{"id":443668,"date":"2026-05-11T18:36:08","date_gmt":"2026-05-11T18:36:08","guid":{"rendered":"https:\/\/www.newsbeep.com\/ie\/443668\/"},"modified":"2026-05-11T18:36:08","modified_gmt":"2026-05-11T18:36:08","slug":"new-ai-tool-predicts-how-cells-choose-their-future-helping-uncover-hidden-drivers-of-development","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/ie\/443668\/","title":{"rendered":"New AI tool predicts how cells choose their future, helping uncover hidden drivers of development"},"content":{"rendered":"

Now,\u00a0new research from\u00a0the\u00a0Stowers Institute for Medical Research<\/a>\u00a0and\u00a0Hemholtz Munich<\/a>, published<\/a> May 11, 2026, in\u00a0Cell,\u00a0has\u00a0developed a new AI framework designed to help answer that question. RegVelo is a model that connects two areas of single-cell biology that have often\u00a0remained\u00a0separate: methods that estimate how cells change over time and methods that infer the gene regulatory networks controlling those changes.\u00a0\u00a0<\/p>\n

By bringing those pieces together,\u00a0RegVelo\u00a0allows researchers\u00a0to\u00a0time travel, predict how cells change, and identify which\u00a0genes control those changes. They can do it\u00a0all through\u00a0computer simulations, eliminating the need\u00a0to run every experiment in the lab.\u00a0\u00a0\u00a0<\/p>\n

“So, why\u00a0is\u00a0this\u00a0important to\u00a0know?”\u00a0said\u00a0Tatjana Sauka-Spengler, Ph.D.,<\/a>\u00a0Stowers Institute Investigator\u00a0and co-senior author of the study. “You\u00a0can\u00a0imagine, if you had\u00a0a very early\u00a0set of cells,\u00a0being equipped with a particular set of instructions could\u00a0allow you to reproduce, in vitro, some of these cell\u00a0types\u00a0in a very natural way. These cells could then be used in cell therapies\u00a0in regenerative medicine.”\u00a0<\/p>\n

Video: Predicting cell fate, hear from the scientists behind the work<\/a>\u00a0<\/p>\n

“Sauka-Spengler and her collaborators have developed a meaningfully different way to process this kind of data,”\u00a0said Stowers President and Chief Scientific Officer\u00a0Alejandro S\u00e1nchez Alvarado, Ph.D.<\/a>\u00a0“It\u00a0allows us to infer the most likely path of each component through space and time, and to use deep learning to predict those\u00a0dynamics\u00a0and test them experimentally.”\u00a0<\/p>\n

In\u00a0the\u00a0study,\u00a0RegVelo\u00a0modeled\u00a0the neural crest,\u00a0a group of early embryonic cells that can become many\u00a0different parts\u00a0of the body.\u00a0\u00a0In zebrafish neural crest development,\u00a0 RegVelo\u00a0identified\u00a0an early driver of pigment cell formation (tfec) and revealed a previously unknown regulator of pigment cell fate (elf1). Those predictions were then supported experimentally, showing that the model could do more than describe developmental change.<\/p>\n

“There is always an initiating, driving element in something that will be defined at the end,” said Sauka-Spengler. “But most times,\u00a0if not always, that element is lost if you’re only\u00a0analyzing\u00a0the final cell state. Development is often described as a series of static snapshots of cell states. What we really want to understand, however, is how cells make decisions\u2014how they transition from one state to another.\u00a0RegVelo\u00a0models how these fate decisions are encoded in gene regulatory networks over time and space, and what drives them.”\u00a0<\/p>\n

By helping connect early regulatory events to later cell fates, the work could also improve how\u00a0scientists\u00a0study developmental disorders and, over time, help guide efforts in regenerative medicine and cell therapy.\u00a0<\/p>\n

“RegVelo’s\u00a0value extends well beyond\u00a0neural crest cells,” said S\u00e1nchez Alvarado. “It’s\u00a0applicable to any system in which cells change over time, from basic developmental biology to modeling\u00a0tumor\u00a0trajectories and the cellular outcomes that may inform treatment. It deserves attention from anyone working on cellular dynamics.”\u00a0\u00a0<\/p>\n

Bridging a long-standing gap in single-cell biology\u00a0<\/p>\n

Single-cell biology\u00a0research\u00a0has made it possible to build increasingly detailed maps of development. RNA velocity methods can help researchers estimate how cells move through developmental landscapes, while gene regulatory network approaches can\u00a0identify\u00a0relationships among genes. But those methods have typically been used in parallel rather than together. RNA velocity methods often do not directly model transcriptional regulation, while regulatory network approaches\u00a0generally do\u00a0not capture cellular dynamics over time.\u00a0<\/p>\n

“For a long time, cellular dynamics and gene regulation have largely been modeled separately,” said the study’s co-senior author Prof. Fabian J. Theis, Ph.D., Director of the Computational Health Center (CHC) at Helmholtz Munich and Professor at the Technical University of Munich (TUM). “RegVelo\u00a0brings those pieces together, allowing us to ask not only how cells are changing, but which regulatory interactions are helping drive those changes.”\u00a0<\/p>\n

