SEATTLE -- Parse Biosciences, the leading provider of scalable and accessible single cell sequencing solutions, announced an alliance with bit.bio to create a comprehensive map of transcription factor-driven cell identity, encompassing both cell state and cell fate. This map will serve as the foundational blueprint for developing highly accurate, human-relevant models at scale. By precisely mimicking in vivo biological responses, these models will significantly advance predictive drug discovery and therapeutic development.

The alliance will leverage cutting-edge techniques in massively parallel causal transcriptomics, which allows scientists to test thousands of genetic variables simultaneously to understand what drives cell behavior. bit.bio will contribute its industry-leading cell programming technology, opti-ox™, as well as its proprietary Discovery platform, The Cell Foundry™, and Parse its scalable single cell technology, Evercode™. The result will build on existing proprietary data to an unprecedented bit.bio dataset that maps how specific genetic inputs lead to specific biological outputs. Ultimately, this dataset will guide not only bit.bio but the wider industry on how therapies are designed and human cells manufactured at scale, while also feeding AI models that can predict how cells respond to drugs or disease.

“Cells operate on code, and by mapping how specific transcription factors dictate cell fate, we are unlocking that operating system. This collaboration doesn't just generate data; it provides a foundational map for bit.bio to scale human-relevant models and feed predictive AI systems, moving the entire field closer to reliably replicating and therefore predicting human biology,” remarks Przemek Obloj, CEO of bit.bio.

“Researchers need insights that they can translate into impact,” states Charlie Roco, PhD, Co-founder and Chief Technology Officer at Parse Biosciences. “Our close alliance with bit.bio will create foundational datasets that establish clear causal links between genetic changes and biological outcomes, the kind of information that predictive medicine needs but has rarely had.”