Blank Bio GTM brain
Blank Bio develops RNA foundation models to help pharma teams select oncology trial patients and predict disease progression.
category
Precision oncology clinical trial AImarket profile
- text: Clinical development teams need to extract patient-level biological information from increasingly available bulk RNA sequencing data.
- text: Oncology trials increasingly use genomic or other biomarkers to guide patient selection and treatment decisions.
personas
- title: VP Clinical Development, Oncologypains:
- Poorly selected patients can obscure efficacy and increase trial cost.
- Trial design must balance enrollment burden with statistical power.
- title: Head of Translational Medicine or Biomarkerspains:
- Existing biomarkers may miss relevant variation in tumor biology.
- RNA profiles contain signals that are difficult to interpret and validate for a specific therapy.
- title: Clinical Data Science Leadpains:
- Needs evidence that model predictions generalize across cohorts and indications.
- Must integrate molecular data with trial endpoints and covariates.
icp
- text: Pharma and biotech sponsors running oncology clinical development programs with access to patient RNA-seq data.
- text: Teams designing trials with patient stratification or prognostic adjustment needs; no public employee-count threshold is specified.
message pillars
- text: Use RNA to identify patients most likely to benefit.
- text: Predict disease trajectories to inform trial design.
- text: Make better use of existing molecular data.
objections
- objection: Are model predictions validated for our cancer and therapy?response: Request indication-specific retrospective validation, cohort details and prospective evaluation plans before use in trial decisions.
- objection: Will RNA data and patient privacy constraints prevent collaboration?response: Discuss sample requirements, data rights and secure analysis arrangements early.
- objection: Can the approach really reduce trial size?response: Ask for a power analysis with assumptions and comparison to existing prognostic covariates.
competitors
- name: Foundation Medicinewhy: Offers genomic oncology profiling used in therapy and trial selection.
- name: ArteraAIwhy: Develops predictive and prognostic oncology models using a different data modality.
influencers
- name: Jonny Hsuurl: https://www.ycombinator.com/companies/blank-biowhy: Co-founder described in the YC launch.
keywords
- RNA biomarkers oncology trials
- RNA sequencing patient stratification
- clinical trial prognostic biomarkers
- cancer treatment response prediction
- RNA foundation model pharma
- oncology trial patient selection
voice
- scientific
- measured
- clinically focused
signals
- text: An oncology sponsor launching a trial with available tumor RNA-seq and an unmet patient selection question is a strong prospect.
- text: A clinical development team redesigning power calculations or seeking prognostic covariates may be receptive.
stack
- bulk RNA-seq
pricing
model: unknown
motion
sales_ledchannels
- YC launch
- website
- X
confidence
mediumFounders
- name: Jonny Hsutitle: Founder/CEOrole: CEObio: Working on foundation models for RNA therapeutics. I was an early employee at Valence Discovery, a biotech startup that spun out from Mila. I led product and strategy. Valence was acquired by Recursion (NASDAQ: RXRX) in May 2023. I stayed on afterwards to help build out the AI research engine of Recursion called Valence Labs. Biochemist by training | Waterloo graduate
- name: Philip Fradkintitle: Founderrole: Founderbio: Building AI for the most designable molecule in the world: RNA Published at top ML & Bio conferences including best paper at Foundation models for science @ Neurips. Built self-supervised learning applications for RNA, small molecules, and phenomics. Playing long term games in ML for Biology. One of the first employees at Deep Genomics. PhD from University of Toronto.
- name: Ian Shititle: Founder/CTOrole: CTObio: Building foundational models for RNA therapeutics at Blank Bio. Just defended my PhD in CS at the University of Toronto. Published at ICML, NeurIPS, Nature Comms; used 4 GPUs to pre-train an mRNA foundation model that beat competitors using months of compute on thousands of H100s. Now scaling our models to unlock new possibilities in the RNA therapeutic space. Previously at Amazon building software, interned at Pinterest and Amazon as a research scientist in between.