A new article in Science Policy Forum voices concern about a particular line of biological research which, if successful in the long term, could eventually create a grave threat to humanity and to most life on Earth.
Fortunately, the threat is distant, and avoidable—but only if we have common knowledge of it.
What follows is an explanation of the threat, what we can do about it, and my comments.
Background: chirality
Glucose, a building block of sugars and starches, looks like this:
But there is also a molecule that is the exact mirror-image of glucose. It is called simply L-glucose (in contrast, the glucose in our food and bodies is sometimes called D-glucose):
This is not just the same molecule flipped around, or looked at from the other side: it’s inverted, as your left hand is vs. your right.
Some molecules, such as water or glycerol, are symmetric, and so there is no distinction between their “left-handed” and “right-handed” versions. But many, like glucose, have this asymmetry that gives them a mirrored twin. Such asymmetric molecules are called chiral.
Chiral molecules include not only glucose, but proteins, DNA and RNA. In short, life is chiral.
Mirror life
All life on Earth, from bacteria to humans, has matching chirality, reflecting our common biological ancestry: all cells use left-handed amino acids, right-handed nucleotides, etc. But there is no known reason why an entire cell, organism, or ecosystem could not exist with the opposite chirality for each type of molecule. Call it “mirror life.”
Mirror life would interact with Earth life in strange ways, because every subsystem in our bodies is tuned to Earth chirality. Proteins evolved to fit other molecules, and would fit a mirror molecule the way your left shoe fits your right foot. Mirror food, for instance, might be less digestible to animals, because the enzymes that break down our food are chiral.
And, crucially, mirror cells might be largely invisible to the immune system of every organism on the planet.
The threat
A mirror virus would likely be harmless to us: it would be incompatible with our cells’ machinery, and thus unable to replicate in our bodies. A mirror bacterium, on the other hand, could be a lethal threat, even if it is a mirror of a species that is normally harmless.
Mirror bacteria could enter the body via the eyes, nose, or mouth, or through wounds, all of which happen frequently with normal bacteria. They would not necessarily need any special adhesion to our cells in order to do this.
Once inside, mirror bacteria might evade most of our immune defenses. They would be less vulnerable to the enzymes in our bodily fluids, such as lysozyme, that normally break down bacterial proteins. The surface proteins of mirror bacteria would likely not be recognized by our immune cells, and so much of the immune system might not trigger. They might not be broken down by enzymes in order to present antigens to T-cells, and so might not stimulate antibody production.
In the body, mirror bacteria could feed on achiral molecules such as glycerol and ammonia. E. coli, for instance, will replicate in growth media containing only achiral nutrients; mirror E. coli would do the same. With the right genes, mirror bacteria could even feed on the glucose in our bodies (there are Earth bacteria that can use mirrored L-glucose; therefore their mirror twins would be able to use normal D-glucose). Unlike humans, bacteria do not require certain essential amino acids, instead synthesizing what they need from simpler molecules in the environment.
Mirror bacteria might thus have free reign within the bodies not just of humans but also much of multicellular life on Earth. They would have no natural predators. They would be immune to existing bacteriophages. They would be an invasive species colonizing what might be, to them, an untouched environment.
The pathology of a mirror infection is unclear. The bacteria and their biomolecules would have limited interaction with our own cells. But they could produce toxic byproducts, and in any case, the unchecked growth of bacterial cells within the body could plausibly lead to a sepsis-like condition that could easily be fatal.
Defense would be difficult and severely limited
We could mount multiple forms of defense against mirror bacteria. First-line defenses such as hand-washing, sterilization, and gloves or masks would still be effective. We might be able to treat infections with mirror antibiotics. We might be able to immunize people, pets, livestock and crops with mirror vaccines, or to genetically engineer crops to have natural resistance. We might be able to engineer mirror bacteriophages.
Most of these measures, however, would only protect treated individuals or specific crops. It would be extremely difficult, likely impossible, to protect the ecosystem as a whole. In a world overrun by mirror bacteria, the best case for humanity might be that only our species continues, along with a small number of animal and plant species that we need to survive. In any case, the biosphere would be irreparably altered, in the greatest extinction event of the last two billion years.
Are we sure?
The threat of mirror bacteria is a prediction by a group of scientists, including experts in synthetic biology, evolutionary biology, immunology, and biosecurity. The prediction is not certain.
