Genomic Foundation Models and Synthetic Biology
Examining AI applications and biosecurity guardrails across gene editing, de-extinction, and DNA generation.
0 sourcesVoices in this topic
All paragraphs
Oct 20, 2026
- Alex Rives Biohub just announced a $1.8B expansion of its Virtual Biology Initiative, coordinating the Department of Energy, NIH, Google DeepMind, Isomorphic Labs, and Meta on data generation for a general model of cellular biology. The effort aims to build contextual maps — spatial biology linking molecular readouts to imaging “at the scale of hundreds of billions or …
- Rives sees observability as a particularly fundamental bottleneck for virtual cell models, but not the only one. “There’s so much about the cell that we just can’t measure”; progress requires models, data generation at scale, and observation tools. He …
- The attainable five-year target is an “information-theoretic model of the cell” — a probabilistic transition function from cell state plus inputs to a distribution of next states — building toward “a world model of life.” In “the limit of infinite data and compute,” architectures probably end up the same; cellular biology is far from that limit, so inductive …
- Measurement hardware is where Biohub’s thesis gets expressed: the laser phase plate — “the most powerful standing-wave laser in the world” — brings phase contrast to cryo-electron tomography, helping scientists make out individual molecules and how they interact in the living cell. Biohub also uses whole-organism zebrafish imaging to track every cell from embryo to fully developed organism.
- The LLM playbook transfers to biology: pretraining on statistical patterns, elicitation, then “RLVR for biology” with lab verification — “empirical AI” that asks a question, performs the experiment, learns, and proposes a better one in a recursive loop. Unlike math and coding, verification must happen in the laboratory, not through fast computation.
- Timeline and payoff: first drafts of health-and-disease cell atlases within one or two years, a “pretty comprehensive map” within five — then the question becomes “How do I intervene to reverse a state that’s pathologic?” Rives says he has thought less about EHR data; he worries that without a causal basis, models could learn “a bunch of correlations,” while …
Sep 30, 2026
- Moonshots Lamm says AI’s near-term biological value is less autonomous discovery than connecting fragmented research, standardizing language, and designing experiments that laboratories still must validate. Inconsistent gene names and protocols can produce 40–60% replication failure rates; Dave Blundin adds that the dataset may be more valuable …
- Ben Lamm Lamm rejects literal resurrection as the end state: synthetic biology can produce close analogues, but incomplete fossils, epigenetics, environment, and development make exact restoration implausible. Fewer than 100 tyrannosaurs have been found despite billions said to have lived, so humanity is likelier to build “programmable biological …
- Lamm expects the capability to engineer key phenotypes, synthesize or multiplex-edit organisms, and develop them outside the womb in fewer than 10 years. Colossal moved from celebrating 20 edits to consistently exceeding 300 at more than 90% efficiency and is testing 1,000; Lamm nevertheless …
- Lamm forecasts a fully extrauterine mammalian birth within 24 months, from conception to birth without a surrogate; Peter calls that timeline very likely. Separately, Colossal is mapping genotype to phenotype across size, coat color, folds, scales, feathers, tusks, and patterns. The first …
- The broader infrastructure thesis is to “back up life” before Lamm’s projected loss of half of global biodiversity over the next 25 years. Colossal offers conservation technologies openly through 75 partners, is building government biorepositories, and wants billions in …
Sep 27, 2026
Sep 23, 2026
- Eric Nguyen Radical Numerics is betting that genome language models will progress from reading DNA to designing it, with defense built into the same technical approach. Eric Nguyen traces the path from HyenaDNA’s million-token context to Evo’s generative genomics and Omni’s task alignment. Because a model …
- Omni’s claimed breakthrough is not merely scale but the post-training that turns a foundation model into a usable genomic system. Evo and Evo 2 showed broad capabilities yet could lose to specialized models; Omni uses task-specific formatting, special tokens, supervised …
- Latent Space The high-value wedge is the roughly 98% of the human genome outside protein-coding regions, where conventional interpretation remains weakest. Coding regions constitute only about 1.5–2% of the genome, while many disease-associated variants sit in regulatory regions whose effects …
- Eric Nguyen Radical’s most speculative design result treats biological optimization trajectories as a genomic version of chain-of-thought reasoning. Given RNA aptamers ranked from low to progressively higher fitness, the model continued the trajectory and generated plausible sequences …
- Long biological context, rather than isolated protein structure, is the company’s proposed technical advantage. Nguyen describes DNA as an “imprint of the physical world”: upstream regulatory regions, neighboring genes, organism identity, and …
- Latent Space Biosecurity is both a mission commitment and a potential product category, but the speakers do not pretend the screening problem is solved. Radical divides defense into detection, attribution, countermeasures, and government-level deterrence; its models are intended to recognize …