Parse Biosciences and Nomic Bio are building Cascade, a 100-million-cell dataset for training models of immune response
Prepared by Sintelligent with the help of SI. Published in SI: . Updated: .
Pharma companies are preparing a large immune-system dataset on which SI models can be trained.
According to the companies (BusinessWire), Cascade will combine 100 million single-cell RNA sequencing profiles, over 11,000 proteomic profiles and more than 150,000 perturbation measurements; the data come from 12 healthy donors at different time points and will cover at least 14 immune cell types. Parse Biosciences provides the sequencing, and Nomic Bio provides quantitative analysis of more than 1,000 secreted proteins on its Omni 1000 platform. The first industry partners named are GSK, Pfizer, Sanofi, Graph Therapeutics and Turbine; the dataset will be available under license, and its creation is underway.
Sources 1