North China Electric Power University
Decoding genetic codes, mapping biological functions
Geneticode Lab develops computational methods that read biological function from genetic sequence. Current work focuses on protein function annotation and the effects of amino-acid mutations.
Sequence-based Gene Ontology function prediction from the lab is out in Frontiers in Genetics. Dong Wang is a corresponding author. Code is in the S2DA-GO repository.
Placeholder
Replace this item in _data/news.yml, or add a dated Markdown file under _posts/ and link it here.
S2DA-GO predicts Gene Ontology functions from protein sequence. A global sequence branch is paired with a gradient-decoupled cross-attention branch and with semantic priors from GO term text, so rare functional labels interfere less with the shared representation.
SpaSem (Spatial–Semantic Integration) is a dual-stream model for zero-shot prediction of protein mutation effects. It fuses geometric structure with longer-range evolutionary signal so variants can be scored without building a new structure for every mutant. A formal citation has not been added yet.
2026
Applied Sciences 16 (17), 8437 (2026)
2026
Frontiers in Genetics 17, 1880976 (2026)
Corresponding author: Dong Wang
Wang H, Xiang F, Zhang J, Wu T, Wang D, Wang Q, Lu B and Fu F (2026) S2DA-GO: enhancing protein function prediction via gradient-decoupled cross-attention and semantic priors. Front. Genet. 17:1880976. doi: 10.3389/fgene.2026.1880976
2026
Briefings in Bioinformatics 27 (4), bbag408 (2026)
Corresponding authors: Dong Wang and Tao Jiang
Dong Wang, Hailong Wang, Tao Jiang, Bin Lu, Fujun Xiang, Qiang Wang, SSAS-GO: structure-sequence adaptive synergy network for protein function prediction, Briefings in Bioinformatics, Volume 27, Issue 4, July 2026, bbag408, https://doi.org/10.1093/bib/bbag408
