Key points: • An HDMLF framework is proposed to predict EC numbers by using protein sequence data. • A protein language model and an extreme multilabel classifier are adopted to reduce the heavy head-crafted feature engineering and elevate the prediction performance. • The proposed framework remarkably outperforms the existing state-of-the-art method in terms of accuracy and mF1 score by 70% and 20%, respectively. • An online service and an offline bundle are provided for end users to annotate EC numbers in high throughput easily and efficiently.