Chirality is real. Mirror biomolecules, such as L-glucose, are real and exist in nature. Larger mirror biomolecules have been created in the lab, and there is experimental evidence that mirror proteins do not reliably trigger certain immune responses. Mirror cells, however, including bacteria, have never been known to exist, and have never been studied directly.
It’s conceivable that mirror bacteria would present a much lesser threat, or no significant threat. It’s also conceivable, but less likely, that mirror life can’t exist at all for some reason.
Indeed, the threat is not obvious, even to experts, even though the possibility of mirror life has been known for a long time. In a WIRED article from 2010, for instance, MIT biologist George Church was asked about mirror pathogens and initially replied that they could not infect us. It was only recently that anyone began seriously investigating the threat of immune evasion, and even then, most of the scientists involved were initially skeptical. (Church is now a signatory on today’s article.)
However, the scientists on this article have thought through these questions from many angles, applying the best current scientific knowledge across physics, chemistry, biology, and health, and the disaster scenarios are simply too plausible for comfort.
Mirror life is a long-term goal of some scientific research
Mirror life hasn’t evolved on Earth in the last 3.5 billion years, so why worry about it now? Because the creation of mirror life is a long-term goal of multiple research labs investigating it.
Fortunately, we are not close to this happening. The technology to create mirror life does not currently exist. Even if we put in a massive effort and concentrated tremendous resources on it, it would take a decade.
Further, let me stress that this is a minor subfield of biological research, and not heavily funded. So on our present course, it is decades away. (That is, setting aside any significant acceleration of biological research from AI or other technologies.)
Still, the fact is that some researchers have been on this path. Like most scientists who had considered the question, they did not see the risks, thinking that mirror life would have limited interaction with us and therefore be harmless. They are not to be blamed for this. In fact, after a more in-depth discussion, many of them have signed today’s article.
What to do?
The article recommends that humanity avoid creating mirror bacteria, even as a scientific experiment, no matter how tight the biosecurity around it (which can never be perfect). Funders should not fund such research; governments should even ban it.
This is a simple cost-benefit calculation. On the cost side, the threat is plausible, and the potential damage incalculable. Thus, the risk is immense. On the benefit side, there is no crucial goal for humanity that is known to be enabled by mirror life. Restricting this research would not fundamentally impede progress in biology or bioengineering generally.
Not all forms of mirror biology would even need to be restricted. For instance, there are potential uses for mirror proteins, and those can be safely engineered in the lab. The only dangerous technologies are the creation of full mirror cells, and certain enabling technologies which could easily lead to that (such as the creation of a full mirror genome or key components of a proteome).
In short, by pruning off a relatively small branch of the tech tree, we can avoid a true existential risk.
The article also recommends research to develop surveillance and countermeasures, in case humanity ever does encounter mirror bacteria. This research can be advanced significantly without creating full mirror cells.
We have time to react
Given that the threat is relatively distant, no immediate action is needed. We have time to discuss it thoroughly, among a wider set of participants. The article released today is meant to be the beginning of that wider conversation, not a call to urgent action.
The above is largely summarized from the Science article, supplemented by the accompanying technical report and conversations with some of the researchers involved. What follows are purely my own thoughts.
The far future
I agree with the article’s recommendations for the foreseeable future. However, I can imagine the cost-benefit calculus changing in the long term, such that it would make sense to reconsider synthesizing mirror life.
On the cost side, future technologies could improve biocontainment. Imagine, for instance, a space-based bio lab, fully roboticized, in orbit around the Sun. Suppose this lab can accept shipments of materials, but nothing ever leaves it. Such a lab, separated by more than 1 AU from Earth, might provide sufficient protection for very dangerous experiments.
More speculatively, a mature and globally deployed nanotechnology might make control of the ecosystem possible, in which case mirror bacteria would pose no threat.
On the benefit side, we might someday decide that research on mirror organisms is necessary—before we encounter them in the wild, on other planets or their moons. While there is no evidence of advanced civilizations elsewhere in the observable universe, it is entirely possible that the universe is chock-full of bacterial life. And if the particular chirality of Earth life is a biohistorical accident, then there could be entire planets full of mirror life. Better to learn about it deliberately, in a lab, under controlled conditions, then to encounter it accidentally, and without warning.
Again, all of these are far-future speculations, which shouldn’t affect decisions we make in the present.
Optimism, pessimism, and progress
This article could be considered “pessimistic.” It considers an unproven threat, generated by uncreated technology, which might exist decades from now.
