IEEE transactions on computational biology and bioinformatics最新文献_第7页

A Multi-Modal Framework for Phage-Host Interaction Prediction Using Multi-View Contrastive Learning. 基于多视角对比学习的噬菌体-宿主相互作用预测的多模态框架。

IEEE transactions on computational biology and bioinformatics Pub Date : 2026-09-01 DOI: 10.1109/TCBBIO.2026.3707293

Yue Huang, Song Jiang, Yuting Tan, Xianjun Shen, Weizhong Zhao

{"title":"A Multi-Modal Framework for Phage-Host Interaction Prediction Using Multi-View Contrastive Learning.","authors":"Yue Huang, Song Jiang, Yuting Tan, Xianjun Shen, Weizhong Zhao","doi":"10.1109/TCBBIO.2026.3707293","DOIUrl":"10.1109/TCBBIO.2026.3707293","url":null,"abstract":"Phage therapy is emerging as a promising strategy to combat the growing challenge of antibiotic resistance. The efficacy of this therapeutic approach critically depends on the precise prediction of phage-host interactions (PHI). However, existing computational methods exhibit notable limitations in multi-source bioinformatics data integration and heterogeneous network representation. To address these limitations, we propose MCL-PHI, a novel framework that achieves high-precision prediction by integrating multi-modal features with multi-view contrastive learning. Specifically, a Large Language Model (LLM) utilizing Chain-of-Thought reasoning is employed to generate structured knowledge descriptions. These descriptions are subsequently encoded by BioBERT to yield domain-enhanced semantic representations, which are then fused with genomic features to construct a comprehensive heterogeneous network. Furthermore, the core of our framework is a multi-view graph neural network that captures both local topology and high-order meta-path semantics, reinforced by a contrastive learning strategy to maximize representational consistency. Finally, an adaptive multi-head attention mechanism fuses these representations for link prediction. Extensive experiments demonstrate that MCL-PHI significantly outperforms six state-of-the-art baseline methods. Ablation studies and case analyses further validate the efficacy of individual modules and the framework's potential in discovering novel PHIs.","PeriodicalId":520987,"journal":{"name":"IEEE transactions on computational biology and bioinformatics","volume":"PP ","pages":"1904-1915"},"PeriodicalIF":0.0,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148335682","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

Decoding Gene-Disease Associations With Computational Methods: A Survey. 用计算方法解码基因-疾病关联：一项调查。

IEEE transactions on computational biology and bioinformatics Pub Date : 2026-09-01 DOI: 10.1109/TCBBIO.2026.3707525

Yupeng Zhai, Mengjing Li, Lei Yu, Xiao Wang, Shi Luo, Linyao Yang

{"title":"Decoding Gene-Disease Associations With Computational Methods: A Survey.","authors":"Yupeng Zhai, Mengjing Li, Lei Yu, Xiao Wang, Shi Luo, Linyao Yang","doi":"10.1109/TCBBIO.2026.3707525","DOIUrl":"10.1109/TCBBIO.2026.3707525","url":null,"abstract":"Identifying gene-disease associations (GDAs) remains a fundamental challenge in biomedical research due to the enormous combinatorial space of candidate gene-disease pairs and the limited scalability of experimental validation. As wet-lab studies cannot keep pace with rapidly expanding omics data, computational approaches have become essential for prioritizing plausible GDAs and accelerating biological discovery. Recent advances in artificial intelligence (AI), particularly graph neural networks (GNNs) and large language models (LLMs), are transforming this field by enabling richer biological representations and more accurate predictive modeling. In this survey, we provide a unified and up-to-date overview of AI-driven GDA prediction. We first summarize major public resources containing gene, disease, and auxiliary biological information that underpin computational studies. We then review methodological developments ranging from traditional network-based methods to machine learning, deep learning, and the emerging integration of GNNs and LLMs, which has received limited attention in previous GDA-focused surveys. Representative applications in gene prioritization, drug repurposing, and clinical research are also discussed to demonstrate the practical impact of these approaches. Finally, we outline current challenges and promising future directions. By integrating data resources, methodological advances, and translational applications, this survey provides a comprehensive overview of modern AI techniques for GDA prediction and aims to support the development of more robust, interpretable, and clinically actionable computational tools.","PeriodicalId":520987,"journal":{"name":"IEEE transactions on computational biology and bioinformatics","volume":"PP ","pages":"1846-1865"},"PeriodicalIF":0.0,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148335696","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 Knowledge Graph-Driven Multimodal Framework for Drug-Disease Association Prediction. 知识图驱动的药物-疾病关联预测多模式框架。

