Scientists Custom Print 16 Never-Before-Seen Real-World Viruses

Scientists right here in the good old US of A recently announced that for the very first time ever they were able to create, using AI, viruses never before seen in nature. But don't worry, these new viruses were designed to target specific strains of E. coli bacteria only that became resistant to the natural antibacterials available. This development, it obviously marks a major milestone in the field of synthetic biology and it opens the door to potentially rapid advancements in human health care because if they're able to attack E. coli bacteria using these AI generated viruses, well, they could figure out rather quickly probably how to target other types of bacteria that's been plaguing humans for millennia. However, if you happen to experience the early 2020s, then you probably can imagine how this can all go horribly wrong. And so today let's go through the details of these newly created AI real world viruses together right after you take a super quick moment to smash those like and subscribe buttons so this video can be picked up by the algorithm and shared out to ever more people. Thank you so much for that. Now, before we get into the details of the newly generated viruses, let's first quickly unpack the details behind the AI system that was used to generate them. It's called EVO2 and it is the largest open source DNA language model for biology. Researchers developed this AI program after feeding it for years with genetic data sequences that were drawn from millions of animals, plants, microbes, and viruses. Here is Stanford professor Mr. Patrick Hsu describing it. EVO2 itself is trained on whole genome sequences, 9 trillion base pairs spanning all domains of life. This was assembled through a massive scientific effort spanning 20 or 30 years of people sequencing these genomes that we use to train the model. And the model learns from these genome sequences, the rules underlying these sequences, and then using those rules to generate new DNA. We can then use the technologies for writing and editing DNA to test in the lab. Now, in case you haven't been on the inside of a biology classroom since high school, here's a quick 30 second refresher. Nucleotides are those strings of building blocks like letters that can be used in a different combination within a sentence. The letters are A, C, G, T. Hundreds of these nucleotides come together to form what are known as genes. And depending on the sequence of the letters, different genes have different instructions encoded on them for building different types of proteins or other types of molecules. And so the large language models for the general public, things like Chad, GPT, or Grok, they're built based on the input of millions of books. Evo, however, was fed trillions of different gene combinations, which over time allowed this AI model to learn which combinations produce something biologically meaningful rather than just background noise. And Evo learned to make novel predictions, meaning it could predict what a theoretical combination of nucleotides would possibly result in the real world. Here's how the Arx Institute puts it. And for your reference, the Arx Institute were involved in building the Evo 2 AI model. Quote, trained on genome sequences across all domains of life, from bacteria and phagy genomes to plants and animals, including humans, the model is incredibly flexible. Not only can Evo 2 be used to make predictions, such as identifying disease-causing mutations, it also features strong generative capability. This article then continues to reference what we alluded to at the very top of the episode. Quote, one of our notable successes has been our functional bacteriophagy, representing the first AI-designed and experimentally validated organisms. Building a custom phagy holds the potential to treat antibiotic-resistant bacteria, which rapidly evolve resistance to traditional antibiotic treatments and are a growing problem. Essentially, what they were able to do was to teach the AI to recognize patterns of DNA structures in nature, and then to use that data to write recipes for brand new viruses not found in nature. And so for a while now, scientists have been able to use AI to generate one of the simplest biological organisms that you can find, something known as bacteriophages. The name literally means bacteria eater, and it's basically a tiny virus that infects and destroys bacteria. The current scientific understanding is that they cannot harm humans, animals, or plants. Instead, they only target single-celled bacterial germs. And so this has been happening for a while now. Scientists have been cloning these bacteriophages and creating synthetic versions of the original. However, what makes this latest development so groundbreaking is that this is the first time that a brand new synthetic bacteriophage genome was modeled entirely by AI and then brought to life in a lab, meaning this is not just a copy and paste job. This is not a simple clone of an existing virus that already exists in nature. Instead, the AI was able to look at the genome of a specific virus as well as the other viruses in the, I guess, family tree vicinity, and