Most successful scientists are optimists. They have to be, since the vast majority of experiments fail. In graduate school, I remember sitting in the lab at Rockefeller University in New York at 3 a.m., surrounded by stacks of culture dishes for growing cancer cells, none quite showing me what I hoped to find. But glimmers of interesting changes in the cells promised future success and made me feel the experiments wanted to work. That optimism drove me to keep trying. One day, they did work and I uncovered a new insight about a process in those cancer cells that no one had described before.
In 2026, there seem to be plenty of good reasons to be optimistic about science: Breakthroughs are everywhere.
Want to stay on top of the science and politics driving biotech today? Sign up to get our biotech newsletter in your inbox.
Good morning. Today, we have some AI drug development news and an examination of the growing longevity industry.
The need-to-know this morning
The FDA has pushed back the decision date for AstraZeneca’s experimental breast cancer drug camizestrant, following a negative vote from a group of agency advisers, the company said. The extra time will allow the FDA to review additional analyses that AstraZeneca is providing. FDA advisers took issue with the study design of the pivotal SERENA-6 trial, though European regulators have recommended the drug be approved. AstraZeneca did not specify the new target date for an FDA decision.
Blackstone Life Sciences, a private equity fund, is providing Apogee Therapeutics with up to $1.3 billion to pay for the Phase 3 development and potential commercialization of zumilokibart, the biotech’s long-acting treatment for atopic dermatitis.
Kailera’s own ‘triple-G’ drug also looks very powerful
Kailera said yesterday that its investigational obesity drug that targets three hormones led to significant weight loss in a Phase 1 study.
Good morning, everyone, and how are you today? The middle of the week has finally arrived, and you should congratulate yourselves for making it this far and deciding to soldier on. After all, consider the alternatives. None too pleasant, yes? This calls for a delicious cuppa stimulation. Our choice today is pomegranate green tea. As always, we invite you to join us. Meanwhile, here are some tidbits. Hope you have a meaningful and productive day, and please do keep in touch. We treasure your messages. …
The U.S. Food and Drug Administration has extended the decision deadline for an experimental breast cancer pill from AstraZeneca in order to review additional data, Reuters notes. The delay comes after a majority of an FDA advisory panel in April votedagainst the drug in combination with another type of therapy known as CDK4/6 inhibitor, due to concerns about the design of a key late-stage trial rather than its safety or efficacy. The company said it has submitted additional analyses requested by the FDA to support its new drug application, including data linked to longer-term efficacy outcomes that will be presented at a conference on June 2. AstraZeneca’s camizestrant pill is designed for patients with a type of breast cancer in which tumors carry a specific mutation.
Brazil approved the country’s first generic version of Novo Nordisk’s Ozempic shot, opening the door to cheaper competition in one of the world’s fastest-growing markets for weight loss and diabetes drugs, Bloomberg News writes. EMS, a Brazilian pharmaceutical company, was cleared to sell its copycat drug, Ozivy, to treat adults with type 2 diabetes as an adjunct to diet and exercise. EMS plans to sell Ozivy for 30% less than Ozempic, and expects it to hit the market within 30 days. The approval marks a milestone for Brazil’s pharmaceutical industry as local drugmakers seek to enter the booming market for GLP-1 medicines, the class of drugs that includes Ozempic. The company plans to make 350,000 pens available initially and expects to sell about 1.2 million units in the first year.
Having a lifestyle that promotes heart health may have been key in determining who died or was hospitalized during the COVID-19 pandemic.
Research in the Journal of the American Heart Association (AHA) suggests these healthy behaviors—involving diet, exercise, smoking, and sleep as well as body measures—could not only protect against cardiovascular disease but also have other benefits.
Specifically, they may help the body cope with the stress of infections such as those caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), even in people without clinical cardiovascular disease.
Adults with the highest heart health scores were nearly half as likely to die or be hospitalized as a result of COVID-19 compared with those who had the lowest scores.
“In many ways, a viral infection is like a cardiac stress test, except it’s not controlled,” explained researcher Elizabeth Oelsner, MD, from Columbia University.
“At the beginning of the pandemic, we immediately saw that COVID-19 was a particularly severe stress on the body. Our results highlight that better heart health, which is something that individuals can work on, likely prepares you better for real-life stress tests such as infectious diseases like COVID-19.”
