Targeting Challenging Proteins From Integrin Family

Background

Heterodimeric receptors from the integrin family involved in protein-protein interactions (PPIs).
Promising for immunological disorders, inflammation, and cancers.
No binding sites for small molecules are known.
No potent small molecule binders exist.
Challenging target, often deemed undruggable by small molecules.

Project workflow:

AI-driven MD Simulations: Predicted integrin conformational changes using integrin crystal structures.
AI-driven Pocket Extractor: Identified binding pockets within dynamic conformations by our validated proprietary technique.
Virtual Screening: Screened approximately 5 million compounds with proprietary AI algorithms to evaluate potential interactions.
Secondary ArtiDock Docking: Refined the selection using AI docking.

In Vitro Testing: Conducted ligand displacement assays on top candidates to validate their ability to compete with a known ligand for binding. SPR analysis was used to measure binding kinetics and affinity, providing detailed insights into the strength of the interactions.

Results

Improved Hit Rate and Validation: Achieved a 12% hit rate with 97 promising hits out of ~1,200 compounds.
Targeted Binding Pockets: Identified 4 pockets including one cryptic pocket and successfully targeted three specific binding pockets—Pocket I (41 hits), Pocket II (40 hits), and Pocket III (16 hits).
Potency: The top 32 compounds showed potency within the range of 1–10 μM.

Binding Affinity: SPR analysis confirmed that one of the top compounds has a Kd of 0.35 μM, demonstrating strong binding affinity.