IEEE transactions on computational biology and bioinformatics最新文献_第2页

SOC-DGL: Social Interaction Behavior Inspired Dual Graph Learning Framework for Drug-Target Interaction Identification. 社会互动行为启发的药物-靶标相互作用识别对偶图学习框架。

IEEE transactions on computational biology and bioinformatics Pub Date : 2026-10-13 DOI: 10.1109/TCBBIO.2026.3742812

Xiang Zhao, Ruijie Li, Qiao Ning, Shikai Guo, Hui Li, Qian Ma

{"title":"SOC-DGL: Social Interaction Behavior Inspired Dual Graph Learning Framework for Drug-Target Interaction Identification.","authors":"Xiang Zhao, Ruijie Li, Qiao Ning, Shikai Guo, Hui Li, Qian Ma","doi":"10.1109/TCBBIO.2026.3742812","DOIUrl":"https://doi.org/10.1109/TCBBIO.2026.3742812","url":null,"abstract":"The identification of drug-target interactions (DTI) is critical for drug discovery and repositioning, as it reveals potential therapeutic uses of existing drugs, accelerating development and reducing costs. However, most existing models focus only on direct similarity in homogeneous graphs, failing to exploit the rich similarity in heterogeneous graphs. To address this gap, inspired by real-world social interaction behaviors, we propose SOC-DGL, which comprises two specialized modules: the Affinity-Driven Graph Learning (ADGL) module, learning global similarity through an affinity-enhanced drug-target graph, and the Equilibrium-Driven Graph Learning (EDGL) module, capturing higher-order similarity by amplifying the influence of even-hop neighbors using an even-polynomial graph filter based on balance theory. This dual approach enables SOC-DGL to effectively capture similarity information across multiple interaction scales within affinity and association matrices. To address the issue of imbalance in DTI datasets, we propose an adjustable Reweighted Loss Function (RLF) that moderates the positive-class compensation weight in weighted binary cross-entropy through an adjustable parameter. Experiments on four benchmark datasets show that SOC-DGL achieves competitive performance under both balanced and imbalanced settings. Moreover, SOC-DGL predicts the top 9 drugs known to bind ABL1, and further analyzes the 10th-ranked drug, which has not been experimentally confirmed to interact with ABL1, providing supporting evidence for its potential binding. The source code is available for academic purposes at https://github.com/Zhaoxiang0422/SOC-DGL.","PeriodicalId":520987,"journal":{"name":"IEEE transactions on computational biology and bioinformatics","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149187618","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

GraphSurv: A Graph-Based Framework for Dynamic Survival Analysis With Longitudinal Data. GraphSurv：一个基于图形的纵向数据动态生存分析框架。

IEEE transactions on computational biology and bioinformatics Pub Date : 2026-10-12 DOI: 10.1109/TCBBIO.2026.3741569

Junbei Zhang, Xuejing Zhao

{"title":"GraphSurv: A Graph-Based Framework for Dynamic Survival Analysis With Longitudinal Data.","authors":"Junbei Zhang, Xuejing Zhao","doi":"10.1109/TCBBIO.2026.3741569","DOIUrl":"10.1109/TCBBIO.2026.3741569","url":null,"abstract":"Dynamic survival analysis in longitudinal biomedical studies updates individualized event-risk estimates as repeated clinical measurements accumulate. These data are often irregularly sampled, multivariate, and incomplete, requiring models to capture both temporal dependencies across visits and cross-variable dependencies within visits. To address these challenges, we propose GraphSurv, a graph-based framework that represents longitudinal histories through visit-level temporal states and variable-specific representations. Bidirectional message passing and explicit inter-visit interval encoding jointly capture cross-variable and temporal dependencies, and the learned representations are used for discrete-time hazard modeling and dynamic survival prediction. Experiments on real-world longitudinal survival datasets show competitive performance across discrimination and calibration metrics, with the most consistent improvements in time-dependent discrimination. Landmark evaluations further demonstrate adaptive risk updating as follow-up information accrues. SHAP-based interpretation of the predicted risk scores also indicates that the proposed framework can reveal clinically meaningful and time-varying feature contributions to risk prediction.","PeriodicalId":520987,"journal":{"name":"IEEE transactions on computational biology and bioinformatics","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149166317","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

scHCL-SDA: A Homophily-Aware Contrastive Learning with Spectral Distribution Alignment for scRNA-seq Data Clustering. scHCL-SDA：基于谱分布对齐的scRNA-seq数据聚类的同源性感知对比学习。

IEEE transactions on computational biology and bioinformatics Pub Date : 2026-10-09 DOI: 10.1109/TCBBIO.2026.3742164