The findings come from the Collaborative Cohort of Cohorts for COVID-19 Research (C4R), a collection of 14 U.S. studies that accrued extensive health information from participants.
The current analysis included 29,740 adults without clinical cardiovascular disease as of March 2020. Their average age of 66 years, and 61% were women.
Among the participants, just over a third each were White and Hispanic/Latino, while just over a fifth were Black.
Cardiovascular health was measured according to the AHA’s Life’s Essential Eight (LE8), a summary measure that scores diet, physical activity, cigarette use, sleep, body mass index, blood pressure, lipids, and glucose levels each out of 100.
Around 18% of study participants had high heart health(LE8 ≥80), 70% had moderate heart health (LE8 ≥50 to <80), and 12% had low heart health (LE8 <50).
The American Heart Association’s Life’s Essential 8 is a wheel shape with eight wedges representing the eight elements that are essential for cardiovascular health. [American Heart Association]
There were 681 severe COVID-19 cases from March 2020 to March 2023. Just over half the participants were known to have received a COVID-19 vaccination before contracting the virus.
Adults with high LE8 scores had a 46% reduction in risk of COVID-19 hospitalization or death compared with those who had low scores. In addition, every 14-point increase in LE8 was linked with a 20% lower risk of COVID-19 hospitalization or death.
Higher scores for physical activity, weight, blood pressure and sleep patterns were individually associated with lower risk of severe COVID-19.
The benefits of heart heath were similar across different participant groups and continued through the study period and when vaccines became available.
“COVID-19 caused 1.22 million deaths in the U.S. between March 2020 and March 2025, so it’s essential that we understand how important health components, such as heart health, relate to severity of COVID-19 infections,” said lead researcher Tim Plante, MD, from the University of Vermont.
“Our findings suggest that the tremendous impact of COVID-19 on the U.S. could have been reduced if the general population had had better heart health prior to the onset of the pandemic.”
You’re reading the web edition of STAT’s AI Prognosis newsletter, our subscriber-exclusive guide to artificial intelligence in health care and medicine. Sign up to get it delivered in your inbox every Wednesday.
Sometimes I feel like a Negative Nathan here, but the degree to which college kids hate AI (even if they feel forced to use it) restores my belief that I am not wrong. There’s something special about being human, and we don’t have to surrender that just because powerful people (who didn’t have to deal with this as they tried to enter the workforce, or maintain a career) command us to.
Biohub, the non-profit research organization co-founded by Priscilla Chan, MD, and Mark Zuckerberg, has now unveiled the latest update to the ESM protein language model family, with expanded capabilities in binder design and protein function mapping for therapeutic discovery.The release comes just seven months after Biohub recruited the team behind EvolutionaryScale.
The system includes ESMC (Evolutionary Scale Modeling Cambrian), a language model trained on approximately 2.8 billion sequences drawn from a breadth of life, including organisms adapted to extreme environments, and more than 20,000 types of proteins found in the human body. Evolutionary information encoded in ESMC is translated into atomic-resolution protein structures and interactions using the design engine and prediction model, ESMFold2.
Alex Rives, PhD, head of science at Biohub and former chief scientist at EvolutionaryScale, presented the work at this week’s “AI in Biology” symposium at Cold Spring Harbor Laboratory.
These models aim to transform the earliest stages of drug discovery by making biology more programmable. While traditional discovery workflows rely on slow and resource intensive experimental screens to identify promising drug candidates, rational protein design guided by in silico predictions has the potential to dramatically accelerate development timelines.
“We’re at an exciting point in protein biology where accurate digital representations allow asking experimental questions at a scale that wouldn’t be possible in the laboratory,” Rives told GEN Edge.
ESMC provides a foundation for modeling the sequence, structure, and function of proteins. ESMFold2 predicts the structure of proteins and biomolecular complexes. Features derived from the representations of the model capture fundamental principles of structure and function that form a compositional grammar for protein biology. [Biohub]
ESMFold2 designed high-affinity protein binders against five disease targets in cancer and immunology: receptor tyrosine kinases implicated in tumor growth (EGFR and PDGFRβ), immune checkpoints exploited by cancer cells to evade immune surveillance (PD-L1 and CTLA-4), and a regulator of immune cell signaling (CD45).
