[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122671-en":3,"doc-seo-122671-105":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},122671,549758146520,"Patrick","https://ap-avatar.wpscdn.com/avatar/80002397d8c0411e94?_k=1775819394049821470",8,"Research & Report","SPICE - A Dataset of Drug-like Molecules and Peptides for Training Machine Learning Potentials","SPICE is introduced as a new quantum chemistry dataset designed to train machine learning potentials for molecular simulation of drug-like small molecules interacting with proteins. The dataset provides over 1.1 million conformations spanning small molecules, dimers, dipeptides, and solvated amino acids, covering 15 elements and both charged and uncharged systems. It includes forces and energies computed at the ωB97M-D3(BJ)/def2-TZVPPD level, plus multipole moments and bond orders, enabling models to reach chemical accuracy over broad chemical space for transferable, ready-to-use potential functions.","[www. nature.com/scientificdata](www. nature.com/scientificdata)  \noPEN  \nData DESCRIPtoR  \nSPICE, a Dataset of Drug-like Molecules and Peptides for training Machine Learning Potentials  \nPeter Eastman1 ✉, Pavan Kumar Behara2, David L. Dotson3, Raimondas Galvelis4, John E. Herr5, Josh t. Horton6, Yuezhi Mao1, John D. Chodera7, Benjamin P. Pritchard8, Yuanqing Wang7,9, Gianni De Fabritiis4,10 & thomas E. Markland1  \nMachine learning potentials are an important tool for molecular simulation, but their development is held back by a shortage of high quality datasets to train them on. We describe the SPICE dataset, a new quantum chemistry dataset for training potentials relevant to simulating drug-like small molecules interacting with proteins. It contains over 1.1 million conformations for a diverse set of small molecules, dimers, dipeptides, and solvated amino acids. It includes 15 elements, charged and uncharged molecules, and a wide range of covalent and non-covalent interactions. It provides both forces and energies calculated atthe ωB97M-D3(BJ)/def2-TZVPPD level of theory, along with other useful quantities such as multipole moments and bond orders. We train a set of machine learning potentials on it and demonstrate that they can achieve chemical accuracy across a broad region of chemical space. It can serve as a valuable resource for the creation of transferable, ready to use potential functions for use in molecular simulations.  \nBackground & Summary  \nIntroduction. Machine learning potentials are an important, rapidly advancing tool for molecular simulation1. One creates a neural network or other machine learning model that takes atomic positions as input and produces potential energy and forces as output. The model is typically trained on a dataset of ground state potential energies, and possibly nuclear forces, produced with a conventional quantum chemistry method such as Density Functional Theory (DFT) or Coupled Cluster (CC). The model can be nearly as accurate as the original quantum chemistry method while being orders of magnitude faster to compute2,3. Machine learning potentials have been shown to be a practical tool for improving the accuracy of important calculations, such as protein-ligand binding free energies4,5. Many new architectures for machine learning potentials have been proposed in the last few years6–11.  \nAlthough the methodology for developing machine learning potentials is advancing quickly, much of the practical benefit has yet to be realized. There are very few general, pretrained, ready to use potentials available. A chemist or biologist wishing to perform calculations on a molecule cannot simply select a standard potential function, as they would a DFT functional or molecular mechanics force field. For machine learning potentials to fully realize their promise, the development of pretrained general (or transferrable) potential functions is essential. A user should be able to select a potential function and immediately start performing calculations with it. A major factor currently limiting the creation of pretrained potentials is a lack of suitable training data. Any machine learning model is only as good as the data it is trained on. A person wishing to create a machine  \n1 Department of Chemistry, Stanford University, Stanford, CA, 94305, USA. 2 Department of Pharmaceutical Sciences, University of California, Irvine, CA, 92697, USA. 3the Open force field initiative, Open Molecular Software Foundation, Davis, CA, 95616, USA. 4Acellera Labs, Doctor Trueta 183, 08005, Barcelona, Spain. 5 Department of Chemistry and Biochemistry, University of Notre Dame, Notre Dame, IN, 46556, USA. 6School of natural and Environmental Sciences, Newcastle University, Newcastle upon Tyne, NE1 7RU, United Kingdom. 7computational and Systems Biology Program, Sloan Kettering Institute, Memorial Sloan Kettering Cancer Center, New York, NY, 10065, USA. 8Molecular Sciences Software Institute, Virginia Polytechnic Institut","cbCail6nAkHuoR57","https://ap.wps.com/l/cbCail6nAkHuoR57","pdf",1196814,1,11,"English","en",105,"# Background & Summary\n## Introduction\n## Dataset Motivation and Need for Pretrained Potentials\n## SPICE Dataset Overview\n## Article Organization","[{\"question\":\"What problem does the SPICE dataset address in machine learning potentials?\",\"answer\":\"It tackles the shortage of high-quality training datasets needed to develop general, pretrained potential functions for molecular simulation.\"},{\"question\":\"What kinds of molecular systems and conformations does SPICE include?\",\"answer\":\"SPICE contains over 1.1 million conformations for small molecules, dimers, dipeptides, and solvated amino acids, relevant to environments in drug discovery.\"},{\"question\":\"Which quantum chemistry level does SPICE use to provide forces and energies?\",\"answer\":\"It provides forces and energies calculated at the ωB97M-D3(BJ)/def2-TZVPPD level of theory, along with additional quantities like multipole moments and bond orders.\"}]","SPICE - A Dataset of Drug-like Molecules and Peptides for Training Machine Learning Potentials | PDF",1785812089,28,{"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},"spice-a-dataset-of-drug-like-molecules-and-peptides-for-training-machine-learning-potentials","",{"@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/spice-a-dataset-of-drug-like-molecules-and-peptides-for-training-machine-learning-potentials/122671/",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","2026-08-04",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},"What problem does the SPICE dataset address in machine learning potentials?","Question",{"text":75,"@type":76},"It tackles the shortage of high-quality training datasets needed to develop general, pretrained potential functions for molecular simulation.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What kinds of molecular systems and conformations does SPICE include?",{"text":80,"@type":76},"SPICE contains over 1.1 million conformations for small molecules, dimers, dipeptides, and solvated amino acids, relevant to environments in drug discovery.",{"name":82,"@type":73,"acceptedAnswer":83},"Which quantum chemistry level does SPICE use to provide forces and energies?",{"text":84,"@type":76},"It provides forces and energies calculated at the ωB97M-D3(BJ)/def2-TZVPPD level of theory, along with additional quantities like multipole moments and bond orders.","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},[93,97,101,105,110,115,120,123,128,131,135],{"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":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]