[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126958-en":3,"doc-seo-126958-105":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},126958,687207024478,"Liam","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Harmonizing heterogeneous transcriptomics datasets for machine learning-based analysis to identify spaceflown murine liver-specific changes","Machine learning can strengthen interpretation of high-dimensional molecular assays used in spaceflight studies, yet limited subject numbers within missions restrict model utility. An approach is presented to log transform, scale, and normalize six heterogeneous mouse liver transcriptomics datasets (137 total samples) to mitigate variability across mission origin. The harmonized pipeline enables ML to classify spaceflown versus ground control animals with AUC ≥ 0.87. Harmonized results show concordance with classical, study-by-study omics analyses and demonstrate feasibility for ML on integrated small-sample datasets.","npj | microgravity Article  \n\n| Published in cooperation with the Biodesign Institute at Arizona State University, with the support of NASA |  |  |\n| --- | --- | --- |\n| [https://doi.org/10.1038/s41526-024-00379-3](https://doi.org/10.1038/s41526-024-00379-3) |  |  |\n| Harmonizing heterogeneous transcriptomics datasets for machine learning-based analysis to identify spaceflown murine liver-specific changes\u003Cbr> Check for updates |  |  |\n| Hari Ilangovan 1 , Prachi Kothiyal2, Katherine A. Hoadley 3, Robin Elgart 4, Greg Eley2 & Parastou Eslami5 |  |  |\n| NASA has employed high-throughput molecular assays to identify sub-cellular changes impacting human physiology during spaceflight. Machine learning(ML)methods hold the promise to improve our ability to identify important signals within highly dimensional molecular data. However, the inherent limitation of study subject numbers within a spaceflight mission minimizes the utility of ML approaches. To overcome the sample power limitations, data from multiple spaceflight missions must be aggregated while appropriately addressing intra-and inter-study variabilities. Here we describe an approach to log transform, scale and normalize data from six heterogeneous, mouse liver-derived transcriptomics datasets (ntotal = 137) which enabled ML-methods to classify spaceflown vs. ground control animals (AUC ≥ 0.87) while mitigating the variability from mission-of-origin. Concordance was found between liver-specific biological processes identified from harmonized ML-based analysis and study-by-study classical omics analysis. This work demonstrates the feasibility of applying ML methods on integrated, heterogeneous datasets of small sample size. |  |  |\n| NASA’s long-duration deep space missions beyond low earth orbit (LEO) will expose astronauts to ionizing radiation and microgravity for durations longer than previously encountered by humans1,2. Characterization and mitigation of the adverse effects of prolonged spaceflight are critical for mission success as well as protecting the long-term health of the astronauts. The Rodent Research (RR) missions conducted since 2014 use rodent models flown to the International Space Station (ISS). These missions, originally designed to evaluate testing hardware, have evolved to study relevant biomarkers3, characterize the biological responses of different organs and systems to the space environment, and translate this knowledge from animal studies to inform risk characterization and countermeasure development4.\u003Cbr>When possible, next-generation sequencing (NGS), such as RNA-seq, has been applied to samples collected from the RR missions and the data generated from these experiments have been processed and stored in the NASA Open Science Data Repository (OSDR)5. NGS analysis further expands the biological insights generated from the RR mission models. | Specifically, these data enable interrogation of the impacts of spaceflight atthe molecular level to support translation from animal models to the human as many of the same underlying mechanisms that impact health outcomes are conserved across species. A robust understanding of how changes in gene expression may correlate with changes in relevant phenotypes associated with spaceflight can provide critical information to identify biomarkers for health surveillance and strategic countermeasure deployment, and targets for tactical countermeasure development to mitigate health risks. NASA’s heavy reliance on animal studies to characterize the risks associated with space radiation specifically, necessitates the ability to appropriately and effectively translate animal data to humans. One of the organs of interest and studied in spaceflight missions is the liver. The liver plays a critical role in carbohydrate and lipid metabolism, as well as the processing of xenobiotic substances. Additionally, hepatic cancer is considered radiogenic as it has been shown to develop following exposure to ionizing radiation in both humans and anim","cbCaivhn2I2SAanV","https://ap.wps.com/l/cbCaivhn2I2SAanV","pdf",2901300,1,11,"English","en",105,"# Background\n## Spaceflight health risk context\n## Rodent research missions and RNA-seq data\n# Problem and challenges\n## Small sample sizes and variability across missions\n# Proposed approach\n## Log transform, scaling, and normalization\n## Integrating six heterogeneous mouse liver datasets\n# Results and validation\n## ML classification of spaceflown vs. ground controls\n## Concordance with classical omics analyses\n# Implications\n## Feasibility of ML with integrated small-sample datasets","[{\"question\":\"Why is data harmonization needed for machine learning on spaceflight transcriptomics?\",\"answer\":\"Spaceflight missions have limited numbers of animals per experimental group and datasets differ in mission origin, creating variability that reduces ML effectiveness. Harmonization helps mitigate these intra- and inter-study differences so models can learn relevant signals.\"},{\"question\":\"What preprocessing steps are used in the proposed method?\",\"answer\":\"The approach applies log transformation, scaling, and normalization to six heterogeneous mouse liver-derived transcriptomics datasets before running ML.\"},{\"question\":\"How well does the harmonized ML analysis distinguish spaceflown from ground control animals?\",\"answer\":\"The harmonized ML pipeline classifies spaceflown versus ground control animals with an AUC of at least 0.87 while mitigating variability caused by the mission of origin.\"}]","Harmonizing heterogeneous transcriptomics datasets for machine learning-based analysis to identify spaceflown murine liver-specific changes | PDF",1785935904,28,{"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},"harmonizing-heterogeneous-transcriptomics-datasets-for-machine-learning-based-analysis-to-identify-spaceflown-murine-liver-specific-changes","",{"@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/harmonizing-heterogeneous-transcriptomics-datasets-for-machine-learning-based-analysis-to-identify-spaceflown-murine-liver-specific-changes/126958/",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},"Why is data harmonization needed for machine learning on spaceflight transcriptomics?","Question",{"text":75,"@type":76},"Spaceflight missions have limited numbers of animals per experimental group and datasets differ in mission origin, creating variability that reduces ML effectiveness. Harmonization helps mitigate these intra- and inter-study differences so models can learn relevant signals.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What preprocessing steps are used in the proposed method?",{"text":80,"@type":76},"The approach applies log transformation, scaling, and normalization to six heterogeneous mouse liver-derived transcriptomics datasets before running ML.",{"name":82,"@type":73,"acceptedAnswer":83},"How well does the harmonized ML analysis distinguish spaceflown from ground control animals?",{"text":84,"@type":76},"The harmonized ML pipeline classifies spaceflown versus ground control animals with an AUC of at least 0.87 while mitigating variability caused by the mission of origin.","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"]