YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Enzyme classification: k-mer nearest-neighbour model
CPU-only EC predictor. Sequences (not normalised) are turned into hashed 5-mer log-TF-IDF vectors; for each query the 10 most cosine-similar training sequences vote for their ECs (weights = similarity^6, split evenly over each neighbour's ECs). The top-ranked EC is the first prediction. Empty/no-neighbour inputs fall back to the most frequent training EC.
Train: python train.py --train ../data/train.parquet --vocab ec_vocabulary.json --output weights
Predict: python predict.py --input INPUT.parquet --output OUTPUT.jsonl
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support