Yiwei Fu

Yiwei Fu

Auto-generated profile, based on publicly available information

Yiwei Fu

Peking University, Beijing, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 January 2024 in GigaScience
Verified
Journal Article
Open access
YFYiwei Fu
Yiwei Fu
ZGZhonghui Gu
Zhonghui Gu
XLXiao Luo
Xiao Luo
QGQirui Guo
Qirui Guo
LLLuhua Lai
Luhua Lai
MDMinghua Deng
Minghua Deng
Background: In the face of a growing disparity between high-throughput sequence data and low-throughput experimental studies, the emerging field of deep learning stands as a promising alternative. Generally, many data-driven approaches are capable of facilitating fast and accurate predictions of protein functions. Nevertheless, the inherent statistical nature of deep learning techniques may limit their generalization capabilities when applied to novel nonhomologous proteins that diverge significantly from existing ones. Results: In this work, we herein propose a novel, generalized approach named Graph Adversarial Learning with Alignment (GALA) for protein function prediction. Our GALA method integrates a graph transformer architecture with an attention pooling module to extract embeddings from both protein sequences and structures, facilitating unified learning of protein representations. Particularly noteworthy, GALA incorporates a domain discriminator conditioned on both learnable representations and predicted probabilities, which undergoes adversarial learning to ensure representation invariance across diverse environments. To optimize the model with abundant label information, we generate label embeddings in the hidden space, explicitly aligning them with protein representations. Benchmarked on datasets derived from the PDB database and Swiss-Prot database, our GALA achieves considerable performance comparable to several state-of-the-art methods. Even more, GALA demonstrates wonderful biological interpretability by identifying significant functional residues associated with Gene Ontology terms through class activation mapping. Conclusions: GALA, which leverages adversarial learning and label embedding alignment to acquire domain-invariant protein representations, exhibits outstanding generalizability in function prediction for proteins from previously unseen sequence space. By incorporating the structures predicted by AlphaFold2, GALA demonstrates significant potential for function annotation in newly discovered sequences. A detailed implementation of our GALA is available at https://github.com/fuyw-aisw/GALA.

19 July 2026
Verified
Conference Paper
Open access
YRYingtao Ren
Yingtao Ren
ZZZiyi Zhao
Ziyi Zhao
YFYiwei Fu
Yiwei Fu
XLXiao Luo
Xiao Luo
YCYu-Cheng Chang
Yu-Cheng Chang
CLChin-Teng Lin
Chin-Teng Lin

12 April 2026
Verified
Conference Paper
Open access
WJWei Ju
Wei Ju
SYSiyu Yi
Siyu Yi
ZMZhengyang Mao
Zhengyang Mao
YQYifang Qin
Yifang Qin
YWYifan Wang
Yifan Wang
MZMing Zhang
Ming Zhang

6 November 2026
Verified
Conference Paper
Open access
YFYiwei Fu
Yiwei Fu
CCChunchun Chen
Chunchun Chen
YZYuxing Zhang
Yuxing Zhang
WZWeizhi Zhang
Weizhi Zhang
GZGuanjie Zheng
Guanjie Zheng
MDMinghua Deng
Minghua Deng

1 July 2026 in IEEE Transactions on Knowledge and Data Engineering
Verified
Journal Article
Closed access
YDYuntai Ding
Yuntai Ding
TRTao Ren
Tao Ren
YFYiwei Fu
Yiwei Fu
YWYifan Wang
Yifan Wang
HZHaodong Zhang
Haodong Zhang
XHXian-Sheng Hua
Xian-Sheng Hua