3bmGPT: A novel language model for transforming and analyzing protein-ligand binding interactions in drug discovery.

preprint OA: closed
Full text JSON View at publisher

Abstract

Abstract Emergent Large Language Models (LLMs) show impressive capabilities in performing a wide range of tasks. These models can be harnessed for biophysical use, as well. The main challenge in this endeavor lies in transforming 3D chemical data into 1D language-like data. We developed a method to transform molecular data into language-like data and tokenize it for LLM use in biophysical context. We then trained a model, 3bmGPT, and validated it with a known protein-ligand complex. Using the pre-trained result, the model can assess the chemical properties of targets, detect shared binding properties and structures, and reveal related drugs. 3bmGPT and the synthetic-language to describe binding interactions uncovered novel protein-protein networks influenced by ligands, indicating functionally related yet previously unreported interactions. We provide open access to a fully functional web-based tool utilizing 3bmGPT.
Full text 12,667 characters · extracted from preprint-html · click to expand
3bmGPT: A novel language model for transforming and analyzing protein-ligand binding interactions in drug discovery. | 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 3bmGPT: A novel language model for transforming and analyzing protein-ligand binding interactions in drug discovery. Jongsun Jung, Taeseob Lee, Jonathan Witztum, Heehoon Jung, Ahnjae Jung, and 5 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3760296/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Emergent Large Language Models (LLMs) show impressive capabilities in performing a wide range of tasks. These models can be harnessed for biophysical use, as well. The main challenge in this endeavor lies in transforming 3D chemical data into 1D language-like data. We developed a method to transform molecular data into language-like data and tokenize it for LLM use in biophysical context. We then trained a model, 3bmGPT, and validated it with a known protein-ligand complex. Using the pre-trained result, the model can assess the chemical properties of targets, detect shared binding properties and structures, and reveal related drugs. 3bmGPT and the synthetic-language to describe binding interactions uncovered novel protein-protein networks influenced by ligands, indicating functionally related yet previously unreported interactions. We provide open access to a fully functional web-based tool utilizing 3bmGPT. Biological sciences/Computational biology and bioinformatics/Machine learning Biological sciences/Drug discovery Biological sciences/Computational biology and bioinformatics/Computational models Full Text Additional Declarations Yes there is potential Competing Interest. T.L., J.W., H.J., A.J., J.M., J.H.H., and J.J. have a financial interest in Syntekabio Incorporated, a biotechnology company focused on the drug development using AI algorithms. J.W. and J.J. have a financial interest in Syntekabio USA Incorporated, a business subsidiary of Syntekabio Incorporated. C.Z. has a financial interest in Cerebras Systems, an AI company building computer systems for AI applications. Cite Share Download PDF Status: Posted 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-3760296","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":266542978,"identity":"0a4ef731-8e43-4cba-9ec7-ff115da25374","order_by":0,"name":"Jongsun Jung","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA0klEQVRIiWNgGAWjYBACxgYg8QHMZGNgZjAgUgvjDCCDh2gtIMDMA9dClPIZuYdf2/w5nGfP3pb4uaDAhoG/vTsBv8Nm5KVZ57YdLubhOXZYeoZBGoPEmbMbCGjJMTPObTic2COR3iDNY3CYwUAilwgtFn+AWuSfN/8mVovxYwY2kC1sx4i0peeNGWNvW3piz5m0NGugX3gI+sWwPcf4w48/1ont7ceMbxf8sZHjb+8loKWBgU2CgaEZLsCDVzkIyAOjBphe6ggqHAWjYBSMghEMAEY5ReKBep/OAAAAAElFTkSuQmCC","orcid":"","institution":"Syntekabio USA","correspondingAuthor":true,"prefix":"","firstName":"Jongsun","middleName":"","lastName":"Jung","suffix":""},{"id":266542979,"identity":"7f16a7ed-8323-4115-956a-df680ede51bc","order_by":1,"name":"Taeseob Lee","email":"","orcid":"https://orcid.org/0000-0001-8042-7247","institution":"Syntekabio Incorporated","correspondingAuthor":false,"prefix":"","firstName":"Taeseob","middleName":"","lastName":"Lee","suffix":""},{"id":266542980,"identity":"77afa5fa-6ee2-4861-b986-823d66a9afba","order_by":2,"name":"Jonathan Witztum","email":"","orcid":"https://orcid.org/0000-0003-0092-2366","institution":"Syntekabio USA","correspondingAuthor":false,"prefix":"","firstName":"Jonathan","middleName":"","lastName":"Witztum","suffix":""},{"id":266542981,"identity":"0b1699fc-40b3-4eb0-8373-d851cff7fc6a","order_by":3,"name":"Heehoon Jung","email":"","orcid":"","institution":"Syntekabio Incorporated","correspondingAuthor":false,"prefix":"","firstName":"Heehoon","middleName":"","lastName":"Jung","suffix":""},{"id":266542982,"identity":"b06220cd-bfa4-40e6-a10f-947124dda0ae","order_by":4,"name":"Ahnjae Jung","email":"","orcid":"","institution":"Syntekabio Incorporated","correspondingAuthor":false,"prefix":"","firstName":"Ahnjae","middleName":"","lastName":"Jung","suffix":""},{"id":266542983,"identity":"2d57cc89-6ab9-4eda-b5a1-b88a0b351823","order_by":5,"name":"JaeWoong Min","email":"","orcid":"","institution":"Syntekabio