IEEE transactions on computational biology and bioinformatics最新文献

A DNA Strand Displacement-Based Computing Model for Solving Intractable Graph Problems. 求解棘手图问题的DNA链位移计算模型。

IEEE transactions on computational biology and bioinformatics Pub Date : 2025-10-22 DOI: 10.1109/TCBBIO.2025.3623800

Enqiang Zhu, Xianhang Luo, Chanjuan Liu, Xiaolong Shi, Jin Xu

{"title":"A DNA Strand Displacement-Based Computing Model for Solving Intractable Graph Problems.","authors":"Enqiang Zhu, Xianhang Luo, Chanjuan Liu, Xiaolong Shi, Jin Xu","doi":"10.1109/TCBBIO.2025.3623800","DOIUrl":"https://doi.org/10.1109/TCBBIO.2025.3623800","url":null,"abstract":"Graphs are the primary means of describing the relation between individuals in society, and have been extensively used for analysing various types of networks, such as social networks, biological networks, and electric networks. Many practical problems can be abstracted to graph problems, and cannot be solved efficiently due to their NP-hard nature. DNA computing, leveraging the vast parallelism and high-density storage of DNA molecules, provides a new way for solving intractable problems. However, existing DNA computing models are limited by single computing function. This paper proposed a novel DNA computing model with two DNA modules-a graph representation module (GRM) and a detection module (DM)-that can solve a variety of NP-hard problems. To show the feasibility of the proposed model, we conducted simulation and biochemical experiments on multiple NP-hard problems, such as the minimum dominating set, maximum independent set, and minimum vertex cover. Experimental results showed that the GRM is a universal graph representation module, based on which multiple graph problems can be solved by cascading a proper designed detection module. Our method also highlighted the potential for DNA strand displacement to act as a computation tool to solve intractable graph problems.","PeriodicalId":520987,"journal":{"name":"IEEE transactions on computational biology and bioinformatics","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145351380","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

scMID: a Deep Multi-omics Integration Framework for Comprehensive Single-cell Data Analysis. scMID：用于综合单细胞数据分析的深度多组学集成框架。

IEEE transactions on computational biology and bioinformatics Pub Date : 2025-10-22 DOI: 10.1109/TCBBIO.2025.3624040

Qiu Xiao, Yan Zhang, Wanwan Shi, Li Wang, Ying Zuo, Fei Guo, Jiawei Luo

{"title":"scMID: a Deep Multi-omics Integration Framework for Comprehensive Single-cell Data Analysis.","authors":"Qiu Xiao, Yan Zhang, Wanwan Shi, Li Wang, Ying Zuo, Fei Guo, Jiawei Luo","doi":"10.1109/TCBBIO.2025.3624040","DOIUrl":"https://doi.org/10.1109/TCBBIO.2025.3624040","url":null,"abstract":"Biological research on single cells has witnessed remarkable progress in recent years, with downstream analyses playing a crucial role in uncovering cellular functions and mechanisms. Traditional single-cell analyses, which predominantly rely on single-omics data such as single-cell RNA sequencing, are inherently limited. These methods can only capture one aspect of cellular information, overlooking the complex interplay between different molecular layers, and thus are prone to introducing biases in results. The advent of single cell multi-omics sequencing technologies has revolutionized this landscape. By enabling the integration of diverse molecular profiles, including transcriptomics, epigenomics, and proteomics, these technologies offer a more holistic view of cellular functions. However, existing integration methods often lack the ability to handle the complexity and heterogeneity of multi-omics data, limiting their application in in-depth single-cell studies. In this study, we propose an analysis method based on single-cell multi omics data integration and dropout pattern (scMID). Specifically, scMID utilizes omics-independent deep autoencoders for the alignment of multi-omics data, employs GCN algorithm for data integration, and calculates the gene importance by combining the gene similarity obtained from the binarized dropout pattern. Meanwhile, scMID proposes a dual-strategy for feature gene screening, aiming to identify genes with high biological significance that best match the structural characteristics of reference data. Experimental results demonstrate that scMID significantly improves the accuracy of single-cell clustering in downstream analyses, breaking through the limitations of traditional feature selection methods and providing a superior analytical framework for decoding complex biological information.","PeriodicalId":520987,"journal":{"name":"IEEE transactions on computational biology and bioinformatics","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145350896","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-omics Correlation Reconstruction of Complete Graph Forms Based on the Self-expressive Learning Network for Cancer Subtype Prediction. 基于自表达学习网络的完全图形式多组相关重构用于癌症亚型预测。