An “optimistic” response might be to downgrade the risk. Maybe we could easily defend against any threat, maybe we’d contain it in the lab, maybe it wouldn’t even be a threat, maybe we’ll never even create it, maybe it’s actually impossible.
I advocate neither optimism nor pessimism, but realism and solutionism. We should try to see reality, including risks, as clearly as possible, and we should actively steer towards solutions to any problems we see.
I am curious to know what the reaction to this issue will be from those who self-identify as techno-optimists or as “accelerationists.” But from a techno-humanist viewpoint, I think this is one small corner of the universe that humanity should simply not explore right now, for our own sake. We can achieve the glorious techno-abundant future without opening this particular door—and for the foreseeable future, maybe only by not opening it.
Thanks to Kevin Esvelt for briefing me on this report, and to him and James Wagstaff for answering my questions about it.
Curated. I’d previously heard vague things about Mirror Life but didn’t understand why it would be threatening. This post laid out the case much more clearly than I’d previously heard.
I think it’s very unlikely that a mirror bacterium would be a threat. <1% chance of a mirror-clone being a meaningfully more serious threat to humans as a pathogen than the base bacterium. The adaptive immune system just isn’t chirally dependent. Antibodies are selected as needed from a huge library, and you can get antibodies to loads of unnatural things (PEG, chlorinated benzenes, etc.). They trigger attack mechanisms like MAC which attacks membranes in a similarly independent way.
In fact, mirror amino acids already somewhat common in nature! Bacterial peptidoglycans (which form part of the bacteria’s casing) often use a mix of amino acid in order to resist certain enzymes, but bacteria can still be killed. Plants sometimes produce mirrored amino acids to use as signalling molecules or precursors. There are many organisms which can process and use mirrored amino acids in some way.
The most likely scenario by far is that a mirrored bacteria would be outcompeted by other bacteria and killed by achiral defenses due to having a much harder time replicating than a non-mirrored equivalent.
I’m glad they’re thinking about this but I don’t think it’s scary at all.
The antibodies not being chiral dependent doesn’t mean there aren’t other fundamental links in the whole chain that leads to antibodies being deployed at all that may not be. Mostly I imagine the risk is that we have a lot of systems optimized for dealing with life of a certain chirality. They may be able to cope with the opposite chirality, but less so. COVID alone showed what happens when something far less alien but that is just barely out of distribution for our current immune defenses arrives: literally everyone in the world gets it in a matter of months, a non-insignificant percentage dies even if the pathogen itself would be no more complex or virulent than others we deal with on the daily. And COVID was easy mode. We have examples of far more apocalyptic outcomes from immune naive populations getting in contact with new pathogens.
Here we’re not even talking about somehow innocuous entities. E. Coli can and will kill you if it gets in the wrong place while your defenses are down, no mirroring necessary. Staph. Aureus is everywhere already and will eat your flesh while you still live if given the chance. The only reason why we coexist with these threats is that we are in an armed truce: they can stay within their turf, but as soon as they try and go where they don’t belong, they get terminated with maximum prejudice. Immuno-compromised people have to fear them a lot more. Imagining a version of them that is both antibiotic resistant (because I bet that’s also a consequence of chirality) and able to evade at least the first few layers of immune defenses, until somehow the system scrambles to compensate and manages to churn out a counter-measure, is terrifying enough. That the immune system may eventually cope with them doesn’t mean it wouldn’t be an apocalyptic pandemic (and worse, one that affects man and animal alike, all at once).
Acquired immune systems (antibodies, T cells) are restricted to jawed vertebrates.
You’re saying that we might survive, but our environment/food might not, right?
Yes, antibodies could adapt to mirror pathogens. The concern is that the system which generates antibodies wouldn’t be strongly triggered. The Science article says: “For example, experiments show that mirror proteins resist cleavage into peptides for antigen presentation and do not reliably trigger important adaptive immune responses such as the production of antibodies (11, 12).”
I think this is the crux of the different feelings around this paper. There are a lot of unknowns here. The paper does a good job of acknowledging this and (imo) it justifies a precautionary approach, but I think the breadth of uncertainty is difficult to communicate in e.g. policy briefs or newspaper articles.
Why it may get even worse
I never thought of mirror bacteria before, but now I think it may get even worse.
They will survive somewhere on Earth and then start evolving
Even if they cannot survive inside the human body (due to the adaptive immune system as J Bostock suggested), I strongly believe they can survive somewhere on Earth. This is because some bacteria photosynthesize their own energy and do not need chiral molecules from any other creature to survive. A mirror bacteria of them will have no disadvantages, but be completely safe from bacteriophages.