Incorporated","correspondingAuthor":false,"prefix":"","firstName":"JaeWoong","middleName":"","lastName":"Min","suffix":""},{"id":266542984,"identity":"24827478-6615-409f-b0f9-74fd5a7e911a","order_by":6,"name":"Jong Hong","email":"","orcid":"","institution":"Syntekabio Incorporated","correspondingAuthor":false,"prefix":"","firstName":"Jong","middleName":"","lastName":"Hong","suffix":""},{"id":266542985,"identity":"62cd8599-38d8-4d32-af5c-70b17fe700fd","order_by":7,"name":"Bin Zhang","email":"","orcid":"","institution":"Cerebras Systems","correspondingAuthor":false,"prefix":"","firstName":"Bin","middleName":"","lastName":"Zhang","suffix":""},{"id":266542986,"identity":"bd7fc569-b73d-437c-8133-20ef17006b28","order_by":8,"name":"Junsik An","email":"","orcid":"","institution":"Syntekabio Incorporated","correspondingAuthor":false,"prefix":"","firstName":"Junsik","middleName":"","lastName":"An","suffix":""},{"id":266542987,"identity":"cded96d4-63d8-4661-b959-8de187743e3a","order_by":9,"name":"Woonyoung Hong","email":"","orcid":"","institution":"Syntekabio Incorporated","correspondingAuthor":false,"prefix":"","firstName":"Woonyoung","middleName":"","lastName":"Hong","suffix":""}],"badges":[],"createdAt":"2023-12-15 19:25:09","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3760296/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3760296/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":79796158,"identity":"a1028182-ecf1-47ec-a28f-2de876905fbb","added_by":"auto","created_at":"2025-04-02 23:48:23","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2149369,"visible":true,"origin":"","legend":"Article File","description":"","filename":"Leeet.al.January2024.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3760296/v1_covered_f6980bb2-8803-4940-bb5b-b747f5eca0d7.pdf"}],"financialInterests":"\u003cb\u003eYes\u003c/b\u003e there is potential Competing Interest.\nT.L., J.W., H.J., A.J., J.M., J.H.H., and J.J. have a financial interest in Syntekabio Incorporated, a biotechnology company focused on the drug development using AI algorithms. \r\n\r\nJ.W. and J.J. have a financial interest in Syntekabio USA Incorporated, a business subsidiary of Syntekabio Incorporated. \r\n\r\nC.Z. has a financial interest in Cerebras Systems, an AI company building computer systems for AI applications.","formattedTitle":"3bmGPT: A novel language model for transforming and analyzing protein-ligand binding interactions in drug discovery.","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-3760296/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3760296/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Emergent Large Language Models (LLMs) show impressive capabilities in performing a wide range of tasks. These models can be harnessed for biophysical use, as well. The main challenge in this endeavor lies in transforming 3D chemical data into 1D language-like data. We developed a method to transform molecular data into language-like data and tokenize it for LLM use in biophysical context. We then trained a model, 3bmGPT, and validated it with a known protein-ligand complex. Using the pre-trained result, the model can assess the chemical properties of targets, detect shared binding properties and structures, and reveal related drugs. 3bmGPT and the synthetic-language to describe binding interactions uncovered novel protein-protein networks influenced by ligands, indicating functionally related yet previously unreported interactions. We provide open access to a fully functional web-based tool utilizing 3bmGPT.","manuscriptTitle":"3bmGPT: A novel language model for transforming and analyzing protein-ligand binding interactions in drug discovery.","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-01-12 01:42:33","doi":"10.21203/rs.3.rs-3760296/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"ba9c3421-cf4e-49e2-9de0-4a73515f126d","owner":[],"postedDate":"January 12th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":28093647,"name":"Biological sciences/Computational biology and bioinformatics/Machine learning"},{"id":28093648,"name":"Biological sciences/Drug discovery"},{"id":28093649,"name":"Biological sciences/Computational biology and bioinformatics/Computational models"}],"tags":[],"updatedAt":"2025-04-02T23:40:13+00:00","versionOfRecord":[],"versionCreatedAt":"2024-01-12 01:42:33","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-3760296","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3760296","identity":"rs-3760296","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}

Text is read by the "Ask this paper" AI Q&A widget below. Extraction quality varies by source — PMC NXML preserves structure cleanly, OA-HTML may include some navigation residue, and OA-PDF can have broken hyphenation. The publisher copy (via DOI) is the canonical version.

My notes (saved in your browser only)

Ask this paper AI returns verbatim quotes from the full text · source: preprint-html

Answers must be backed by verbatim quotes from this paper's full text. Hallucinated quotes are dropped automatically; if no verbatim passage answers the question, we say so. How this works

Citation neighborhood (no data yet)

We don't have any in-corpus citations linked to this paper yet. This is a recent paper (2024) — citers typically take a year or two to land, and the OpenAlex reference graph may still be filling in.

Source provenance

europepmc
last seen: 2026-05-20T01:45:00.602351+00:00