Gilad Almogy, CEO of Ultima Genomics, noted that the complexity of cells presents both challenges and opportunities for understanding biological systems.

This initiative aims to transition the Atlas from observational to perturbational data, which is crucial for training machine learning models to predict cellular responses.

Launched two months ago, the Arc Virtual Cell Atlas features over 300 million cells and focuses on generating high-quality datasets to inform virtual cell models and other scientific innovations.

Serge Saxonov, CEO of 10x Genomics, highlighted the innovative potential of building a virtual cell, which could revolutionize scientific research and accelerate drug development.

The vision for the virtual cell includes interactive visualization and manipulation of cellular states, potentially transforming our understanding of cell biology.

Patrick Hsu, co-founder of Arc, advocates for predictive models of cellular responses to improve therapeutic targeting, moving away from traditional experimental methods.

Overall, this collaborative project aims to unite academia, industry, and technology to drive significant advancements in scientific research.

The Arc Institute has partnered with 10x Genomics and Ultima Genomics to enhance the development of the Arc Virtual Cell Atlas, which seeks to create large-scale datasets of cell states for scientific research.

Additionally, 10x Genomics will provide its Chromium Flex technology, enabling researchers to analyze millions of perturbed cells simultaneously, facilitating the exploration of complex biological questions.

To support this effort, Ultima Genomics will utilize its UG 100 sequencing system and Solaris chemistry, designed to produce higher quality data at lower costs.

The collaboration leverages advanced technologies from both 10x and Ultima to enhance data collection processes, making them faster, more detailed, and cost-effective.

Positioned as an open-source resource, the Arc Virtual Cell Atlas aims to standardize and minimize inconsistencies in single-cell data, making it accessible for broader scientific use.