Yihua Song

Dr. Yihua Song

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
10 July 2024 in Biosensors
Verified
Journal Article
Open access
PDF file
CLCan Li
Can Li
WHWei He
Wei He
YSYihua Song
Yihua Song
XZXia Zhang
Xia Zhang
Jianfei SunJianfei Sun
Jianfei Sun
ZZZuojian Zhou
Zuojian Zhou
Cell co-culture technology aims to study the communication mechanism between cells and to better reveal the interactions and regulatory mechanisms involved in processes such as cell growth, differentiation, apoptosis, and other cellular activities. This is achieved by simulating the complex organismic environment. Such studies are of great significance for understanding the physiological and pathological processes of multicellular organisms. As an emerging cell cultivation technology, 3D cell co-culture technology, based on microfluidic chips, can efficiently, rapidly, and accurately achieve cell co-culture. This is accomplished by leveraging the unique microchannel structures and flow characteristics of microfluidic chips. The technology can simulate the native microenvironment of cell growth, providing a new technical platform for studying intercellular communication. It has been widely used in the research of oncology, immunology, neuroscience, and other fields. In this review, we summarize and provide insights into the design of cell co-culture systems on microfluidic chips, the detection methods employed in co-culture systems, and the applications of these models.

21 May 2024 in Molecules
Verified
Journal Article
Open access
PDF file
YYYuqian Yuan
Yuqian Yuan
XTXiaozhu Tang
Xiaozhu Tang
HLHongyan Li
Hongyan Li
XLXufeng Lang
Xufeng Lang
YSYihua Song
Yihua Song
ZZZuojian Zhou
Zuojian Zhou
M6A methylation, a ubiquitous modification on circRNAs, exerts a profound influence on RNA function, intracellular behavior, and diverse biological processes, including disease development. While prediction algorithms exist for mRNA m6A modifications, a critical gap remains in the prediction of circRNA m6A modifications. Therefore, accurate identification and prediction of m6A sites are imperative for understanding RNA function and regulation. This study presents a novel hybrid model combining a convolutional neural network (CNN) and a bidirectional long short-term memory network (BiLSTM) for precise m6A methylation site prediction in circular RNAs (circRNAs) based on data from HEK293 cells. This model exploits the synergy between CNN’s ability to extract intricate sequence features and BiLSTM’s strength in capturing long-range dependencies. Furthermore, the integrated attention mechanism empowers the model to pinpoint critical biological information for studying circRNA m6A methylation. Our model, exhibiting over 78% prediction accuracy on independent datasets, offers not only a valuable tool for scientific research but also a strong foundation for future biomedical applications. This work not only furthers our understanding of gene expression regulation but also opens new avenues for the exploration of circRNA methylation in biological research.

Verified
Journal Article
Open access
PDF file
HXHouxi Xu
Houxi Xu
YSYihua Song
Yihua Song
Chemokines are key proteins that regulate cell migration and immune responses and are essential for modulating the tumor microenvironment. Despite their close association with colon cancer, the expression patterns, prognosis, immunity, and specific roles of chemokines in colon cancer are still not fully understood. In this study, we investigated the mutational features, differential expression, and immunological characteristics of chemokines in colon cancer (COAD) by analyzing the Tumor Genome Atlas (TCGA) database. We clarified the biological functions of these chemokines using Gene Ontology (GO) annotation and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analysis. By univariate and multivariate COX regression analyses, we developed chemokine-based prognostic risk models. In addition, using Gene Set Enrichment Analysis (GSEA) and Gene Set Variant Analysis (GSVA), we analyzed the differences in immune responses and signaling pathways among different risk groups. The results showed that the mutation rate of chemokines was low in COAD, but 25 chemokines were significantly differentially expressed. These chemokines function in several immune-related biological processes and play key roles in signaling pathways including cytokine–cytokine receptor interactions, NF-kappa B, and IL-17. Prognostic risk models based on CCL22, CXCL1, CXCL8, CXCL9, and CXCL11 performed well. GSEA and GSVA analyses showed significant differences in immune responses and signaling pathways across risk groups. In conclusion, this study reveals the potential molecular mechanisms of chemokines in COAD and proposes a new prognostic risk model based on these insights.

24 November 2025 in Scientific Reports
Verified
Journal Article
Open access
PDF file
CGChen Ge
Chen Ge
HPHaoze Pan
Haoze Pan
YSYihua Song
Yihua Song
XZXia Zhang
Xia Zhang
ZZZuojian Zhou
Zuojian Zhou
This paper proposes a novel medical image segmentation method, SEFormer, which effectively leverages both local and global features representations to enhance segmentation accuracy and efficiency. To address the limitations of existing image segmentation methods based on transformers and CNNs cannot in simultaneously capturing both local and global features, we propose a novel hybrid network architecture that combines SENet, CNNs( Specifically ResNet), and Transformer. In this design, SENet is employed to enhance the global feature representation capabilities of CNNs, while the Transformer component compensates for the limitations of CNNs in capturing local and channel-specific features. In addition, to prevent feature loss during feature extraction, we draw inspiration from the concept of image pyramid models, obtain a larger receptive field, and use SE fusion to fuse local and global features in each layer of the feature pyramid, ensuring a more comprehensive and complete representation of image information. In the image segmentation task on the CHASEDB dataset, our method achieves great performance, improving the segmentation accuracy by 3.25% compared to existing methods.

6 March 2024 in Journal of Mechanics in Medicine and Biology
Verified
Journal Article
Closed access
YSYihua Song
Yihua Song
CLCan Li
Can Li
XZXia Zhang
Xia Zhang
ZLZhen Liu
Zhen Liu
NSNingning Song
Ningning Song
ZZZuojian Zhou
Zuojian Zhou

11 October 2023 in Journal of Mechanics in Medicine and Biology
Verified
Journal Article
Closed access
YZYanyu Zhou
Yanyu Zhou
YSYihua Song
Yihua Song
KSKankan She
Kankan She
XLXinxia Li
Xinxia Li
YHYu Hu
Yu Hu
XNXinbao Ning
Xinbao Ning