy prediction. Here, we establish a large-scale dataset for Chiral Molecular ECD spectra~(CMCDS) and propose the ECDFormer for accurate and interpretable ECD spectra prediction. ECDFormer decomposes ECD spectra into peak entities, employs the QFormer architecture to learn peak properties, and renders peaks into spectra. Compared to spectra sequence prediction methods, our decoupled peak prediction approach significantly enhances both accuracy and efficiency, improving the peak symbol accuracy from 37.3\\% to 72.7\\% and dramatically decreasing the time cost from 2-10 CPU hours to 1.5 seconds. More significantly, ECDFormer demonstrated its ability to capture molecular orbital information directly from spectral data using the explainable peak-decoupling approach, showcasing its potential to uncover hidden correlations between molecular substructures and spectral features. Furthermore, ECDFormer proved to be equally proficient at predicting various types of spectra of complex natural products, highlighting its substantial generalization capabilities.","manuscriptTitle":"Decoupled peak property learning for efficient and interpretable ECD spectra prediction","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-06-11 06:30:55","doi":"10.21203/rs.3.rs-4470356/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-computational-science","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"natcomputsci","sideBox":"Learn more about [Nature Computational Science](http://www.nature.com/natcomputsci/)","snPcode":"","submissionUrl":"","title":"Nature Computational Science","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Research","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"6cc96640-3fdd-40b6-9416-db220e8269ba","owner":[],"postedDate":"June 11th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":33071583,"name":"Physical sciences/Chemistry/Theoretical chemistry/Computational chemistry"},{"id":33071584,"name":"Physical sciences/Chemistry/Cheminformatics"}],"tags":[],"updatedAt":"2025-01-04T08:06:02+00:00","versionOfRecord":{"articleIdentity":"rs-4470356","link":"https://doi.org/10.1038/s43588-024-00757-7","journal":{"identity":"nature-computational-science","isVorOnly":false,"title":"Nature Computational Science"},"publishedOn":"2025-01-03 05:00:00","publishedOnDateReadable":"January 3rd, 2025"},"versionCreatedAt":"2024-06-11 06:30:55","video":"","vorDoi":"10.1038/s43588-024-00757-7","vorDoiUrl":"https://doi.org/10.1038/s43588-024-00757-7","workflowStages":[]},"version":"v1","identity":"rs-4470356","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4470356","identity":"rs-4470356","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}