IEEE transactions on computational biology and bioinformatics Pub Date : 2026-09-01 DOI: 10.1109/TCBBIO.2026.3724872

Qichang Zhao, Qiao Ling, Muhammad Habibulla Alamin, Pengcheng Shu, Yuqi Hong, Jianxin Wang

{"title":"A Knowledge Graph-Driven Multimodal Framework for Drug-Disease Association Prediction.","authors":"Qichang Zhao, Qiao Ling, Muhammad Habibulla Alamin, Pengcheng Shu, Yuqi Hong, Jianxin Wang","doi":"10.1109/TCBBIO.2026.3724872","DOIUrl":"10.1109/TCBBIO.2026.3724872","url":null,"abstract":"Drug repurposing represents a cost-effective strategy to identify novel therapeutic applications for existing pharmaceuticals, circumventing the protracted timelines of traditional drug discovery. While knowledge graph (KG) based methods excel at integrating heterogeneous biomedical data, they often struggle to harmonize high-level domain knowledge with fine-grained molecular mechanisms. We propose KGDDA, a multimodal framework designed for drug-disease association prediction that synergistically integrates KGs with medical ontologies. By leveraging an attention-driven fusion mechanism, KGDDA dynamically merges contextual topological embeddings with ontology-derived priors, enabling the adaptive capture of intricate drug-disease interactions. Extensive evaluations on two benchmark datasets demonstrate that KGDDA consistently outperforms state-of-the-art baselines in both predictive accuracy and generalization. Furthermore, case studies on head and neck cancer and small cell lung cancer validate KGDDA's ability to provide actionable mechanistic insights, highlighting its potential to accelerate therapeutic discovery and precision medicine.","PeriodicalId":520987,"journal":{"name":"IEEE transactions on computational biology and bioinformatics","volume":"PP ","pages":"2257-2268"},"PeriodicalIF":0.0,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148805499","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

scGFormer: A Multi-Scale Graph-Transformer for Cell Type Annotation in Single-Cell RNA Sequencing. scGFormer：用于单细胞RNA测序中细胞类型注释的多尺度图形转换器。

IEEE transactions on computational biology and bioinformatics Pub Date : 2026-09-01 DOI: 10.1109/TCBBIO.2026.3730687

Zijian Yuan, Hongwei Zhang, Cheng Liu, Song Zhang, Yong Liu, Liyun Tu

{"title":"scGFormer: A Multi-Scale Graph-Transformer for Cell Type Annotation in Single-Cell RNA Sequencing.","authors":"Zijian Yuan, Hongwei Zhang, Cheng Liu, Song Zhang, Yong Liu, Liyun Tu","doi":"10.1109/TCBBIO.2026.3730687","DOIUrl":"10.1109/TCBBIO.2026.3730687","url":null,"abstract":"Despite the rapid progress of single-cell RNA sequencing (scRNA-seq), accurate cell type annotation remains a major challenge. Existing approaches often struggle with sparse and heterogeneous expression profiles, insufficient gene-level modeling, and complications such as zero inflation and class imbalance. To address these issues, we propose scGFormer (Single-cell Multi-scale Graph Transformer), a unified framework that integrates: (i) Performer-based Global Attention (PGA) to capture long-range dependencies, (ii) Graph-based Local Attention (GLA) to model neighborhood structures, and (iii) a Squeeze-and-Excitation Gene Reweighting module (GeneSE) to enhance gene-level representations. Furthermore, scGFormer is equipped with a biology-guided adaptive contrastive learning strategy, which is designed to account for zero inflation, balance class distributions, and refine dynamic graphs during training, thereby facilitating robustness and adaptability. By explicitly modeling both global and local dependencies while strengthening gene-level representations, scGFormer achieves improved robustness and generalization. Extensive experiments across public datasets demonstrate that scGFormer achieves competitive or superior performance compared with state-of-the-art methods, offering a robust solution for single-cell annotation across diverse datasets and species.","PeriodicalId":520987,"journal":{"name":"IEEE transactions on computational biology and bioinformatics","volume":"PP ","pages":"2324-2333"},"PeriodicalIF":0.0,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148890124","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

Parameter Efficient Deep Learning Models for Multi-Target Binding Affinity and hERG Cardiotoxicity Prediction. 多靶点结合亲和力和hERG心脏毒性预测的参数高效深度学习模型。

IEEE transactions on computational biology and bioinformatics Pub Date : 2026-09-01 DOI: 10.1109/TCBBIO.2026.3705951