IEEE transactions on computational biology and bioinformatics Pub Date : 2025-10-20 DOI: 10.1109/TCBBIO.2025.3623308

Junran Zhao, Yueyi Cai, Shunfang Wang

{"title":"Multi-omics Correlation Reconstruction of Complete Graph Forms Based on the Self-expressive Learning Network for Cancer Subtype Prediction.","authors":"Junran Zhao, Yueyi Cai, Shunfang Wang","doi":"10.1109/TCBBIO.2025.3623308","DOIUrl":"https://doi.org/10.1109/TCBBIO.2025.3623308","url":null,"abstract":"Multi-omics cancer subtype prediction can identify cancer subtypes effectively and has the advantage of correlating genotype and phenotype. However, insufficient exploration of the correlation of information among different omics levels may lead to poor prediction of cancer subtypes. To address this issue, we propose a novel framework, termed Multi-Omics correlation reconstruction (MOCR), which performs reconstruction of complete graph forms based on a self-expressive learning network. Specifically, MOCR first employs autoencoders to unify the dimensions across different omics types. It then leverages parallel query and key networks (QKNets) to learn representations for each omics. These representations are passed into a correlation reconstruction module (CRModule), which computes self-expressive coefficients that jointly capture omics-self characteristics and inter-omics relationships. QKNets and CRModule form a correlative self-expressive learning network, enabling better utilization of the advantages of multi-omics. Importantly, the CRModule's complete graph reconstruction of omics correlations models each omics pair exactly once, thereby avoiding redundancy. Finally, spectral clustering is applied to derive cancer subtypes. We have evaluated our method on nine TCGA cancer datasets and three simulation datasets. The results showed that the MOCR had significant advantages in cancer subtype identification. The complete code is available at https://github.com/JerryZ09/MOCR.","PeriodicalId":520987,"journal":{"name":"IEEE transactions on computational biology and bioinformatics","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145338515","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Nearest Neighbor CCP-Based Molecular Sequence Analysis. 基于最近邻ccp的分子序列分析。

IEEE transactions on computational biology and bioinformatics Pub Date : 2025-10-15 DOI: 10.1109/TCBBIO.2025.3621138

Sarwan Ali, Prakash Chourasia, Bipin Koirala, Murray Patterson

{"title":"Nearest Neighbor CCP-Based Molecular Sequence Analysis.","authors":"Sarwan Ali, Prakash Chourasia, Bipin Koirala, Murray Patterson","doi":"10.1109/TCBBIO.2025.3621138","DOIUrl":"https://doi.org/10.1109/TCBBIO.2025.3621138","url":null,"abstract":"Molecular sequence analysis is crucial for understanding several biological processes, including protein-protein interactions, functional annotation, and disease classification. The large number of sequences and the inherently complicated nature of protein structures make it challenging to analyze such data. Finding patterns and enhancing subsequent research requires the use of dimensionality reduction and feature selection approaches. Recently, a method called Correlated Clustering and Projection (CCP) has been proposed as an effective method for biological sequencing data. The CCP technique remains computationally expensive, despite its effectiveness for sequence visualization. Furthermore, its utility for classifying molecular sequences is still uncertain. To solve these two problems, we present a Nearest-Neighbor Correlated Clustering and Projection (CCP-NN)-based technique for efficiently preprocessing molecular sequence data. To group related molecular sequences and produce representative supersequences, CCP makes use of sequence-to-sequence correlations. As opposed to conventional methods, CCP does not rely on matrix diagonalization, therefore, it can be applied to a range of machine-learning problems. We estimate the density map and compute the correlation using a nearest-neighbor search technique. We perform a molecular sequence classification using CCP and CCP-NN representations to assess the efficacy of our proposed approach. Our findings show that CCP-NN considerably improves the accuracy of the classification task and significantly outperforms CCP in terms of computational runtime.","PeriodicalId":520987,"journal":{"name":"IEEE transactions on computational biology and bioinformatics","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145305237","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

M²BA-MDA: A Multi-Modal Multi-View Bidirectional Attention Network for Microbe-Disease Association Prediction. M2BA-MDA：用于微生物-疾病关联预测的多模态多视图双向关注网络。

