Developing an AI-Generated Peptide Targeting Platelet-type von Willebrand Disease.

Abstract

Platelet-type von Willebrand disease (PT-VWD) is a rare bleeding disorder caused by gain-of-function mutations in platelet glycoprotein Ib alpha (GPIbα). These mutations lead to a hyperactive protein-protein interaction (PPI) with von Willebrand factor (VWF) and pathological platelet aggregation. Counterintuitively, PT-VWD patients suffer from bleeding diathesis as opposed to thrombosis. Despite well-defined genetic etiology, no targeted therapy yet exists for PT-VWD. Here, we sought to develop a peptide inhibitor that selectively targets the aberrant interaction in PT-VWD. Using the In-Silico Protein Synthesizer, we designed and screened 10,000 peptides for predicted affinity and specificity towards GPIbαMet239Val. Functional validation of top-ranked peptides included a combination of in-vitro functional assays using GPIbαGly233Val, Met239Val and ex-vivo PT-VWD patient platelet assays. One peptide, G14, emerged as a potent and selective inhibitor of the GPIbαGly233Val, Met239Val-VWF PPI. Functional assays demonstrated that G14 disrupts this interaction without binding GPIbαWT or VWF alone. The peptide also displays picomolar affinity (6.6 pM) for GPIbαGly233Val, Met239Val. Structural modeling predicted G14 binds the β-switch region of GPIbαGly233Val, Met239Val involving the disease-associated Val239 residue. In PT-VWD patient-derived platelet-rich plasma, G14 selectively inhibited VWF binding and ristocetin-induced agglutination with no measurable effect on healthy samples. The G14 peptide appears to be a highly specific inhibitor of the GPIbαGly233Val, Met239Val-VWF interaction, providing proof-of-concept data for therapeutic development in PT-VWD. Further, the protein and platelet specificity these data suggest that G14 may be a potential diagnostic tool for PT-VWD. The approach highlights the utility of artificial intelligence in targeting disease-specific PPIs with high precision.