This is an ongoing thread for my series, "30 Essays to Make You Love Biology." ❤️🧬 I'll pin it on my profile.

We've rebuilt the entire @AsimovPress website. We experimented with dozens of fonts and type sizes, column widths, and color palettes to find options that felt comfortable to read. JavaScript is also much easier to embed; many of our articles will include interactive elements. Footnotes, too, are now (finally!) visible in the margins.

Here's a company idea around rare diseases that I think somebody ought to build; if they haven't started already. (h/t @eperlste) For context: If you make a qualifying drug for a rare pediatric disease and get approval from the FDA, they give you something called a priority review voucher, or a PRV. These vouchers can be SOLD to other companies, or USED to speed up the review of a drug application. If you use a PRV, the FDA looks at the same requirements, but they just speed up the review. They prioritize it. Drug companies, then, can use these vouchers to save several months of wait time. So if you think a drug is going to have a market of billions of dollars a year (like a new weight-loss pill), that could be worth a lot of money. There's a website called PRV Watch that tracks how much these vouchers actually sell for. They tend to sell for well over a hundred million dollars for a single voucher. Abeona, for example, sold a single PRV for $155 million. So here's the business idea: You choose rare pediatric diseases where there are so few patients that you could make a case to the FDA for testing your drug on like five or ten people. You use computational tools to hopefully increase the likelihood of success. And you run these trials, aiming to get approval with a really small cohort. Let's say you could get all the way to approval for like $5 million to $10 million per drug. And let's say you take ten shots on goal, running ten of these at the same time. If only one of these drugs works out and earns a voucher, that sale could cover the cost of all ten attempts. You'd be profitable after that first tranche. Then, the whole company becomes about treating as many rare diseases as possible and selling vouchers to fund the development of more treatments, which could earn more vouchers. One problem with this approach, though, is that the program isn't permanent. Congress has extended it through September 30, 2029, but that still puts a deadline on getting these drugs approved. You'd have to act now and probably lobby for more extensions. Even so, I think this is a great business model. It basically gives financial incentives to drug developers who want to go out and cure rare diseases that otherwise don't have much of a market. These are diseases that traditional pharma would probably be ill-advised to pursue because they have to recoup all their R&D expenses. With AI and a really small team, you could possibly make a lot of money while developing treatments for people who otherwise might never get them.

Pioneer Labs recently announced they've made a microbe capable of growing on Mars. They say it's the first of a set of "pioneer species" that they plan to send there. But I was surprised when, in our interview, @erika_alden_d said that making this microbe was actually easy! All they really did was take a bunch of terrestrial microbes here on Earth, put them in a chamber, and evolve them. The part of the experiment that was difficult was simulating the Martian soil. How can we be confident that a microbe made on Earth would survive if shipped to Mars? If you ship a microbe to Mars and it dies immediately, you've wasted all this money and energy, and it was all just hype and smoke and mirrors. So what they did was take chemical measurement data from the Martian rovers, like Curiosity, and then use those measurements to recreate the toxins and nutrient composition of Martian dirt. Mars has a lot of perchlorate, for example, which is extremely toxic. It's basically like a bleach that destroys cells. Mars also has much less nitrogen than Earth. The air we breathe is mostly nitrogen (78%), but the Mars is only 3% nitrogen. Mars also doesn't have liquid water; it's frozen. So the part of this interview that I found most interesting is how we simulate another planet here on Earth. We have to do that with the chemistry. And increasingly, Pioneer Labs is thinking about how to simulate the physical conditions on Mars, too, including the pressure, the radiation, and the UV exposure. I think simulating all of those is actually easier than solving the problems they've already solved, because we can just put microbes into vacuums and bombard them with UV lights. Getting the dirt right, I think, was the real achievement in their big announcement.

In 12 weeks, we built a research facility that is run entirely by AI. AI designs, executes, and observes experiments end-to-end across biology, chemistry, and materials science. We’re introducing SciUniverse: a benchmark that measures AI’s ability to do real-world scientific research.

Theory, in biology, has never gotten the same "respect" or "institutional standing" as theoretical physics. This is a shame. Theory building in biology has been at least as fertile and consequential in the process of discovery as in physics. And yet, it has generally been hard to get funding for purely theoretical work in biology. Biology also has difficulty compressing its empirical data into theories. In physics, there’s only one kind of electron, and what applies to one, applies to all. But biological cells and organisms are products of individual developmental and evolutionary histories. Biological variation can itself be irreducible and causally meaningful. This means that, often, biological models have many many parameters! In our latest essay, @ulkar_aghayeva considers whether biology can be made as compressible and comprehensible as physics, and thus restore its institutional standing. She explains how a broad range of phenomena—including biochemical reaction networks, insect flight, and the eukaryotic cell cycle—are well described by so-called sloppy models. In such models, only a few parameter combinations are important to the observable behavior. This discussion is particularly important in light of AI, and in answering this question of whether or not AI systems will ever be able to make great "theoretical leaps" for biology. Read the piece and subscribe: press.asimov.com/articles/th…

This piece is about theoretical biology. But it's also about AI, and the gap between making a prediction and making a “conceptual leap.” The greatest role of AI may be in exploring ways to make biology as compressible and comprehensible as physics. Read the latest essay. 🔻

