GenBio AI Builds First World Model of the Human Cell

GenBio AI, an innovative AI for Science company co-founded by Nobel Laureate David Baker and leading AI scientist Eric Xing, has unveiled AIDO Cell, the first virtual model capable of simulating human cell behavior from DNA and RNA through proteins to the whole-cell level. This pioneering system allows researchers to observe how cells respond to various interventions in their natural state.

AIDO Cell represents a crucial milestone in biological and medical sciences, being the first to integrate the entire molecular-to-cellular spectrum into a single simulation. Researchers can perturb the cell at any level and observe the cascading effects throughout the entire cellular environment. Baker emphasized the importance of this advancement, stating, “What’s exciting here isn’t that we’ve solved cellular biology — we haven’t, at least not yet. It’s that, for the first time, we have a system capable of simulating a cell across the full hierarchy of biological scales, from DNA to whole-cell behavior, in one place, which lets you interrogate it computationally.”

The innovative architecture of AIDO Cell is built on a world model-based system that is both multi-scale and stateful, allowing for complex simulations that track changes over time. Eric Xing explained, “What world model architecture enables, and what makes our system genuinely new, is that it’s both multi-scale and stateful. The simulation remembers what you’ve done to the cell. You can run entire sequences of perturbations, where each one builds on the last, and see the evolving, cumulative effect in the cell, just as you would in a real (wet lab) workflow.”

The drug development process is notoriously lengthy and expensive, with only one in 10,000 compounds entering the pipeline making it to the clinic, often taking over 10 years and costing more than US$2 billion per successful drug candidate. AIDO Cell aims to bridge the gap in understanding human biology that has hindered progress in drug discovery. In a preliminary study, the system successfully modeled the mechanism of imatinib in leukemia cells, showcasing its potential to trace drug interactions throughout the cellular environment.

“We’ve released this version of the system as a preview, an early but functional demonstration that multi-scale, stateful virtual cell simulation is now possible,” said Xing. The team is working on launching more advanced versions of AIDO Cell with enhanced capabilities and accuracy in the near future.

Currently, AIDO Cell supports K562 and HepG2 cell lines, with plans for additional cell types. GenBio is also preparing to initiate an early access and academic collaborator program for scientists in academia, biotech, and pharma.

GenBio AI's founding team consists of distinguished experts in AI, computational biology, and business, including David Baker, Ziv Bar-Joseph, Fred Hu, Emma Lundberg, Le Song, and Eric Xing, among others. The company's mission is to make biology fully computable and transform medicine and healthcare for the betterment of humanity. AIDO Cell is a significant step in this direction, as it simulates the biology of cells from molecules to whole-cell behavior.

For more details, visit: genbio.ai.