{"id":1017,"date":"2025-11-29T03:36:41","date_gmt":"2025-11-29T03:36:41","guid":{"rendered":"https:\/\/www.web-ai-institute.com\/wp\/2025\/11\/29\/ai-finally-takes-on-a-century-old-cancer-mystery\/"},"modified":"2025-11-29T03:36:41","modified_gmt":"2025-11-29T03:36:41","slug":"ai-finally-takes-on-a-century-old-cancer-mystery","status":"publish","type":"post","link":"https:\/\/www.web-ai-institute.com\/wp\/2025\/11\/29\/ai-finally-takes-on-a-century-old-cancer-mystery\/","title":{"rendered":"AI Finally Takes On a Century-Old Cancer Mystery"},"content":{"rendered":"<p><br \/>\n<\/p>\n<div>\n<figure id=\"attachment_480291\" aria-describedby=\"caption-attachment-480291\" style=\"width: 777px\" class=\"wp-caption aligncenter\"><a href=\"https:\/\/scitechdaily.com\/images\/Medically-Accurate-Cancer-Cells-Rendering.jpg\"><img fetchpriority=\"high\" decoding=\"async\" class=\"wp-image-480291 size-large\" src=\"https:\/\/scitechdaily.com\/images\/Medically-Accurate-Cancer-Cells-Rendering-777x518.jpg\" alt=\"Medically Accurate Cancer Cells Rendering\" width=\"777\" height=\"518\" srcset=\"https:\/\/scitechdaily.com\/images\/Medically-Accurate-Cancer-Cells-Rendering-777x518.jpg 777w, https:\/\/scitechdaily.com\/images\/Medically-Accurate-Cancer-Cells-Rendering-400x267.jpg 400w, https:\/\/scitechdaily.com\/images\/Medically-Accurate-Cancer-Cells-Rendering-768x512.jpg 768w, https:\/\/scitechdaily.com\/images\/Medically-Accurate-Cancer-Cells-Rendering-1536x1024.jpg 1536w, https:\/\/scitechdaily.com\/images\/Medically-Accurate-Cancer-Cells-Rendering-150x100.jpg 150w, https:\/\/scitechdaily.com\/images\/Medically-Accurate-Cancer-Cells-Rendering-450x300.jpg 450w, https:\/\/scitechdaily.com\/images\/Medically-Accurate-Cancer-Cells-Rendering-1200x800.jpg 1200w, https:\/\/scitechdaily.com\/images\/Medically-Accurate-Cancer-Cells-Rendering.jpg 2000w\" sizes=\"(max-width: 777px) 100vw, 777px\"\/><\/a><figcaption id=\"caption-attachment-480291\" class=\"wp-caption-text\">A new AI-driven system now allows researchers to track how rare chromosomal errors form inside cells, offering fresh insight into the earliest events that can lead to cancer. Credit: Shutterstock<\/figcaption><\/figure>\n<p><strong>EMBL researchers have created a new AI tool that uses a \u201cmolecular laser tag\u201d approach to identify cells capable of revealing the earliest origins of cancer.<\/strong><\/p>\n<p>The human body depends on accurate genetic instructions to keep its cells working properly. Cancer begins to form when these instructions become disrupted. As genetic mistakes build up over time, cells can lose their normal limits on growth and start multiplying in an uncontrolled way. Chromosomal abnormalities \u2013 numerical and structural defects in chromosomes \u2013 are often one of the earliest changes that push healthy cells toward becoming cancerous.<\/p>\n<p>Researchers in the Korbel Group at EMBL Heidelberg have created a new AI-based tool that gives scientists a way to closely examine how these chromosomal abnormalities develop. The insights gained from this approach may eventually clarify some of the earliest steps that lead to cancer.<\/p>\n<p>\u201cChromosomal abnormalities are a main driver for particularly aggressive cancers, and they\u2019re highly linked to patient death, metastasis, recurrence, chemotherapy resistance, and fast tumor onset,\u201d said Jan Korbel, senior scientist at EMBL and senior author of the new paper, published in the journal <em>Nature<\/em>. \u201cWe wanted to understand what determines the likelihood that cells undergo such chromosomal alterations, and what\u2019s the rate at which such abnormalities arise when a still normal cell divides.\u201d<\/p>\n<p>The connection between abnormal chromosomes and cancer has been considered for a long time. More than 100 years ago, German scientist Theodor Boveri proposed, based on his microscopy observations, that irregular chromosomal content in cells plays a role in driving cancer formation.<\/p>\n<h4>Why Chromosomal Abnormalities Are Hard to Study<\/h4>\n<p>However, spotting these abnormalities has long been difficult because only a small number of cells show them at any moment, and many of those cells either die on their own or are removed through natural selection (or are killed off). Researchers traditionally had to look for these cells by hand through a microscope, and they could collect only a few at once for more detailed study.<\/p>\n<p><iframe loading=\"lazy\" title=\"Machine Learning-Assisted Genomics and Imaging Convergence (MAGIC)\" width=\"640\" height=\"360\" src=\"https:\/\/www.youtube.com\/embed\/OsNviB_R-vE?