AI-generated from publicly available materials.Parse Biosciences and Nomic Bio have partnered to create Cascade, an extensive dataset aimed at enhancing understanding of the human immune response through a combination of single-cell and proteomic data.
The Cascade dataset, consisting of 100 million single-cell RNA-seq profiles and over 11,000 proteomic secretome profiles, aims to provide pharmaceutical companies with a comprehensive view of immune biology. This multimodal dataset captures the responses of various immune cell types to more than 150,000 perturbation conditions, including cytokines and drugs, across multiple timepoints. By integrating transcriptomic and proteomic data, it addresses a significant gap in existing research, paving the way for more accurate predictive models in drug discovery.
Major pharmaceutical players, such as GSK, Pfizer, and Sanofi, have already expressed interest in Cascade, highlighting the industry's growing need for large-scale immune data. The single-cell RNA-seq will be executed in Parse's GigaLab, while Nomic’s Omini 1000 platform will generate the proteomic data, measuring over 1,000 secreted proteins from the samples.
This initiative reflects a crucial advancement in biological AI modeling, as noted by Charlie Roco, PhD, from Parse Biosciences, who emphasized the current data bottleneck in understanding immune responses. The Cascade dataset is expected to significantly enhance the predictive capabilities of AI models used in drug discovery, potentially leading to more effective therapeutic interventions.