IEEE transactions on computational biology and bioinformatics Pub Date : 2025-10-13 DOI: 10.1109/TCBBIO.2025.3620892

Xuliang Guo, Xiangfei Zou, Huilian Xu, Jinsong Gu

{"title":"M2BA-MDA: A Multi-Modal Multi-View Bidirectional Attention Network for Microbe-Disease Association Prediction.","authors":"Xuliang Guo, Xiangfei Zou, Huilian Xu, Jinsong Gu","doi":"10.1109/TCBBIO.2025.3620892","DOIUrl":"https://doi.org/10.1109/TCBBIO.2025.3620892","url":null,"abstract":"Numerous studies have shown that microbes play vital roles in human health and disease. Identifying microbe-disease associations can aid in disease diagnosis, treatment, and prevention. However, traditional biological experiments are time-consuming and costly. Although various computational methods have been developed, accurate and efficient approaches remain limited due to single-source data, insufficient prior knowledge, and suboptimal model performance. This paper proposed M2BA-MDA, a deep learning framework based on multi-modal, multi-view, and bidirectional attention mechanism for predicting potential microbe-disease associations. Firstly, microbe and disease features are extracted using multiple similarity measures and fused for consistency. Secondly, to mitigate gradient vanishing and over-smoothing issues in deep graph attention networks, we propose a stable enhanced graph attention network (EGAT) module incorporating cross-layer connections to extract microbial and disease features from each perspective. Moreover, to more effectively capture the complex interactions between microbes and diseases, we introduce an interaction module based on a bidirectional attention mechanism. This module enhances the mutual dependencies between the two entities and generates their final embeddings. Finally, a deep neural network (DNN) classifier is employed to predict potential associations. Extensive experiments conducted on the HMDAD and DisBiome datasets demonstrate that M2BA-MDA consistently outperforms five state-of-the-art methods. Parameter analysis and ablation studies further confirm the robustness and sensitivity of the model. In addition, case studies validate its effectiveness in identifying disease-associated microbes.","PeriodicalId":520987,"journal":{"name":"IEEE transactions on computational biology and bioinformatics","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145288193","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

DualMarker: A multi-source fusion identification method for prognostic biomarkers of breast cancer based on dual-layer heterogeneous network. DualMarker：一种基于双层异构网络的乳腺癌预后生物标志物多源融合识别方法。

IEEE transactions on computational biology and bioinformatics Pub Date : 2025-10-13 DOI: 10.1109/TCBBIO.2025.3620890

Xingyi Li, Zhelin Zhao, Junming Li, Ju Xiang, Jialu Hu, Xuequn Shang

{"title":"DualMarker: A multi-source fusion identification method for prognostic biomarkers of breast cancer based on dual-layer heterogeneous network.","authors":"Xingyi Li, Zhelin Zhao, Junming Li, Ju Xiang, Jialu Hu, Xuequn Shang","doi":"10.1109/TCBBIO.2025.3620890","DOIUrl":"https://doi.org/10.1109/TCBBIO.2025.3620890","url":null,"abstract":"Breast cancer is a complex disease that arises from multiple factors, including genetics, age, and environmental factors. Prognosis prediction for breast cancer is a challenging task that urgently needs to be addressed. Prognostic biomarkers can aid in predicting clinical outcomes for breast cancer patients, and network-based approaches are frequently employed to identify such biomarkers. However, the accuracy of these approaches based on single source biological network is poor due to incomplete interactions of single biological network. Some network-based approaches that integrate multiple biological networks have not considered network denoising, which may lead to the accuracy of these approaches to be improved. We propose a multi-source fusion identification method named DualMarker for prognostic biomarkers of breast cancer. This method constructs a dual-layer heterogeneous network by integrating multiple biological sources. To decrease the negative effects of incomplete interactions in biological networks, we denoise the constructed network. The ranking of features is obtained by the network propagation algorithm and the initial scoring strategy. Compared with six other network-based methods, DualMarker shows the best performance in six breast cancer datasets. Moreover, we have also demonstrated that the biomarkers identified by DualMarker are of interpretability biologically and closely associated with breast cancer patients' prognosis.","PeriodicalId":520987,"journal":{"name":"IEEE transactions on computational biology and bioinformatics","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145288191","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

LMADCNV: A CNV Detection Method Based on Local Features and MAD for NGS Data. LMADCNV：一种基于局部特征和MAD的NGS数据CNV检测方法。

