How Randomness Drives Aging - DNA Repair, Clocks & Rejuvenation (David Meyer)

[John_Hemming]

How Randomness Drives Aging - DNA Repair, Clocks & Rejuvenation (David Meyer)

O3: Transcript, Summary, Critique

1. Tidied transcript

Lightly edited to remove filler words, correct obvious transcription errors, and clarify speaker turns. Timestamps are approximate.

Time	Speaker	Content
00:00	Host (Shiki Science Show)	“Hello and welcome. Today I’m speaking with Dr David Meyer, an ageing researcher and bioinformatician at the University of Cologne. David works with DNA-methylation and transcriptomic ‘ageing clocks’ to understand what drives ageing.”
00:27	Host	“Let’s start with the basics: what are ageing clocks?”
00:32	Meyer	Ageing has been quantified for decades. The field took off with Steve Horvath’s pan-tissue DNA-methylation clock (≈2013). Horvath pooled many human datasets spanning young to old ages, then used simple machine-learning (often linear regression) to pick CpG sites whose methylation levels shift with age. No single CpG is perfect, but a small panel works surprisingly well; three sites can already predict chronological age to within ≈2 years.
01:53	Meyer	Since Horvath, clocks have expanded beyond DNA methylation to other data types and beyond predicting chronological age to predicting biological endpoints such as all-cause mortality.
02:25	Host	“When you say ‘age’, do you mean chronological or biological?”
02:31	Meyer	First-generation clocks were trained on chronological age because that label is abundant, and we can now predict it with ≈2-year error. The useful signal is the residual (predicted – actual). If you look ‘older’ than your passport, that may correlate with higher disease risk, but the correlation is modest. Second-generation clocks therefore train directly on outcomes such as mortality, giving stronger associations.
04:56	Meyer	Third-generation efforts include tissue-specific clocks and even cross-species clocks (e.g. the recent “mammalian” clock). Different data richness forces people to build many bespoke models—hence all the clocks.
06:02	Host	“Does methylation tell us anything causal about ageing, or is it just correlation?”
06:14	Meyer	Methylation is harder to interpret than RNA or protein because one CpG can affect many genes. Yet certain themes recur—developmental genes are enriched among age-informative CpGs, fuelling speculation about ‘programmed’ ageing. Our 2024 Measure Ageing paper argues that clocks mainly capture accumulating stochastic variation—in other words, cellular noise. In youth the epigenome is tightly regulated; with age, copying errors build up. Formerly repressed genes (often developmental) are randomly derepressed, so clocks read them as ‘older’.
11:30	Host	“But transcriptomic clocks (such as your BiT-Age C. elegans clock) reveal clear gene-expression patterns. How can noise alone explain those?”
12:35	Meyer	Noise isn’t the whole story; there are adaptive responses too (e.g. DNA-damage repair, inflammation). We built BiT-Age partly to dissect those responses in a short-lived organism. Even transcriptomic clocks still scale linearly with injected noise, implying that stochastic variation is universal.
16:21	Host	“Let’s talk about the DREAM complex—your lab showed it represses DNA-repair genes and its activity rises with age. Doesn’t that sound like programmed ageing?”
17:35	Meyer	The DREAM complex is a transcriptional repressor. When we mutate or chemically inhibit it in C. elegans (and in human cells), DNA-repair genes are derepressed and organisms cope better with UV, ionising radiation and chemicals. Long-lived species also keep repair activity higher. Why DREAM tightens with age is unclear; stochastic damage may hit its regulators, or there may be quasi-programmed aspects.
23:29	Meyer	Interventions such as caloric restriction (CR) and rapamycin extend lifespan partly by slowing endogenous damage production and partly by shifting cells from growth to maintenance (autophagy, lysosomal recycling). Both chronological and stochastic clocks show lower ages in CR mice.
27:45	Meyer	A big hurdle is validation. We need longitudinal human data before regulators will accept clocks as clinical endpoints. Meanwhile, clocks are powerful for discovery—e.g. pinpointing which C. elegans neurons age twice as fast as others, or detecting transcriptional rejuvenation during dauer diapause.
35:05	Host	“Cellular reprogramming appears to reset clock age. How can that erase random damage?”
35:12	Meyer	Two things happen: damaged cells are culled, and divisions dilute damage. More intriguingly, the reprogramming factors (OSKM) reset the epigenome—akin to the natural rejuvenation that turns two old gametes into a young embryo. That ‘factory-reset’ probably removes much of the accumulated noise.
38:55	Host	“What underrated directions excite you?”
39:03	Meyer	Post-mitotic rejuvenation. C. elegans dauer larvae or adult diapause can pause for weeks, then resume development with no lifespan penalty. We see real ageing during the pause, followed by a transcriptional ‘rejuvenation’ on exit—without cell division. Uncovering the mechanism could help neurons in humans, where dilution or selective culling is impossible.
44:03	Host	“Final thoughts?”
44:16	Meyer	The field is accelerating—more funding, better cross-species comparisons, stronger focus on DNA-repair capacity. But we still lack longitudinal validation and need to understand adaptive vs. causative pathways.
45:58	Host	“Thanks for the conversation.”

