AlphaFold3 Covalent Inhibitor Predictions for Kinase BTK

Aggregating results from a prospective virtual screening campaign using AlphaFold3 cofolding predictions to discover covalent ligands. It demonstrates the model's application against the kinase BTK, leading to the identification of a novel, potent, and selective covalent small molecule inhibitor. The dataset is 575.5 KB in size, provided in XLSX format.

Use Cases

• Analyze AlphaFold3 cofolding predictions and associated confidence metrics for ranking covalent binders against property-matched decoys.
• Compare the performance of AlphaFold3 predictions with state-of-the-art covalent docking tools for a set of protein kinases.
• Validate the subangstrom accuracy of predicted AF3 binding modes using co-crystallography data from the discovered inhibitor.
• Examine the chemical distinctness, potent inhibition in vitro and in cells, and kinome/proteomic selectivity of the discovered covalent small molecule.

Strengths

• Data is derived from a prospective virtual screening campaign demonstrating a practical application of AlphaFold3 for drug discovery.
• Results include validation via co-crystallography confirming subangstrom accuracy of the predicted binding mode.
• The study specifically targets the kinase BTK, a member of a prolific family of drug targets.

Limitations

• The dataset is small at 575.5 KB, indicating limited scope and likely a small number of records or compounds.
• Specific data structure, column names, and row counts are not provided, complicating direct analysis.
• Focus is on a single model kinase (BTK), limiting generalizability to other protein families without further study.

Provenance

Source

figshare, authored by Yoav Shamir.

Collection Method

Generated from a prospective virtual screening campaign using AlphaFold3 cofolding predictions and validated experimentally.

Freshness

Last updated on 2026-03-20.