Interdisciplinary Sciences: Computational Life Sciences最新文献

{"title":"AWTI-Net Enables Accurate and Interpretable Functional Assessment of Disease-Associated LncRNA Mutations.","authors":"Haipeng Zhu, Douyue Li, Zehang Jiang, Minglei Yang, Guoying Wang, Wenliang Zhang","doi":"10.1007/s12539-026-00869-w","DOIUrl":"https://doi.org/10.1007/s12539-026-00869-w","url":null,"abstract":"<p><p>Long non-coding RNA (lncRNA) variants contribute to human disease, yet systematic evaluation of their functional impact is limited by the lack of high-quality benchmark datasets for computational tool development. To address this, we curated three comprehensive datasets, lncRNAVar-Literature, lncRNAVar-GWAS, and Mpravardb, by integrating disease-associated variants from published studies and genome-wide association analyses with putatively benign variants derived from the 1000 Genomes Project. Using these datasets, we characterized structural, miRNA-targeting, and evolutionary features distinguishing functional from non-functional lncRNA variants. Based on these insights, we developed an adaptive wavelet-Transformer interpretable network (AWTI-Net), an integrative and interpretable framework combining multi-scale wavelet-based sequence encoding, LSTM-driven temporal modeling, a frequency-aware memory Transformer, and an adaptive decision-making mechanism to capture hierarchical lncRNA variant features. AWTI-Net consistently achieved superior performance across accuracy, specificity, sensitivity, and F1 score on both benchmark datasets. Ablation analyses demonstrated complementary contributions of individual modules and synergistic effects of multidimensional features, while entropy-guided path selection enabled biologically interpretable predictions. Across independent evaluations, AWTI-Net outperformed widely used noncoding variant predictors-including CADD, Eigen, GWAVA, DANN, and FATHMM-achieving AUCs of 0.9948 and 0.9852 on lncRNAVar-GWAS and lncRNAVar-Literature, respectively. AWTI-Net was evaluated against 13 mainstream machine learning models and 15 state-of-the-art deep learning frameworks across three independent benchmark datasets, consistently demonstrating superior and more balanced performance across most evaluation metrics compared with competing methods. Importantly, it effectively prioritized hepatocellular carcinoma-associated lncRNA variants, highlighting its potential as a robust and interpretable tool for genetic studies of disease-associated noncoding variation.</p>","PeriodicalId":13670,"journal":{"name":"Interdisciplinary Sciences: Computational Life Sciences","volume":" ","pages":""},"PeriodicalIF":5.2,"publicationDate":"2026-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148827962","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hierarchical Graph Representation Learning for Protein-Protein Interaction Site Prediction.","authors":"Wenjun Xu, Xiaosong Wang, Zihao Zhao, Lei Chen, Ming Deng, Yunyun Sun, Lichuan Gu","doi":"10.1007/s12539-026-00868-x","DOIUrl":"https://doi.org/10.1007/s12539-026-00868-x","url":null,"abstract":"<p><p>Precisely identifying protein-binding locations is essential for advancing protein engineering and pharmaceutical discovery. However, due to the intrinsically hierarchical nature of protein data, extracting deep representations from such data remains a difficult task. Furthermore, issues such as class imbalance and uneven topological distribution of interaction sites limit further improvements in prediction performance. To tackle these issues, we present HGRL-PPIS, a novel hierarchical graph representation learning approach for predicting protein-protein interaction sites. Specifically, our framework first constructs a three-tier graph encompassing a protein-level graph, residue-level and atomic-level graphs. A Transformer-based module is then employed to enable efficient cross-hierarchical information propagation. To mitigate the class imbalance caused by the sparse and uneven distribution of binding sites, we introduce a prototypical graph neural network training strategy that balances data distribution and enhances prediction accuracy. Our experiments reveal that HGRL-PPIS achieves superior performance over competing methods on multiple benchmark datasets, enabling more reliable detection of protein-protein binding residues.