Fairuz Shadmani Shishir, Bishnu Sarker, Cuncong Zhong, Sumaiya Shomaji

{"title":"Parameter Efficient Deep Learning Models for Multi-Target Binding Affinity and hERG Cardiotoxicity Prediction.","authors":"Fairuz Shadmani Shishir, Bishnu Sarker, Cuncong Zhong, Sumaiya Shomaji","doi":"10.1109/TCBBIO.2026.3705951","DOIUrl":"10.1109/TCBBIO.2026.3705951","url":null,"abstract":"Accurately predicting binding affinity and toxicity is critical to drug discovery, offering the potential to reduce development costs and enhance safety profiles. Traditional computational methods, such as molecular docking and quantitative structure-activity relationship (QSAR) models, rely heavily on handcrafted features and domain expertise, limiting their scalability and generalizability to novel compounds. Recent advances in chemical language models (CLMs), which leverage Simplified Molecular Input Line Entry System (SMILES) representations, offer a scalable alternative by capturing complex molecular properties through learned representations. In this study, we propose a dual-paradigm framework for binding affinity prediction of 3 protein targets and cardiotoxicity for human ether-à-go-go related gene (hERG). The first component utilizes a specialized graph neural network (GNN) that operates directly on molecular graphs, treating atoms as nodes and bonds as edges. The second component employs a CLM fine-tuned via Low-Rank Adaptation (LoRA), enabling efficient adaptation of large pre-trained models to specific toxicological tasks with minimal parameter overhead. Our hybrid framework demonstrates superior performance, achieving an average AUROC of 0.92 across three protein targets, while the LoRA-adapted CLM attains an AUROC of 0.93 for cardiotoxicity prediction, offering a 98% reduction in trainable parameters, outperforming the performance of existing models.","PeriodicalId":520987,"journal":{"name":"IEEE transactions on computational biology and bioinformatics","volume":"PP ","pages":"1866-1878"},"PeriodicalIF":0.0,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148304578","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

D2Sim: A Computational Simulator for Nanopore Sequencing Based DNA Data Storage. D2Sim：基于纳米孔测序的DNA数据存储计算模拟器。

IEEE transactions on computational biology and bioinformatics Pub Date : 2026-09-01 DOI: 10.1109/TCBBIO.2026.3716589

Subhasiny Sankar, Yixin Wang, Md Noor-A-Rahim, Erry Gunawan, Yong Liang Guan, Chueh Loo Poh

{"title":"D2Sim: A Computational Simulator for Nanopore Sequencing Based DNA Data Storage.","authors":"Subhasiny Sankar, Yixin Wang, Md Noor-A-Rahim, Erry Gunawan, Yong Liang Guan, Chueh Loo Poh","doi":"10.1109/TCBBIO.2026.3716589","DOIUrl":"10.1109/TCBBIO.2026.3716589","url":null,"abstract":"DNA data storage has gained significant attention because of its high storage density and durability. However, errors during the storage and reading processes compromise data integrity, prompting research into error correction strategies. Researchers have explored physical (data copies) and logical redundancy (added redundancy in error-correcting codes) to mitigate errors. Evaluating these designs and reconstruction methods typically involves time-consuming and costly trials. To streamline this process, we designed a computational channel simulator, namely D2Sim, for Nanopore sequencing-based DNA data storage. This simulator mimics real experiments, generating data with certain redundancy and errors at the receiver. Integrated with DeepSimulator, D2Sim outputs signals closely resembling actual signals of Nanopore-based DNA storage. Comparative analysis reveals that the proposed simulator yields 16.7% to 88.7% lower sample difference deviations than signals from DeepSimulator alone. This cost-effective and time-efficient tool facilitates the assessment of physical and logical redundancy for data reconstruction in DNA data storage without the need for real-time experiments.","PeriodicalId":520987,"journal":{"name":"IEEE transactions on computational biology and bioinformatics","volume":"PP ","pages":"2091-2102"},"PeriodicalIF":0.0,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148582139","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

HDGGCN: Heterogeneous Disease-Gene Network Representation Learning Using Similarity-Based Adjacency Matrix Generation. 基于相似度邻接矩阵生成的异质疾病基因网络表示学习。

IEEE transactions on computational biology and bioinformatics Pub Date : 2026-09-01 DOI: 10.1109/TCBBIO.2026.3721748

