ec-knn-v3

CPU-only enzyme EC prediction for the Leak CURBER enzyme classification task.

MMseqs2 search of each unique input against the full training set (prebuilt index), then a bit-score-weighted vote over the ECs of the top hits. The first EC in the list is the best guess; up to two more are added when their vote is close. Inputs with no hit get the most frequent training EC. A time guard stops searching early and uses the fallback EC for the remaining (longest) inputs if the machine is slow.

Run: python /app/predict.py --input INPUT.parquet --output OUTPUT.jsonl

Downloads last month: 40

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support