[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125677-en":3,"doc-seo-125677-105":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":4,"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},125677,8796095360427,"Lucas Martin","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"Research & Report","Machine learning approaches in microbiome research - challenges and best practices","Machine learning-based predictive analysis of microbiome data within end-to-end workflows faces domain-specific difficulties across preprocessing, feature selection, predictive modeling, performance estimation, model interpretation, and biological inference. To support decision-making, the review compiles recommendations for algorithm choice, pipeline construction, and evaluation from the COST Action ML4Microbiome. On a multi-cohort shotgun metagenomics colorectal-cancer dataset, compositional transformations and filtering do not always enhance prediction, while multivariate feature selection like Statistically Equivalent Signatures reduces classification error. With separate test validation, combining this feature selection with random forest yields the most accurate estimates, and logistic regression with ICE visualization provides interpretable, biologically informative results for clinicians and nonexperts in translational settings.","TYPE Review  \nPUBLISHED 22 September 2023 DOI 10.3389/fmicb.2023.1261889  \nOPEN ACCESS  \nEDITED BY  \nDimitris G. Hatzinikolaou,  \nNational and Kapodistrian University of Athens, Greece  \nREVIEWED BY  \nZhenglin Tan,  \nHubei University of Economics, China Eswarappa Pradeep Bulagonda, Sri Sathya Sai Institute of Higher Learning (SSSIHL), India  \n*CORRESPONDENCE  \nGeorgios Papoutsoglou  \n [papoutsoglou@csd.uoc.gr](papoutsoglou@csd.uoc.gr)[ ](papoutsoglou@csd.uoc.gr)Magali Berland  \n [magali.berland@inrae.fr](magali.berland@inrae.fr)[ ](magali.berland@inrae.fr)RECEIVED 19 July 2023 ACCEPTED 04 September 2023 PUBLISHED 22 September 2023  \nCITATION  \nPapoutsoglou G, Tarazona S, Lopes MB, Klammsteiner T, Ibrahimi E, Eckenberger J, Novielli P, Tonda A, Simeon A, Shigdel R, Béreux S, Vitali G, Tangaro S, Lahti L, Temko A, Claesson MJ and Berland M (2023) Machine learning approaches in microbiome research:  \nchallenges and best practices.  \nFront. Microbiol. 14:1261889.  \ndoi: 10.3389/fmicb.2023.1261889  \nCOPYRIGHT  \n© 2023 Papoutsoglou, Tarazona, Lopes, Klammsteiner, Ibrahimi, Eckenberger, Novielli, Tonda, Simeon, Shigdel, Béreux, Vitali, Tangaro, Lahti, Temko, Claesson and Berland. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.  \nMachine learning approaches in microbiome research: challengesand best practices  \nGeorgios Papoutsoglou 1, 2*, Sonia Tarazona3, Marta B. Lopes4, 5, Thomas Klammsteiner 6, 7, Eliana Ibrahimi 8, Julia Eckenberger 9, 10, Pierfrancesco Novielli 11, 12 , Alberto Tonda 13, 14, Andrea Simeon 15, Rajesh Shigdel 16, Stéphane Béreux 17, 18, Giacomo Vitali 17, Sabina Tangaro 11, 12, Leo Lahti 19, Andriy Temko 20,  \nMarcus J. Claesson 9, 10 and Magali Berland 17*  \n1 Department of Computer Science, University of Crete, Heraklion, Greece, 2JADBio Gnosis DA S.A., Science and Technology Park of Crete, Heraklion, Greece, 3 Department of Applied Statistics and Operations Research and Quality, Polytechnic University of Valencia, Valencia, Spain, 4Center for Mathematics and Applications (NOVA Math), NOVA School of Science and Technology, Caparica, Portugal, 5 Research and Development Unit for Mechanical and Industrial Engineering (UNIDEMI), Department of Mechanical and Industrial Engineering, NOVA School of Science and Technology, Caparica, Portugal, 6 Department of Ecology, Universität Innsbruck, Innsbruck, Austria, 7 Department of Microbiology, Universität Innsbruck, Innsbruck, Austria, 8 Department of Biology, University of Tirana, Tirana, Albania, 9School of Microbiology, University College Cork, Cork, Ireland, 10APC Microbiome Ireland, Cork, Ireland, 11 Department of Soil, Plant, and Food Sciences, University of Bari Aldo Moro, Bari, Italy, 12 National Institute for Nuclear Physics, Bari Division, Bari, Italy, 13 UMR 518 MIA-PS, INRAE, ParisSaclay University, Palaiseau, France, 14Complex Systems Institute of Paris Ile-de-France (ISC-PIF) -UAR 3611 CNRS, Paris, France, 15 BioSense Institute, University of Novi Sad, Novi Sad, Serbia, 16 Department of Clinical Science, University of Bergen, Bergen, Norway, 17 MetaGenoPolis, INRAE, Paris-Saclay University, Jouy-en-Josas, France, 18 MaIAGE, INRAE, Paris-Saclay University, Jouy-en-Josas, France, 19 Department of Computing, University of Turku, Turku, Finland, 20 Department of Electrical and Electronic Engineering, University College Cork, Cork, Ireland  \nMicrobiome data predictive analysis within a machine learning (ML) workflow presents numerous domain-specific challenges involving preprocessing, featureselection, predictive modeling, performance estimation, model interpretation, an","cbCailUD6RmCj2Bt","https://ap.wps.com/l/cbCailUD6RmCj2Bt","pdf",4286875,1,21,"English","en",105,"# Introduction\n## Background: microbiome diversity and dysbiosis\n## ML workflow challenges and decision support\n# Data, preprocessing, and feature selection\n## Compositional transformations and filtering\n## Multivariate feature selection methods\n# Predictive modeling and evaluation\n## Random forest performance estimation\n## Logistic regression interpretability\n# Model interpretation and biological insights\n## ICE plots and biological inference\n# Conclusion and recommendations","[{\"question\":\"What main challenges does machine learning face in microbiome predictive analysis?\",\"answer\":\"The review highlights challenges in preprocessing, feature selection, predictive modeling, performance estimation, model interpretation, and extracting biological information from results.\"},{\"question\":\"Do compositional transformations and filtering always improve prediction?\",\"answer\":\"No. The review demonstrates that these preprocessing steps do not always lead to better predictive performance.\"},{\"question\":\"Which approaches performed best for disease diagnosis and biomarker discovery?\",\"answer\":\"Multivariate feature selection such as Statistically Equivalent Signatures reduced classification error, and when combined with random forest it produced the most accurate performance estimates on a separate test dataset.\"}]","Machine learning approaches in microbiome research - challenges and best practices | PDF",1785900608,53,{"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},"machine-learning-approaches-in-microbiome-research-challenges-and-best-practices","",{"@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/machine-learning-approaches-in-microbiome-research-challenges-and-best-practices/125677/",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","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What main challenges does machine learning face in microbiome predictive analysis?","Question",{"text":75,"@type":76},"The review highlights challenges in preprocessing, feature selection, predictive modeling, performance estimation, model interpretation, and extracting biological information from results.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Do compositional transformations and filtering always improve prediction?",{"text":80,"@type":76},"No. The review demonstrates that these preprocessing steps do not always lead to better predictive performance.",{"name":82,"@type":73,"acceptedAnswer":83},"Which approaches performed best for disease diagnosis and biomarker discovery?",{"text":84,"@type":76},"Multivariate feature selection such as Statistically Equivalent Signatures reduced classification error, and when combined with random forest it produced the most accurate performance estimates on a separate test dataset.","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"]