Zhaoyang Liu

Dr. Zhaoyang Liu

orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
19 January 2021 in International Journal of Intelligent Systems
Verified
Journal Article
Closed access
PDF file
YXYuteng Xiao
Yuteng Xiao
HYHongsheng Yin
Hongsheng Yin
HQHongang Qi
Hongang Qi
Yudong ZhangYudong Zhang
Yudong Zhang
ZLZhaoyang Liu
Zhaoyang Liu

25 March 2021 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
ZLZhaoyang Liu
Zhaoyang Liu
YXYuteng Xiao
Yuteng Xiao
HYHongsheng Yin
Hongsheng Yin
XLXiaodan Li
Xiaodan Li
SCShutao Chen
Shutao Chen
LZLin Zhang
Lin Zhang
N6-methyladenosine (m 6 A) has been shown to play crucial roles in RNA metabolism, physiology, and pathological processes. However, the specific regulatory mechanisms of most methylation sites remain uncharted due to the complexity of life processes. Biological experimental methods are costly to solve this problem, and computational methods are relatively lacking. The discovery of local co-methylation patterns (LCPs) of m 6 A epi-transcriptome data can benefit to solve the above problems. Based on this, we propose a novel biclustering algorithm based on the beta distribution (BDBB), which realizes the mining of LCPs of m 6 A epi-transcriptome data. BDBB employs the Gibbs sampling method to complete parameter estimation. In the process of modeling, LCPs are recognized as sharp beta distributions compared to the background distribution. Simulation study showed BDBB can extract all the three actual LCPs implanted in the background data and the overlap conditions between them with considerable accuracy (almost close to 100%). On MeRIP-Seq data of 69,446 methylation sites under 32 experimental conditions from 10 human cell lines, BDBB unveiled two LCPs, and Gene Ontology (GO) enrichment analysis showed that they were enriched in histone modification and embryo development, etc. important biological processes respectively. The GOE_Score scoring indicated that the biclustering results of BDBB in the m 6 A epi-transcriptome data are more biologically meaningful than the results of other biclustering algorithms.

2 January 2026 in Journal of Cheminformatics
Verified
Journal Article
Open access
PDF file
HZHang Zhu
Hang Zhu
SYSisi Yuan
Sisi Yuan
MTMingJing Tang
MingJing Tang
GZGuifei Zhou
Guifei Zhou
ZHZhanxuan Hu
Zhanxuan Hu
CLChunyan Li
Chunyan Li
Molecular representation learning (MRL) is a crucial link between machine learning and chemistry. It plays a vital role in predicting molecular properties

19 November 2025 in BMC Bioinformatics
Verified
Journal Article
Open access
HWHonglei Wang
Honglei Wang
XZXuesong Zhang
Xuesong Zhang
YSYanjing Sun
Yanjing Sun
ZLZhaoyang Liu
Zhaoyang Liu
LZLin Zhang
Lin Zhang
Background: RNA methylation (RM) regulates gene expression regulation, RNA stability, and protein translation. Accurate prediction of RM modification sites is essential for understanding their biological functions. However, existing wet-lab detection techniques face challenges including operational complexity and high costs. Deep learning (DL) methods have been applied to this task. However, existing methods show performance degradation with smaller training datasets. For instance, the Bidirectional Gated Recurrent Unit (BGRU) demonstrates substantial performance degradation. Contrastive Learning Network (CNN) can extract local pattern features but learns overly specific patterns with sample-limited data, resulting in poor feature generalization. Bidirectional Long Short-Term Memory (BiLSTM) excels at modeling long-range dependencies but cannot sufficiently learn gating mechanism parameters to capture effective sequence representations with limited samples. Transformer processes sequences in parallel and captures global dependencies through self-attention, but its quadratic computational complexity and large parameter count make it prone to overfitting on small datasets. Current DL methods show reduced performance when training data is limited. Results: This study proposes a Multi-view Contrastive Learning with CNN-BiLSTM-Attention (MCLCBA) framework for RM modification site prediction. The multi-view approach comprises a primary view and auxiliary view, where the primary view utilizes DNA Bidirectional Encoder Representations from Transformers (DNABERT) to extract sequence contextual features, and the auxiliary view employs Chaos Game Representation (CGR) to extract structural features. Feature extraction includes four components: data augmentation, multi-view encoders, projection heads, and contrastive loss functions. By implementing dual differential data augmentation strategies and constructing multi-view network architectures for feature processing and fusion, the model learns discriminative feature representations invariant to data augmentation through maximizing positive sample similarity while minimizing negative sample similarity. This effectively addresses sample-limited feature learning scenarios. Experimental results on the sample-limited m 7 G dataset demonstrate that MCLCBA achieves AUROC and AUPRC of 85.64% and 86.94%, respectively, improving upon existing methods by 5–6% in both metrics. Conclusions: Through multi-view contrastive learning, MCLCBA provides an approach for RM sites under sample-limited scenarios.

20 October 2023
Verified
Conference Paper
Open access
XXXiaoxue Xiang
Xiaoxue Xiang
CCChangfang Chen
Changfang Chen
Ruixia LiuRuixia Liu
Ruixia Liu
ZLZhaoyang Liu
Zhaoyang Liu
The electrocardiogram (ECG) can provide detailed information about the rhythm and function of the heart, and provide guidance for doctors. However, the ECG signals are susceptible to be contaminated by noise, which affects the accuracy of the waveforms. In view of this, a denoising method for ECG signals based on multi-scale residual dense U-Net is proposed. A dual-branch residual dense block is proposed, which realizes the adaptive extraction of local multi-scale features of ECG signals. By integrating the block into the up-sampling and down-sampling of U-Net, the multi-scale features of ECG signals can be extracted. By reducing the size of the feature maps, the down-sampling can realize a better trade-off between efficiency and effectiveness in exploiting the hierarchical features. By skip connection, the restored features from up-sampling are fused with the down-sampling features, and are transferred to the dual-branch residual dense block. This operation avoids the information loss and captures more accurate contextual information. It has been verified that the waveforms obtained by this method are basically consistent with the waveforms of the clean signals and effectively retains the important waveform information of the ECG signals.

29 July 2020 in Journal of Ambient Intelligence and Humanized Computing
Verified
Journal Article
Closed access
PDF file
ZLZhaoyang Liu
Zhaoyang Liu
KFKun Fu
Kun Fu
HYHongsheng Yin
Hongsheng Yin
KXKaijian Xia
Kaijian Xia
YXYuteng Xiao
Yuteng Xiao
GLGangshen Li
Gangshen Li