IET Systems Biology最新文献_第3页

IF 1.9 4区生物学

IET Systems Biology Pub Date : 2026-03-31

引用次数: 0

Application of Fast Integration Strategy for Multi-Omics Data and Limited Random Forest Model in Survival Prediction of Glioblastoma 多组学数据快速整合策略与有限随机森林模型在胶质母细胞瘤存活预测中的应用。

IF 1.9 4区生物学

IET Systems Biology Pub Date : 2026-03-31 DOI: 10.1049/syb2.70062

Ze Liu, Yanhui Wu, Shanshan Wang, Fei Lin, Lin Wan, Peng Song

{"title":"Application of Fast Integration Strategy for Multi-Omics Data and Limited Random Forest Model in Survival Prediction of Glioblastoma","authors":"Ze Liu, Yanhui Wu, Shanshan Wang, Fei Lin, Lin Wan, Peng Song","doi":"10.1049/syb2.70062","DOIUrl":"10.1049/syb2.70062","url":null,"abstract":"Gliomas exhibit significant prognostic heterogeneity, and single-omics data/existing technologies struggle to balance multi-omics integration efficiency, prediction accuracy, and clinical adaptability—hindering the clinical translation of precise prognostic assessment. Focussing on glioblastoma (GBM) and lower-grade glioma (LGG), this study proposes an integrated solution: three-step multi-omics feature selection combined with the limited random forest (FRF) model, using TCGA-derived transcriptomic, genomic, epigenomic and clinical survival data. Prognosis-related features are first screened using univariate Cox regression, refined by random forest-based feature importance for dimensionality reduction and then integrated into a multi-omics matrix through sample matching. The FRF model balances efficiency and accuracy by limiting decision tree number and depth, optimising node splitting criteria, and adding a dual-weighted correction mechanism. Results show that FRF achieves an AUC of 0.96 for GBM, outperforms logistic regression (LR) and support vector machine (SVM) across all LGG metrics, and reduces training time to minutes—meeting the 2-h clinical prognostic demand. Ablation experiments confirm that the multi-omics model improves performance by 11.63% compared with the optimal single-omics model, with core features consistent with glioma molecular mechanisms. This resolves the challenge of rapid integration and precise prediction, providing an efficient tool for glioma prognostic assessment and supporting multi-omics clinical translation.","PeriodicalId":50379,"journal":{"name":"IET Systems Biology","volume":"20 1","pages":""},"PeriodicalIF":1.9,"publicationDate":"2026-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/syb2.70062","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147595477","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

IF 1.9 4区生物学

IET Systems Biology Pub Date : 2026-03-30

引用次数: 0

CFMF: A Clustering-Free Cell Marker Finder for Single-Cell Transcriptomic Data CFMF：用于单细胞转录组学数据的无聚类细胞标记查找器。

IF 1.9 4区生物学

IET Systems Biology Pub Date : 2026-03-30 DOI: 10.1049/syb2.70065

Shumin Yin, Ke Liu

{"title":"CFMF: A Clustering-Free Cell Marker Finder for Single-Cell Transcriptomic Data","authors":"Shumin Yin, Ke Liu","doi":"10.1049/syb2.70065","DOIUrl":"10.1049/syb2.70065","url":null,"abstract":"The discovery of novel cell types and their marker genes is a fundamental goal of single-cell RNA sequencing (scRNA-seq). Nevertheless, most conventional methods rely on cell clustering, a process in which parameter selection is often non-trivial and subjective. To address such limitations, we developed Clustering-Free Cell Marker Finder (CFMF), a novel computational framework that enables the discovery of marker genes without clustering. We first validated CFMF using the PBMC3K dataset and found that it not only recovered canonical marker genes, but also uncovered novel marker genes. When validating with glioblastoma datasets, CFMF successfully recapitulated established cellular state signatures. Using human normal lung scRNA-seq datasets, we demonstrated its superior sensitivity in rare cell type detection even at very low prevalence. We utilised CFMF to perform integrative analysis on colorectal cancer scRNA-seq datasets and defined seven distinct transcriptional states including an LGR5+ state that is strongly associated with metastasis. Finally, we systematically benchmarked CFMF against widely used gene selection methods across multiple scRNA-seq datasets and revealed that CFMF appeared to more effectively identify biologically meaningful genes. In summary, we provide a powerful framework for the discovery of marker genes and the analysis of tumour heterogeneity, which may facilitate our understanding of complex biological systems.","PeriodicalId":50379,"journal":{"name":"IET Systems Biology","volume":"20 1","pages":""},"PeriodicalIF":1.9,"publicationDate":"2026-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/syb2.70065","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147576297","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

