tyang816 / ProtLOCA

πŸ“ˆ Using structure information only for protein homology detection (IEEE BIBM 2024).

Repository from Github https://github.comtyang816/ProtLOCARepository from Github https://github.comtyang816/ProtLOCA

Protein Representation Learning with Sequence Information Embedding: Does it Always Lead to a Better Performance?

πŸš€ Introduction (Venus-ProtLOCA/ ProtLOCA)

Using structure information only for protein homology detection.

fig1

fig2

πŸ“‘ Results

News

  • [2024.08.22] Congratulations! Our paper was accepted at IEEE International Conference on Bioinformatics and Biomedicine 2024 (IEEE BIBM 2024)!

Paper Results

result

πŸ›« Requirement

Please make sure you have installed Anaconda3 or Miniconda3.

conda env create -f environment.yaml
conda activate protloca

🧬 Start with ProtLOCA

Train from scratch

Script example can be found at script/.

πŸ™Œ Citation

Please cite our work if you have used our code or data. We are pleased to see improvements in the subsequent work.

@inproceedings{tan2024protloca,
  title={Protein representation learning with sequence information embedding: Does it always lead to a better performance?},
  author={Tan, Yang and Zheng, Lirong and Zhong, Bozitao and Hong, Liang and Zhou, Bingxin},
  booktitle={2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)},
  pages={233--239},
  year={2024},
  organization={IEEE}
}

About

πŸ“ˆ Using structure information only for protein homology detection (IEEE BIBM 2024).

License:Other


Languages

Language:Python 97.5%Language:Shell 2.5%