then it was able to create new mutations of that virus that did not exist in nature originally. Here's specifically how the researchers did it. They trained the Evo AI using the genes of a certain bacteriophage and also about 15,000 of that bacteriophage's closest relatives. Then once the AI model was familiar with the genomes of that virus family, the researchers then prompted the model, just like I guess we prompt Chad GPT, they just prompted it to write new versions of its own. The Evo AI then generated 700,000 potential new versions, and out of those, the scientists selected 285 that they thought had the best chance of succeeding. They then synthesized these 285 AI-generated real-world virus genomes in a lab, and they ran a test. They found three strains of E. coli bacteria that were resistant to the natural bacteriophage, and they tested whether or not any of these AI-generated bacteriophages would work instead. And wouldn't you believe it? Out of the 285 AI-generated bacteriophages, 16 of them successfully assembled into functioning viruses capable of infecting the resistant strains of E. coli. And voila, just like that, 16 never-before-seen viruses capable of infecting bacteria cells that had previously been immune to that same virus in nature. In the study where these findings were published, which was Science Magazine, the researchers dubbed it, quote, an exciting proof of concept that paves the way for larger and more complex designs. Also, in an Arc Institute article regarding the study, the researchers noted that there are some near-term opportunities for follow-up research in this direction. Quote, phagy therapy is becoming an increasingly effective way of fighting multi-drug-resistant bacteria. Near-term therapeutic targets include plant pathogen-specific phagies. Clinically relevant bacterial pathogens in these settings are a bacteria which causes respiratory infections or another which causes black rot disease in crops. And then in terms of the money that might come from this discovery, they claim to not yet have a roadmap. Here is Brian High, a contributing researcher for the study, discussing the matter of money. Quote, we don't have plans right now to commercialize this work. We're an academic lab funded by philanthropy and government grants. It is our responsibility to put the basic technology out there for use by as many people as possible because of the vast potential benefits to health and humanity. Now, at this point, while some of you are probably impressed with this technological breakthrough, you might also probably be a bit concerned that this is just another step towards someone creating some new form of virus that can And you're not alone. That potential danger was also on the minds of the researchers who were training the Evo AI model, which is why they claim they did not provide the model with any data about viruses that can infect either humans, animals, plants, or fungi. They were only training it on viruses specific to bacteria. Quote, this work was conducted with comprehensive safety protocols that exceeded standard requirements. All experiments took place in dedicated biosafety cabinets with specialized disposal procedures and equipment never left the containment area. We used only non-pathogenic bacterial hosts, E. coli, C. and other common laboratory strains of E. coli, ensuring that both the original and AI-designed bacteriophages posed no risk to human health. And then they also went further. Quote, our computational approach incorporates built-in safety constraints. Evo cannot generate human viral sequences due to deliberate training data exclusions, preventing both accidental and intentional misuse for pathogen design. Which is all very assuring, but assurances aside, once the genie is out of the bottle, it's not clear what direction it will take. Which ARC themselves admit to, which is made more evident when you remember that it's actually an open source AI model. Quote, even as we push forward new discoveries, human safety and ethical use have been at the forefront of ARC's approach to this exciting new technology. However, further work for model alignment will be needed for ongoing biosafety as future versions of biological foundation models become more capable, and ARC and our collaborators are proud to be at the forefront of those efforts. A more succinct version of that concern was actually voiced by Dr. Inglesby from the John Hopkins Center for Health and Security, and here is what he said on the matter. Quote, existing governance frameworks are insufficient for overseeing generative genomics. The question is no longer whether generative viral genome design will exist. It is whether society can build oversight that allows its benefits to unfold while preventing it from enabling serious harm. Now, interestingly, just one month before the creation of the 16 new AI-generated viruses was published, the NIH rolled out a new policy. You can see it up on your screen. It's a policy for stopping high-risk life science research, and specifically, it would bar scientists from experiments that would make biological agents more harmful. I guess another term for gain-of-function research. Here's an excerpt from the