IF 1.9 4区生物学

IET Systems Biology Pub Date : 2026-03-27

引用次数: 0

Deep Learning Can Predict the Overall Survival of Cervical Cancer Based on Histopathological Image, Gene Mutation and Clinical Information 基于组织病理图像、基因突变和临床信息，深度学习可以预测宫颈癌的总体生存。

IF 1.9 4区生物学

IET Systems Biology Pub Date : 2026-03-27 DOI: 10.1049/syb2.70060

Jie Shen, Zheng Miao, Lixia Wang, Zhen Huo, Tao Lu, Yuebin Liang, Binbin Ji, ShuXue Xi, Geng Tian, Jialiang Yang, Fuquan Zhang

{"title":"Deep Learning Can Predict the Overall Survival of Cervical Cancer Based on Histopathological Image, Gene Mutation and Clinical Information","authors":"Jie Shen, Zheng Miao, Lixia Wang, Zhen Huo, Tao Lu, Yuebin Liang, Binbin Ji, ShuXue Xi, Geng Tian, Jialiang Yang, Fuquan Zhang","doi":"10.1049/syb2.70060","DOIUrl":"10.1049/syb2.70060","url":null,"abstract":"The fusion of data features from different modes, such as pathology images and sequence data, has the potential to predict the overall survival (OS) of patients with cervical cancer. This study aims to develop a novel prediction model for overall survival (OS) that incorporates pathology images, clinical data and molecular data. The model underwent training using comprehensive cervical cancer data from The Cancer Genome Atlas (TCGA), which include 119 patients. To independently validate the model, we used a manually collected dataset from Peking Union Medical College Hospital (PUMCH), comprising 53 patients with cervical cancer. LASSO Cox regression analysis was applied to identify relevant features associated with overall survival (OS), resulting in the identification of 484 genes, including RGR, DBN1 and CALCR, as well as numerous image features. Building upon these findings, a multimodal deep learning model was developed to effectively classify the overall survival (OS) of patients with cervical cancer into two categories: short term (ST: ≤ 3 years) and long term (LT: > 3 years) based on the integration of pathology images and clinical features. The developed model achieved reasonably good prediction accuracy in the independent testing dataset from PUMCH, with an area under the curve (AUC) value of 0.783. In conclusion, the combination of pathology images with clinical and molecular data enables the creation of accurate and reliable prediction models for cervical cancer.","PeriodicalId":50379,"journal":{"name":"IET Systems Biology","volume":"20 1","pages":""},"PeriodicalIF":1.9,"publicationDate":"2026-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/syb2.70060","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147534230","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Decoding the Anti-Tumour Mechanism of ɑ-Solanine: SRC Inhibition and Ferroptosis Induction in Colon Cancer 解析茄碱在结肠癌中的抗肿瘤机制：SRC抑制和铁下垂诱导。