IEEE transactions on computational biology and bioinformatics Pub Date : 2025-10-13 DOI: 10.1109/TCBBIO.2025.3620990

Xiaojun Ge, Shaojie Cheng, Kang Liu, Kun Xie, Yang Guo

{"title":"LMADCNV: A CNV Detection Method Based on Local Features and MAD for NGS Data.","authors":"Xiaojun Ge, Shaojie Cheng, Kang Liu, Kun Xie, Yang Guo","doi":"10.1109/TCBBIO.2025.3620990","DOIUrl":"https://doi.org/10.1109/TCBBIO.2025.3620990","url":null,"abstract":"Copy number variations (CNVs) are a type of structural variation in the genome that impact gene dosage, with significant implications for both normal phenotypic variability and susceptibility to disease. The existing copy number variation detection methods have unstable sensitivity in data with different coverage depths, and cannot identify shorter copy number variation fragments. In this context, we introduce a new method called LMADCNV, specifically designed for detecting CNVs in single-sample data from next-generation sequencing (NGS). LMADCNV employs local features constructed via a cluster partitioning strategy, in conjunction with an anomaly scoring mechanism predicated on median absolute deviation, to facilitate the detection of CNVs. This innovative approach prudently leverages the positional correlation inherent in read depth (RD) data to achieve increased sensitivity without a significant loss in precision. Empirical validation through simulation and real-sample experiments confirms the superiority of LMADCNV over other seven CNV detection methods. LMADCNV not only offers a novel perspective for extracting local features but also shows promise as a robust and effective tool for CNV detection.","PeriodicalId":520987,"journal":{"name":"IEEE transactions on computational biology and bioinformatics","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145288192","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Hypergraph Convolutional Network with Explicit High-Order Interaction Information Extraction for Drug Repositioning. 基于显式高阶交互信息提取的超图卷积网络药物重新定位。

IEEE transactions on computational biology and bioinformatics Pub Date : 2025-10-08 DOI: 10.1109/TCBBIO.2025.3619038

Xiang Du, Xinliang Sun, Min Zeng, Wei Tan, Min Li

{"title":"A Hypergraph Convolutional Network with Explicit High-Order Interaction Information Extraction for Drug Repositioning.","authors":"Xiang Du, Xinliang Sun, Min Zeng, Wei Tan, Min Li","doi":"10.1109/TCBBIO.2025.3619038","DOIUrl":"https://doi.org/10.1109/TCBBIO.2025.3619038","url":null,"abstract":"Drug repositioning, a promising strategy in drug development, aims to identify new indications for existing drugs, reduce costs, and lower safety risks. Due to their unique advantages in modeling higher-order relations among nodes, hypergraphs and hypergraph neural networks (HGNN) have become increasingly popular in drug repositioning. However, most HGNN-based methods fail to account for the diverse relations generated during the convolution process and do not explicitly model high-order interactions, limiting their ability to capture high-order interaction information adequately. To address these limitations, we propose a hypergraph convolutional network with explicit high-order interaction extraction for drug repositioning, termed HGCNDR. Our model introduces a relation-aware hypergraph convolution operation to handle distinct relation types and an effective strategy using the Hadamard product to model high-order interactions among drugs and diseases, efficiently extracting the resulting high-order interaction information. Specifically, HGCNDR constructs two feature graphs and a hypergraph based on drug similarity features, disease similarity features, and drug-disease association networks. HGCNDR then employs graph convolutional networks to extract embeddings from the feature graphs, while using the relation-aware hypergraph convolution operation and the strategy to extract structural and high-order interaction information embeddings from the hypergraph. Additionally, to preserve the common semantics between the embeddings extracted from the feature graphs and the hypergraph, HGCNDR introduces a consistency constraint. The experimental results demonstrate that HGCNDR has competitive performance compared to several baseline methods. Moreover, case studies on Alzheimer's disease and Breast carcinoma confirm that HGCNDR is able to retrieve more actual drug-disease associations in the top prediction results.","PeriodicalId":520987,"journal":{"name":"IEEE transactions on computational biology and bioinformatics","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145254412","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Predicting Driver Genes from Multi-Omics Data Using Hierarchical Multi-Feature Synergy Model. 利用分层多特征协同模型从多组学数据预测驱动基因。

IEEE transactions on computational biology and bioinformatics Pub Date : 2025-10-08 DOI: 10.1109/TCBBIO.2025.3619158

