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

Canonical: https://mudpie.ai/companies/blank-bio/
Breadcrumb: [Home](https://mudpie.ai/) / [Companies](https://mudpie.ai/companies/) / [Blank Bio: RNA foundation models for patient selection and disease trajectories](https://mudpie.ai/companies/blank-bio/)
Author: Ali Abouelatta (https://mudpie.ai/authors/ali-abouelatta/)
Published: 2026-09-19
Updated: 2026-09-19
Research type: Company profile
Method: Company and accelerator sources checked 2026-09-19. Product claims are attributed to their sources; this is research, not a hands-on product trial.

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](https://www.blank.bio/); [YC company profile](https://www.ycombinator.com/companies/blank-bio)). The company's launch also describes mRNA sequence design, target identification, biomarker discovery, and patient stratification as expansion areas ([Blank Bio YC launch](https://www.ycombinator.com/launches/O8Z-blank-bio-computational-toolkit-for-rna-therapeutics)).

| 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](https://www.ycombinator.com/companies/blank-bio)). 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

- [YC company profile](https://www.ycombinator.com/companies/blank-bio)
- [Blank Bio homepage](https://www.blank.bio/)
- [Blank Bio YC launch](https://www.ycombinator.com/launches/O8Z-blank-bio-computational-toolkit-for-rna-therapeutics)

## 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](https://mudpie.ai/research/yc-cohorts-2026-09-19.json).

## 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](https://mudpie.ai/research/yc-homepage-links-2026-09-19.json) · [Collection method](https://mudpie.ai/research/yc-homepage-methods/README.md). Missing links here do not establish that a capability or file is absent elsewhere.


## Author disclosure

I cofound Lazyweb and publish Mudpie. This is an owner-written publication, not an independent testing organization. Research notes distinguish observations, sourced reporting and editorial judgment.