{"paper_id":"4a8099c5-e55b-44d6-bcc1-fbfff63a7bb9","body_text":"Revisiting Molecular Descriptors with TDiMS for Interpretable Intramolecular Interactions Based on Substructure Pairs | 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 Brief Communication Revisiting Molecular Descriptors with TDiMS for Interpretable Intramolecular Interactions Based on Substructure Pairs Lisa Hamada, Akihiro Kishimoto, Kohei Miyaguchi, Masataka Hirose, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6141459/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted You are reading this latest preprint version Abstract Molecular descriptors play a crucial role in representing the structural features of molecules for machine learning-based physical property prediction. However, current descriptors either consider only local aspects of molecular structures or fail to effectively learn nonlocal structural features involving long-distance intramolecular interactions. To address this issue, we present a new descriptor named TDiMS. TDiMS effectively summarizes the enumerated pairwise topological distances between molecular substructures, thus capturing nonlocal interactions. Our evaluation shows that TDiMS successfully identifies essential features of large structures and outperforms other representative descriptors. Additionally, these identified features are highly interpretable for experts in material discovery. Physical sciences/Chemistry/Cheminformatics Physical sciences/Materials science/Theory and computation/Computational methods Full Text Additional Declarations There is NO Competing Interest. Supplementary Files TDiMSsupplementary250120.pdf TDiMSwithSmallRefData.zip Supplementary code files Cite Share Download PDF Status: Under Review 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-6141459\",\"acceptedTermsAndConditions\":true,\"allowDirectSubmit\":false,\"archivedVersions\":[],\"articleType\":\"Brief Communication\",\"associatedPublications\":[],\"authors\":[{\"id\":438115652,\"identity\":\"d0e1f137-ea20-483c-8489-913d141bcd5d\",\"order_by\":0,\"name\":\"Lisa Hamada\",\"email\":\"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAx0lEQVRIiWNgGAWjYBACA2YgwdgGYiYwPkhsIFELswFxWhgQWtgkGInSws7+8ANjm100f3vys4qHO7Yx8Ld3JxBwGI+xBOO/5NwZZ56Z3Ug8c5tB4szZDYS0MEgwtjHnNtxIAGppu81gIJFLSAv74x+MbfW582+kfysgUguDGdCWw7kbbuSYMRCphcfMIrHteO7GM2+KJYB+4SHoF/v+449vfGyrzp13PH3jx587bsvxt/fi1wIGCUhsHsLKR8EoGAWjYBQQBAAUPEsf9+qrgAAAAABJRU5ErkJggg==\",\"orcid\":\"https://orcid.org/0009-0008-8939-4793\",\"institution\":\"IBM Research\",\"correspondingAuthor\":true,\"prefix\":\"\",\"firstName\":\"Lisa\",\"middleName\":\"\",\"lastName\":\"Hamada\",\"suffix\":\"\"},{\"id\":438115653,\"identity\":\"b014ecf8-bd8c-4a92-a33e-2a48a43b5553\",\"order_by\":1,\"name\":\"Akihiro Kishimoto\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"IBM Research\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Akihiro\",\"middleName\":\"\",\"lastName\":\"Kishimoto\",\"suffix\":\"\"},{\"id\":438115654,\"identity\":\"8ab34c50-ec5d-4e9d-b553-aa375e8350e5\",\"order_by\":2,\"name\":\"Kohei Miyaguchi\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"IBM Research\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Kohei\",\"middleName\":\"\",\"lastName\":\"Miyaguchi\",\"suffix\":\"\"},{\"id\":438115655,\"identity\":\"2693f1eb-c88e-4c6f-9e58-8e91e367a84f\",\"order_by\":3,\"name\":\"Masataka Hirose\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"JSR Corporation\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Masataka\",\"middleName\":\"\",\"lastName\":\"Hirose\",\"suffix\":\"\"},{\"id\":438115656,\"identity\":\"efad2b50-c69c-4678-895c-62677142ce14\",\"order_by\":4,\"name\":\"Junta Fuchiwaki\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"JSR Corporation\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Junta\",\"middleName\":\"\",\"lastName\":\"Fuchiwaki\",\"suffix\":\"\"},{\"id\":438115657,\"identity\":\"4612e77c-81a7-4e5a-b310-07c7077544ef\",\"order_by\":5,\"name\":\"Indra Priyadarsini\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"IBM Research\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Indra\",\"middleName\":\"\",\"lastName\":\"Priyadarsini\",\"suffix\":\"\"},{\"id\":438115658,\"identity\":\"ea45ba91-fefd-46c2-b02b-0f960a1d3f57\",\"order_by\":6,\"name\":\"Seiji Takeda\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"IBM Research\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Seiji\",\"middleName\":\"\",\"lastName\":\"Takeda\",\"suffix\":\"\"}],\"badges\":[],\"createdAt\":\"2025-03-02 