</p>","PeriodicalId":13670,"journal":{"name":"Interdisciplinary Sciences: Computational Life Sciences","volume":" ","pages":""},"PeriodicalIF":5.2,"publicationDate":"2026-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148828040","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predicting circRNA-Drug Sensitivity Using Integrated Hybrid Graph and Molecular Features.","authors":"Yongtian Wang, Wenkai Shen, Jiahao Li, Jialu Hu, Jiajie Peng, Zhuhong You, Xuequn Shang","doi":"10.1007/s12539-026-00870-3","DOIUrl":"https://doi.org/10.1007/s12539-026-00870-3","url":null,"abstract":"<p><p>Circular RNAs (circRNAs) are a class of covalently closed RNA molecules that exhibit high stability and play crucial roles in tumorigenesis and therapeutic response. Increasing evidence highlights their potential as biomarkers for drug sensitivity and resistance. However, uncovering circRNA-drug interactions remain challenging: experimental approaches are costly and time-consuming, while many existing computational methods rely on limited similarity features, leading to incomplete utilization of available data and reduced predictive accuracy. We propose HMCDSP, a hybrid molecular and network-based circRNA-Drug sensitivity prediction framework. HMCDSP integrates BERT-derived circRNA sequence embeddings and SMILES-based drug representations with network-level features learned through a two-layer hybrid graph neural network combining Graph Convolutional Networks (GCN) and Graph Attention Networks (GAT). To address data sparsity, circRNA and drug similarity networks were constructed by fusing sequence-derived metrics with Gaussian Interaction Profile kernels. On the NcRNADrug benchmark, HMCDSP consistently outperformed six state-of-the-art methods, achieving an average Area Under Curve (AUC) of 0.9588 and Area Under the Precision-Recall Curve‌ (AUPRC) of 0.9622. Ablation analyses confirmed the complementary contributions of molecular and network features, while classifier comparisons established the superiority of the Multilayer Perceptron (MLP) predictor. Case studies further validated predicted circRNA-drug associations, including cisplatin, enzalutamide, and sorafenib, against published experimental findings, demonstrating HMCDSP's capacity to reveal clinically relevant biomarkers and inform personalized therapeutic strategies.</p>","PeriodicalId":13670,"journal":{"name":"Interdisciplinary Sciences: Computational Life Sciences","volume":" ","pages":""},"PeriodicalIF":5.2,"publicationDate":"2026-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148828002","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intelligent Medication Recommendation via Dynamic Prescription Modeling and Molecular Substructure Learning.","authors":"Yabin Kuang, Minzhu Xie, Jiancheng Zhong","doi":"10.1007/s12539-026-00861-4","DOIUrl":"https://doi.org/10.1007/s12539-026-00861-4","url":null,"abstract":"<p><p>Medication recommendation system is a critical application of artificial intelligence in healthcare, supporting clinicians in prescribing effective and safe drug combinations. To achieve more comprehensive recommendation, further research is required in three key areas: (1) Identifying more detailed and relevant drug substructure information to optimize drug combinations, as specific drug substructures impact therapeutic effects and side effects. (2) Capturing historical prescription dynamics to reflect patient condition progression over time. (3) Integrating correlations among medical codes to provide a comprehensive representation of patient conditions, given that certain diagnoses often co-occur. This paper proposes dynamic medication recommendation system DynMedRec, a computational model for medication recommendation that prioritizes prescription dynamics and structured drug molecule information. DynMedRec captures fine-grained drug information by modeling the interactions between substructures and employing a clinical-context query mechanism to generate adaptive molecular representations. Additionally, it integrates structural correlations among medical codes to enhance visit-level patient representations. To preserve long-term longitudinal dependencies, an enhanced recurrent neural network is proposed to model dynamic changes in historical prescriptions. DynMedRec was trained on the MIMIC-III dataset using a visit-by-visit training approach. Extensive experiments and in-depth analyses further demonstrate that DynMedRec outperforms existing state-of-the-art methods across diverse scenarios.</p>","PeriodicalId":13670,"journal":{"name":"Interdisciplinary Sciences: Computational Life Sciences","volume":" ","pages":""},"PeriodicalIF":5.2,"publicationDate":"2026-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148828025","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"3D Geometric Equivariant Graph Neural Networks with Contrastive Learning for Protein-Ligand Binding Affinity Prediction.","authors":"Gaili Li, Yongna Yuan, Xiuping Chen, Ping Wang","doi":"10.1007/s12539-026-00867-y","DOIUrl":"https://doi.org/10.1007/s12539-026-00867-y","url":null,"abstract":"<p><p>Protein-Ligand Binding Affinity (PLBA) prediction is a key task in computer aided drug design, underpinning virtual screening, lead optimization, and drug repurposing. Despite recent advances in deep learning, many existing methods