Ginkgo Bioworks  announced its partnership with Deep Origin on a 4.5-year project funded by the Advanced Research Projects Agency for Health (ARPA-H) Computational ADME-Tox and Physiology Analysis for Safer Therapeutics (CATALYST) program. CATALYST is led by ARPA-H Health Science Futures Mission Office Acting Deputy Director Andy Kilianski, Ph.D.

The collaboration, Pharmacological Research and Evaluation through Digital Integration and Clinical Trial Simulation (PREDICTS), aims to develop a revolutionary computational platform for drug safety.

As part of this team, Ginkgo will be leveraging its 'Datapoints' platform for perturbation response profiling to generate high-quality, high-throughput, structured data sets to support AI model training, including small molecule drug and genetic perturbations spanning multiple cell and tissue types. Readouts will include cell type-specific toxicity endpoints, DRUG-seq transcriptomics, and cell painting.

"It's a great opportunity to get to work with the PREDICTS team led by Deep Origin," said Jesse Dill, Senior Director at Ginkgo Bioworks. "It's an extraordinary group with an ambitious vision, and we are excited to generate data characterizing cellular responses to drug treatments to support this effort.

George Pilitsis, Director at Ginkgo Bioworks, added, "we are beyond excited and thankful for the opportunity to work with Deep Origin and ARPA-H to push the boundaries of multi-omics data generation and support the vision to transform drug discovery with purpose-built, relevant in vitro models coupled with cutting edge AI."

Dr. Natalie Ma, PhD, Head of Business Development at Deep Origin, shared "Ginkgo's high throughput in vitro platforms mean we can generate data at scale, enabling detailed modeling of a wide array of different cell types in tissues and organs."  

This partnership underscores Ginkgo's commitment to collaborating with innovative, interdisciplinary teams and highlights its expertise in structured generation of large data sets for small molecule drug developability profiling.