SEGT-GO: a graph transformer method based on PPI serialization and explanatory artificial intelligence for protein function prediction
Compared to the advanced network method DeepGraphGO, SEGT-GO achieves more competitive results in standard large-scale datasets and superior results on small ones, validating its ability to extract functional information from deep proteins. Furthermore, SEGT-GO achieves superior results in cross-species learning and prediction of the functions of unseen proteins, further proving the method's strong generalization.
Authors
- Haotian Zhang (ORCID: https://orcid.org/0000-0002-5447-547X)
- Dongjie Zhu
- Yumeng Liu (ORCID: https://orcid.org/0000-0002-3006-1053)
- Yundong Sun
- Baohui Lin
- Yansong Wang (ORCID: https://orcid.org/0000-0001-8843-0029)
- Xiaopeng Jin (ORCID: https://orcid.org/0000-0001-9481-3309)
- Xiaoling Luo
Institutions
- Shenzhen University (CN)
- Harbin Institute of Technology (CN)
- Shenzhen Technology University (CN)
- Weihai Science and Technology Bureau (CN)
Publication Details
- Journal
- BMC Bioinformatics
- Published
- 2025-02-10
- DOI
- https://doi.org/10.1186/s12859-025-06059-7
- Citations
- 4
- Primary Topic
- Bioinformatics and Genomic Networks
- Type
- article
- Field-Weighted Citation Impact
- 2.42
Funders
- Shenzhen Technology University
- National Natural Science Foundation of China
- Shenzhen Municipal Science and Technology Innovation Council