IF 1.9 4区生物学

IET Systems Biology Pub Date : 2026-03-05 DOI: 10.1049/syb2.70057

Chao Zheng, Yu Mao, Yongfeng Chen, Jianping Ye

{"title":"Decoding the Anti-Tumour Mechanism of ɑ-Solanine: SRC Inhibition and Ferroptosis Induction in Colon Cancer","authors":"Chao Zheng, Yu Mao, Yongfeng Chen, Jianping Ye","doi":"10.1049/syb2.70057","DOIUrl":"10.1049/syb2.70057","url":null,"abstract":"α-Solanine, a steroidal alkaloid glycoside, exhibits significant anti-tumour properties with potential therapeutic applications in colon cancer. Its relevance was explored through network pharmacology, bioinformatics analysis and experimental validation. α-Solanine treatment significantly inhibited HT29 colon cancer cell proliferation and migration dose-dependently, reducing Ki67 and PCNA expression markers. Target prediction using PharmMapper and GeneCards databases revealed 90 potential targets, with network analysis identifying SRC as the key molecular target. Molecular docking confirmed stable α-solanine-SRC binding (−9.3 kcal/mol). TCGA analysis demonstrated SRC upregulation in colon cancer across tumour stages T1–T4, with high expression correlating negatively with immune infiltration and poor prognosis. Pathway analysis revealed SRC's involvement in PI3K/AKT/mTOR signalling, regulating ferroptosis-related genes. Experimental validation showed α-solanine increased ROS, MDA and iron levels while decreasing GSH, promoting ferroptosis. Gene silencing confirmed SRC's critical role in cancer progression, with α-solanine's effects suppressed upon SRC upregulation. These findings suggest that SRC is a potential target of α-solanine, and that its anticancer effects may involve inhibition of SRC and suppression of the PI3K/AKT/mTOR pathway. The ferroptosis-mediated mechanisms highlight α-solanine's therapeutic potential and suggest promising avenues for colon cancer treatment development.","PeriodicalId":50379,"journal":{"name":"IET Systems Biology","volume":"20 1","pages":""},"PeriodicalIF":1.9,"publicationDate":"2026-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12963022/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147367091","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

IF 1.9 4区生物学

IET Systems Biology Pub Date : 2026-03-05

引用次数: 0

TSSP-UNet: A Two-Stage Weakly Supervised Pathological Image Segmentation With Point Annotations TSSP-UNet：带点注释的两阶段弱监督病理图像分割。

IF 1.9 4区生物学

IET Systems Biology Pub Date : 2026-03-03 DOI: 10.1049/syb2.70055

Shaoqiang Wang, Guiling Shi, Yuchen Wang, Qiang Li, Yawu Zhao, Xiaochun Cheng

{"title":"TSSP-UNet: A Two-Stage Weakly Supervised Pathological Image Segmentation With Point Annotations","authors":"Shaoqiang Wang, Guiling Shi, Yuchen Wang, Qiang Li, Yawu Zhao, Xiaochun Cheng","doi":"10.1049/syb2.70055","DOIUrl":"10.1049/syb2.70055","url":null,"abstract":"Deep convolutional neural networks have demonstrated remarkable effectiveness in image segmentation. However, segmentation becomes challenging when training on images with complex instances. Moreover, obtaining annotations for high-precision data is also difficult. Weakly supervised learning can address this issue by using nonspecialised annotations or supervised information from segmentation algorithms. In this study, we proposed TSSP-UNet: a two-stage weakly supervised segmentation approach. In the first stage, we trained a segmentation network augmented with constraint and attention mechanisms. These mechanisms are designed to operate on boundaries and superpixels generated from pseudo-labels. For the attention network, two pseudo-labels were used with a binary mask to add contour information to the segmentation process. Furthermore, a feature aggregation segmentation network was applied to the prominent foreground area in the image by incrementally adding elements. In the second stage, a refined confident learning algorithm improved the pseudo-labels at the pixel level and then TSSP-UNet was retrained using the modified superpixel labels. Testing on the MoNuSeg and TNBC datasets demonstrates that the approach performs well in the weakly supervised cell nucleus segmentation task compared with baseline methods.","PeriodicalId":50379,"journal":{"name":"IET Systems Biology","volume":"20 1","pages":""},"PeriodicalIF":1.9,"publicationDate":"2026-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12956481/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147349473","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

IF 1.9 4区生物学

IET Systems Biology Pub Date : 2026-03-03

引用次数: 0