---

2. Concise summary

1. What ageing clocks are – Statistical models built from age-related biomarkers (initially DNA CpG methylation) that predict chronological age or outcomes like mortality.
2. First- vs. second- vs. third-generation clocks – Chronological, outcome-based, tissue- or species-general models respectively.
3. Key claim – Clocks largely measure the amount of stochastic epigenetic noise that accumulates with age, not specific causal pathways. Evidence: artificially adding noise to young datasets pushes clock age upward linearly. (nature.com)
4. Transcriptomic clocks – BiT-Age (binarised C. elegans RNA-seq) also tracks noise but exposes adaptive pathways (immune, neuropeptide signalling) that correlate with lifespan. (pmc.ncbi.nlm.nih.gov)
5. DREAM complex – A conserved repressor of DNA-repair genes. Lowering DREAM activity boosts repair and stress resistance; long-lived species tend to have higher repair capacity. (nature.com, pubmed.ncbi.nlm.nih.gov)
6. Interventions – Caloric restriction and rapamycin slow damage accrual and ramp up maintenance pathways; both lower clock-predicted ages.
7. Rejuvenation – Full or partial OSKM reprogramming resets methylation clocks via cell selection, damage dilution and epigenetic ‘factory-reset’. Dauer/adult diapause in C. elegans shows a division-free rejuvenation that may illuminate neuron ageing.
8. Field outlook – Urgent need for longitudinal validation so clocks can serve as clinical endpoints; cross-species comparative genomics and repair-centric interventions are promising research fronts.

---

3. Critique

Aspect	Strengths	Limitations / open questions
Framing of clocks as noise meters	Grounded in a clever in silico noise-injection experiment; fits the observation that many age-informative CpGs sit in tightly repressed developmental loci where even tiny derepression is conspicuous.	Evidence remains correlative. Noise injection is necessary for a clock signal, but not sufficient to prove that noise is the driver of ageing rather than a parallel marker. No direct demonstration that reducing noise slows functional ageing.
Use of C. elegans models (BiT-Age, DREAM, diapause)	Short lifespan, abundant mutants, and cell-type resolution make worms ideal for causal tests that are impossible in humans.	Translational relevance can be weak: worms lack DNA methylation, have radically different somatic/germ-line demarcation, and rely on dauer-specific physiology absent in mammals.
DREAM complex narrative	Highlights a conserved master regulator and provides a mechanistic bridge between DNA repair capacity and lifespan. Fits comparative genomics data.	It is unclear why DREAM activity changes with age. The programme/noise dichotomy may be false; feedback between damage and DREAM could create quasi-programmed dynamics.
Intervention logic (CR, rapamycin)	Sensibly links metabolic slowdown and maintenance up-regulation to reduced noise accumulation, consistent with multi-omics CR studies.	The discussion underplays other CR targets (e.g. gut-brain endocrine axes) and ignores that CR benefits plateau or reverse in some contexts.
Reprogramming as rejuvenation	Poses a coherent multi-mechanism explanation (cell culling + dilution + epi-reset). Acknowledges clinical hurdles and potential in partial reprogramming.	Assumes that epigenetic reset eliminates functional damage, but permanent DNA mutations, mitochondrial deletions or cross-linked proteins may still matter. Long-term safety (e.g. tumorigenesis) is not addressed.
Field outlook	Correctly identifies the validation gap as the bottleneck for clinical translation of clocks.	Only briefly touches on ethical, regulatory and equity issues that will surface once interventions mature.