Rong Dong, Zhenqiu Shu, Yun Bai, Kaiwen Tan, Hongbin Wang

{"title":"scHCL-SDA: A Homophily-Aware Contrastive Learning with Spectral Distribution Alignment for scRNA-seq Data Clustering.","authors":"Rong Dong, Zhenqiu Shu, Yun Bai, Kaiwen Tan, Hongbin Wang","doi":"10.1109/TCBBIO.2026.3742164","DOIUrl":"10.1109/TCBBIO.2026.3742164","url":null,"abstract":"Graph contrastive learning has recently shown strong potential for single-cell RNA sequencing (scRNA-seq) data clustering via modeling pairwise cell relationships. Nevertheless, most of them rely on the homophily assumption, which posits that adjacent cells in the graph share similar biological identities. This assumption, however, frequently fails in practical scRNA-seq datasets owing to complex heterogeneous cellular architectures. Such heterogeneity can lead to erroneous connections in low-homophily neighborhoods, thereby resulting in suboptimal clustering performance. To address this issue, we propose a homophily-aware contrastive learning with spectral distribution alignment (scHCL-SDA) for clustering scRNA-seq data. Specifically, the proposed scHCL-SDA method constructs an expression view from the original gene expression matrix and generates a graph-filteblue augmentation view through graph-guided multi-round noise filtering. Then, a spectral distribution alignment mechanism is introduced to address the cross-view distribution shift problem and thus enhance representation consistency of multi-view scRNA-seq data. To blueuce the interference caused by false negative samples during training, it employs Debiased InfoNCE contrastive learning and then designs a progressive fusion strategy to achieve smooth multi-view feature fusion and deep semantic interactions. Furthermore, we introduce an adaptive homophily-aware consistency contrastive learning mechanism to dynamically construct reliable neighborhoods, thereby effectively blueucing structural noise in low-homophily graphs. Comparative experiments on real datasets show the effectiveness of the proposed scHCL-SDA method in scRNA-seq data clustering. The source code for this work is available at: https://github.com/szq0816/scHCL-SDA.","PeriodicalId":520987,"journal":{"name":"IEEE transactions on computational biology and bioinformatics","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149149559","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

SSL-InsNet: A Sequence Structured Labeling Framework for Large-Scale Genomic Insertion Detection Leveraging Time-Distributed Dual Transformer. SSL-InsNet：利用时间分布双变压器进行大规模基因组插入检测的序列结构化标记框架。

IEEE transactions on computational biology and bioinformatics Pub Date : 2026-10-09 DOI: 10.1109/TCBBIO.2026.3742332

Chunxiao Lai, Bo Han, Chong Cheng, Jing Peng, Xiaohui Yuan

{"title":"SSL-InsNet: A Sequence Structured Labeling Framework for Large-Scale Genomic Insertion Detection Leveraging Time-Distributed Dual Transformer.","authors":"Chunxiao Lai, Bo Han, Chong Cheng, Jing Peng, Xiaohui Yuan","doi":"10.1109/TCBBIO.2026.3742332","DOIUrl":"10.1109/TCBBIO.2026.3742332","url":null,"abstract":"Genomic structural variations (SVs) are pivotal in pathogenesis, yet existing methods often fail to maintain structural consistency for ultra-long variants spanning extensive intervals. In this paper, we propose SSL-InsNet, a novel sequence structured labeling framework that reformulates large-scale genomic insertion detection as a structured tagging task. Within a dual-transformer architecture, we develop a Multi-level Spatial Perception (MSP) module that integrates a Spatial Transformer (S-Trans) with deep convolutions via a hierarchical attention mechanism to simultaneously resolve micro-scale breakpoint motifs and regional genomic contexts. To suppress alignment artifacts, a Confidence-gated Feature Integration (CFI) module is introduced to adaptively fuse these heterogeneous spatial features based on learnable descriptors. Concurrently, a Time-distributed Transformer (T Trans) models macro-scale long-distance dependencies along the temporal axis across consecutive segments, ensuring global structural coherence. To optimize the sequential tags, we propose the Neighborhood-Weighted Focal Loss (NWFL) to explicitly enforce biological spatial continuity and penalize frag mented predictions. Comprehensive benchmarking on multiple long-read sequencing datasets demonstrates that SSL-InsNet consistently achieves state-of-the-art performance. Notably, for large-scale insertions, our framework effectively mitigates signal fragmentation and yields a superior balance between precision and recall, outperforming competitive deep learning baselines by a significant margin.","PeriodicalId":520987,"journal":{"name":"IEEE transactions on computational biology and bioinformatics","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149149219","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

