Developing an artificial intelligence–generated peptide targeting platelet-type von Willebrand disease
Bibliographic record
Abstract
ABSTRACT: Platelet-type von Willebrand disease (PT-VWD) refers to a rare bleeding disorder caused by gain-of-function mutations in platelet glycoprotein Ibα (GPIbα). These mutations lead to a hyperactive protein-protein interaction (PPI) with von Willebrand factor (VWF) and pathological platelet aggregation. Counterintuitively, patients with PT-VWD present with a bleeding diathesis as opposed to thrombosis. Despite well-defined genetic etiology, no targeted therapy 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 toward GPIbαMet239Val. Functional validation of top-ranked peptides included a combination of in vitro functional assays using GPIbαGly233Val, Met239Val and ex vivo platelet assays from patients with PT-VWD. 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 platelet-rich plasma from a patient with PT-VWD, G14 selectively inhibited platelet-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. Furthermore, the protein and platelet specificity of 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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".