They may evolve poisons against lifeforms with the opposite chirality
They will adapt to normal life, and normal life will adapt to them, but large animals like humans evolve very slowly and won’t adapt to them fast enough.
As they compete against normal bacteria, fungi and protists, they might evolve various kinds of deadly poisons designed to kill all lifeforms with the opposite chirality. Microorganisms are known for using chemical warfare to kill their competitors: Penicillium fungi evolved penicillin in order to kill all kinds of bacteria. Penicillin only kills bacteria and does not hurt eukaryotes like fungi or humans. This way the Penicillium fungi avoids poisoning itself.
The mirror bacteria might evolve deadly poisons against all lifeforms with the opposite chirality, without having to worry about poisoning themselves due to the chirality difference. This lack of self-poisoning may allow the poisons evolve faster and be more potent. It’s very hard to evolve a new poison and evolve resistance to your own poison at the same time, because evolution cannot plan ahead. If a new poison attacks a fundamental part of all lifeforms, the organism making it will kill itself before it can evolve any resistance. Unless it’s one of the mirror bacteria.
Chiral molecules include the amino acids which make up all proteins, and the lipid bilayer which cover all cells, so the mirror bacteria’s poisons have an unprecedented range of potential targets.
If the mirror bacteria become extremely widespread, their “antimirroral” poisons designed to fight competing microbes may also become widespread, and kill humans as a side effect. As collateral damage.
Alternatively, they might also evolve to directly infect large animals and kill humans.
I think the poison scenario may be worse because they can kill from a distance. Even if you sanitize entire cities with mirror antibiotics, poison from outside might still arrive due to the wind. Anyone with allergies knows the air is filled with spores and other biology.
Optimism
We can prepare for the risk before it happens. Not only can we make mirror antibiotics but “antimirroral” chemicals much stronger and less specific than antibiotics, which targets all mirror proteins etc. Well adapted mirror bacteria may survive far higher concentrations of “antimirrorics” than humans, but humans can pump out far higher concentrations of “antimirrorics” than the mirror bacteria, so we may win the fight if we prepare.
I also like your space lab idea, it allows us to empirically test how dangerous mirror life is without actually risking extinction. Not all risks can be empirically tested like this.
If there is an equilibrium, It will probably be a world where half the bacteria is of each chirality. If there are bacteria of both kinds which can eat the opposite kind, then the more numerous bacteria will always replicate more slowly.
Eukaryotes evolve much more slowly, and would likely all be wiped out.
I don’t know about microscopic eukaryotes, but yes the risk is that slow-evolving life (like humans) may be wiped out.
I agree the equilibrium could be close to half mirror bacteria, though in my mind a 1:10 ratio is “close to half.” The minority chirality has various advantages. It is less vulnerable to bacteriophages (and possibly other predators). It encounters the majority chirality more frequently than the majority chirality encounters it. This means the majority chirality has very little evolutionary pressure to adapt against it, while it has lots of evolutionary pressure to adapt to the majority chirality. The minority chirality will likely produce “antimirrorics” much more, until the two sides balance out (within an environment).
It probably won’t be exactly half, because normal chirality life does start off with way more species. It might evolve better “antimirrorics” or better resistance to them. The mirror bacteria will lack the adaptions to survive in many environments, though if it evolves quickly it might survive in enough major environments to become a severe risk.
That was a fascinating post, thanks for writing it!
Quote from the AI voiced podcast version of this post.
Yes, creating mirror life would be a terrible existential risk. But how did this sneak up on us? People were talking about this risk in the 1990s if not earlier. Did the next generation never hear of it?
I think until recently, most scientists assumed that mirror bacteria would (a) not be able to replicate well in an environment without many matching-chirality nutrients, and/or (b) would be caught by the immune system. It’s only recently that a group of scientists got more concerned and did a more in-depth investigation of the question.
How is it that some tiny number of man made mirror life forms would be such a threat to the millions of naturally occurring life forms, but those millions of naturally occurring life forms would not be an absolutely overwhelming symmetrical threat to those few man made mirror forms? This whole analysis seems to be assuming that the man made mirror forms will have some grossly asymmetrical advantage.
Can’t you ask the same question for any invasive species? Yet invasive species exist. “How is it that some people putting a few Nile perch into Lake Victoria in the 1950s would cause ‘the extinction or near-extinction of several hundred native species’, but the native species of Lake Victoria would not be an absolutely overwhelming symmetrical threat to those Nile perch?”
