Category: AI &amp; ML

Evidence-first notes on bioscience and deep tech, at the edge of the lab and the market. Information only — not investment advice. The paper discussed here is an unpeer-reviewed arXiv preprint (submitted 2026-08-11), and every comparison in it — including the one summarized below — is an in silico structural alignment and scoring exercise. No…

A genome language model designed working bacteriophages — and a second paper the same week shows the capability is not uniform

Aug 10, 2026

—

by

Evidence-first notes on bioscience and deep tech, at the edge of the lab and the market. Information only — not investment advice, not medical advice. The 30-second version What. A paper in Science (6 August 2026) reports the first generative design of complete bacteriophage genomes using genome language models. Working from the phage ΦX174 as…

A concept-bottleneck AI predicts immunotherapy response across cancers — but every result is retrospective, and the survival win rests on one sponsor’s own trial

Jul 25, 2026

—

by

Evidence-first notes on bioscience and deep tech, at the edge of the lab and the market. Information only — not investment advice. The 30-second version What. A Harvard (Zitnik lab) and Roche team published COMPASS in Nature Medicine (2026-07-03, doi:10.1038/s41591-026-04502-7): a lightweight (~1.02M-parameter) “concept-bottleneck” transformer that reads a tumour’s bulk RNA-seq and predicts response to…

The commercial landscape of AI protein design — funding is at the $10^9 scale, but the number of approved de novo AI-designed protein drugs is zero

Jul 17, 2026

—

by

Evidence-first notes on bioscience and deep tech, at the edge of the lab and the market. Information only — not investment advice, not medical advice. All funding, valuation and milestone totals are attributed to each company’s press releases or media reports; many details cannot be independently verified and are marked as such. Vendor blog/preprint performance…

Bio Foundation Models: Where the Capital Is, Where the Evidence Isn’t, and Why the Two Point in Opposite Directions

—

by

Evidence-first notes on bioscience and deep tech, at the edge of the lab and the market. Information only — not investment advice. The 30-second version What. Capital and reproducibility in biology’s foundation models flow in opposite directions: the largest raise sits behind the most closed engine (Isomorphic Labs, a $2.1B Series B in May 2026,…

Benchmark reality for bio foundation models: how data leakage, missing baselines and metric choice inflate “beats baseline” claims

—

by

Evidence-first notes on bioscience and deep tech, at the edge of the lab and the market. Information only — not investment advice. The 30-second version What. A leaderboard number for a bio foundation model (bio-FM) is the product of model ability and how forgiving the evaluation is. Data leakage is close to the default, not…

Have cell / virtual-cell foundation models beaten the linear baseline? An honest read (Part 3)

—

by

Evidence-first notes on bioscience and deep tech, at the edge of the lab and the market. Information only — not investment advice. The 30-second version What. This is the most skeptical axis of the bio-foundation-model series. As of 2026-07, cell / virtual-cell foundation models (scGPT, Geneformer, scFoundation, Arc STATE and others) do not yet consistently…

Genome foundation models and the “noncoding SOTA” claim: what Evo2 really beats, and where it does not

—

by

Evidence-first notes on bioscience and deep tech, at the edge of the lab and the market. Information only — not investment advice. The 30-second version What. Evo2 (Arc Institute · NVIDIA · Stanford · UC Berkeley · UCSF; 7B / 40B parameters, ~9.3 trillion nucleotides of training data) claims a new state of the art…

Protein foundation models (AlphaFold3, ESM3): does beating the specialist baseline mean generalization — or memorization?

—

by