Blank Bio: RNA foundation models for patient selection and disease trajectories

Blank Bio is an applied AI lab using RNA foundation models to help pharma teams make better clinical-development decisions. The reader decision is whether the company is a fit for an organization working on RNA therapeutics, patient selection, or disease-progression modeling—not whether a public model description is already evidence of a treatment outcome.

What it does

Blank Bio says its models learn patterns in RNA data linked to disease progression and response to treatment. Its current site highlights two applications: disease-trajectory modeling and patient selection, with the broader goal of helping pharma design more efficient trials and identify biological differences between patients (Blank Bio homepage; YC company profile). The company's launch also describes mRNA sequence design, target identification, biomarker discovery, and patient stratification as expansion areas (Blank Bio YC launch).

Fact	What the public sources say
Buyer	Pharma and biotech teams working on therapeutics and clinical development
Core data	RNA and bulk RNA-seq data are central to the public product description
Applications	Disease trajectory modeling and patient selection; additional research uses are described
Public partnerships	The launch says open-source models are used by Sanofi and GSK and that Blank Bio works with the Arc Institute
Founders	Jonny Hsu, Philip Fradkin, and Ian Shi

Why it fits

The product's practical promise is not “AI discovers drugs” in the abstract. It is a narrower attempt to turn a molecular profile into a better trial-design or patient-selection signal. That could matter to a development team already generating RNA data but struggling to use it in a decision that is both biologically meaningful and operationally measurable.

The founder-market fit is unusually deep. YC describes Hsu as an early Valence Discovery employee who stayed through its acquisition by Recursion, Fradkin as an early Deep Genomics employee with ML-for-biology research, and Shi as a computational-biology researcher who built RNA models and worked at Amazon (YC company profile). Their backgrounds explain the focus on RNA foundation models and translational research.

The tradeoff is validation and deployment detail. A pharma team should resolve assay compatibility, cohort size, label quality, external validation, interpretability, data rights, and how a model output enters a trial decision. “Used by” and “helps identify” are public company claims; the reviewed sources do not establish a clinical benefit, regulatory approval, or treatment recommendation. Pricing was not published.

Short version: Blank Bio is a serious diligence candidate for RNA-heavy drug-development teams. Its value will be decided by prospective validation and fit with the buyer's trial data, not by model scale alone.

Sources checked — 2026-09-19

Cohort context

Blank Bio is listed in Summer 2025. In our 2026-09-18 directory snapshot, 11 of 166 listed companies in that cohort have YC’s primary industry label Healthcare (6.6%). This is a current-directory comparison, not an original intake count or a performance ranking. Nine-cohort dataset.

Public website snapshot

Observed 2026-09-19T16:17:58.788Z in raw homepage HTML. This records visible metadata and advertised links, not agent execution or product quality.

Signal	Homepage observation
Product description metadata	Observed
Canonical link	Observed
H1 or H2 heading	Observed
Typed structured data	Not observed in this response
Docs/developer link	Not observed in this response
Pricing link	Not observed in this response
llms.txt link	Not observed in this response
Markdown alternate	Not observed in this response

Public observations · Collection method. Missing links here do not establish that a capability or file is absent elsewhere.