NIH announcement. Quote, this groundbreaking government-wide policy establishes, for the first time, an explicit prohibition on dangerous gain-of-function research, which can significantly endanger American lives and pose substantial risk to our nation's security. Which is amazing. For the very first time, a prohibition on gain-of-function research. That probably deserves an episode of its own to unpack. Regardless, though, the policy also does a couple of other things. It introduces enhanced reporting requirements for all life science research, and it seeks to strengthen global safeguards by instituting new international restrictions. Meaning, in theory, you'll no longer be allowed to fund research to be done in a country like China, for instance, that would have been illegal to be done here in the U.S. However, it's, again, beyond worth mentioning that these AI models, well, the effectiveness of the restrictions against them are really dubious. I mean, EVO2 is, again, an open-sourced AI model, so anyone can run the models to create AI viruses or the bacteria. You just feed in the genomes as training data, and then you ask it to model new variations. You then just need a lab that's capable of virus synthesizing to bring the new models to life. So, I don't know. Leave your thoughts in the comments section below. Are we heading towards a very bright future, where these AI models can now cure diseases that have plagued us for millennia, or will this go very sideways? And also, what can us normal human people watching it do besides just watch it unfold and hope for the best? I mean, this is really like a good example of the march of progress, and there is no stopping progress. You just have to, I guess, wait and see where it ultimately leads to. Also, this does kind of tie in a little bit to what we discussed in a very previous episode, like maybe a year ago, with what the CCP were allegedly, reportedly working on, which are viruses capable of attacking specific human genomic traits, meaning a specific ethnicity that could be targeted using a virus. So, I guess that also ties into this type of research and development. Yeah, leave your thoughts in the comments section below, what you think about it. And then also, if you want the links to this research paper, I'll throw that down in the description box below, which is that description box right below this like and subscribe buttons, both of which I hope you smash. And then lastly, on a different topic, although I guess it's tangentially related to these viruses, if you've ever wondered what happens to humans after we die? Great question, I'm sure you've wondered it, I've wondered it myself quite a lot. Well, over at the Epoch Times, we just published a phenomenal new film interviewing people who surprisingly know what happens, at least to them, after they die. Because these people, they either experienced clinical death, meaning no breath, no heartbeat, no brain activity, or they were in a very deep coma, meaning just no brain activity. But regardless of which camp they fell into, they came back to life, and remembered everything that they experienced on the other side, and then sat down with the Epoch Times to tell us about it. And their stories are amazing. The music they were able to hear, the way that the music was affecting the world that they saw, the portals that they went down, how they were transported from one world to a higher world, to a higher world, the beings they interacted with, the life review they were able to do of their own lives. It's truly an amazing movie. And it's done in a great way, because as they're being interviewed, they recreated the scene so you can actually see what they're talking about in, I guess, these other realms, other dimensional realms. It's a phenomenal new film, and it sort of explores this new scientific research area of NDEs, which is, in my opinion, a great direction for us to travel in terms of scientific research, because this can really have the impact of changing what we collectively understand life to be, which is the ultimate question, I guess, that we need to answer as people, but also, I guess, what science is actually meant for, to answer that question. What is all this, actually? What is life? So anyway, it's a great documentary. I would highly, beyond recommend it. I was thinking about it for days after I finished watching it, and you can check it out. It'll be linked right there at the very top of the description box below. I hope you check it out. Again, it's called Final Hours. Technically, I was dead, but I felt that this was more real than real, and I felt more alive than life itself. Thousands have glimpsed something vast and loving waiting on the other side. I was surrounded by beings, some of them I recognize from this life. It's more just like a light, the light of God. I was so happy. I just felt like more and more of the pain of this world was just floating away. What do these human experiences mean for our collective soul? The more we can come into harmony, love, and kindness, the more we're aligned with the essence of the universe. Until next time, I'm your host, Roman from The Epic Times. Stay informed, and most importantly, stay free.