[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-290823-105":59,"doc-detail-290823-en":131},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","understanding-biology-with-machine-learning-compression-intelligibility-and-dependency","Understanding biology with machine learning - compression, intelligibility, and dependency","","Machine learning (ML) is increasingly used to interrogate biological systems whose complexity resists law-like, deductive explanation. As a result, embeddings, clusters, and attributions are often overinterpreted, dependencies are left implicit, and claims about explainability are often insufficiently bounded. This work proposes a framework connecting ML to scientific understanding in biology via compression, qualitative intelligibility, and dependency models. Compression encodes biological structure, qualitative intelligibility maps high-dimensional measurements to human-graspable objects, and dependency modelling makes relations explicit to guide prediction and intervention.",{"@graph":69,"@context":123},[70,84,106],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/understanding-biology-with-machine-learning-compression-intelligibility-and-dependency/290823/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/understanding-biology-with-machine-learning-compression-intelligibility-and-dependency/290823.png","ImageObject",300,407,{"name":92,"@type":93},"Skyler","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-31","2026-09-17",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",14,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"Why do ML applications in biology often risk overinterpretation?","Question",{"text":113,"@type":114},"Because biological complexity can resist deductive, law-like explanation, and embeddings, clusters, and attributions may be interpreted without clear bounds. Dependencies can also remain implicit, weakening explainability claims.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"What does the framework mean by compression in ML for biology?",{"text":118,"@type":114},"Compression happens when inductive biases encode biological structure, reducing the effective hypothesis space and producing representations aligned with known biology.",{"name":120,"@type":111,"acceptedAnswer":121},"How does qualitative intelligibility support biological reasoning?",{"text":122,"@type":114},"It converts high-dimensional measurements into human-graspable objects such as embeddings, clusters, and trajectories, enabling accurate qualitative reasoning without exact computation.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},290823,1789642653,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":39,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":130,"read_time":46,"preview_page_count":4},2336464648746,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","Artiϧcial Intelligence in the Life Sciences 9 (2026) 100161  \nContents lists available at ScienceDirect  \nArtificial Intelligence in the Life Sciences  \njournal [homepage:](homepage: www.elsevier.com/locate/ailsci)[ www.elsevier.com/locate/ailsci](homepage: www.elsevier.com/locate/ailsci)  \n| Viewpoint\u003Cbr>Understanding biology with machine learning: compression, intelligibility, and dependency\u003Cbr>Elsa Lawrence a,1, Adham El-Shazlyb,1, Srijit Seal c,d , Chaitanya K Joshie, Pietro Li`o e, Andreas Bender f,c,g,h, Shantanu Singhd, Pietro Sormannic,j,*, Ola Spjuthi,*,\u003Cbr>Matthew Greenigc,*\u003Cbr>a Department of Pharmacology, University of Cambridge, UK b Department of Philosophy, University of Cambridge, UK c Department of Chemistry, University of Cambridge, United Kingdom d Broad Institute of MIT and Harvard, Cambridge, MA, United States\u003Cbr>e Department of Computer Science and Technology, University of Cambridge, UK\u003Cbr>f Center for Biotechnology, College of Medicine and Health Sciences, Khalifa University of Science and Technology, Abu Dhabi, United Arab Emirates g STAR-UBB Institute, Babe-Bolyai University, Cluj-Napoca, Romania\u003Cbr>h Research Center for Functional Genomics, Biomedicine and Translational Medicine, Iuliu Hatieganu University of Medicine and Pharmacy, Cluj-Napoca, Romania i Department of Pharmaceutical Biosciences and Science for Life Laboratory, Uppsala University, Uppsala, Sweden\u003Cbr>j Department of Chemical Engineering, Imperial College London, London, United Kingdom |  |  |\n| --- | --- | --- |\n| A R T I C L E I N F O |  | A B S T R A C T |\n| Keywords:\u003Cbr>Machine learning Artificial intelligence Philosophy of science Biological understanding Information compression Qualitative intelligibility Inductive bias Computational irreducibility Dimensionality reduction Epistemology of science |  | Machine learning (ML) is increasingly used to interrogate biological systems whose complexity resists law-like, deductive explanation. As a result, embeddings, clusters, and attributions are often overinterpreted, dependencies are left implicit, and claims about explainability are often insufficiently bounded. In this work, we present a framework for contextualizing how machine learning contributes to scientific understanding in biology via compression, qualitative intelligibility, and dependency models. Compression is achieved when inductive biases encode biological structure, reducing the effective hypothesis space and yielding representations aligned with known biology. Qualitative intelligibility is supported when high-dimensional measurements are mapped to human-graspable objects, such as embeddings, clusters, and trajectories, that enable accurate qualitative reasoning without exact calculation. Dependency modelling is realized when learned models make explicit the pattern of relations among system components and thereby guide prediction and intervention. We examine how these principles manifest in successful ML applications and discuss considerations that emerge from this framework. Overall, when viewed through these lenses, ML can transform predictive success into interventionguiding knowledge in the life sciences. |\n\n1. Introduction  \nIt has become increasingly recognized that artificial intelligence (AI), and in particular, machine learning (ML), is accelerating research across a range of scientific disciplines [1], providing a means of identifying patterns in datasets of scale and complexity that preclude their analysis with traditional scientific methods alone. Several experimental modalities in biology are now routinely generating datasets in high-throughput that are being combined with ML approaches for analysis, interpretation, and prediction [2–7], defining an important  \nrole for these models in advancing scientific knowledge and understanding. Many biological regularities are context-conditional and scale-specific (for example, Mendelian segregation under defined conditions, allometric scaling within clades, recurre","cbCaifrjMYmrEbg5","https://ap.wps.com/l/cbCaifrjMYmrEbg5","pdf",1359604,"English","# Introduction\n## ML in biology: data scale and complexity\n## Models as complements to mechanistic understanding\n## Epistemological motivation and framework overview","[{\"question\":\"Why do ML applications in biology often risk overinterpretation?\",\"answer\":\"Because biological complexity can resist deductive, law-like explanation, and embeddings, clusters, and attributions may be interpreted without clear bounds. Dependencies can also remain implicit, weakening explainability claims.\"},{\"question\":\"What does the framework mean by compression in ML for biology?\",\"answer\":\"Compression happens when inductive biases encode biological structure, reducing the effective hypothesis space and producing representations aligned with known biology.\"},{\"question\":\"How does qualitative intelligibility support biological reasoning?\",\"answer\":\"It converts high-dimensional measurements into human-graspable objects such as embeddings, clusters, and trajectories, enabling accurate qualitative reasoning without exact computation.\"}]","Understanding biology with machine learning - compression, intelligibility, and dependency | PDF"]