Blank Bio announced the closing of a $7.2 million seed financing alongside a strategic collaboration with PacBio to advance RNA foundation models for precision oncology applications.
The San Francisco-based company is building foundation models trained on tumor transcriptomes to improve patient-level prediction across oncology. The financing proceeds will support continued model development, expanded collaborations with pharmaceutical and diagnostic companies, and the generation of new long-read RNA sequencing datasets focused on biomarkers, clinical trial design, and diagnostics.
As part of the collaboration, Blank Bio and PacBio will generate PacBio HiFi long-read bulk RNA sequencing data from up to 100 fresh frozen patient tumor samples spanning multiple cancer indications. The sequencing work will be conducted at Seattle Children’s Research Institute, where Kinnex RNA libraries will be automated using the SPTLabtech firefly+ platform.
Blank Bio plans to use the resulting data to further train and evaluate its models, particularly for oncology applications involving patient stratification, biomarker discovery, and clinical interpretation.
The company said its models are designed to capture molecular complexity that is often lost in traditional RNA-seq analysis pipelines, which typically reduce transcriptomic data into simplified gene-level summaries. Blank Bio’s approach focuses on preserving isoform architecture, mutational complexity, and patient-specific tumor biology signals.
The oversubscribed seed round included participation from Define Ventures, Leonis Capital, Nova Threshold, Ripple Ventures, SignalFire, Y Combinator, and other investors.
Blank Bio said the financing will support expanded partnerships with pharmaceutical and diagnostic companies in addition to new data generation initiatives.
The company’s team includes AI scientists and engineers from organizations including Recursion, Deep Genomics, DeepMind, and Amazon, as well as researchers affiliated with Memorial Sloan Kettering Cancer Center, Stanford University, and the Vector Institute.
Blank Bio noted that its prior academic work on RNA foundation models, Orthrus, was recently published in Nature Methods.
The company said it is deploying its RNA foundation models across predictive biomarkers, prognostic biomarkers and patient trajectory modeling, and clinical diagnostics.
KEY QUOTES:
“Bulk RNA-seq is one of the most clinically accessible and information-rich assays in oncology, but much of its signal is still reduced to simplified gene-level summaries. Blank Bio was founded to apply foundation models to the full molecular detail contained in each patient’s tumor transcriptome and turn that information into more precise, clinically useful predictions. This financing will support continued model development and partnership expansion, while our collaboration with PacBio will generate the high-resolution long-read RNA data needed to further train and evaluate these models in patient tumor samples.”
Jonathan Hsu, CEO and Co-Founder, Blank Bio
“PacBio HiFi long-read sequencing was built to resolve biology that other technologies miss, and nowhere is that more consequential than in the complex transcriptomes of patient tumors. Blank Bio’s foundation models demonstrate how high-resolution RNA data and machine learning can advance the next generation of precision oncology applications, from biomarkers and diagnostics to clinical trial design.”
David Miller, Global Vice President of Marketing, PacBio
“Blank Bio is building at the intersection of two major shifts in biology: the expanding clinical use of RNA-seq and the emergence of foundation models capable of learning complex biological patterns at scale. The company brings together deep scientific and technical expertise in RNA biology, machine learning, and oncology, with a platform that has the potential to turn transcriptomic data into a more powerful layer of patient-level insight for drug development and diagnostics.”
Sahir Raoof, TechBio Advisor, SignalFire
