(Press-News.org) REDWOOD CITY, Calif. — July 10, 2025 — Today, the Chan Zuckerberg Initiative (CZI) announced its latest AI model aimed at helping researchers better understand how cells behave by focusing on the key networks that control cell behavior, making complex biological problems, like cancer, easier to solve.
The model, GREmLN (Gene Regulatory Embedding-based Large Neural model), is a milestone in CZI’s grand challenge to build a family of AI biomodels that predict and understand how cells work at every level — from molecules to entire biological systems — and help scientists cure, prevent, and manage all disease. GREmLN is designed to help researchers identify how the genes of a cell work together — and what can make them go awry, giving way to diseases such as cancer or neurodegeneration.
“GREmLN is a novel approach to understanding how cells make decisions and, just as importantly, how those decisions go wrong in diseases like cancer,” said Andrea Califano, president of the Chan Zuckerberg Biohub New York and Clyde and Helen Wu professor of chemical and systems biology at Columbia University Vagelos College of Physicians and Surgeons. “Our model provides an approach, grounded in biology, to leverage AI for deriving new insights into health and disease. This model doesn’t try to reshape biology to fit AI, it reshapes AI to fit biology.”
Unlike most AI models, GREmLN focuses on the “molecular logic” that defines how genes interact and influence each other, similar to a conversation inside the cell. It will give scientists a way to track the critical changes that pinpoint the earliest signs of disease and the possible targets for new treatments.
GREmLN is trained on more than 11 million data points from Chan Zuckerberg CellxGene, a tool used by thousands of scientists every week to help make discoveries faster by exploring and comparing data from individual cells that span tissues like the brain, lung, kidney, and blood.
Soon the model will be scaled up to help address critical biological and medical questions, so that researchers may detect the early signs of a cell turning cancerous or of a neuron starting to accrue damage — before these changes become irreversible.
“Understanding cellular behavior means understanding the network of conversations happening inside every cell,” said Theofanis Karaletsos, senior director of AI at CZI. “GREmLN captures that complexity in a way we’ve never been able to before. It’s a step toward building systems that help us simulate and predict the behavior of cells.”
In the future, GREmLN could power a wide range of research applications, from blocking the ability of cancer cells to evade therapy to preventing inflammation from producing irreversible damage to our brain cells. It could also help researchers predict how cells will react to new drugs and eventually dramatically increase the success of those drugs in clinical trials. Ultimately, GREmLN is part of a new wave of AI tools designed to help scientists understand the complex logic of life itself.
GREmLN joins a suite of biomodels built by CZI and its Biohubs, including the recently released TranscriptFormer, the first generative AI model to bring together datasets of different species at scale with the goal of helping researchers explore how cells work. Both models have broad applications for biomedical research, disease diagnosis and therapeutic development. The models are part of the organization’s virtual cell platform, which is open and accessible to the global scientific community. Researchers can access GREmLN on the platform, including a quick start tutorial; the codebase on GitHub; and the preprint on bioRxiv. in our blog about GREmLN.
###
About the Chan Zuckerberg Initiative
The Chan Zuckerberg Initiative was founded in 2015 to help solve some of society’s toughest challenges — from eradicating disease and improving education, to addressing the needs of our local communities. Our mission is to build a better future for everyone. For more information, please visit chanzuckerberg.com and czbiohub.org.
END
A new process could help to treat liver disease without needing an organ transplant, a new study reveals.
Hepatic progenitor cells (HPCs) can help to repair the liver, but they often don’t stick well to the existing tissue, making treatment less effective.
Scientists at the University of Birmingham have now developed a method to coat HPCs with natural sugars (polysaccharides) – such as hyaluronic acid and alginate – making the cells ‘stickier’.
The coated cells showed a significant increase ...
Children with multiple long-term health issues undergo severe emotional stress at the same time as they are trying to cope with the physical challenges of their condition, a study has found.
Research led by the University of Plymouth used AI language models to analyse sentiments and emotions expressed by almost 400 paediatric patients and their caregivers on social media. In particular, they wanted to assess young people’s opinions regarding their care and experiences during the COVID-19 pandemic, and the impact that had on their emotional and psychological wellbeing.
