[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126017-en":3,"doc-seo-126017-105":30,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":11,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},126017,2336474466412,"Ezra","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Highly Accurate Prediction of NMR Chemical Shifts from Low-Level Quantum Mechanics Calculations Using Machine Learning","Theoretical predictions of NMR chemical shifts from first principles can streamline experimental interpretation and structure identification across gas, solution, and solid-state phases. However, achieving high accuracy with gold-standard CCSD(T) plus complete basis set treatments is often prohibitively expensive. Machine learning offers cheaper alternatives but struggles to generalize beyond the training distribution. This work develops and evaluates ML models using low-level QM features to predict high-level chemical shieldings with robust performance and error-aware reliability.","UC Berkeley  \nUC Berkeley Previously Published Works  \nTitle  \nHighly Accurate Prediction of NMR Chemical Shifts from Low-Level Quantum Mechanics Calculations Using Machine Learning.  \nPermalink  \n[https://escholarship.org/uc/item/1j12p9g2](https://escholarship.org/uc/item/1j12p9g2)  \nJournal  \nJournal of Chemical Theory and Computation, 20(5)  \nAuthors  \nLi, Jie  \nLiang, Jiashu Wang, Zheet al.  \nPublication Date  \n2024-03-12  \nDOI  \n10.1021/acs.jctc.3c01256  \nPeer reviewed  \n[eScholarship.org](eScholarship.org) Powered by the California Digital Library  \nUniversity of California  \nAuthor Manuscript Author Manuscript Author Manuscript Author Manuscript  \n\n|  | HHS Public Access\u003Cbr>Author manuscript\u003Cbr>J Chem Theory Comput. Author manuscript; available in PMC 2025 January 06. |\n| --- | --- |\n\nPublished in final edited form as:  \nJ Chem Theory Comput. 2024 March 12; 20(5): 2152–2166. doi:10.1021/acs.jctc.3c01256 .  \nHighly Accurate Prediction of NMR Chemical Shifts from LowLevel Quantum Mechanics Calculations Using Machine Learning  \nJie Li 1,\\# , Jiashu Liang 1,\\# , Zhe Wang 1 , Aleksandra L. Ptaszek2,3 , Xiao Liu 1 , Brad Ganoe 1 , Martin Head-Gordon 1,4 , Teresa Head-Gordon 1,4,5  \n1 Pitzer Center for Theoretical Chemistry, Department of Chemistry, University of California, Berkeley, California 94720, United States.  \n2Christian Doppler Laboratory for High-Content Structural Biology and Biotechnology, Department of Structural and Computational Biology, Max Perutz Laboratories, University of Vienna, Campus Vienna Biocenter 5, Vienna 1030, Austria.  \n3Laboratory for Computer-Aided Molecular Design, Division of Medicinal Chemistry, Otto Loewi Research Center, Medical University Graz, Neue Stiftingtalstrasse 6/III, Graz 8010, Austria.  \n4Chemical Sciences Division, Lawrence Berkeley National Laboratory, Berkeley, California 94720, United States.  \n5 Departments of Bioengineering and Chemical and Biomolecular Engineering, University of California, Berkeley, Berkeley, California 94720, United States.  \nAbstract  \nTheoretical predictions of NMR chemical shifts from first principles can greatly facilitate experimental interpretation and structure identification of molecules in gas, solution, and solidstate phases. However, accurate prediction of chemical shifts using the gold-standard coupled cluster with a full treatment of singles and doubles and triplet perturbation (CCSD(T)) method with a complete basis set (CBS) can be prohibitively expensive. By contrast, machine learning (ML) methods offer inexpensive alternatives for chemical shift predictions but are hampered by generalization to molecules outside the original training set. Here we propose several new  \nhEg@quleenlteyrib.eduution.   \nAUTHOR CONTRIBUTIONS  \nJie L., Jiashu L., M.H.G, and T.H.G. designed the project. Jie L. and Jiashu L. designed the ML models, and A.L.P. helped train the TEV model. Z.W., X.L. Jiashu L. generated the QM data. All authors discussed the results and made comments and edits to the manuscript.  \nDATA AND CODE AVAILABILITY  \nThe code package is provided through GitHub repository link: [https://github.com/THGLab/iShiftML](https://github.com/THGLab/iShiftML)  \nDS-SS (subsampled dataset from ANI-1 with unstable molecules excluded): [https://github.com/THGLab/iShiftML/blob/master/](https://github.com/THGLab/iShiftML/blob/master/)[ ](https://github.com/THGLab/iShiftML/blob/master/)[dataset/DS-SS.txt](dataset/DS-SS.txt)  \nDS-AL (active learning dataset): [https://github.com/THGLab/iShiftML/blob/master/dataset/DS-AL.txt](https://github.com/THGLab/iShiftML/blob/master/dataset/DS-AL.txt)  \nRemoved chemical shielding: [8_atom/mol_34274/99.xyz/atom_6](8_atom/mol_34274/99.xyz/atom_6) (calculated low-level chemical shielding: −2.066, calculated high  \nlevel chemical shielding: 197.792) SUPPORTING INFORMATION  \nScatter plots and tabulated values of experimental chemical shifts versus the predicted or calculated chemical shieldings under the low-level DFT calculati","cbCailGvIupXQlIZ","https://ap.wps.com/l/cbCailGvIupXQlIZ","pdf",1680547,1,34,"English","en",105,"# Abstract\n## Introduction\n## Author Contributions\n## Data and Code Availability\n## Supporting Information\n## Declaration of Interests","[{\"question\":\"Why is predicting NMR chemical shifts from first principles often expensive?\",\"answer\":\"Accurate shift predictions typically require gold-standard CCSD(T) calculations with a complete basis set, which are computationally expensive.\"},{\"question\":\"What key limitation affects existing machine-learning approaches for chemical shift prediction?\",\"answer\":\"They can be hindered by poor generalization to molecules outside the original training set.\"},{\"question\":\"How does the proposed method improve efficiency and reliability of predictions?\",\"answer\":\"It uses low-level quantum-mechanics-derived feature representations and introduces a progressive active learning workflow to reduce expensive high-level calculations, while providing error estimation to flag unreliable predictions.\"}]","Highly Accurate Prediction of NMR Chemical Shifts from Low-Level Quantum Mechanics Calculations Using Machine Learning | PDF",1785902565,86,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":28},"highly-accurate-prediction-of-nmr-chemical-shifts-from-low-level-quantum-mechanics-calculations-using-machine-learning","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/highly-accurate-prediction-of-nmr-chemical-shifts-from-low-level-quantum-mechanics-calculations-using-machine-learning/126017/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-25","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":11},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why is predicting NMR chemical shifts from first principles often expensive?","Question",{"text":76,"@type":77},"Accurate shift predictions typically require gold-standard CCSD(T) calculations with a complete basis set, which are computationally expensive.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What key limitation affects existing machine-learning approaches for chemical shift prediction?",{"text":81,"@type":77},"They can be hindered by poor generalization to molecules outside the original training set.",{"name":83,"@type":74,"acceptedAnswer":84},"How does the proposed method improve efficiency and reliability of predictions?",{"text":85,"@type":77},"It uses low-level quantum-mechanics-derived feature representations and introduces a progressive active learning workflow to reduce expensive high-level calculations, while providing error estimation to flag unreliable predictions.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]