[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122361-en":3,"doc-seo-122361-105":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},122361,1374391974468,"Eden","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","An evaluation methodology for machine learning-based tandem mass spectra similarity prediction","Machine learning-based prediction of tandem mass spectra (MS/MS) structural similarity is advancing as an alternative to algorithmic spectral matching, especially for scalable identification of small molecules used in metabolomics and natural products. A major obstacle remains the lack of standardized benchmarks, evaluation protocols, and safeguards against data leakage across training and test data. This study presents a new train/test split evaluation methodology that varies structural similarity, introduces domain-inspired accuracy metrics for realistic retrieval tasks, compares alternative training strategies, and highlights the impact of collision energy on errors while releasing updated datasets and pipelines for community use.","UC Riverside  \nUC Riverside Previously Published Works  \nTitle  \nAn evaluation methodology for machine learning-based tandem mass spectra similarity prediction.  \nPermalink  \n[https://escholarship.org/uc/item/5kw514nz](https://escholarship.org/uc/item/5kw514nz)  \nJournal  \nBMC Bioinformatics, 26(1)  \nISSN  \n1471-2105  \nAuthors  \nStrobel, Michael  \nGil-de-la-Fuente, Alberto Zare Shahneh, Mohammad et al.  \nPublication Date  \n2025-07-01  \nDOI  \n10.1186/s12859-025-06194-1  \nCopyright Information  \nThis work is made available under the terms of a Creative Commons Attribution License, available at [https://creativecommons.org/licenses/by/4.0/](https://creativecommons.org/licenses/by/4.0/)  \nPeer reviewed  \n[eScholarship.org](eScholarship.org) Powered by the California Digital Library  \nUniversity of California  \nStrobel et al. BMC Bioinformatics (2025) 26:174 [https://doi.org/10.1186/s12859-025-06194-1](https://doi.org/10.1186/s12859-025-06194-1)  \nBMC Bioinformatics  \nRESEARCH Open Access  \nAn evaluation methodology for machine learning-based tandem mass spectra similarity prediction  \nMichael Strobel 1, Alberto Gil-de-la-Fuente2, Mohammad Reza Zare Shahneh 1, Yasin El Abiead3, Roman Bushuiev4,5, Anton Bushuiev5, Tomáš Pluskal4 and Mingxun Wang 1*  \n*Correspondence:  \nMingxun Wang [mingxun.wang@cs. ucr.edu](mingxun.wang@cs. ucr.edu)[ ](mingxun.wang@cs. ucr.edu)1Department of Computer Science and Engineering, University of California Riverside, 900 University Ave., Riverside, CA 92521, USA 2Information Technologies Department, Escuela Politécnica Superior, Universidad San PabloCEU, CEU Universities, Urbanización Montepríncipe, Boadilla Del monte, 28668 Madrid, Spain  \n3Skaggs School of Pharmacy and Pharmaceutical Science, University of California San Diego, 9255 Pharmacy Ln, San Diego, CA 92093, USA  \n4Institute of Organic Chemistry and Biochemistry, Czech Academy of Sciences, Flemingovo nám. 542/2, Prague 16000, Czech Republic 5Czech Institute of Informatics, Robotics and Cybernetics, Jugoslávských partyzánů 1580/3, Prague 16000, Czech Republic  \nAbstract  \nBackground Untargeted tandem mass spectrometry serves as a scalable solution for the organization of small molecules. One of the most prevalent techniques for analyzing the acquired tandem mass spectrometry data (MS/MS) -called molecular networking-organizes and visualizes putatively structurally related compounds. However, a key bottleneck of this approach is the comparison of MS/MS spectra used to identify nearby structural neighbors. Machine learning (ML) approaches have emerged as a promising technique to predict structural similarity from MS/MS that may surpass the current state-of-the-art algorithmic methods. However, the comparison between these different ML methods remains a challenge because there is a lack of standardization to benchmark, evaluate, and compare MS/MS similarity methods, and there are no methods that address data leakage between training and test data in order to analyze model generalizability.  \nResult In this work, we present the creation of a new evaluation methodology using a train/test split that allows for the evaluation of machine learning models at varying degrees of structural similarity between training and test sets. We also introduce a training and evaluation framework that measures prediction accuracy on domaininspired annotation and retrieval metrics designed to mirror real-world applications. We further show how two alternative training methods that leverage MS specific insights (e. g., similar instrumentation, collision energy, adduct) affect method performance and demonstrate the orthogonality of the proposed metrics. We especially highlight the role that collision energy plays in prediction errors. Finally, we release a continually updated version of our dataset online along with our data cleaning and splitting pipelines for community use.  \nConclusion It is our hope that this benchmark will serve as the basis of development for future ","cbCaiikCITk5FNRT","https://ap.wps.com/l/cbCaiikCITk5FNRT","pdf",3088967,1,18,"English","en",105,"# Abstract\n## Background\n## Result\n## Conclusion\n# Main Content (Unfinished Extract)","[{\"question\":\"What evaluation problem does this work target for ML-based MS/MS similarity prediction?\",\"answer\":\"It addresses the lack of standardization to benchmark and compare MS/MS similarity methods, including the need to handle data leakage between training and test sets.\"},{\"question\":\"How does the proposed methodology enable evaluation under different structural similarities?\",\"answer\":\"It uses a train/test split scheme that varies the degree of structural similarity between training and test sets.\"},{\"question\":\"Which factors and metrics does the framework use to assess prediction performance?\",\"answer\":\"It introduces domain-inspired annotation and retrieval metrics and examines how MS-specific training choices (e.g., instrumentation, collision energy, adduct) affect performance, emphasizing collision energy’s role in prediction errors.\"}]","An evaluation methodology for machine learning-based tandem mass spectra similarity prediction | PDF",1785810241,45,{"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},"an-evaluation-methodology-for-machine-learning-based-tandem-mass-spectra-similarity-prediction","",{"@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/an-evaluation-methodology-for-machine-learning-based-tandem-mass-spectra-similarity-prediction/122361/",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 evaluation problem does this work target for ML-based MS/MS similarity prediction?","Question",{"text":75,"@type":76},"It addresses the lack of standardization to benchmark and compare MS/MS similarity methods, including the need to handle data leakage between training and test sets.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed methodology enable evaluation under different structural similarities?",{"text":80,"@type":76},"It uses a train/test split scheme that varies the degree of structural similarity between training and test sets.",{"name":82,"@type":73,"acceptedAnswer":83},"Which factors and metrics does the framework use to assess prediction performance?",{"text":84,"@type":76},"It introduces domain-inspired annotation and retrieval metrics and examines how MS-specific training choices (e.g., instrumentation, collision energy, adduct) affect performance, emphasizing collision energy’s role in prediction errors.","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"]