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" allowfullscreen><\/iframe><br \/><em>Machine learning-assisted genomics and imaging convergence (MAGIC). Credit: Daniela Velasco\/EMBL<\/em><\/p>\n<p>Marco Cosenza, Research Scientist in the Korbel Group, hit upon the solution to this problem after working with other teams at EMBL wrestling with similar challenges. He and his collaborators developed a new, autonomous system that combines automated microscopy, single-cell sequencing, and AI, which they named <strong>m<\/strong>achine learning-<strong>a<\/strong>ssisted <strong>g<\/strong>enomics and <strong>i<\/strong>maging <strong>c<\/strong>onvergence \u2013 or MAGIC.<\/p>\n<h4>\u2018Laser tag\u2019 to precisely identify and mark cells<\/h4>\n<p>Essentially, MAGIC operates like a fully automated game of laser tag. It spots \u2018enemies\u2019, or cells, with a particular kind of visible feature. For this study, the scientists focused on a cellular structure called a \u2018micronucleus\u2019. Micronuclei are tiny enclosed compartments inside cells that contain a small portion of the cells\u2019 <span class=\"glossaryLink\" aria-describedby=\"tt\" data-cmtooltip=\"cmtt_a15e5d2ae3fd42fd6258493af70006cf\" data-gt-translate-attributes=\"[{\" attribute=\"\" tabindex=\"0\" role=\"link\">DNA<\/span>, broken off from the bulk of the genome. Cells with micronuclei tend to produce new chromosomal abnormalities, which makes them more likely to turn cancerous.<\/p>\n<p>Once cells with micronuclei are detected, the system \u2018tags\u2019 them using a laser. For this, the scientists used a photoconvertible dye \u2013 a fluorescent molecule that undergoes a chemical transformation if light is shone on it, changing the color of light it emits.<\/p>\n<p>\u201cThis project combined a lot of my interests in one,\u201d said Cosenza. \u201cIt involves genomics, microscopic imaging, and robotic automation. During the COVID-19-related lockdown in 2020, I could really spend some time on learning and applying AI computer vision technologies to the biological image data we had collected before. Afterwards, we designed experiments to validate it and take it further.\u201d<\/p>\n<figure id=\"attachment_502177\" aria-describedby=\"caption-attachment-502177\" style=\"width: 777px\" class=\"wp-caption aligncenter\"><a href=\"https:\/\/scitechdaily.com\/images\/MAGIC-AI-Laser-System.jpg\"><img loading=\"lazy\" decoding=\"async\" class=\"size-large wp-image-502177\" src=\"https:\/\/scitechdaily.com\/images\/MAGIC-AI-Laser-System-777x466.jpg\" alt=\"MAGIC AI Laser System\" width=\"777\" height=\"466\" srcset=\"https:\/\/scitechdaily.com\/images\/MAGIC-AI-Laser-System-777x466.jpg 777w, https:\/\/scitechdaily.com\/images\/MAGIC-AI-Laser-System-400x240.jpg 400w, https:\/\/scitechdaily.com\/images\/MAGIC-AI-Laser-System-768x461.jpg 768w, https:\/\/scitechdaily.com\/images\/MAGIC-AI-Laser-System-150x90.jpg 150w, https:\/\/scitechdaily.com\/images\/MAGIC-AI-Laser-System-450x270.jpg 450w, https:\/\/scitechdaily.com\/images\/MAGIC-AI-Laser-System.jpg 1000w\" sizes=\"auto, (max-width: 777px) 100vw, 777px\"\/><\/a><figcaption id=\"caption-attachment-502177\" class=\"wp-caption-text\">MAGIC operates like a fully automated game of laser tag, spotting cells with a particular visible feature, like the presence of micronuclei, and marking them using a system involving a laser and a photoconvertible dye. Credit: Daniela Velasco\/EMBL<\/figcaption><\/figure>\n<p>In practice, MAGIC works like this. First, an automated microscope captures a series of images of a cell sample. Next, a <span class=\"glossaryLink\" aria-describedby=\"tt\" data-cmtooltip=\"cmtt_701379cd27f61e1d003b9b925711fbe9\" data-gt-translate-attributes=\"[{\" attribute=\"\" tabindex=\"0\" role=\"link\">machine learning<\/span> algorithm, trained on manually annotated datasets of micronuclei-containing cells, scans the images. When the algorithm spots cells with micronuclei, it shares their location with the microscope and instructs it to shine light specifically on those cells, permanently tagging them. The tagged cells can then easily be separated from these still-living cells using methods like flow cytometry, and subsequently be subjected to deeper analysis, e.g. by looking at their cellular genomes.<\/p>\n<h4>Scaling Up a Previously Slow Process<\/h4>\n<p>By automating the previously labor-intensive, time-consuming, and error-prone process of detecting cells with micronuclei, MAGIC allows scientists to study such cells at a scale and speed previously unheard of. In less than a day, scientists can analyze nearly 100,000 cells using this method.