As someone who did this kind of genome mining work during my PhD, some thoughts on this Anthropic announcement: First, the very simplified version of what they did is that they noticed two genes (one known, one new) sitting next to a weird repeating piece of DNA. More specifically, they described an unusual reverse transcriptase (RT) associated with a repetitive DNA array and an unknown accessory protein. This kind of process was used to understand CRISPR back in 2002 and was key to the gene editing tools we use today. To put this into context, though, people have been finding RTs associated with CRISPR arrays since 2008, and this general kind of genome-neighborhood mining has been used to discover new biological systems for decades. The basic genome-mining strategy is well established, and there are now mature tools and published pipelines for doing much of this. There are papers that discover and experimentally validate dozens of new systems using this approach in a single study. Doing it in bacteriophage genomes is also nothing new (eg CasPhi). Finding a weird cluster of genes and repeats is often the easy part. The hard part, and where the real discoveries come from, is figuring out what the system actually does. Eg for the bridge-RNA discovery in 2024 from @arcinstitute or the discovery of CasPhi in 2020 from @DoudnaJennifer they figured out the pieces of the system and the rules for what makes it work so it can be used. Anthropic does not yet know what this does. They’ve shown that the repeat array produces RNAs, but not what those RNAs do, what the RT does with them, or whether the system has any of the programmable properties that make the CRISPR comparison justified. I’m genuinely rooting for all of the frontier labs to seriously get into biological discovery, and I’m excited about what comes out of it. But announcing these very early, incremental findings with the framing of a major discovery doesn’t help. I’d much rather they set the bar high now, so that when an AI actually discovers a fundamentally new biological mechanism, everyone appreciates how big a deal it is.

I wish we didn’t need these again, but here is the honest version of Anthropic’s biology announcement 🥳🥳🥳 (Caveat: I haven’t worked in bioinformatics for many years.) The good: Anthropic ran ~950 Claude agents over a large biological sequence database. Claude searched, wrote code, compared sequences and genomic neighborhoods, and found an interesting pattern that apparently had not been noticed before: a known reverse transcriptase associated with another gene and a repetitive DNA array. That is cool. Automating this kind of open-ended bioinformatics search at scale is useful, and Claude may have found a lead a human would have missed. But: Claude did not do a biological experiment. It searched databases and analyzed data. Humans then took the candidate into the wet lab. And the wet-lab result so far is modest: they showed that the repeat array produces short RNAs. We still don’t know what the system does. No function, mechanism, phenotype, targeting, defense activity, or programmability has been demonstrated. This is also where the CRISPR framing gets ahead of the result. Right now, “it has some features reminiscent of known programmable systems” is a hypothesis for what to investigate next, not a discovery that it behaves like CRISPR. And there is a missing baseline: bioinformatics has had tools for finding unusual gene neighborhoods and candidate systems for years. The interesting comparison is 950 Claude agents vs. an expert using the best existing computational pipelines - not Claude vs. someone manually looking through 200,000 sequences. So my honest announcement would be: Claude autonomously found an interesting candidate for a previously uncharacterized biological system. A small human wet-lab experiment confirmed that part of the candidate is expressed. We don’t yet know what it does. That is a good result. But in a regular biology lab, this isn’t the finished paper. It is the result you show at lab meeting and say: “This looks interesting. Now we need to figure out what the hell it does.” Maybe that next step leads to a major discovery. But that discovery hasn’t happened yet.

Without a mechanism, I’m struggling to understand the importance of this. Host-pathogen interactions have been a rich source of biological tools for decades; it’s where CRISPR and restriction enzymes and Agrobacterium came from. But the way we get these tools to be great, and useful, is by understanding their mechanism such that we can begin engineering and improving them. I’m sure AI tools will be helpful for molecular characterization and engineering; so why not wait to announce until you actually do that?

Private personal AI. Reversing cellular age. Brain-computer interfaces. Universal fabricators. Funding human agency. New life on Mars. Whether AI can be conscious, and whether it matters. Nov 13-15, Vision Weekend returns to San Francisco! Three days of expert talks, curated 1-on-1s, tech demos, a $10K pitch grant, and our main 40th anniversary celebration in the US. Speakers include: • Wojciech Zaremba (OpenAI Foundation) • Matthew MacDougall (Neuralink) • Illia Polosukhin (NEAR Protocol) • Max Hodak (Science Corporation) • Matthew Botvinick (Anthropic) • Nan Ransohoff (Frontier Climate) • Séb Krier (Google DeepMind) • Seemay Chou (Astera Institute) • Robin Hanson (George Mason University) • Alex Gladstein (Human Rights Foundation) + many more. Full lineup in thread. Join us across iconic Bay Area locations, including Lighthaven, @internetarchive, USS Hornet aircraft carrier, and lab tours at @E11BIO, @LongshotSpace, @calwave_energy, @DolphinLabs, @ScienceCorp_ , plus a cypherpunk party at our AI node. Get tickets before prices increase Oct 1. Link in thread.

Building ANNs in Cells... Screen grab of training and pruning an ANN, and compiling it into DNA. Read here to see the implementation in human cells: biorxiv.org/content/10.64898…