What's Happening?
Parse Biosciences, a single-cell sequencing provider, and Nomic Bio, a proteomics profiling leader, have announced a partnership to develop 'Cascade,' a 100 million cell foundational dataset focused on understanding the human immune response. This multimodal,
AI-ready dataset aims to provide pharmaceutical partners with cellular and protein-level insights into immune biology, thereby accelerating drug target identification and validation. Cascade will integrate 100 million single-cell RNA-seq profiles with over 11,000 proteomic secretome profiles. These profiles will capture how different immune cell types respond to more than 150,000 individual and combinatorial cytokine and drug perturbation conditions across multiple timepoints. The single-cell RNA-seq data will be generated in Parse's GigaLab, while Nomic's Omini 1000 platform will measure over 1,000 secreted proteins. Leading pharmaceutical and biotechnology companies, including GSK, Pfizer, Sanofi, Graph Therapeutics, and Turbine, have already committed as foundational partners.
Why It's Important?
This collaboration is significant because it addresses a critical data bottleneck in biological AI modeling, particularly concerning the human immune response. Current AI models often lack comprehensive, large-scale datasets that capture both cellular state changes and protein signaling. Cascade's multimodal and time-resolved nature will offer an unprecedented view into the mechanisms driving human immune signaling, enabling researchers to build more predictive virtual cell models. This will allow for a deeper understanding of how immune responses develop and how they change under various perturbations, which is crucial for developing more effective immune-modulating therapies. The involvement of major pharmaceutical companies as foundational partners underscores the industry's demand for such extensive and integrated datasets to enhance drug discovery and development processes.
What's Next?
Data generation for the Cascade dataset is currently underway. Once completed, the dataset will be available for licensing to other organizations. Parse Biosciences and Nomic Bio are continuing to welcome additional partners interested in leveraging this resource for their research and development efforts. The extensible experimental framework of Cascade means it can serve as a starting point for adding new biological contexts, disease-specific questions, and data modalities, ensuring its long-term utility for AI model development and evaluation. Researchers will be able to use this data to test hypotheses, train AI models, and benchmark their performance, potentially leading to new discoveries in immune biology and therapeutic interventions.
Beyond the Headlines
The creation of the Cascade dataset represents a significant step towards integrating advanced biological data with artificial intelligence to revolutionize drug discovery. By combining transcriptomic and proteomic data at such a massive scale, the partnership is setting a new standard for comprehensive biological profiling. This initiative could lead to a paradigm shift in how drug targets are identified and validated, moving towards more data-driven and predictive approaches. Furthermore, the time-resolved aspect of the dataset will allow for the study of dynamic biological processes, offering insights that static measurements cannot provide. This could also foster greater collaboration between technology providers and pharmaceutical companies, accelerating the pace of innovation in the biotechnology sector and ultimately benefiting patient care through more targeted and effective treatments.
