[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120598-en":3,"doc-seo-120598-105":30,"detail-sidebar-cat-0-en-105":91},{"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":20,"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},120598,1099514068365,"Aurelia","https://ap-avatar.wpscdn.com/avatar/10000253d8d9f28188e?_k=1776742907772140068",8,"Research & Report","Chemical shifts in molecular solids by machine learning","Solid-state nuclear magnetic resonance (NMR) chemical shifts depend strongly on local atomic environments, making them powerful for structure elucidation of powdered solids and amorphous materials. Structure determination, however, requires accurate calculations, which are costly with first-principles density functional theory (DFT). This work introduces a machine learning approach that learns local environments to predict chemical shifts of molecular solids and polymorphs with DFT-level accuracy, and enables structure identification by matching experimental shifts to ML predictions.","ARTICLE  \n DOI: 10.1038/s41467-018-06972-x  OPEN  \nChemical shifts in molecular solids by machine learning  \nFederico M. Paruzzo1, Albert Hofstetter  1, Félix Musil2, Sandip De  2, Michele Ceriotti  2 & Lyndon Emsley1  \nDue to their strong dependence on local atonic environments, NMR chemical shifts are among the most powerful tools for strucutre elucidation of powdered solids or amorphous materials. Unfortunately, using them for structure determination depends on the ability to calculate them, which comes at the cost of high accuracy first-principles calculations. Machine learning has recently emerged as a way to overcome the need for quantum chemical calculations, but for chemical shifts in solids it is hindered by the chemical and combinatorial space spanned by molecular solids, the strong dependency of chemical shifts on their environment, and the lack of an experimental database of shifts. We propose a machine learning method based on local environments to accurately predict chemical shifts of molecular solids and their polymorphs to within DFT accuracy. We also demonstrate that the trained model is able to determine, based on the match between experimentally measured and ML-predicted shifts, the structures of cocaine and the drug 4-[4-(2-adamantylcarbamoyl)-5-tert-butylpyrazol-1-yl]benzoic acid.  \n1 Institut des Sciences et Ingénierie Chimiques, Ecole Polytechnique Fédérale de Lausanne (EPFL), 1015 Lausanne, Switzerland. 2 Institut des Sciences et Génie Matériaux, Ecole Polytechnique Fédérale de Lausanne (EPFL), 1015 Lausanne, Switzerland. Correspondence and requests for materials should be addressed to M. C. (email: michele. ceriotti@epfl . ch) or to L. E. (email: lyndon. emsley@epfl . ch)  \nNATURE COMMUNICATIONS | (2018)9:4501 |DOI: [10.1038/s41467-018-06972-x |www.nature.com/naturecommunications](10.1038/s41467-018-06972-x |www.nature.com/naturecommunications) 1  \nS  \nolid-state nuclear magnetic resonance (NMR) spectroscopy is among the most powerful methods for determining the atomic-level structure and dynamics of powdered and  \namorphous solids. Notably, solid-state NMR directly probes the local atomic environments and thus allows for characterization without the need for long-range order. This has led to its broad use today in many fields including for instance materials and pharmaceutical chemistry. In the latter the determination of structure and packing is essential to elaborate structure–property relations for formulations in the drug development process.  \nA revolution in solid-state NMR has occurred with the introduction of accurate methods to calculate chemical shifts 1–3, in particular using plane wave density functional theory (DFT) methods developed for periodic systems based on the projected augmented wave (PAW)/gauge including PAW (GIPAW) approach4–6. This has enabled very rapid development of chemical shift-based NMR crystallography, which is now widely used to validate structures of molecular solids and identify known polymorphs7–26, or more recently in combination with crystal structure prediction (CSP) protocols, to determine de novo crystal structures from powders27–32. Recent studies also suggest that the structural accuracy of chemical shift-based solid-state NMR crystallography is at least comparable with more traditional methods, such as single crystal X-ray diffraction33.  \nThe power of the method arises from the fact that plane wave DFT with the GIPAW method is accurate enough to reproduce the exquisite sensitivity of chemical shifts to changes in local atomic environments. However, this approach also has severe limitations. The cubic scaling of the computational cost with system size prevents the application to larger and more complex crystals, or nonequilibrium structures. If one wanted to use more accurate ab initio calculations, the expense is prohibitive.  \nMachine learning (ML) is emerging as a new tool in many areas of chemical and physical science, and potentially provides a method to br","cbCaimXncMs6te1F","https://ap.wps.com/l/cbCaimXncMs6te1F","pdf",1497550,1,10,"English","en",105,"# Introduction\n## Solid-state NMR and chemical-shift-based crystallography\n## Limitations of first-principles calculations\n## Motivation for machine learning\n# Method\n## Local-environment machine learning framework\n## Training data and test prediction strategy\n# Demonstrations","[{\"question\":\"Why are NMR chemical shifts important for studying molecular solids?\",\"answer\":\"They are highly sensitive to local atomic environments, allowing characterization of powdered and amorphous solids without requiring long-range order.\"},{\"question\":\"What prevents widespread structure determination using chemical shifts?\",\"answer\":\" Accurate prediction typically depends on high-accuracy first-principles calculations, which are computationally expensive.\"},{\"question\":\"How does the proposed machine learning method enable chemical-shift prediction and structure identification?\",\"answer\":\"It learns local environments from DFT-calculated shifts for diverse structures, then predicts shifts for new materials and determines structures by matching experimentally measured shifts with ML-predicted ones.\"}]","Chemical shifts in molecular solids by machine learning | PDF",1785730829,25,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":28},"chemical-shifts-in-molecular-solids-by-machine-learning","",{"@graph":36,"@context":85},[37,54,68],{"@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/chemical-shifts-in-molecular-solids-by-machine-learning/120598/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why are NMR chemical shifts important for studying molecular solids?","Question",{"text":75,"@type":76},"They are highly sensitive to local atomic environments, allowing characterization of powdered and amorphous solids without requiring long-range order.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What prevents widespread structure determination using chemical shifts?",{"text":80,"@type":76},"Accurate prediction typically depends on high-accuracy first-principles calculations, which are computationally expensive.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the proposed machine learning method enable chemical-shift prediction and structure identification?",{"text":84,"@type":76},"It learns local environments from DFT-calculated shifts for diverse structures, then predicts shifts for new materials and determines structures by matching experimentally measured shifts with ML-predicted ones.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":21,"slug":133},"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]