StructAMP: A Residual Multi-Modal Framework for Leakage-Controlled Antimicrobial Peptide Prediction. StructAMP：泄漏控制抗菌肽预测的残余多模态框架。

IEEE transactions on computational biology and bioinformatics Pub Date : 2026-10-09 DOI: 10.1109/TCBBIO.2026.3741949

Mingjian Zhang, Guodong Li, Ying Chang, Dongxu Li, Ziwen Cui, Yue Yang, Hengchuang Yin, Lun Hu

{"title":"StructAMP: A Residual Multi-Modal Framework for Leakage-Controlled Antimicrobial Peptide Prediction.","authors":"Mingjian Zhang, Guodong Li, Ying Chang, Dongxu Li, Ziwen Cui, Yue Yang, Hengchuang Yin, Lun Hu","doi":"10.1109/TCBBIO.2026.3741949","DOIUrl":"10.1109/TCBBIO.2026.3741949","url":null,"abstract":"Reliable evaluation of antimicrobial peptide (AMP) predictors is complicated by train-test sequence-similarity leakage and mismatched comparisons with strong protein language model baselines. We present a leakage-controlled framework that quantifies auxiliary-modality value through zero-initialized residual corrections to a frozen, fold-matched ESM2-650 M predictor. StructAMP combines GVP-encoded ESMFold geometry, 457 physicochemical descriptors, and Label-Wise Attention. Five shared homology-grouped folds were constructed from 21,094 internal peptides; independent fold-specific filtering at 40% identity and 80% bidirectional coverage retained 14,456 test peptides. An analogously filtered external cohort retained 3,135 peptides. Internally, StructAMP achieved an AUC of $0.9227pm 0.0125$, an MCC of $0.7335pm 0.0325$, and an AMP-only Macro-F1 of $0.6220pm 0.0114$. It did not significantly improve binary discrimination over sequence-only and produced a statistically significant but negligible Macro-F1 reduction of 0.0026. Across uncertainty, perturbation, external, and ablation analyses, pretrained sequence information supplied most predictive signal. StructAMP therefore provides a matched framework for evaluating incremental multimodal value rather than evidence that additional modalities necessarily improve AMP prediction. Conclusions are limited to ESM2-650 M, the tested static ESMFold/GVP representations and descriptors, and frozen-sequence residual training; they do not imply that three-dimensional peptide structure is generally uninformative.","PeriodicalId":520987,"journal":{"name":"IEEE transactions on computational biology and bioinformatics","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149148825","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

CellCom2: An Integrated Web Platform for Flexible Prediction and Visualization Analysis of Cell-cell Communication. CellCom2：一个用于灵活预测和可视化分析细胞-细胞通信的集成Web平台。

IEEE transactions on computational biology and bioinformatics Pub Date : 2026-10-08 DOI: 10.1109/TCBBIO.2026.3741541

Jianing Wang, Jin A, Guohang He, Hanjun Pan, Ruiqing Zheng, Chaojin Wu, Min Li

{"title":"CellCom2: An Integrated Web Platform for Flexible Prediction and Visualization Analysis of Cell-cell Communication.","authors":"Jianing Wang, Jin A, Guohang He, Hanjun Pan, Ruiqing Zheng, Chaojin Wu, Min Li","doi":"10.1109/TCBBIO.2026.3741541","DOIUrl":"https://doi.org/10.1109/TCBBIO.2026.3741541","url":null,"abstract":"Cell-cell communication across diverse cell types and tissues underlies proper organismal function and is primarily mediated by interactions between secreted ligands and cell-surface receptors. Understanding these molecular interactions is essential for elucidating regulatory networks governing physiological and pathological processes and for identifying potential therapeutic targets. Although several computational tools have been developed for inferring intercellular communication, many existing methods require substantial programming expertise, rely on restricted or method-specific biological resources, and provide limited result visualization. To overcome these limitations, we developed CellCom2, an upgraded version of CellCom, a user-friendly web platform for the prediction and visualization analysis of ligand-receptor-mediated intercellular communication. CellCom2 integrates a comprehensive collection of prior biological knowledge, including ligand-receptor, receptor-transcription factor, and transcription factor-target gene interactions, together with a suite of state-of-the-art prediction algorithms. The platform allows flexible, user-defined combinations of biological resources and computational methods to accommodate diverse analysis scenarios. To reconcile results from different methods, CellCom2 implements a principled consensus integration strategy that assigns adaptive weights to quantify inter-method agreement and produce robust communication scores. In addition, CellCom2 provides systematic and multiscale visualization to facilitate the interpretation of intercellular communication patterns. Validation on multiple scRNA-seq and spatial transcriptomics datasets demonstrates that CellCom2 enhances the reliability, interpretability, and reproducibility of intercellular communication inference.","PeriodicalId":520987,"journal":{"name":"IEEE transactions on computational biology and bioinformatics","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149140352","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

