ECRECer

ECRECer predicts and recommends Enzyme Commission (EC) numbers from protein FASTA sequences. It implements the hierarchical dual-core multitask learning workflow described in the ECRECer papers, with local inference support for annotation, recommendation, and hybrid sequence-alignment modes.

Installation

Install the Python package from a built wheel or PyPI package:

python -m pip install ecrecer

The package intentionally does not include large data files, UniProt snapshots, feature banks, or trained model weights. Prepare those artifacts separately and point ECRECer at their root directory with ECRECER_ROOT.

For the RTX 5090 runtime, install PyTorch from the CUDA 13.0 PyTorch index first, then install the pinned runtime stack:

python -m pip install --index-url https://download.pytorch.org/whl/cu130 torch==2.13.0+cu130
python -m pip install -r requirements/runtime-5090.txt

Artifact Layout

ECRECER_ROOT should contain the same runtime artifact layout used by the repository checkout:

ECRECER_ROOT/
  data/
    dict/
    featureBank/
    uniprot/
  model/
  results/
  tmp/

Required production artifacts include:

• data/uniprot/sprot_latest.feather
• data/featureBank/embd_esm32.feather
• data/dict/dict_label_task1.h5
• data/dict/dict_label_task2.h5
• data/dict/dict_label_task3.h5
• model/isenzyme.h5
• model/howmany_enzyme.h5
• model/ec.h5

Set the artifact root before running:

export ECRECER_ROOT=/path/to/ecrecer_artifacts

Quick Start

Use data/sample_10.fasta for a minimal local run when the artifact root is this repository checkout:

export ECRECER_ROOT=/path/to/ecrecer_artifacts
ecrecer -i "$ECRECER_ROOT/data/sample_10.fasta" -o /tmp/ecrecer_sample10.tsv -mode p -topk 5
sed -n '1,5p' /tmp/ecrecer_sample10.tsv

Command Line Usage

Prediction mode writes final EC predictions:

ecrecer -i input.fasta -o output.tsv -mode p -topk 5

Recommendation mode writes top-k EC candidates with scores:

ecrecer -i input.fasta -o recommendations.tsv -mode r -topk 10

Hybrid mode also uses DIAMOND sequence alignment and requires a DIAMOND executable plus a production BLAST database under data/uniprot_blast_db/:

ecrecer -i input.fasta -o hybrid.tsv -mode h -topk 10

Legacy script usage is still supported:

python production.py -i input.fasta -o output.tsv -mode p -topk 5

Input And Output Example

Input is a standard FASTA file:

>query_1
MKTAYIAKQRQISFVKSHFSRQDILD
>query_2
MGSSHHHHHHSSGLVPRGSHM

Prediction mode (-mode p) writes a tab-separated table with one row per input sequence:

id_input	ec_pred
query_1	2.6.1.19
query_2	-

Recommendation mode (-mode r) returns top-k candidate EC numbers and probabilities:

id_input	dmlf_recomendations
query_1	[('2.6.1.19', 0.685800), ('2.6.1.22', 0.248600)]

- indicates a predicted non-enzyme or no EC assignment. For exact values, use the output generated by the installed model artifacts.

GPU Runtime Notes

• The validated 5090 stack uses PyTorch 2.13.0+cu130 for ESM embedding.
• Existing .h5 prediction heads are loaded through TensorFlow/Keras compatibility wrappers.
• TensorFlow 2.21.0 can see RTX 5090 GPUs but may JIT kernels from PTX because current wheels do not ship native kernels for compute capability 12.0a.

Docker And Singularity

Container images remain useful for users who prefer a prebuilt runtime:

docker pull kingstdio/ecrecer
sudo docker run -it -d --gpus all --name ecrecer -v "$PWD":/home kingstdio/ecrecer
sudo docker exec ecrecer python /ecrecer/production.py -i /home/input.fasta -o /home/output.tsv -mode h -topk 10

wget -c https://tibd-public-datasets.s3.us-east-1.amazonaws.com/ecrecer/sifimages/ecrecer.sif
singularity run --nv ecrecer.sif python /ecrecer/production.py -i input.fasta -o output.tsv -mode h -topk 10

Citation

If ECRECer is useful in your work, please cite:

@article{shi2023enzyme,
  title={Enzyme Commission Number Prediction and Benchmarking with Hierarchical Dual-core Multitask Learning Framework},
  author={Shi, Zhenkun and Deng, Rui and Yuan, Qianqian and Mao, Zhitao and Wang, Ruoyu and Li, Haoran and Liao, Xiaoping and Ma, Hongwu},
  journal={Research},
  year={2023},
  publisher={AAAS}
}

Earlier preprint:

Shi, Zhenkun, Qianqian Yuan, Ruoyu Wang, Haoran Li, Xiaoping Liao, and Hongwu Ma. ECRECer: Enzyme Commission Number Recommendation and Benchmarking based on Multiagent Dual-core Learning. arXiv:2202.03632.

License

ECRECer is released under the MIT License. See LICENSE.