# Cascade Dataset Empowers Pharma with 100 Million Single-Cell Profiles

> The Cascade dataset, a collaboration between Parse Biosciences and Nomic Bio, provides unprecedented insights into immune responses with 100 million single-cell profiles. This innovative resource is set to transform drug discovery by bridging critical data gaps in immune signaling mechanisms.

**Source**: genengnews.com | **Published**: 2026-10-30 | **Type**: article

## Key Facts

- Cascade dataset combines 100M cells, enhancing drug target validation for pharma partners.
- GSK, Pfizer, and Sanofi's involvement highlights urgent demand for multimodal immune data.
- High throughput capabilities at Parse’s GigaLab position them as leaders in scalable sequencing.
- Data bottleneck in biological AI modeling reveals vulnerability in current drug discovery processes.
- Predictive modeling improvements from Cascade indicate strategic shifts in immune response research.

## Summary

Parse Biosciences, a subsidiary of QIAGEN, and Nomic Bio have announced a strategic partnership to create Cascade, a groundbreaking dataset comprising 100 million single-cell profiles and extensive proteomic data. This initiative aims to enhance the understanding of the human immune response, a critical area for pharmaceutical research and drug development. The significance of this dataset lies in its potential to accelerate the identification and validation of new drug targets, addressing a pressing need for comprehensive immune data in the industry.

The Cascade dataset is notable for its multimodal approach, integrating single-cell RNA sequencing with over 11,000 proteomic secretome profiles. This combination captures the responses of various immune cell types to over 150,000 individual and combinatorial cytokine and drug perturbations across multiple timepoints. By providing a detailed view of immune signaling mechanisms, Cascade aims to fill a substantial data gap that has traditionally hindered the development of predictive models for drug discovery. This initiative reflects a growing recognition of the importance of high-quality, large-scale datasets in advancing biological AI modeling.

The demand for such extensive immune data is underscored by the participation of major pharmaceutical companies, including GSK, Pfizer, Sanofi, Graph Therapeutics, and Turbine. Their commitment to the Cascade project highlights the competitive dynamics within the biopharmaceutical sector, where the ability to leverage advanced datasets can significantly enhance research capabilities and accelerate drug development timelines. As companies increasingly seek to integrate AI into their discovery processes, the availability of rich datasets like Cascade will be crucial for driving innovation and maintaining competitive advantage.

The data generation will take place in Parse’s GigaLab, a high-throughput facility capable of processing billions of cells annually. This operational capacity positions Parse as a leader in the single-cell sequencing space, while Nomic’s Omini 1000 platform will facilitate the measurement of over 1,000 secreted proteins. The collaboration between these two companies not only enhances their individual capabilities but also signals a trend toward partnerships that combine expertise in genomics and proteomics to address complex biological questions.

Charlie Roco, co-founder and CTO of Parse Biosciences, emphasized the current bottleneck in biological AI modeling due to a lack of comprehensive data on the human immune response. The Cascade dataset is positioned as a solution to this challenge, promising to improve the predictive power of AI models used by partner companies. This development could lead to more effective drug discovery processes, ultimately resulting in faster and more targeted therapeutic options for patients.

As the pharmaceutical industry continues to evolve, the creation of datasets like Cascade signals a shift toward data-driven approaches in drug discovery. Companies that can effectively harness and analyze large-scale biological data will likely gain a significant edge in the competitive landscape. The integration of advanced AI modeling with rich datasets will not only enhance research outcomes but also reshape the future of therapeutic development, making it crucial for industry leaders to stay attuned to these emerging trends. The success of Cascade may set a precedent for future collaborations that prioritize data accessibility and multimodal analysis, further transforming the landscape of biopharmaceutical research.

## Entities

- **Companies**: Parse Biosciences, Nomic Bio, QIAGEN, GSK, Pfizer, Sanofi, Graph Therapeutics, Turbine
- **Products**: Cascade, Omini 1000
- **Technologies**: single-cell RNA-seq, proteomic profiling
- **People**: Charlie Roco

## Key Concepts

partnership, immune response, drug discovery, multimodal dataset, single-cell sequencing, proteomic secretome, AI modeling, data bottleneck

## Definitions

- **Cascade**: A 100 million cell foundational dataset designed to understand the human immune response through multimodal data.
- **single-cell RNA-seq**: A technology that allows for the analysis of gene expression at the individual cell level.
- **proteomic profiling**: The large-scale study of proteins, particularly their functions and structures.
- **perturbation dataset**: A dataset that captures responses of cells to various treatments or conditions over time.
- **biological AI modeling**: The use of artificial intelligence to model biological processes, particularly in drug discovery.

## Use Cases

- Accelerating the identification of new drug targets
- Understanding immune cell responses to treatments
- Building predictive virtual cell models
- Enhancing AI models for drug discovery
- Profiling billions of cells annually

## Frequently Asked Questions

**What is the purpose of the Cascade dataset?**

The Cascade dataset aims to provide insights into the human immune response by combining single-cell RNA-seq and proteomic data. This will help pharmaceutical partners identify and validate new drug targets more effectively.

**How does Cascade improve drug discovery?**

By offering a multimodal view of immune cell responses, Cascade fills critical data gaps that can enhance the predictive power of AI models used in drug discovery. This allows researchers to better understand immune signaling mechanisms.

**What technologies are used to generate the dataset?**

The dataset is generated using single-cell RNA-seq technology for transcriptomic data and the Omini 1000 platform for proteomic secretome data. This combination allows for a comprehensive analysis of immune responses.

**Who are the partners involved in the Cascade project?**

The Cascade project involves partnerships with several leading pharmaceutical and biotechnology companies, including GSK, Pfizer, Sanofi, Graph Therapeutics, and Turbine, highlighting the demand for large-scale immune data.

**What challenges does biological AI modeling face?**

Biological AI modeling currently faces a data bottleneck, as there is limited available data on human immune responses to key perturbations. Cascade aims to address this issue by providing a rich dataset for analysis.

## Links

- [Read on Welcome.AI](https://welcome.ai/content/cascade-dataset-empowers-pharma-with-100-million-single-cell-profiles)
- [Original source](https://www.genengnews.com/topics/omics/100-million-cell-ai-ready-dataset-with-single-cell-and-proteomic-data-created-by-parse-and-nomic/)

---

Source: Welcome.AI | https://welcome.ai/content/cascade-dataset-empowers-pharma-with-100-million-single-cell-profiles