[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124741-en":3,"doc-seo-124741-105":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},124741,16904993612988,"Olivia Brown","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Causal Machine Learning for Single-Cell Genomics - Perspective","Advances in single-cell omics enable detailed transcription profiles of individual cells and, when paired with large-scale perturbation screens, allow measurement of targeted perturbations’ effects across the whole transcriptome. This supports stronger mechanistic understanding of gene causality in processes such as gene regulation, disease progression, and cellular development. The task remains challenging due to high-dimensional measurements and complex biological systems. The perspective reviews how current causal methods apply to single-cell genomics, challenges key assumptions, and highlights open problems including generalization, interpretability, and causal modeling of dynamics.","Causal machine learning for single-cell genomics  \nAlejandro Tejada-Lapuerta1 ,5* , Paul Bertin2 ,3* , Stefan Bauer4 ,5 , Hananeh Aliee6☨ , Yoshua  \nBengio2 ,3☨ , Fabian J. Theis1 ,5☨  \n1 Institute of Computational Biology, Helmholtz Munich, Munich, Germany  \n2 Mila, the Quebec AI Institute, Montreal, Canada  \n3 Université de Montréal, Montréal, Canada  \n4 Helmholtz AI, Munich, Germany  \n5 Technical University of Munich, Munich, Germany  \n6 Sanger Institute, Cambridge, UK  \n* Equal contribution  \n☨ Correspondence to \u003C [ha10@sanger.ac.uk](ha10@sanger.ac.uk) >, \u003C [yoshua.bengio@mila.quebec](yoshua.bengio@mila.quebec) >  \nand \u003C [fabian.theis@helmholtz-munich.de](fabian.theis@helmholtz-munich.de) >  \nAbstract  \nAdvances in single-cell omics allow for unprecedented insights into the transcription profiles of individual cells. When combined with large-scale perturbation screens, through which specific biological mechanisms can be targeted, these technologies allow for measuring the effect of targeted perturbations on the whole transcriptome. These advances provide an opportunity to better understand the causative role of genes in complex biological processes such as gene regulation, disease progression or cellular development. However, the high-dimensional nature of the data, coupled with the intricate complexity of biological systems renders this task nontrivial. Within the machine learning community, there has been a recent increase of interest in causality, with a focus on adapting established causal techniques and algorithms to handle high-dimensional data. In this perspective, we delineate the application of these methodologies within the realm of single-cell genomics and their challenges. We first present the model that underlies most of current causal approaches to single-cell biology and discuss and challenge the assumptions it entails from the biological point of view. We then identify open problems in the application of causal approaches to single-cell data: generalising to unseen environments, learning interpretable models, and learning causal models of dynamics. For each problem, we discuss how various research directions – including the development of computational approaches and the adaptation of experimental protocols – may offer ways forward, or on the contrary pose some difficulties. With the advent of single cell atlases and increasing perturbation data, we expect causal models to become a crucial tool for informed experimental design.  \nIntroduction and motivation  \nCells are the basic unit of life, and the biological functions they perform, as well as the identity they acquire are the result of physical and biochemical processes that happen in nature. In particular, these processes influence how cells respond to treatments and other perturbations. Technological advances in molecular profiling at single-cell resolution have provided an unprecedented view on cellular processes. It is now possible to jointly measure multiple modalities, such as chromatin accessibility, RNA expression and protein abundance, in a single cell1–4 . Furthermore, such rich molecular measurements can be accompanied by additional information on the temporal or spatial context of the cell5–9. The above measurements can be performed at high-throughput, allowing us to sample several thousands of single cells in a single experiment – and millions of cells by a single lab within weeks –, enabling the assembly of detailed molecular maps of cellular variation and tissue organisation. Classical scientific approaches may fail at modelling and identifying the behaviours and dynamics of complex biological systems due to the huge number of variables of interest – typically in the order of 104 􀕜􀕗 105–1* , the often multimodal nature of the biological observations and partial observability of the system.  \nMachine learning has proven useful for solving complex tasks on high dimensional data infields such as computer vision and natural language processing","cbCaicXmJyZJ1Dig","https://ap.wps.com/l/cbCaicXmJyZJ1Dig","pdf",3184753,1,36,"English","en",105,"# Abstract\n# Introduction and motivation\n## Single-cell omics and perturbation data\n## Limits of statistical learning\n## Causal learning across environments","[{\"question\":\"What problem does causal machine learning address in single-cell genomics?\",\"answer\":\"It targets the challenge that statistical learning methods may fail when experimental conditions shift, by modeling relationships that remain invariant across different environments such as perturbations or exposure types.\"},{\"question\":\"Why is single-cell causal learning difficult?\",\"answer\":\"The data are high-dimensional, observations can be multimodal, and biological systems are only partially observable, making modeling and identification of underlying causal mechanisms nontrivial.\"},{\"question\":\"What open problems does the perspective highlight?\",\"answer\":\"Key gaps include generalizing to unseen environments, learning interpretable causal models, and learning causal models of biological dynamics under changing conditions.\"}]","Causal Machine Learning for Single-Cell Genomics - Perspective | PDF",1785894230,91,{"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},"causal-machine-learning-for-single-cell-genomics-perspective","",{"@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/causal-machine-learning-for-single-cell-genomics-perspective/124741/",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":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does causal machine learning address in single-cell genomics?","Question",{"text":75,"@type":76},"It targets the challenge that statistical learning methods may fail when experimental conditions shift, by modeling relationships that remain invariant across different environments such as perturbations or exposure types.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Why is single-cell causal learning difficult?",{"text":80,"@type":76},"The data are high-dimensional, observations can be multimodal, and biological systems are only partially observable, making modeling and identification of underlying causal mechanisms nontrivial.",{"name":82,"@type":73,"acceptedAnswer":83},"What open problems does the perspective highlight?",{"text":84,"@type":76},"Key gaps include generalizing to unseen environments, learning interpretable causal models, and learning causal models of biological dynamics under changing conditions.","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"]