Lab-validated designs achieved hit rates ranging from 36–88% for compact mini-binders and 15–29% for antibody-derived formats, while also demonstrating nanomolar binding affinity, high specificity, and favorable stability profiles consistent with potential clinical utility. Notably, binders for PD-L1 showed therapeutic function and restored T-cell signaling in laboratory tests by blocking the same pathway as approved checkpoint therapies.
Rather than requiring multiple sequence alignments (MSAs) to build representations, ESMFold2 captures evolutionary information encoded during pretraining. The model also uses a looped transformer architecture, which allows compute to scale at inference time and avoids overfitting that can arise when training is constrained by limited experimental protein structures.
In benchmarking, ESMFold2 performed favorably when compared against Chai-1 from Chai Discovery, Boltz-1 from MIT (whose developers have since launched a public benefit corporation), and AlphaFold 3 from Google DeepMind.
The models are accessible under the highly permissive Massachusetts Institute of Technology (MIT) license for both commercial and non-commercial use. The work is described as a preprint that has not yet been peer reviewed.
“All in” on AI biology
Last November, Chan and Zuckerberg made the pledge to go “all in on AI-powered biology,” announcing that the organization’s scientific teams will now unite under a single entity, known as Biohub, where the duo would place the majority of their philanthropic effort.
Concurrently, Rives and EvolutionaryScale colleagues were recruited to tackle disease by decoding the “grammar” of amino acids through billions of years of evolution. That same mission had once secured a whopping $142 million seed round when the startup unveiled in 2024. The raise was led by Nat Friedman, Daniel Gross and Lux Capital, and included participation from Amazon Web Services (AWS) and NVentures, Nvidia’s corporate venture arm.
Biohub continues to advance virtual biology by building digital representations of molecules, genomes, cells, and living systems. The new ESM release joins Biohub’s growing ecosystem of biology models, including TranscriptFormer, which was published in Science earlier this month.
The organization recently invested $500 million in the Virtual Biology Initiative, a five-year campaign to accelerate the creation of technologies and multi-modal datasets to build predictive models of biology. The commitment comes a few months after the organization announced a collaboration with Arc Institute and Tahoe Therapeutics to build the largest single cell chemical perturbation dataset to power the virtual cell.
Evolution is all you need
Biohub has applied the new ESM models to generate theESM Atlas, a mapping of 6.8 billion sequences and 1.1 billion predicted structures to protein function using ESMC’s representations. Generating this atlas would have taken “billions of years of experimental work,” but was condensed into a couple of weeks with computational inference. The ESM Atlas is released open-source.
By probing ESMC’s representations using sparse autoencoders (SAEs), a technique for identifying interpretable structure in large language models, the authors found that the model independently learned hierarchical organization covering the basic chemistry of individual amino acids, local structural interactions, and functional concepts across unrelated proteins, despite being trained only on sequence data.
Notably, ESM Atlas SAE feature clusters brought together RNA-guided DNA endonucleases, eukaryotic Fanzor proteins and their evolutionary ancestor, prokaryotic TnpB, despite their high evolutionary divergence and low sequence similarity. These insights could support the development of new gene-editing tools.
While the preprint’s results are still a step away from clinical impact, Rives reiterates the power of open science in placing these tools in the hands of researchers working directly in translational research.
Biohub is partnering with a number of platform partners, including AWS Bio Discovery, Benchling, Phylo, Tamarind Bio, Modal, Tool Universe, and SandboxAQ, to make the models widely available.
![The American Heart Association's Life’s Essential 8 is a wheel shape with 8 wedges representing the eight elements that are essential for cardiovascular health [American Heart Association]](https://www.insideprecisionmedicine.com/wp-content/uploads/2026/05/AHA-Lifes-Essential-8-Circle-gr-300x300.jpg)
![ESMC provides a foundation for modeling the sequence, structure, and function of proteins. ESMFold2 predicts the structure of proteins and biomolecular complexes. Features derived from the representations of the model capture fundamental principles of structure and function that form a compositional grammar for protein biology. [Biohub]](https://www.genengnews.com/wp-content/uploads/2026/05/Viz1-11-1024x576.png)