100 Million-Cell AI-Ready Dataset with Single-Cell and Proteomic Data Created by Parse and Nomic

Parse Biosciences, a provider of single-cell sequencing, and Nomic Bio, focused on proteomic profiling, have formed a partnership to create Cascade, a groundbreaking dataset containing 100 million cells. The dataset aims to provide pharma partners with unprecedented cellular and protein-level insights into immune biology, enabling the identification and validation of new drug targets.

Cascade is a multimodal, perturbation dataset that captures immune cell responses to treatment over multiple timepoints, combining 100 million single-cell RNA-seq profiles with over 11,000 proteomic secretome profiles. By pairing transcriptomic and proteomic readouts, Cascade will offer researchers a deeper understanding of the mechanisms behind human immune signaling, addressing a critical data gap in predictive, virtual cell models.

Key pharmaceutical and biotechnology companies, including GSK, Pfizer, Sanofi, Graph Therapeutics, and Turbine, have already committed to the project, highlighting the demand for large-scale, multimodal immune data in drug discovery. The single-cell RNA-seq data will be generated in Parse's GigaLab, a high-throughput service lab capable of profiling billions of cells annually, while the proteomic secretome data will be generated through Nomic's Omini 1000 platform, measuring over 1,000 secreted proteins across all samples.

Parse's co-founder and chief technology officer, Charlie Roco, emphasized the importance of this project in overcoming the data bottleneck in biological AI modeling, which could significantly improve the predictive power of AI models used in drug discovery.