AI-Designed Cyclic Peptides: A New Frontier in Controllable Immunotherapy

Recent breakthroughs in computational biology have introduced AI-designed cyclic peptides as a transformative tool for immune checkpoint modulation. While traditional monoclonal antibodies have revolutionized oncology and autoimmune treatment, they often face limitations. These biologic agents typically exhibit prolonged receptor occupancy. Consequently, clinicians struggle to reverse their effects quickly if adverse reactions occur. A new study highlights the discovery of CIP-3, a synthetic cyclic peptide that targets the CD28 costimulatory receptor with high precision and pharmacologic reversibility.

Bridging the Gap Between Small Molecules and Biologics

The immune system relies on a delicate balance of signals to prevent autoimmunity while maintaining defense against pathogens. CD28 is a critical costimulatory receptor that amplifies T-cell activation. However, targeting the shallow protein-protein interaction (PPI) interface of CD28 has historically challenged drug developers. Traditional small molecules are often too small to disrupt these large surfaces effectively. Conversely, biologics are large and persistent. AI-designed cyclic peptides offer a middle ground, combining the high affinity of antibodies with the synthetic controllability of small molecules.

Therapeutic Advantages of AI-designed cyclic peptides

The lead candidate, CIP-3, was identified using an AI-guided strategy that integrates reinforcement learning and structural prediction. This peptide binds the CD28 extracellular domain with nanomolar affinity. Furthermore, it disrupts the interaction between CD28 and its natural ligands without causing intrinsic agonist activity. Most importantly, CIP-3 exhibits rapid pharmacologic reversibility. This feature allows for exposure-dependent control of immune signaling, which is a significant advantage over long-acting biologics. Therefore, clinicians can potentially fine-tune immunosuppression levels based on the patient's immediate clinical needs.

Promising Results in Chronic Colitis Models

Researchers evaluated the efficacy of CIP-3 in a T-cell transfer model of chronic colitis. The results demonstrated that the peptide confers dose-dependent therapeutic benefits. Specifically, it reduced systemic inflammatory cytokines and preserved tissue integrity in the colon. Moreover, testing on patient-derived peripheral blood mononuclear cells (PBMCs) from individuals with ulcerative colitis showed efficacy comparable to benchmark anti-CD28 biologics. These findings suggest that AI-designed cyclic peptides could soon provide a safer alternative for managing inflammatory bowel diseases and other autoimmune conditions.

Frequently Asked Questions

How do these cyclic peptides differ from standard biologics?

Unlike monoclonal antibodies that remain bound to receptors for weeks, these peptides offer rapid reversibility. This allows for tighter control over immune suppression and a faster recovery of immune function if treatment must be stopped.

Why is CD28 a significant target for colitis?

CD28 is essential for the activation and survival of T-cells. By blocking its interaction with ligands, researchers can suppress the overactive T-cell responses that drive chronic inflammation in ulcerative colitis and Crohn’s disease.

Is this technology limited to autoimmune diseases?

No, the AI-guided design platform can potentially target various immune checkpoints. This versatility makes it applicable to oncology, where precise modulation of T-cell activity is vital for effective immunotherapy.

Disclaimer: This content is for informational and educational purposes only. It does not constitute medical advice or establish a doctor-patient relationship. Always seek the advice of a qualified healthcare provider regarding any medical condition. Refer to the latest local and national guidelines for clinical practice.

References

Kuncewicz K et al. AI-Designed Cyclic Peptides Enable Controllable Modulation of the CD28 Immune Checkpoint. Adv Sci (Weinh). 2026 May 30. doi: 10.1002/advs.75892. PMID: 42216689.

Esensten JH et al. CD28 Costimulation: From Mechanism to Therapy. Immunity. 2016;44(5):973-988.

Ledford H. AI-designed proteins: The revolution comes to therapeutics. Nature. 2023;621:242-243.