The framework jointly models splicing kinetics and gene regulatory relationships, allowing researchers to\u00a0map the hidden timeline of cell development, predict\u00a0how cells shift from one state to another, and test what might happen\u00a0when specific regulators are perturbed. In practical terms, that means scientists can ask a more mechanistic question than simply\u00a0“Where is this cell going?”\u00a0Now they can ask,\u00a0“Which genes are helping push it there?”\u00a0<\/p>\n

Joining forces\u00a0<\/p>\n

The work also reflects a deep collaboration between complementary teams.\u00a0Sauka-Spengler’s\u00a0Lab,\u00a0which transitioned from the\u00a0University of Oxford<\/a>\u00a0to the Stowers Institute in 2022,\u00a0brought\u00a0a high-resolution gene regulatory scaffold for cranial neural crest development, while Theis’s group brought\u00a0computational\u00a0expertise\u00a0in\u00a0modeling\u00a0and defining\u00a0developmental trajectories\u00a0of single cells and\u00a0using RNA\u00a0velocity\u00a0analyses. Together, those approaches were combined into a shared deep learning model\u00a0that made developmental transitions highly predictive and testable.\u00a0<\/p>\n

“What made this work especially powerful was the combination of complementary strengths\u2026high-resolution gene regulatory circuitry from\u00a0our lab\u00a0and dynamic trajectory\u00a0and network\u00a0modeling\u00a0from\u00a0Fabian’s team,”\u00a0 Sauka-Spengler\u00a0said. “RegVelo emerged from integrating those two views into one framework.”\u00a0<\/p>\n

What are Gene Regulatory Networks?\u00a0<\/p>\n

Video: Tatjana Sauka-Spengler, Ph.D., on decoding the cell’s instructions<\/a>\u00a0<\/p>\n

Gene\u00a0regulatory networks are the ordered sets of instructions that help guide a cell from one identity to another.\u00a0<\/p>\n

“They are\u00a0a cascade of events,”\u00a0Sauka-Spengler explained.\u00a0“One\u00a0group of genes activates or suppresses another, pushing a cell down one path instead of another. That matters because every cell in the body starts with the same DNA. What makes a skin cell different from a neuron or a muscle cell is not the genome itself, but which genes are turned on, when they are activated, and in what combinations.”\u00a0<\/p>\n

The process can be compared to an electronic circuit.\u00a0Some genes act like “go” signals, others like brakes, and together they create a code that scientists are trying to decipher.\u00a0<\/p>\n

How it works: a deeper dive into the findings\u00a0and implications\u00a0<\/p>\n

The\u00a0team\u00a0used\u00a0RegVelo\u00a0to\u00a0identify\u00a0an early pigment driver and revealed a previously unknown regulator of pigment cell fate\u00a0in zebrafish. The researchers applied the framework\u00a0across multiple systems, including cell cycle, pancreatic endocrinogenesis,\u00a0hematopoiesis, myogenesis, hindbrain development, and zebrafish neural crest development. Across these settings, the model performed comparably to or better than leading approaches in inferring latent time, velocity, terminal states, and lineage-associated drivers.\u00a0<\/p>\n

One of the most compelling examples came in the neural crest, a developmental system that gives rise to many different cell types, including pigment cells, craniofacial tissues, and parts of the peripheral nervous system. There,\u00a0RegVelo\u00a0proved especially useful because it could\u00a0identify\u00a0regulators acting early in a developmental trajectory,\u00a0even when those genes were not strongly expressed in the final cell state.\u00a0<\/p>\n

Using that approach, the researchers found that\u00a0tfec appears to act as an early driver of pigment cell development. They also identified elf1 as a previously unknown regulator of pigment lineage fate.\u00a0\u00a0<\/p>\n

Follow-up experiments, including CRISPR\/Cas9-mediated knockout and single-cell Perturb-seq, supported both predictions, showing that the model could do more than describe developmental change\u2014it could generate biologically meaningful hypotheses that held up in living systems.\u00a0<\/p>\n

“RegVelo\u00a0is a model that integrates these two knowledges and basically allows us to prove the validity of our discoveries,”\u00a0Sauka-Spengler said. “We’re able to predict\u00a0the essential drivers of particular cell fate and cell commitments, and then we’re able to simulate this perturbation and read out clearly the effect on very downstream outcomes.”\u00a0<\/p>\n

That capability matters, in part, because of scale. Researchers are often dealing with hundreds, and\u00a0sometimes thousands, of\u00a0possible factors. Experimentally perturbing each of them one by one would be costly and impractical.\u00a0RegVelo\u00a0helps narrow that search.<\/p>\n

“Because we’re talking about networks involving hundreds, and sometimes multiple hundreds of genes, imagining that we would want to perturb all of them and\u00a0analyze\u00a0all of them would not really be feasible,”\u00a0Sauka-Spengler said. “So,\u00a0we can use\u00a0RegVelo\u00a0as both analysis and a prediction and screening tool for future experiments.”\u00a0<\/p>\n

Computational\u00a0modeling\u00a0with experimental validation: a more predictive and promising combination\u00a0\u00a0<\/p>\n

