An anonymous reader quotes a report from Ars Technica: On Thursday, OpenAI announced it had developed a large language model specifically trained on common biology workflows. Called GPT-Rosalind after Rosalind Franklin, the model appears to differ from most science-focused models from major tech companies, which have generally taken a more generic approach that works for various fields. In a press briefing, Yunyun Wang, OpenAI's Life Sciences Product Lead, said the system was designed to tackle two major roadblocks faced by current biology researchers. One is the massive datasets created by decades of genome sequencing and protein biochemistry, which can be too much for any one researcher to take in. The second is that biology has many highly specialized subfields, each with its own techniques and jargon. So, for example, a geneticist who finds themselves working on a gene that's active in brain cells might struggle to understand the immense neurobiological literature. Wang said the company had taken an LLM and trained it on 50 of the most common biological workflows, as well as on how to access the major public databases of biological information. Further training has resulted in a system that can suggest likely biological pathways and prioritize potential drug targets. "We're connecting genotype to phenotype through known pathways and regulatory mechanisms, infer likely structural or functional properties of proteins, and really leveraging this mechanistic understanding," Wang said. To address LLMs' tendencies toward sycophancy and overenthusiasm, OpenAI says it has tuned the model to be more skeptical, so it's more likely to tell you when something is a bad drug target. There was a lot of talk about GPT-Rosalind's "reasoning" and "expert-level" abilities. We were told that the former was defined as being able to work through complex, multi-step processes, while the latter was derived from the model's performance on a handful of benchmarks. Access to GPT-Rosalind is currently limited "due to concerns about the model's potential for harmful outputs if asked to do something like optimize a virus's infectivity," notes Ars. Only U.S.-based organizations can request access at the moment.

Read more of this story at Slashdot.

The biotech industry's engineered cells could become an $8 trillion market by 2035, notes Phys.org. But how do you keep them from being stolen? Their article notes "an uptick in the theft and smuggling of high-value biological materials, including specially engineered cells." In Science Advances, a team of U.S. researchers present a new approach to genetically securing precious biological material. They created a genetic combination lock in which the locking or encryption process scrambled the DNA of a cell so that its important instructions were non-functional and couldn't be easily read or used. The unlocking, or decryption, process involves adding a series of chemicals in a precise order over time — like entering a password — to activate recombinases, which then unscramble the DNA to their original, functional form... They created a biological keypad with nine distinct chemicals, each acting as a one-digit input. By using the same chemicals in pairs to form two-digit inputs, where two chemicals must be present simultaneously to activate a sensor, they expanded the keypad to 45 possible chemical inputs without introducing any new chemicals. They also added safety penalties — if someone tampers with the system, toxins are released — making it extremely unlikely for an unauthorized person to access the cells. "The researchers conducted an ethical hacking exercise on the test lock and found that random guessing yielded a 0.2% success rate, remarkably close to the theoretical target of 0.1%."

Read more of this story at Slashdot.