Mengyuan Jin, Yin Zhang, Jia Liu, Rui Xiao, Fang Hu

{"title":"HDGGCN: Heterogeneous Disease-Gene Network Representation Learning Using Similarity-Based Adjacency Matrix Generation.","authors":"Mengyuan Jin, Yin Zhang, Jia Liu, Rui Xiao, Fang Hu","doi":"10.1109/TCBBIO.2026.3721748","DOIUrl":"10.1109/TCBBIO.2026.3721748","url":null,"abstract":"The discovery of disease-related genes is crucial for understanding disease mechanisms, which can effectively improve clinical diagnosis and treatment and ultimately realize precision medicine. However, due to the sparse and complex characteristics of bioinformatics data, it is difficult to fuse multiple-source information and extract the features of high-dimensional sparse data to achieve satisfactory prediction performance. In this paper, we propose a heterogeneous disease-gene network representation using similarity-based adjacency matrix generation (HDGGCN) to realize disease-gene prediction. First, we present a cosine similarity-based adjacency matrix generation strategy to reconstruct the disease-gene-GO heterogeneous network. Then, the reconstructed adjacency matrices and the feature matrices are taken as the inputs of the graph convolutional neural network (GCN), and the low-dimensional node representations will be generated. Finally, a novel data partitioning mechanism is presented to achieve high-performance prediction. The HDGGCN algorithm's effectiveness has been verified by four representative evaluation metrics, including Precision, Recall, F1-score, and Association Precision (AP). Specifically, compared to state-of-the-art baseline models, HDGGCN yields minimum performance improvements of $1.0%-2.4%$ in Precision, $0.6%-1.2%$ in Recall, and $1.0%-1.3%$ in F1-score across TOP-5 to TOP-20 cutoffs, alongside at least a 3.0% increase in AP.","PeriodicalId":520987,"journal":{"name":"IEEE transactions on computational biology and bioinformatics","volume":"PP ","pages":"2126-2139"},"PeriodicalIF":0.0,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148690736","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 Denoising Adversarial Model Based on Hyperellipsoidal Knowledge Representation Learning for DTI Prediction. 基于超椭球体知识表示学习的DTI预测去噪对抗模型。

IEEE transactions on computational biology and bioinformatics Pub Date : 2026-09-01 DOI: 10.1109/TCBBIO.2026.3710670

Chunming Yang, Fang Xiong, Yue Luo, Fangying Wang

{"title":"A Denoising Adversarial Model Based on Hyperellipsoidal Knowledge Representation Learning for DTI Prediction.","authors":"Chunming Yang, Fang Xiong, Yue Luo, Fangying Wang","doi":"10.1109/TCBBIO.2026.3710670","DOIUrl":"10.1109/TCBBIO.2026.3710670","url":null,"abstract":"The prediction of drug-target interactions (DTI) is of critical importance in the field of drug discovery. Knowledge representation learning is commonly used to embed high-dimensional, sparse drug knowledge graphs into low-dimensional, dense vector spaces. Existing methods primarily rely on node features of drug knowledge graphs, which often neglect inherent biases introduced by network characteristics, such as noise, long-tail distribution, data sparsity, and complex relations (1-N, N-1, N-N). This oversight leads to incomplete semantic representation of knowledge graphs during the embedding process, thereby resulting in suboptimal DTI prediction performance. To address these challenges, we propose a novel model termed DAH-DTI, which comprises four components: knowledge graph denoising, high-quality negative sample generation, hyperellipsoid knowledge graph embedding based on Mahalanobis distance, and DTI link prediction. Specifically, the knowledge graph is first denoised to filter out noisy triples and obtain a high-quality gold dataset. Subsequently, adversarial negative sampling is incorporated during pre-training to moderately expand the number of triples. Next, the tail entities of the triples are embedded into a predefined hyperellipsoid for model training. Finally, the trained model is applied to all potential unknown drug-target pairs through link prediction to predict potential DTIs. Experimental results demonstrate that by effectively addressing challenges including data noise, long-tail distribution, data sparsity, and complex relations. The DAH-DTI achieves significant improvements in ACCU, REC, MRR, and Hit@10 on a multi-level phenotype-drug-molecular knowledge graph. Furthermore, molecular docking simulations validate the reliability of DAH-DTI predictions for DTI involving the AR target. In summary, DAH-DTI provides a promising approach to mitigate inherent biases caused by network characteristics and accurately predict potential drug-target interactions.","PeriodicalId":520987,"journal":{"name":"IEEE transactions on computational biology and bioinformatics","volume":"PP ","pages":"1955-1966"},"PeriodicalIF":0.0,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148400504","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

Cell Type-Specific Isoform Function Prediction by Multiplex Heterogeneous Network. 基于多重异构网络的细胞类型特异性异构体功能预测。

IEEE transactions on computational biology and bioinformatics Pub Date : 2026-09-01 DOI: 10.1109/TCBBIO.2026.3728504