Using anonymous data sourced from the Care Opinion platform they found that of the narratives analysed, almost ...
[Vienna, July 10, 2025] – Do you think you know which species are most vulnerable in an ecosystem? A novel analytical method developed by Italian physicists at the Complexity Science Hub (CSH) suggests there's more to discover. In their recent study, they found out how species like lizards and rabbits in South Florida's cypress wetlands are among their ecosystem's most at-risk species, pointing to vulnerabilities that aren't always obvious.
The study, published in Chaos, Solitons & Fractals, introduces an innovative tool to map and measure species' ecological roles and vulnerabilities. ...
Researchers have discovered a simple yet powerful way to protect atoms from losing information—a key challenge in developing reliable quantum technologies. By shining a single, carefully tuned laser beam on a gas of atoms, they managed to keep the atoms' internal spins synchronized, dramatically reducing the rate at which information is lost. In quantum sensors and memory systems, atoms often lose their magnetic orientation—or "spin"—when they collide with each other or the walls of their ...
When we’re taking antibiotics, some of the dose is excreted with urine and feces and ends up in our wastewater. The presence of this low dose of antibiotic creates an opportunity for resistant bacteria to evolve. Scientists studying antibiotic resistant bacteria in wastewater at a treatment plant discovered multi-drug resistant strains of bacteria species which are usually not dangerous to healthy people, but which could transmit genes for antibiotic resistance to much more dangerous bacteria like E. coli.
The scientists then challenged the bacteria with natural compounds which could potentially be included in wastewater treatment to kill off bacteria and fight ...
Dr. Ho Sang Jung and his research team from the Advanced Bio and Healthcare Materials Research Division at the Korea Institute of Materials Science(KIMS) have developed an optical biosensor capable of detecting trace amounts of cancer cell DNA in the bloodstream with high sensitivity, enabling early cancer diagnosis. Compared to conventional liquid biopsy techniques, this biosensor offers superior sensitivity and specificity, and its standout feature lies in its ability to diagnose cancer early using only light signals and AI-based analysis, without the need for complex testing procedures.
When cancer cells develop, subtle chemical changes ...
A research team led by Prof. Xiaoqiang Huang from Nanjing University has achieved a major breakthrough in the field of asymmetric electroenzymatic catalysis, developing a novel non-natural dynamic kinetic oxidation system by integrating ferrocene methanol-mediated anodic oxidation with thiamine diphosphate (ThDP)-dependent enzyme catalysis.
The work, supported by electron paramagnetic resonance (EPR) measurements at the Steady-State Strong Magnetic Field Facility, the Hefei Institutes of Physical Science of the Chinese Academy of Sciences has been published in Nature.
Electrochemistry is undergoing a resurgence in synthetic chemistry due to its ...
Key takeaways
A team at Harvard and Technical University of Vienna have invented a new tunable laser that uses a series of rings to smoothly emit many light wavelengths from a single chip.
The laser could replace many of today’s products that face tradeoffs in accuracy, range, and cost.
Tunable lasers are used in many applications, from gas sensing to medical diagnostics.
Researchers in the Harvard John A. Paulson School of Engineering and Applied Sciences (SEAS) and Technical University of Vienna (TU Wien) have invented a new type of tunable semiconductor laser that ...
A research team led by Prof. SHENG Zhigao from the High Magnetic Field Laboratory, the Hefei Institutes of Physical Science of the Chinese Academy of Sciences, in collaboration with Prof. A.V. Kimel from Radboud University, has demonstrated that strong magnetic fields can effectively regulate laser-induced ultrafast demagnetization in a two-dimensional van der Waals (vdW) ferromagnet.
The findings were published online in National Science Review.
Suppressing slow processes could boost spin-based data processing to femtosecond speeds, potentially revolutionizing information technology. Therefore, understanding and controlling ultrafast ...
A research team led by Prof. LI Hai from the Hefei Institutes of Physical Science of the Chinese Academy of Sciences, has developed a new model that can accurately predict lung motion caused by breathing, offering safer and more precise options for lung biopsies and radiotherapy.
The findings were published in Computerized Medical Imaging and Graphics.
Lung motion during breathing poses a significant challenge in lung cancer treatment, as tumors can shift, making it difficult for doctors to target them ...