Zhipeng Hu, Xiaoyan Kui, Canwei Liu, Shen Jiang, Min Zhang, Ziwei Zou, Beiji Zou

{"title":"Predicting Driver Genes from Multi-Omics Data Using Hierarchical Multi-Feature Synergy Model.","authors":"Zhipeng Hu, Xiaoyan Kui, Canwei Liu, Shen Jiang, Min Zhang, Ziwei Zou, Beiji Zou","doi":"10.1109/TCBBIO.2025.3619158","DOIUrl":"https://doi.org/10.1109/TCBBIO.2025.3619158","url":null,"abstract":"Cancer is an extremely complex disease, whose occurrence and development are influenced by a multitude of factors, among which the abnormal activity of cancer driver genes plays a crucial role in the pathological process. Identifying these genes allows researchers to understand pathogenic mechanisms and biological functions of cancer, facilitating the development of targeted therapies. Current methods for identifying driver genes often ignore the synergism among genes and the importance of features, thereby affecting identification accuracy. In this paper, we propose a cancer driver genes identification method called HMFS, which is based on the hierarchical multi-feature synergy model. Firstly, a hypergraph is constructed using Node2vec and K-means algorithm. By analyzing the topological feature and mutual exclusion degree of genes in each hyperedge, the Mutation Aggregation Coefficient is extracted. Then, based on the functional expression mechanism of genes, differential expression analysis is performed using miRNA and mRNA expression data. Finally, by analyzing the importance among features, the Hierarchical Multi-Feature Synergy is proposed for features fusion. In this paper, experiments are conducted on three real cancer datasets. Compared with seven representative methods, HMFS has the best performance on all evaluation indicators. HMFS source code can be obtained from https://github.com/DriverGene/HMFS.git.","PeriodicalId":520987,"journal":{"name":"IEEE transactions on computational biology and bioinformatics","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145254434","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

scTECTA: Asymmetric Deep Transfer Learning for Cross-Patient Tumor Microenvironment Single-Cell Annotation. scTECTA：跨患者肿瘤微环境单细胞注释的非对称深度迁移学习。

IEEE transactions on computational biology and bioinformatics Pub Date : 2025-10-07 DOI: 10.1109/TCBBIO.2025.3618727

Zi-Yi Zeng, Xi-Yue Cao, Yue-Chao Li, Hai-Ru You, Zhu-Hong You, Yu-An Huang

{"title":"scTECTA: Asymmetric Deep Transfer Learning for Cross-Patient Tumor Microenvironment Single-Cell Annotation.","authors":"Zi-Yi Zeng, Xi-Yue Cao, Yue-Chao Li, Hai-Ru You, Zhu-Hong You, Yu-An Huang","doi":"10.1109/TCBBIO.2025.3618727","DOIUrl":"https://doi.org/10.1109/TCBBIO.2025.3618727","url":null,"abstract":"Cellular heterogeneity and dynamic interactions within the tumor microenvironment are critical drivers of cancer initiation and progression. Single-cell RNA sequencing, with its high-resolution capabilities, has significantly advanced the study of cellular heterogeneity in the tumor microenvironment. However, existing single-cell annotation methods are limited by data sparsity, biological heterogeneity, and batch effects, which hinder their broader application in this context. To address this, we propose scTECTA, an innovative graph neural network-based method that employs transfer learning to seamlessly transfer celltype annotation knowledge from a well-annotated source domain to an unannotated target domain. This approach leverages graph domain adaptation, integrating novel asymmetric neural network architecture and domain-adversarial learning framework. By harnessing the generalization capabilities of graph convolutional network to correct distribution shifts and employing adversarial training to further align expression profiles across batches, scTECTA substantially enhances predictive precision and robustness. We performed a systematic evaluation across multiple datasets from diverse sources, encompassing six cancer types from 34 patients, to compare the cell-type classification performance of scTECTA against 10 benchmark methods. The results demonstrate that scTECTA markedly outperforms benchmark methods in cell-type classification and exhibits robust batcheffect correction, establishing it as an efficient and powerful tool for tumor microenvironment cell-type annotation. The scTECTA code is freely available on GitHub (https://github.com/TiffanyLab/scTECTA).","PeriodicalId":520987,"journal":{"name":"IEEE transactions on computational biology and bioinformatics","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145246335","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0