Tong Gu, Hanwen Luo, Yuequn Wang, Mengzhu Wang, Jun Wang, Zhongmin Yan, Guoxian Yu

{"title":"Cell Type-Specific Isoform Function Prediction by Multiplex Heterogeneous Network.","authors":"Tong Gu, Hanwen Luo, Yuequn Wang, Mengzhu Wang, Jun Wang, Zhongmin Yan, Guoxian Yu","doi":"10.1109/TCBBIO.2026.3728504","DOIUrl":"10.1109/TCBBIO.2026.3728504","url":null,"abstract":"Alternatively spliced isoforms from the same gene can perform distinct functions; however, their cell-type-specific roles remain largely uncharacterized, limiting our ability to understand cellular diversity and development beyond traditional gene-level analyses. We present cIsoFun, a multi-modal fusion framework for cell-type-specific isoform function prediction from single-cell transcriptomics data. cIsoFun leverages pre-trained ESM-2 and BERT models to extract initial sequence features, constructs a multiplex heterogeneous network over genes, isoforms, GO terms, and cell types to represent their complex relationships, and applies relation-aware attention to integrate multi-modal information and refine node embeddings. It then optimizes a multi-component loss on the updated embeddings to predict isoform functions, enabling biological interpretability via sequence-importance and cell-type-specific analyses. Experiments demonstrate that cIsoFun outperforms existing methods, particularly for sparse GO terms, and reveal distinct functional programs across contexts: kidney tumor cells are enriched for metabolism and growth regulation, skin tumor cells emphasize immune surveillance and migration, and cell lines prioritize DNA repair and telomere maintenance. Sequence-importance analysis highlights critical amino-acid regions and shows that domains annotated with the same function can exhibit distinct importance profiles across spliced isoforms. Together, these results provide new insights into cell-type-specific isoform functionality and establish cIsoFun as a practical tool for single-cell isoform analysis.","PeriodicalId":520987,"journal":{"name":"IEEE transactions on computational biology and bioinformatics","volume":"PP ","pages":"2269-2280"},"PeriodicalIF":0.0,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148852337","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-view Graph Learning Framework with Spectral Encoding and Sparse Cross-Attention for miRNA-Drug Association Prediction. 基于谱编码和稀疏交叉关注的多视图图学习框架用于mirna -药物关联预测。

IEEE transactions on computational biology and bioinformatics Pub Date : 2026-09-01 DOI: 10.1109/TCBBIO.2026.3729865

Ru Nie, Ying Fu, Zhengwei Li, Lei Wang, Zhanguo Xia, Yujun Zhao

{"title":"Multi-view Graph Learning Framework with Spectral Encoding and Sparse Cross-Attention for miRNA-Drug Association Prediction.","authors":"Ru Nie, Ying Fu, Zhengwei Li, Lei Wang, Zhanguo Xia, Yujun Zhao","doi":"10.1109/TCBBIO.2026.3729865","DOIUrl":"10.1109/TCBBIO.2026.3729865","url":null,"abstract":"Chemoresistance is a major contributor to cancer treatment failure, and microRNAs (miRNAs) play a critical role in mediating this resistance by regulating gene expression. Therefore, identifying miRNA-drug associations is of great significance for advancing cancer therapy. However, existing computational models face significant challenges, including heterogeneous feature integration and data sparsity. To overcome these limitations, we propose a novel Multi-view Graph Learning Framework with Spectral Encoding and Sparse Cross-Attention (MVGSCA) for predicting miRNA-drug associations. The model constructs node features based on miRNA sequence similarity and drug SMILES similarity. Then it builds two distinct graphs: a gene-mediated functional graph from miRNA-drug target interactions and an association-guided structural graph from known miRNA-drug associations. These two graphs are linearly combined to produce a collaborative feature representation. To capture both local and global topological features, the model applies local power filtering and global heat kernel diffusion, followed by spectral encoding via Poisson-Charlier polynomial approximation to enhance the feature representation. Furthermore, a sparse cross-attention mechanism is introduced to dynamically weight and integrate heterogeneous features from multiple sources. On a benchmark dataset with 8,720 associations, MVGSCA achieves an AUC of 96.32% and an AUPR of 95.69% under five-fold cross-validation, significantly outperforming six state-of-the-art methods. Experimental results show that MVGSCA effectively integrates heterogeneous biological information and achieves superior prediction performance, offering valuable insights into cancer resistance mechanisms and supporting drug discovery efforts.","PeriodicalId":520987,"journal":{"name":"IEEE transactions on computational biology and bioinformatics","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148877116","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