Overall appraisal

Dr Meyer gives a clear, data-driven account of why stochastic damage and imperfect maintenance may dominate the ageing landscape, without resorting to speculative teleology. The interview shines when it connects molecular mechanisms (DREAM, OSKM) to organismal phenotypes via quantitative clocks. It is weakest where any clock-centric discussion often falters: establishing causality, generalising from worms to humans, and grappling with non-epigenetic damage. Still, the conversation is a valuable primer on the state of clock research and a thoughtful roadmap for next-generation geroscience.

[John_Hemming]

Incidentally I think the approach presented in the video is wrong.

[Tim]

A new article in The Atlantic, taken from behind a paywall, focuses on continuing research into the link between aging and DNA mutations.

The DNA Fix for Aging

Everyone’s DNA keeps mutating. Could correcting those errors lead to longevity?

By Roxanne Khamsi

Illustration by Seba Cestaro

April 16, 2026, 1:11 PM ET

On his son’s fourth birthday, Michael Prescott had his first heart attack. Prescott, who worked as a civil engineer designing bridges in Tennessee, was in his 30s, and until that day, he had appeared to be in excellent health. But within two years of that first heart attack, he had four more. His doctors, who were baffled by his repeated medical crises, decided that he needed a heart transplant. In 2001, he underwent the procedure in Nashville. But a few years later, he needed a kidney transplant too. No one could explain why his organs were failing him.

As time dragged on, Prescott’s symptoms became more outwardly visible. His skin began wrinkling like that of someone decades older than him, and he developed cataracts. By his early 40s, Prescott looked like he was in his 60s. When he attended baseball games with his son, Carter, people would mistake him for the boy’s grandfather.

Frustrated, Prescott decided to diagnose himself. He would sit for hours in the living room in his favorite chair, his slim form enveloped in a sweatshirt with the logo of his favorite football team, the Tennessee Volunteers, as he read one research article after another. “He had a hard time sleeping at night,” Carter told me, “and so he’d be in his recliner with his little lamp, on his laptop, just kind of scouring through stuff, taking notes and trying to figure it out.” Finally, Prescott struck upon a disease that seemed to explain everything. His doctors agreed to test him right away, and the results vindicated his hunch. Prescott had a real illness with a real name: Werner syndrome.

A person with Werner syndrome seems to age at fast‑forward speed. By their mid-20s, they experience hair loss, muscle atrophy, and loss of the fat under their skin. During their next decade of life, many patients develop other early hallmarks of aging, such as hardened blood vessels. Individuals with this condition live, on average, until their early 50s. They lack a functioning version of a DNA-stabilizing protein, and their cells rapidly accumulate sequence errors as they age.

A version of that same process occurs even in those of us without Werner syndrome. We all amass DNA damage and countless mutations in our tissues throughout our lives. We just do so a bit more gradually.

Scientists now recognize that spontaneous DNA errors, which we acquire in early development all the way until our last breath, can drive several ailments such as heart disease, autoimmunity, epilepsy, Alzheimer’s disease, and cancer. These errors could even be the missing piece in explaining the universal phenomenon of aging.

Scientists’ earliest understanding of genetic disease had to do with mutations in the genetic code people inherit at birth. (Think of hereditary disorders such as hemophilia, cystic fibrosis, and sickle cell disease.) Later, they came to understand that epigenetic marks—the chemical tags that sit on top of genes, helping switch them on and off—can play a role too. More recently, scientists have discovered the massive number of sequence mutations everyone experiences throughout life. Consider this stark possibility: Even as you read this sentence, the brain cells you are using to process it might be mutating.

Unlike inherited conditions, spontaneous genetic diseases can emerge at any point in a person’s life. Some non-inherited genetic diseases are rare, such as the bone condition melorheostosis, which was first described decades ago and causes a painful overgrowth of bone that on X-rays resembles dripping candle wax. But the list of diseases linked to spontaneous mutations expands with each passing year, thanks in part to advances that enable scientists to decipher the DNA of single cells rather than bulk-tissue samples alone. In 2020, doctors added a new one to the list. They discovered a sometimes-fatal inflammatory disorder resulting from spontaneous mutations in the UBA1 gene. Non-inherited genetic errors have also been implicated more and more in common conditions: Upwards of one-third of children with autism spectrum disorder possess spontaneous mutations that appear connected to their condition.