22:50:09\",\"currentVersionCode\":1,\"declarations\":\"\",\"doi\":\"10.21203/rs.3.rs-6141459/v1\",\"doiUrl\":\"https://doi.org/10.21203/rs.3.rs-6141459/v1\",\"draftVersion\":[],\"editorialEvents\":[],\"editorialNote\":\"\",\"failedWorkflow\":false,\"files\":[{\"id\":80018253,\"identity\":\"8f52c9b7-7151-4952-9213-ef00e7545f8f\",\"added_by\":\"auto\",\"created_at\":\"2025-04-07 04:07:23\",\"extension\":\"pdf\",\"order_by\":2,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"supplement\",\"size\":899993,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"TDiMSsupplementary250120.pdf\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-6141459/v1/c25531f900ed661417e4b187.pdf\"},{\"id\":80018254,\"identity\":\"89175f6e-d249-4a18-a9a7-7c79be4a9421\",\"added_by\":\"auto\",\"created_at\":\"2025-04-07 04:07:26\",\"extension\":\"zip\",\"order_by\":3,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"supplement\",\"size\":170002045,\"visible\":true,\"origin\":\"\",\"legend\":\"Supplementary code files\",\"description\":\"\",\"filename\":\"TDiMSwithSmallRefData.zip\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-6141459/v1/658c59ac03f960ed51d12739.zip\"}],\"financialInterests\":\"There is \\u003cb\\u003eNO\\u003c/b\\u003e Competing Interest.\",\"formattedTitle\":\"Revisiting Molecular Descriptors with TDiMS for Interpretable Intramolecular Interactions Based on Substructure Pairs\",\"fulltext\":[],\"fulltextSource\":\"\",\"fullText\":\"\",\"funders\":[],\"hasAdminPriorityOnWorkflow\":false,\"hasManuscriptDocX\":false,\"hasOptedInToPreprint\":true,\"hasPassedJournalQc\":\"\",\"hasAnyPriority\":true,\"hideJournal\":false,\"highlight\":\"\",\"institution\":\"\",\"isAcceptedByJournal\":false,\"isAuthorSuppliedPdf\":true,\"isDeskRejected\":\"\",\"isHiddenFromSearch\":false,\"isInQc\":false,\"isInWorkflow\":false,\"isPdf\":true,\"isPdfUpToDate\":true,\"isWithdrawnOrRetracted\":false,\"journal\":{\"display\":true,\"email\":\"info@researchsquare.com\",\"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\":\"\",\"lastPublishedDoi\":\"10.21203/rs.3.rs-6141459/v1\",\"lastPublishedDoiUrl\":\"https://doi.org/10.21203/rs.3.rs-6141459/v1\",\"license\":{\"name\":\"CC BY 4.0\",\"url\":\"https://creativecommons.org/licenses/by/4.0/\"},\"manuscriptAbstract\":\"Molecular descriptors play a crucial role in representing the structural features of molecules for machine learning-based physical property prediction. However, current descriptors either consider only local aspects of molecular structures or fail to effectively learn nonlocal structural features involving long-distance intramolecular interactions. To address this issue, we present a new descriptor named TDiMS. TDiMS effectively summarizes the enumerated pairwise topological distances between molecular substructures, thus capturing nonlocal interactions. \\r\\nOur evaluation shows that TDiMS successfully identifies essential features of large structures and outperforms other representative descriptors. Additionally, these identified features are highly interpretable for experts in material discovery.\",\"manuscriptTitle\":\"Revisiting Molecular Descriptors with TDiMS for Interpretable Intramolecular Interactions Based on Substructure Pairs\",\"msid\":\"\",\"msnumber\":\"\",\"nonDraftVersions\":[{\"code\":1,\"date\":\"2025-04-07 04:07:18\",\"doi\":\"10.21203/rs.3.rs-6141459/v1\",\"editorialEvents\":[],\"status\":\"published\",\"journal\":{\"display\":true,\"email\":\"info@researchsquare.com\",\"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\":\"fb74fcaf-e63c-4459-bb0d-d356946cf3bd\",\"owner\":[],\"postedDate\":\"April 7th, 2025\",\"published\":true,\"recentEditorialEvents\":[],\"rejectedJournal\":[],\"revision\":\"\",\"amendment\":\"\",\"status\":\"under-review\",\"subjectAreas\":[{\"id\":46655516,\"name\":\"Physical sciences/Chemistry/Cheminformatics\"},{\"id\":46655517,\"name\":\"Physical sciences/Materials science/Theory and computation/Computational methods\"}],\"tags\":[],\"updatedAt\":\"2026-04-10T06:20:19+00:00\",\"versionOfRecord\":[],\"versionCreatedAt\":\"2025-04-07 04:07:18\",\"video\":\"\",\"vorDoi\":\"\",\"vorDoiUrl\":\"\",\"workflowStages\":[]},\"version\":\"v1\",\"identity\":\"rs-6141459\",\"journalConfig\":\"researchsquare\"},\"__N_SSP\":true},\"page\":\"/article/[identity]/[[...version]]\",\"query\":{\"redirect\":\"/article/rs-6141459\",\"identity\":\"rs-6141459\",\"version\":[\"v1\"]},\"buildId\":\"8U1c8b4HqxoKbykW_rLl7\",\"isFallback\":false,\"isExperimentalCompile\":false,\"dynamicIds\":[84888],\"gssp\":true,\"scriptLoader\":[]}","source_license":"CC-BY-4.0","license_restricted":false}