Zifo, the leading global enabler of AI and data-driven enterprise informatics for science driven organizations and Maze Therapeutics Inc have partnered to solve the critical challenge of managing, storing, and scaling massive, disparate biobank data to help in their quest for precision medicine via AI-powered scientific workflows.
While massive, well-defined biobanks like UK Biobank and the All of Us Research Program have made huge genetic and phenotypic datasets available, researchers often struggle with static tools that are difficult to implement, scale, and extend for complex scientific workflows.
The current landscape forces a disjointed, manual process where researchers must stitch together different platforms and datasets to connect the dots between genetic signals, biological pathways, and phenotypes.
Zifo’s solution, developed in partnership with Maze Therapeutics addresses the manual effort and data fragmentation with AI-enabled workflows.
“Working with Zifo, we have gained a truly scalable and robust solution for managing our biobank data. The platform’s ability to handle diverse datasets and render results so quickly has been a game-changer for our research, allowing us to accelerate our work in target identification and validation,” a Maze spokesperson said.
“Our translational genomics solution provides a dynamic, integrated system that takes researchers from population-scale signals to biological insights,” said Sandor Szalma, Scientific Advisor and a Data Veteran in the Omics space at Zifo. “We are solving a fundamental problem for the industry by offering a seamless journey through previously fragmented data. The ability to render summary statistics in under five seconds is a testament to the solution’s robust back-end engineering, which is crucial for accelerating decision-making and empowering scientists to focus on the science rather than the technology.”
The Zifo platform integrates downstream analysis workflows, enabling a seamless process from data ingestion to meaningful discoveries. Its architecture is built to be scalable and future-ready, with a data model and back-end engineering designed to accommodate new biobank data, such as UKBB-Proteomics, AGD/NashBio, and G&H. This lays the groundwork for future AI solutions for protein modeling and genotype phenotype mapping, making the data “AI-ready” and further de-risking drug targets.