Scientists’ greater understanding of acquired mutations is already inspiring major updates to medical treatment. Take cancer: Decades ago, oncologists believed that tumors were driven by a couple of genetic errors. Now they know that cancers are rife with genetic change—by some estimates, thousands upon thousands of mutations per advanced tumor. By sequencing the genetic changes in a tumor, scientists can figure out which mutations fuel its growth, and design drugs to strike those targets. Meanwhile, in neurology, some epilepsy patients have received drugs for their seizures that target specific spontaneous mutations detected in their brains.

For decades, scientists have suspected that acquired mutations might also explain health problems adults experience as they age. Among the earliest researchers to make the connection were physicists who had worked on developing the first atomic bombs. The United States used these weapons to kill hundreds of thousands of people at the end of World War II, and they have since been linked to cancers in people exposed to the bombs’ mutation‑inducing radiation. Understanding the effects of such mutations remained an obsession for some Manhattan Project scientists, including Gioacchino Failla and Leo Szilard. In the 1950s, they theorized that “hits” to the genome could explain the universal process of aging.

By the next decade, British scientists observed that many men seem to be losing copies of their Y chromosome as they age. Scientists now know that almost half of men over the age of 70 have lost the Y chromosome in some of their blood cells—a phenomenon that has been linked to an increased risk of cancer. (Women also seem to lose copies of their X chromosome as they age, but the number of published studies related to this phenomenon is paltry.) In recent years, geneticists have found that people in their later decades of life are more likely to have blood cells with mutations in specific genes. These cells, present in about 10 to 20 percent of people ages 65 and older, double someone’s risk of coronary heart disease and stroke. Medical researchers have estimated that a single white blood cell from a 100‑year‑old can contain more than 3,000 acquired mutations.

Now that scientists have described just how much mutation happens in aging, they’re curious if DNA repair might offer a counteracting force. In other words, does fixing DNA improve longevity? Biologists are taking different tacks to find out. Some have turned to gene editing to try to create antiaging therapies: One company, Spellcheck Bio, has started designing a treatment that relies on the CRISPR-Cas9 genome‑editing system to look for—and correct—DNA mutations.

Vera Gorbunova, a biologist at the University of Rochester, traveled to the sea around Utqiagvik, Alaska, to study the genes of the mammal with the longest lifespan on Earth: the bowhead whale. “This is the only mammal proven to live longer than humans,” she told me. One bowhead whale was estimated to have lived to 211, and genetic clues suggest that members of the species could have a maximum lifespan of 268 years. Gorbunova and her colleagues worked with the local Inupiat community to collect small samples from whales hunted using traditional methods. In the lab, the scientists observed that the bowhead cells mended breaks and mismatches in their genetic sequence extremely well. The cells also contained astronomical levels of a molecule known as cold‑inducible RNA-binding protein, or CIRBP. Gorbunova imagines that proteins such as CIRBP—if they do indeed counteract DNA damage—could perhaps have a place in modern medicine.

Gorbunova is on the scientific advisory board of the start-up Genflow Biosciences, which leans into the belief that activating DNA repair might reduce damage to the genome, and therefore extend life. All of the drugs it has in development involve the SIRT6 gene, which makes a protein that helps guide DNA repair. Gorbunova previously helped lead a genetic-sequencing project that found that some centenarians possessed a rare variant of the SIRT6 gene that enhances genomic stability. The company aims to start clinical trials on a compound to reverse liver damage, and on another one it hopes will have antiaging effects in dogs. Genflow is also developing a drug to treat Werner syndrome, the inherited genetic condition of accelerated aging that affected Michael Prescott.

Prescott, for his part, forged ahead despite his worrisome prognosis. He continued cheering on the Tennessee Volunteers and guiding his son through life. Ultimately, though, Prescott developed cancer—another common complication of Werner syndrome. He died at age 52, weighing only 65 pounds.

The breakthroughs of recent years came too late for patients such as Prescott. But with the new understanding that DNA is dynamic and endlessly changing, modern medicine is now better equipped to adapt to—and perhaps even influence—the cacophony of mutations we all inevitably accumulate.

This article was adapted from Roxanne Khamsi’s new book, Beyond Inheritance: Our Ever-Mutating Cells and a New Understanding of Health.

By Roxanne Khamsi