Blank Bio Secures $7.2M Seed Funding and PacBio Partnership to Advance RNA Foundation Models for Precision Oncology
核心洞察
Blank Bio (搜索) closed a $7.2 million seed financing round and formed a strategic collaboration with Pacific Biosciences (搜索) to develop RNA (搜索) foundation models for precision oncology applications.
The partnership will generate PacBio (搜索) HiFi long-read RNA (搜索) sequencing data from up to 100 patient tumor samples to train AI models that capture molecular complexity beyond standard gene-level summaries.
The company's RNA (搜索) foundation models aim to improve patient stratification, biomarker discovery, and clinical trial design by extracting patient-level variation from bulk RNA-seq data that traditional pipelines discard.
Blank Bio (搜索), an applied AI research lab focused on RNA (搜索) foundation models, announced the completion of a $7.2 million seed financing round alongside a strategic collaboration with Pacific Biosciences (搜索) (Nasdaq: PACB) to advance precision oncology applications. The partnership aims to generate high-resolution RNA sequencing data that will enhance the company's artificial intelligence models for tumor transcriptome analysis.
Strategic Collaboration with PacBio
The collaboration will produce PacBio (搜索) HiFi long-read bulk RNA (搜索) sequencing data from up to 100 fresh frozen patient tumor samples spanning multiple cancer indications. Sequencing operations will be conducted at Seattle Children's Research Institute, utilizing automated Kinnex RNA libraries on the SPTLabtech firefly® platform.
"PacBio (搜索) 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," said David Miller, Global Vice President of Marketing at PacBio. "Blank Bio (搜索)'s foundation models demonstrate how high-resolution RNA (搜索) data and machine learning can advance the next generation of precision oncology applications, from biomarkers and diagnostics to clinical trial design."
Addressing Limitations in Current RNA-seq Analysis
Bulk RNA (搜索)-seq has become increasingly utilized across oncology research, drug development, and clinical care due to its ability to capture molecular states of tumor samples at clinically deployable scale and cost. However, standard analytical workflows typically compress RNA-seq data into per-gene count summaries, which limits their capacity to capture isoform architecture, mutational complexity, and other patient-specific tumor biology features.
"Bulk RNA (搜索)-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," explained Jonathan Hsu, CEO and Co-Founder of Blank Bio (搜索). "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."
Funding and Investor Support
The oversubscribed seed round included participation from Define Ventures (搜索), Leonis Capital (搜索), Nova Threshold (搜索), Ripple Ventures (搜索), SignalFire (搜索), Y Combinator (搜索), and other investors. The proceeds will support continued model development, expanded pharmaceutical and diagnostic collaborations, and new data generation initiatives.
"Blank Bio (搜索) is building at the intersection of two major shifts in biology: the expanding clinical use of RNA (搜索)-seq and the emergence of foundation models capable of learning complex biological patterns at scale," said Sahir Raoof, TechBio advisor to SignalFire (搜索). "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."
Technology Applications and Team Expertise
Blank Bio (搜索) is deploying its RNA (搜索) foundation models across three primary areas: predictive biomarkers for characterizing trial populations and identifying likely responders, prognostic biomarkers and patient trajectory modeling for disease progression prediction, and clinical diagnostics to augment existing RNA-seq tests and improve sensitivity and specificity.
The company's team comprises AI scientists and engineers from organizations including Recursion, Deep Genomics, DeepMind, Amazon, Memorial Sloan Kettering Cancer Centre, Stanford, and the Vector Institute. The team has published research in Nature Methods, Nature Genetics, Nature Biotechnology, ICML, and NeurIPS, including their prior academic work on RNA (搜索) foundation models called Orthrus, recently published in Nature Methods.
The collaboration with PacBio (搜索) will enable Blank Bio (搜索) to further train and evaluate its models using high-resolution long-read RNA (搜索) data, focusing on oncology applications where incorporating RNA-level signals may improve patient stratification, biomarker discovery, and clinical interpretation.