The team\u00a0describes\u00a0RegVelo\u00a0as a step toward a more predictive form of developmental biology,\u00a0in which computational models help prioritize experiments, uncover hidden regulators, and forecast how cell fates may change when gene networks are perturbed.\u00a0RegVelo\u00a0reveals how cells transition between states and\u00a0identifies\u00a0the gene interactions that drive their fate decisions.\u00a0<\/p>\n

The implications could extend well beyond one developmental system. High-resolution regulatory understanding could help researchers better\u00a0identify\u00a0the causes of developmental defects and, over time, direct cells more precisely in\u00a0cell therapies and\u00a0regenerative medicine\u00a0\u2014 from repairing heart muscle\u00a0and growing skin grafts to developing lab-grown\u00a0cartilage.\u00a0Craniofacial disorders, pigment cell defects, and broader efforts to guide stem cells or organoids toward desired cell states are among the areas where that deeper understanding could matter.\u00a0<\/p>\n

“Having a full resolution of gene regulatory circuitry that has been predicted, simulated, perturbed and then validated gives us a very solid tool in our hands,”\u00a0Sauka-Spengler said. “We can start from stem cells or from naive cells and develop new ways of directing them towards the cell types that can then be used in cell therapies for purposes of treatments.”\u00a0<\/p>\n

The\u00a0study suggests\u00a0that the framework could be extended in the future to incorporate additional\u00a0regulatory layers, including chromatin, protein activity, and other multimodal measurements.\u00a0\u00a0<\/p>\n

While there are\u00a0current limitations \u2014\u00a0including simplifying assumptions around latent time, regulatory interactions, and computational cost \u2014 the study offers a compelling proof of principle. “When dynamic cell-state\u00a0modeling\u00a0is linked directly to gene regulation, it becomes possible to move closer to mechanism and then discovery,” Sauka-Spengler explained.<\/p>\n

More information:<\/p>\n

Read the press release from Helmholtz Munich here<\/a>.<\/p>\n

Additional\u00a0authors include Weixu Wang, Zhiiyuan Hu, Philipp Weiler, Sarah Mayes, Marius Lange, Daniel M. Fountain, Julianna O. Haug, Jingye Wang, and Zhengyuan Xue\u00a0<\/p>\n

Research at the Stowers Institute was supported by institutional funding to Tatjana Sauka-Spengler, Ph.D., and by\u00a0Wellcome\u00a0Trust Award 215615\/Z\/19\/Z. Additional support for the broader collaborative work came from the European Union\/ERC\u00a0DeepCell\u00a0project (101054957), the\u00a0Wellcome\u00a0Leap\u00a0\u0394Tissue\u00a0Program (9E8E84F7-8991-4D4A-A9EC), the European Union’s Horizon 2022 research and innovation programme (101057775), the German Federal Ministry of Education and Research through the HOPARL project (031L0289A), the DFG Graduate School of QBM (GSC 1006), the Joachim Herz Foundation, an EMBO Postdoctoral Fellowship, the Fundamental Research Funds for the Central Universities (2042025kf0022, 2042022dx0003), and the National Natural Science Foundation of China (32500725).\u00a0<\/p>\n

About the Stowers Institute for Medical Research\u202f\u00a0<\/p>\n

Founded in 1994 through the generosity of Jim Stowers, founder of American Century Investments, and his wife, Virginia, the Stowers Institute for Medical Research is a non-profit, biomedical research organization with a focus on foundational research. Its mission is to expand our understanding of the secrets of life and improve life’s quality through innovative approaches to the causes, treatment, and prevention of diseases.\u202f\u00a0<\/p>\n

The Institute consists of 24 independent research programs. Of the approximately 500 members, over 370 are scientific staff that include principal investigators, technology center directors, postdoctoral scientists, graduate students, and technical support staff. Learn more about the Institute at\u202fwww.stowers.org<\/a>\u202fand about its graduate program at\u202fwww.stowers.org\/gradschool<\/a>.\u00a0<\/p>\n

Media Contact:\u00a0\u00a0
Joe Chiodo, Director of Communications\u00a0\u00a0\u00a0
724.462.8529\u00a0\u00a0\u00a0
[email\u00a0protected]<\/a><\/p>\n

SOURCE Stowers Institute for Medical Research<\/p>\n

\"\"<\/p>\n","protected":false},"excerpt":{"rendered":"Now,\u00a0new research from\u00a0the\u00a0Stowers Institute for Medical Research\u00a0and\u00a0Hemholtz Munich, published May 11, 2026, in\u00a0Cell,\u00a0has\u00a0developed a new AI framework designed…\n","protected":false},"author":2,"featured_media":443669,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[7],"tags":[61,60,82,193090],"class_list":["post-443668","post","type-post","status-publish","format-standard","has-post-thumbnail","category-science","tag-ie","tag-ireland","tag-science","tag-stowers-institute-for-medical-research"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/posts\/443668","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/comments?post=443668"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/posts\/443668\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/media\/443669"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/media?parent=443668"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/categories?post=443668"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/ie\/wp-json\/wp\/v2\/tags?post=443668"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}