<\/p>\n<p>The team used MAGIC to analyze chromosomal abnormalities in cultured cells originally derived from normal human cells. Their results showed that a little more than 10% of all cell divisions result in spontaneous chromosomal abnormalities of some kind and that this rate nearly doubles when a particular gene \u2013 p53, a well-known tumor suppressor \u2013 is mutated. The scientists also studied other triggers and contributors to chromosomal abnormality formation, such as the presence and location of double-stranded DNA breaks within a chromosome.<\/p>\n<p>The study involved collaborations across and outside EMBL, with key contributions from the Advanced Light Microscopy Facility (ALMF) and the Pepperkok Team at EMBL Heidelberg, Isidro Cortes-Ciriano\u2019s group at EMBL-EBI, and Andreas Kulozik\u2019s team at the German Cancer Research Centre (DKFZ), which also forms part of the Molecular Medicine Partnership Unit (MMPU) between EMBL and the University of Heidelberg.<\/p>\n<p>MAGIC is a highly versatile and adaptable technique. While the scientists trained it for this study to spot cells that had micronuclei, the algorithm can, in theory, be trained on many different kinds of datasets to detect different cellular features.<\/p>\n<p>\u201cAs long as you have a feature that can be discriminated visually from a \u2018regular\u2019 cell, you can \u2013 thanks to AI \u2013 train the system to detect it,\u201d said Korbel, \u201cOur system therefore has potential to advance future discoveries in numerous areas of biology.\u201d<\/p>\n<p>Reference: \u201cOrigins of chromosome instability unveiled by coupled imaging and genomics\u201d by Marco Raffaele Cosenza, Alice Gaiatto, B\u00fc\u015fra Erarslan Uysal, \u00c1lvaro Andrades, Nina Luisa Sautter, Marina Simunovic, Michael Adrian Jendrusch, Sonia Zumalave, Tobias Rausch, Aliaksandr Halavatyi, Eva-Maria Geissen, Joshua Lucas Eigenmann, Thomas Weber, Patrick Hasenfeld, Eva Benito, Catherine Stober, Isidro Cortes-Ciriano, Andreas E. Kulozik, Rainer Pepperkok and Jan O. Korbel, 29 October 2025, <i>Nature<\/i>.<br \/><a href=\"https:\/\/www.nature.com\/articles\/s41586-025-09632-5\">DOI: 10.1038\/s41586-025-09632-5<\/a><!--TrendMD v2.4.8--><\/p>\n<p><b>Never miss a breakthrough: <a href=\"https:\/\/scitechdaily.com\/newsletter\/\">Join the SciTechDaily newsletter.<\/a><\/b><br \/><b>Follow us on <a href=\"https:\/\/www.google.com\/preferences\/source?q=scitechdaily.com\">Google<\/a> and <a href=\"https:\/\/news.google.com\/publications\/CAAqLAgKIiZDQklTRmdnTWFoSUtFSE5qYVhSbFkyaGtZV2xzZVM1amIyMG9BQVAB?hl=en-US&amp;gl=US&amp;ceid=US%3Aen\">Google News<\/a>.<\/b><\/p>\n<\/p><\/div>\n<p><br \/>\n<br \/><a href=\"https:\/\/scitechdaily.com\/ai-finally-takes-on-a-century-old-cancer-mystery\/\">Source link <\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>A new AI-driven system now allows researchers to track how rare chromosomal errors form inside cells, offering fresh insight into the earliest events that can lead to cancer. Credit: Shutterstock EMBL researchers have created a new AI tool that uses a \u201cmolecular laser tag\u201d approach to identify cells capable of revealing the earliest origins of&#8230;<\/p>\n","protected":false},"author":91,"featured_media":1018,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"pagelayer_contact_templates":[],"_pagelayer_content":"","footnotes":""},"categories":[41],"tags":[],"class_list":["post-1017","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news"],"_links":{"self":[{"href":"https:\/\/www.web-ai-institute.com\/wp\/wp-json\/wp\/v2\/posts\/1017","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.web-ai-institute.com\/wp\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.web-ai-institute.com\/wp\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.web-ai-institute.com\/wp\/wp-json\/wp\/v2\/users\/91"}],"replies":[{"embeddable":true,"href":"https:\/\/www.web-ai-institute.com\/wp\/wp-json\/wp\/v2\/comments?post=1017"}],"version-history":[{"count":0,"href":"https:\/\/www.web-ai-institute.com\/wp\/wp-json\/wp\/v2\/posts\/1017\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.web-ai-institute.com\/wp\/wp-json\/wp\/v2\/media\/1018"}],"wp:attachment":[{"href":"https:\/\/www.web-ai-institute.com\/wp\/wp-json\/wp\/v2\/media?parent=1017"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.web-ai-institute.com\/wp\/wp-json\/wp\/v2\/categories?post=1017"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.web-ai-institute.com\/wp\/wp-json\/wp\/v2\/tags?post=1017"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}