Parse and Graph aim to profile hundreds of millions of immune cells – an atlas for AI drug discovery

Parse Biosciences and Graph Therapeutics announced a strategic collaboration to build a large functional immune perturbation atlas by combining Graph’s patient‑derived disease models and active‑learning perturbation selection with Parse’s GigLab Evercode single‑cell platform. The project will profile hundreds of millions of cells across disease contexts to map immune and tissue interactions relevant to autoimmune and immune‑mediated diseases. The partners argue the atlas will reduce late‑stage translational risk by revealing context‑specific cellular responses and enabling AI‑first drug discovery workflows, potentially accelerating target validation and lowering the cost of failed late‑stage programs.