What if AI could invent enzymes that nature hasn’t seen? 👩‍🔬🧑‍🔬 Introducing 🪩 DISCO: Diffusion for Sequence-structure CO-design 14 rounds of directed evolution and over a year of wet lab work. That's what it took to engineer an enzyme for selective C(sp³)–H insertion, one of the most challenging transformations in organic chemistry. DISCO surpasses this with a single plate. No pre-specified catalytic residues, no template, no theozyme, no inverse folding, just joint diffusion over protein sequence and structure. 📝 Blog: disco-design.github.io/ 📄 Paper: arxiv.org/abs/2604.05181 💻 Code: github.com/DISCO-design/DISC…

Yes

Start a company in AI for Science. The Encode: AI for Science fellowship offers a year of freedom to build what matters -- salary, 100k GBP of compute, and partnership with the top scientists in the UK. No equity or fees, it's a fully funded fellowship! Apply by March 28

Software horror: litellm PyPI supply chain attack. Simple `pip install litellm` was enough to exfiltrate SSH keys, AWS/GCP/Azure creds, Kubernetes configs, git credentials, env vars (all your API keys), shell history, crypto wallets, SSL private keys, CI/CD secrets, database passwords. LiteLLM itself has 97 million downloads per month which is already terrible, but much worse, the contagion spreads to any project that depends on litellm. For example, if you did `pip install dspy` (which depended on litellm>=1.64.0), you'd also be pwnd. Same for any other large project that depended on litellm. Afaict the poisoned version was up for only less than ~1 hour. The attack had a bug which led to its discovery - Callum McMahon was using an MCP plugin inside Cursor that pulled in litellm as a transitive dependency. When litellm 1.82.8 installed, their machine ran out of RAM and crashed. So if the attacker didn't vibe code this attack it could have been undetected for many days or weeks. Supply chain attacks like this are basically the scariest thing imaginable in modern software. Every time you install any depedency you could be pulling in a poisoned package anywhere deep inside its entire depedency tree. This is especially risky with large projects that might have lots and lots of dependencies. The credentials that do get stolen in each attack can then be used to take over more accounts and compromise more packages. Classical software engineering would have you believe that dependencies are good (we're building pyramids from bricks), but imo this has to be re-evaluated, and it's why I've been so growingly averse to them, preferring to use LLMs to "yoink" functionality when it's simple enough and possible.

just got invited to peer review a paper I'm one of the authors on

People will be like "I can't believe they made star trek woke" and then you tune into 90s star trek and there's a transgender worm walking across the transgender carpet in the gay communist space station

Sad news time: after 6 years, this is my last week employed at Nickelodeon.

Modeling all 28,000 genes at once: a foundation model for single-cell transcriptomics Every cell in your body carries the same genome, yet a neuron looks and behaves nothing like a liver cell. The difference lies in which genes are turned on or off—and at what level. Single-cell RNA sequencing (scRNA-seq) lets us measure that expression profile one cell at a time, revealing rare cell populations, gene regulation, and drug response at unprecedented resolution. Foundation models pretrained on millions of cells have become powerful tools for analyzing these data. But they all share a practical compromise: restricting their attention mechanism to ~2,000 highly expressed genes and discarding the remaining ~26,000. Many of those excluded genes, despite low expression, act as regulatory switches, fine-tuners of signaling pathways, and drivers of context-specific responses like immune activation or drug resistance. Ignoring them means learning an incomplete picture of the cell. Ding Bai and coauthors address this with scLong, a billion-parameter model pretrained on 48 million cells that performs self-attention across all 27,874 human genes. To make this feasible, they use a dual encoder: a large Performer (42 layers) processes the top 4,096 high-expression genes, while a smaller one (2 layers) handles the remaining ~24,000. Both outputs merge through a full-length encoder capturing cross-group interactions. scLong also integrates Gene Ontology knowledge via a graph convolutional network, embedding each gene with information about its known functions, processes, and cellular localization—context that expression data alone cannot provide. Results are consistent and broad. In predicting transcriptional responses to genetic perturbations, scLong achieves a Pearson correlation of 0.63 on unseen perturbations, compared to 0.56–0.58 for existing models and GEARS. It outperforms Geneformer, scGPT, and DeepCE on chemical perturbation prediction across all metrics, reaches 0.873 Pearson for cancer drug response, and surpasses both Geneformer and DeepSEM in gene regulatory network inference. The broader point: in biological foundation models, what you choose to attend to shapes what you can learn. By including low-expression genes and grounding representations in functional knowledge, scLong shows that scaling context—not just parameters—is key to capturing the full complexity of cellular regulation. A principle relevant wherever long-range feature dependencies are biologically meaningful but computationally expensive to model. Paper: nature.com/articles/s41467-0…

One small step towards solving the "real" protein folding problem! 🤓

Delta fine per cough

BoltzGen is now also on bioArxiv, including new selectivity results! biorxiv.org/content/10.1101/… Addition: None of our nanobody binders interacts with the off-target control HSA (a highly interactive and abundant protein in human serum)!

I do not think you can pursue meaningful research without (1) some grandiose delusion about your abilities (2) a sense of esthetics and harmony to judge ideas still free of experimental confirmation (3) an unreasonable taste for the required tangible work (e.g. programming)

Today we’re thrilled to announce JAM-2 — the first AI model capable of generating drug-quality antibodies straight from the computer, with industry-leading success rates. > Drug-like affinities: Picomolar to single-digit nanomolar antibody binders for half of 26 targets while testing <45 designs each. > Unlocking hard targets: Up to 11% success rate for direct on-cell GPCR binders; top antibody hits in the single-digit nanomolar range. > Unprecedented epitope breadth: JAM-2 routinely designed antibodies that hit 30–70% of user-defined epitopes, now enabling intentional design of biology — not chance discovery. > Drug-like developability: Over 50% of antibody designs passed core industry developability criteria with zero optimization. > Massive leverage: A four-person team prosecuted 16 targets in parallel in < 1 month. JAM-2 is the first de novo antibody design capability ready for front-line use in drug discovery, matching or surpassing traditional discovery approaches. We’re already deploying JAM-2 with multiple large pharma partners and seeing excellent results. If you’re interested in partnering on molecule development or accessing JAM-2, contact bd@nabla.bio. Read more in our whitepaper (link below)

the future of biology will be programmed by frontier ai systems and @profluentbio is the leader of this new category @airstreet is investing for the third time in this remarkable company since our inception round i’m so proud of what @thisismadani and the team have created to date - multiple firsts, immense ambition, scientific integrity and commercial pull and it is still day 1!

I’m pleased to share that I am joining @NVIDIA Ventures as Portfolio Manager today. After spending the past several years immersed in the world of tech and techbio startups, building products, partnering with founders, and helping scale technologies, this transition feels like a natural evolution.

Filed in "photos which are terrifying if you know what they are, nonthreatening otherwise."

Happy Halloween!