AlphaMissense is a catalogue of predictions for human missense variants, classifying each as likely pathogenic or likely benign. It covers all 71 million possible missense variants.
DatasetFree
Step 1: Read the announcement to understand how scores are defined.
Step 2: Download the catalogue of predictions.
Step 3: Look up your missense variants of interest.
Step 4: Choose a score threshold that fits your accuracy needs.
Step 5: Use the results to prioritize variants for further study.
A value between 0 and 1 that approximately rates how likely a variant is pathogenic.
89% of the 71 million variants, with 57% predicted likely benign and 32% likely pathogenic.
No. It does not predict changes in protein structure or stability. It uses related protein sequences and the structural context of the variant.
Yes. The announcement says the predictions are freely available for commercial and researcher use.
Our World in Data HealthOur World in Data's global health collection brings together charts, data and writing on life expectancy, child and infant mortality, and healthcare spending. Charts are open access under a Creative Commons BY license.
Claude Protein Binder DesignA data release of 1,440 de novo miniprotein binders designed by Claude models acting as autonomous protein-design agents, with wet-lab results from two contract research organizations. It covers 16 targets.