Parse Biosciences Partners with Tahoe Therapeutics and Codebreaker Labs for Massive Single Cell Sequencing Projects
核心洞察
Parse Biosciences (搜索)' GigaLab will generate data for Tahoe Therapeutics (搜索)' 300 million cell project, representing the largest perturbation-focused single cell dataset ever produced to power AI-driven drug discovery models.
The collaboration with Tahoe will create foundational datasets incorporating multiple tissue types, thousands of compounds, and genome-scale perturbations to enable virtual cell models for therapeutic prediction.
Parse has also partnered with Codebreaker Labs (搜索) to develop a platform testing thousands of genetic variants in parallel at single cell resolution, addressing limitations in rare variant studies.
Parse Biosciences (搜索) has announced two major collaborations that position the company at the forefront of large-scale single cell sequencing for AI-powered drug discovery and genomics research. The Seattle-based company's GigaLab facility will support Tahoe Therapeutics (搜索)' ambitious 300 million cell project while simultaneously partnering with Codebreaker Labs (搜索) to advance causal genomics at unprecedented scale.
Record-Breaking Dataset for AI Drug Discovery
Tahoe Therapeutics (搜索) has selected Parse's GigaLab to generate what will become the largest perturbation-focused single cell dataset ever produced. The 300-million-cell project will utilize Tahoe's proprietary Mosaic technology (搜索) to create samples from large arrays of disease models that have been genetically or chemically perturbed. Parse will apply its Evercode (搜索)™ chemistry and high-throughput automation to process these samples.
"This collaboration demonstrates how scalable single cell technology can meet the demands of modern drug discovery," said Charlie Roco, PhD, Chief Technology Officer and Co-founder at Parse Biosciences (搜索). "By combining our GigaLab platform with Tahoe's perturbation engine, we are enabling a dataset that can power the next generation of AI models, changing how therapies are discovered."
The GigaLab facility, designed specifically for million- to hundred-million-cell projects, integrates high-capacity liquid handling, standardized workflows, and end-to-end quality control to enable dataset sizes previously unattainable for most research organizations. The Tahoe project represents one of the largest sequencing initiatives undertaken at GigaLab to date.
Foundational Datasets for Virtual Cell Models
The massive dataset will expand Tahoe Therapeutics (搜索)' lead in building foundational perturbation datasets that capture how drugs, targets, and disease contexts interact across diverse biological systems. These high-dimensional datasets form the foundation for virtual cell models that enable more accurate predictions of therapeutic response, mechanism of action, and patient variability.
Current drug discovery pipelines are constrained by datasets that lack drug discovery-focused perturbations and biological diversity needed to train predictive AI systems. Tahoe's foundational datasets will incorporate multiple tissue types and disease states, thousands of compounds and genome-scale perturbations, pathway- and cell-type-specific signatures at unprecedented scale, and high-resolution views of mechanism, plasticity, and drug response.
"Scaling single cell perturbation data is essential for building AI models that understand human biology," said Johnny Yu, CSO of Tahoe Therapeutics (搜索). "Leveraging Parse's GigaLab, we're able to perform single cell sequencing on samples generated from our Mosaic technology (搜索) at unprecedented depth and diversity, moving us closer to scale of foundational datasets that power our virtual cell models, which can predict therapeutic outcomes across patients and diseases."
Breakthrough Platform for Rare Variant Studies
In a separate collaboration, Parse Biosciences (搜索) has partnered with Codebreaker Labs (搜索) to develop a platform capable of testing thousands of genetic variants in parallel and measuring their effects at single cell resolution. This partnership addresses a critical limitation in current genomic studies, which rely heavily on observational data from variants that appear in large populations.
Rare and private variants, often seen in only one individual or family, are nearly impossible to study using traditional approaches because too few carriers exist to draw statistically meaningful conclusions. The new platform addresses this limitation by engineering variants at scale and measuring their impact in human cells, generating causal labels that observational datasets cannot create.
"We are excited to work with Parse on this groundbreaking platform," says Ryan Gill, PhD, CEO and Co-Founder of Codebreaker Labs (搜索). "Together, we are pioneering a new class of genomics data with the potential to impact whole-genome interpretation, target discovery and validation, and even precision clinical trial design."
Implications for Precision Medicine
The collaboration between Parse and Codebreaker has broad implications for biopharma and precision medicine. Researchers will be able to generate causal data, clinicians will be able to access new functional maps for interpreting genomes, and AI teams will be able to use high-dimensional datasets to build more accurate models.
"By combining our scalable platform for single cell with Codebreaker's engineered variant libraries, we can create a unified platform that experimentally determines how thousands of variants influence disease state and progression, and how these rare variants might be more effectively treated in a clinical setting," said Roco.
Industrial-Scale Single Cell Biology
Both partnerships highlight a new reality in the life sciences: the next generation of therapeutic discovery requires data at a scale that only a small number of expert entities, equipped with highly automated, industrial-grade platforms, can produce. Parse continues to set the standard for what is technically feasible in large-scale single cell biology while enabling innovators to build AI systems rooted in far richer biological context than was previously possible.