MiRNA-Disease Association Prediction Using Game Optimization and Multi-view Representation Learning. 基于博弈优化和多视角表示学习的mirna -疾病关联预测。

IEEE transactions on computational biology and bioinformatics Pub Date : 2026-10-07 DOI: 10.1109/TCBBIO.2026.3741557

Yangfeng Zhu, Yongxian Fan, Guicong Sun, Xiaoyong Pan

{"title":"MiRNA-Disease Association Prediction Using Game Optimization and Multi-view Representation Learning.","authors":"Yangfeng Zhu, Yongxian Fan, Guicong Sun, Xiaoyong Pan","doi":"10.1109/TCBBIO.2026.3741557","DOIUrl":"10.1109/TCBBIO.2026.3741557","url":null,"abstract":"MiRNAs influence cellular functions by regulating gene expression and interacting with diverse biomolecules within the cell. Accurate prediction of miRNA disease associations (MDA) plays a crucial role in dis ease diagnosis, treatment, and drug development. However, most computational methods focus on graph information and ignore other information when extracting miRNA and disease features. Therefore, we propose a computational method based on game optimization and multi view representation learning (GMIMDA) for predicting MDA. Specifically, GMIMDA first integrates multi-source similarity views using the similarity network fusion (SNF) technique and constructs multi-view complementary representations by extracting linear, nonlinear, and graph structure representations of miRNA and disease via singular value decom position with weighted scaling (SVD-WS), nonnegative matrix factorization (NMF), and graph convolutional networks (GCNs), respectively. Second, to enhance the interactivity between nodes, GMIMDA uses graph features as initial strategies of participants in game theory modeling and selects optimal strategies based on the Nash equilibrium. Finally, GMIMDA fuses the outputs of multi-view representation learning and inputs them into the Kolmogorov-Arnold Networks (KANs) for making predictions, using symbolic activation functions to reveal the mapping relationship between input and output. Experimental results demon strate that GMIMDA outperforms existing approaches in three different databases. Case studies provide additional evidence supporting the effectiveness of GMIMDA in identifying unknown disease-associated miRNAs in practical applications.","PeriodicalId":520987,"journal":{"name":"IEEE transactions on computational biology and bioinformatics","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149130234","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

CIM-DTA: Conditional Interaction Modulation for Cold-Start Drug-Target Affinity Prediction. CIM-DTA：冷启动药物-靶标亲和力预测的条件相互作用调制。

IEEE transactions on computational biology and bioinformatics Pub Date : 2026-10-07 DOI: 10.1109/TCBBIO.2026.3741529

Ziyou Zhou, Min Chen

{"title":"CIM-DTA: Conditional Interaction Modulation for Cold-Start Drug-Target Affinity Prediction.","authors":"Ziyou Zhou, Min Chen","doi":"10.1109/TCBBIO.2026.3741529","DOIUrl":"10.1109/TCBBIO.2026.3741529","url":null,"abstract":"Drug-target affinity prediction under cold-start set tings suffers from distribution shifts between training and testing data. This leads to poor generalization for unseen drugs or targets. To address this issue, we propose a conditional inter action modulation framework. The model explicitly captures pair-specific interaction contexts. It integrates molecular graph representations with contextual protein embeddings from ESM-2. A conditional response vector is constructed to guide interaction modeling. This vector modulates the network through hierarchical interaction modulation, including attention bias adjustment, feature activation gating, and feature distribution recalibration. In addition, a condition-aware hypernetwork head enables adaptive affinity prediction. Experiments on the Davis and BindingDB Kd datasets are conducted under warm, cold-drug, and cold target settings. CIM-DTA achieves competitive performance on the Davis and BindingDB-Kd datasets, particularly under cold start settings. It also maintains stable performance under strict cold-start scenarios. Ablation studies and case analyses further verify its effectiveness in modeling pair-specific interaction con texts.","PeriodicalId":520987,"journal":{"name":"IEEE transactions on computational biology and bioinformatics","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149130230","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

Hypergraph-Attention-Guided Graph Refinement and Feature Decoupling for Single-Cell RNA-seq Clustering. 单细胞RNA-seq聚类的超图注意引导图细化和特征解耦。

IEEE transactions on computational biology and bioinformatics Pub Date : 2026-10-01 DOI: 10.1109/TCBBIO.2026.3738851

