bioRxiv Preprint: AI-Designed Cyclic Peptide CIP-3 Achieves Nanomolar Antagonism of CD28 Immune Checkpoint
A March 2026 bioRxiv preprint reports an AI-guided strategy for the discovery of cyclic peptide antagonists targeting the CD28 immune checkpoint, with the lead candidate CIP-3 binding the CD28 extracellular domain at nanomolar affinity and producing controllable modulation in cellular assays. CD28 is the principal T-cell co-stimulatory receptor and a high-value target for autoimmunity and transplantation, where current biologics (abatacept, belatacept) are large fusion proteins with associated dosing and immunogenicity tradeoffs. CIP-3's small cyclic-peptide format opens the prospect of subcutaneous dosing with a different PK profile. The work illustrates how AI-driven cyclic-peptide design is expanding beyond GLP-1 mimetics into immune-checkpoint pharmacology.