AI drug design has moved from a small-molecule story to a peptide story. Generative models — RFDiffusion adaptations for cyclic backbones, AfCycDesign, ProteinMPNN-derived sequence designers — now generate cyclic peptide candidates that survive experimental validation against targets that resisted traditional medicinal chemistry. Synthesis chemistry has advanced in parallel: one-pot ligations, photo-redox macrocyclizations, and biocatalytic cascades close the loop between in-silico design and tractable scaffolds.
Covered here: the May 2026 CycloPepper Nature Communications paper — a machine-learning-guided platform that predicts cyclization outcomes and accelerates automated synthesis — and CIP-3, an AI-designed cyclic peptide CD28 antagonist with nanomolar affinity reported on bioRxiv in March 2026. Earlier coverage included CyclicMPNN for stable cyclic peptide sequence generation and the broader Drug Discovery World May 2026 review on the algorithmic stack and its industrial implications.
Stories here cover the model architectures, the experimental validations, and the platforms moving AI peptide design out of academic labs. See #cyclic-peptide, #machine-learning, and #drug-discovery.
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.
A May 2026 Drug Discovery World feature consolidates the case for cyclic peptides as a distinct therapeutic modality: larger and more selective than small molecules, more permeable and cheaper to manufacture than antibodies, and uniquely suited for protein-protein-interaction targets that have resisted traditional drug discovery. The piece traces the recent algorithmic stack — RFDiffusion adaptations for cyclic backbones, AfCycDesign, ProteinMPNN-derived sequence design — alongside the synthesis chemistry advances (one-pot ligations, photo-redox macrocyclizations) that turn computational hits into tractable scaffolds. Over 40 cyclic peptide drugs are now FDA-approved across endocrine, oncology, and antimicrobial uses, and 6+ peptide-drug conjugates sit in Phase 3, per the late-April PDC market analysis.