Xiang-Zhen Kong, Hui-Bo Tian, Jun-Liang Shang, Jin-Xing Liu, Sheng-Jun Li

{"title":"Hypergraph-Attention-Guided Graph Refinement and Feature Decoupling for Single-Cell RNA-seq Clustering.","authors":"Xiang-Zhen Kong, Hui-Bo Tian, Jun-Liang Shang, Jin-Xing Liu, Sheng-Jun Li","doi":"10.1109/TCBBIO.2026.3738851","DOIUrl":"https://doi.org/10.1109/TCBBIO.2026.3738851","url":null,"abstract":"Advances in single-cell RNA sequencing (scRNA-seq) enable the exploration of cellular heterogeneity at single-cell resolution. Accurate cell clustering is a prerequisite for delineating these identities; however, the inherent sparsity and prevalent dropout noise of scRNA-seq data pose major algorithmic challenges. Existing graph-based deep learning methods often struggle in this regime, suffering from the structural fragility of static neighbor graphs and the dimensional redundancy of latent embeddings. Thus, we introduce a novel method named Hypergraph-Attention-Guided Graph Refinement and Feature Decoupling for Single-Cell RNA-seq Clustering (scHAG), a deep graph clustering framework that synergizes generative pre-training, dynamic topological refinement, and orthogonal feature decoupling. To establish a robust semantic foundation, scHAG combines a Masked Autoencoder (MAE) with Zero-Inflated Negative Binomial (ZINB) modeling to mitigate dropout effects. A Hypergraph Attention-guided Structural Refinement (HAG-SR) module then captures high-order cellular relationships and reweights potentially spurious connections to obtain a more reliable graph topology. To prevent dimensional collapse, the framework incorporates a Barlow Twins objective that enforces cross-correlation orthogonalization, yielding highly discriminative embeddings. An adaptive gating module subsequently balances global topological priors with local neighborhood information. Experimental results on fourteen real datasets demonstrate that scHAG achieves highly competitive clustering accuracy and robust performance across diverse noise conditions. By circumventing the quadratic memory bottlenecks of standard graph networks, scHAG provides a memory-efficient and scalable framework for analysis of large-scale single-cell transcriptomic data.","PeriodicalId":520987,"journal":{"name":"IEEE transactions on computational biology and bioinformatics","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149123046","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

InterActRNA: A Co-Evolutionary Geometric Deep Learning Framework for RNA-Small Molecule Binding Affinity Prediction. InterActRNA：用于rna -小分子结合亲和力预测的协同进化几何深度学习框架。

IEEE transactions on computational biology and bioinformatics Pub Date : 2026-09-30 DOI: 10.1109/TCBBIO.2026.3738861

Jinmiao Song, Qilin Feng, Lei Deng, Shengwei Tian, Qimeng Yang, Annan Gao

{"title":"InterActRNA: A Co-Evolutionary Geometric Deep Learning Framework for RNA-Small Molecule Binding Affinity Prediction.","authors":"Jinmiao Song, Qilin Feng, Lei Deng, Shengwei Tian, Qimeng Yang, Annan Gao","doi":"10.1109/TCBBIO.2026.3738861","DOIUrl":"https://doi.org/10.1109/TCBBIO.2026.3738861","url":null,"abstract":"RNA is identified as a critical therapeutic target due to its involvement in various cellular functions. Accurate prediction of RNA-small molecule affinity (RSMA) is prioritized for accelerating drug discovery. However, existing deep learning models predominantly treat RNA and small molecules as static entities. The dynamic induced-fit-inspired co-adaptation and multi-scale chemical information are not adequately captured. In this study, InterActRNA is presented as a co-evolutionary geometric deep learning framework. To emulate the induced-fit-inspired dynamic co-adaptation mechanism, an Interleaved Guided Encoding Module is designed. An Iterative Drug Encoder and a Hierarchical RNA Encoder are incorporated to exchange information via cooperative attention. Feature learning in one modality is real-time guided by the contextual information of the partner. Furthermore, a Cross-Modality Substructure Similarity (SSIM) module is introduced. Pairwise interactions between small molecule functional groups and RNA structural motifs are explicitly modeled. The predictive capability is evaluated on the industry-standard R-SIM dataset. InterActRNA consistently outperforms state-of-the-art baselines in both regression and classification tasks. Robustness in rigorous cold-start scenarios is demonstrated. Finally, key pharmacophores are pinpointed through interpretability analysis. The potential to guide rational RNA-targeted drug design is confirmed.","PeriodicalId":520987,"journal":{"name":"IEEE transactions on computational biology and bioinformatics","volume":"PP ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2026-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149140350","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