The asymmetric advantage of bacteria is that they can invade your body but not vice versa.
Good post! We will soon have very powerful quantum computers that probably could simulate what will happen if a mirror bacteria is confronted with the human immune system. Maybe there is no risk at all or an existential risk to humanity. This should be a prioritized task for our first powerful quantum computer to find out.
Really insightful read, thank you. Personally , I’m on the optimistic side of our ecosystem’s capabilities, but I’m not deeply knowledgeable in biochemistry or the detailed policy implications surrounding mirror life, so I sought an external perspective from a large language model (ChatGPT o1 pro mode) to help organize some thoughts. What follows is an AI-generated approach to governance and oversight strategies in response to the original discussion. I’m posting it here to see if others—who know more than I do—find these suggestions useful or flawed. Any critical feedback or pointing out of errors would be greatly appreciated.
ChatGPT: One angle that might offer more insight is to consider institutional and structural measures that encourage early, proactive governance even before the technology nears feasibility—essentially putting in place “epistemic tripwires.” While the article and its technical supplement suggest discussions and eventual regulations, we can get more granular about how to develop a system that’s both flexible and anticipatory. For instance:
Tiered research oversight: We could create formalized checkpoints at which research teams would need to seek an external, international evaluation before moving from simpler mirror biomolecule work (like individual proteins) to more integrated systems (like partial ribosomal complexes or membrane structures). This isn’t just a bureaucratic hurdle. It’s a designed pause where researchers must present data on safety, containment measures, and justifications for advancing closer to a living mirror cell. Such a tiered approach isn’t explicitly described in detail in the article, but it would translate broad recommendations into an actionable process.
Embedded bioethics and biosecurity consultants: Instead of ad hoc or after-the-fact consultations, any lab or funding body working on advanced synthetic biology could have embedded experts in biosecurity and ethics who help shape the research direction from the start. As soon as work begins to drift toward enabling technologies (like large-scale synthesis of mirror nucleic acids), these advisors can flag potential risks and escalate them to regulatory bodies. This approach can create an early-warning pipeline rather than waiting for completed results to prompt retrospective bans.
Scenario modeling and quantitative risk assessment tools: While the article points out that mirror organisms would represent unprecedented risks, it doesn’t delve deeply into how we could quantify and update those risk assessments over time. Developing and refining scenario models—similar to those used in epidemiology or nuclear risk—could help track evolving technological capabilities. Modeling can incorporate likelihood estimates, potential escape scenarios, and effectiveness of proposed countermeasures. Updating these models annually would give the research community and policymakers a “dashboard” for how close we might be getting to a point of concern, well before any dangerous lab strain exists.
International “pre-emptive prohibition” treaties with sunset clauses: While calls for bans are mentioned, a treaty that is both pre-emptive and contains a mechanism for periodic review would provide flexibility. It would start by forbidding creation of full mirror cells but incorporate scheduled re-evaluation every 5–10 years as science advances or as we develop better containment methods. This moves beyond a permanent ban mentality toward a dynamic governance instrument—one that can relax or tighten its stance as understanding and defensive technologies improve.
Public engagement and “citizen juries”: To broaden trust and acceptance of any regulatory approach, we could periodically convene diverse citizen panels to discuss the latest findings, models, and governance measures. While the article encourages discussion, making the public a direct stakeholder in the decision-making process—beyond just being informed—could help keep policy aligned with societal values and allow for more nuanced decisions than a top-down ban. If research shows that partial mirror organisms (like “mirror vesicles”) can be studied safely, it might be easier to secure measured public support if they’ve been involved in the oversight framework from the start.
Taken together, these measures focus not just on identifying the risk and calling for dialogue or bans, but on building a structured, evolving system of oversight that can adapt to new discoveries. They give a clearer path to implementing the article’s recommendations in a way that is transparent, dynamic, and resistant to the inertia or sudden overreactions that can plague emerging technology governance.
This implies that we should stop life from developing independently, and that if contact is made with aliens then the human making contact and any environment that’s been in chain of proximity should be spaced
Given that mirror life hasn’t arisen independently on Earth in ~4B years, I don’t think we need to take any steps to stop it from doing so in the future. Either abiogenesis is extremely rare, or when new life does arise naturally, it is so weak that it is outcompeted by more evolved life.
I agree that this is a risk from any extraterrestrial life we might encounter.