fail to fully exploit three-dimensional (3D) geometric information and remain sensitive to conformational variability. To address these limitations, we propose 3D-GEGCL, a framework that integrates 3D geometrically equivariant graph neural networks with self-supervised contrastive learning for robust and accurate PLBA prediction. Protein-ligand complexes are represented as atomic-level 3D geometric graphs and encoded using an E(3)-equivariant network to ensure physical consistency under rotations and translations, while contrastive learning enforces representation consistency across geometrically perturbed views. Comprehensive evaluations conducted on the PDBbind v2019 and CSAR-HiQ benchmarks reveal that 3D-GEGCL achieves superior performance over existing leading methods across a range of assessment criteria. Additional ablation analyses validate the synergistic roles of geometric equivariance and contrastive learning, underscoring the robustness and broad applicability of the introduced framework. Implementation scripts for the various model components are publicly accessible via https://github.com/ligaili01/3D-GEGCL .</p>","PeriodicalId":13670,"journal":{"name":"Interdisciplinary Sciences: Computational Life Sciences","volume":" ","pages":""},"PeriodicalIF":5.2,"publicationDate":"2026-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148828004","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"scLGGCL: Label-Guided Graph Contrastive Learning for Single-Cell Fusion Clustering.","authors":"Wenjing Su, Baojuan Qin, Junliang Shang, Yan Zhao, Xiaohan Zhang, Yan Sun, Jin-Xing Liu","doi":"10.1007/s12539-026-00858-z","DOIUrl":"https://doi.org/10.1007/s12539-026-00858-z","url":null,"abstract":"<p><p>Single-cell RNA sequencing (scRNA-seq) provides transcriptomic profiles at cellular resolution, enabling the study of tissue heterogeneity. A critical step in scRNA-seq analysis is cell clustering, which identifies distinct subpopulations for downstream biological interpretation. However, most existing clustering algorithms fail to simultaneously leverage cellular attributes and intercellular structural relationships. Additionally, graph-based methods that employ contrastive learning typically neglect cell-level semantic similarity. We present scLGGCL, a label-guided graph contrastive learning approach to tackle the above limitations. The framework integrates three modules: dual-reconstruction to fuse attribute-structure information, contrastive learning under label guidance to extract semantic similarities, and deep embedding clustering to enable iterative optimization. Comprehensive evaluations on single and cross-dataset benchmarks show that scLGGCL achieves superior clustering performance. Code is available at https://github.com/CDMBlab/scLGGCL .</p>","PeriodicalId":13670,"journal":{"name":"Interdisciplinary Sciences: Computational Life Sciences","volume":" ","pages":""},"PeriodicalIF":5.2,"publicationDate":"2026-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148812918","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"UniPept: A Universal Model for Predicting Peptide Properties Based on Atom-Residue Dual-Scale Integration.","authors":"Haoshuang Wu, Yu Deng, Zhen Li, Mingming Qi, Yanshi Wei, Linlin Zhuo, Quan Zou, Wenqian Zhang","doi":"10.1007/s12539-026-00863-2","DOIUrl":"https://doi.org/10.1007/s12539-026-00863-2","url":null,"abstract":"<p><p>Naturally occurring in animals, plants, and other organisms, peptides exhibit strong antibacterial activity and hold promise as alternatives to conventional antibiotics. However, evaluating peptide properties such as toxicity, antibacterial activity, and anticancer potential remains a critical step in the drug development. Current peptide property prediction methods often rely on single-scale sequence or structural information, failing to capture the complex multi-scale data necessary for accurate predictions. To address this challenge, we propose UniPept, a novel model for peptide property prediction that integrates atomic-level and residue-level features to generate robust peptide representations. We first extract atomic two-dimensional(2D) descriptors and atom-atom pairwise geometry from the peptide sequence to derive atomic-level geometric features. Residue-level features are obtained using a protein language model, while a residue dictionary provides amino acid index profiles and residue-residue geometric relationships to construct residue-level geometric representations. Finally, atomic and residue features are integrated via a gated attention mechanism. This multi-scale fusion strategy enhances peptide representations. Extensive experiments demonstrate that the proposed method accurately predicts peptide properties and that UniPept outperforms competing approaches in interaction and binding affinity prediction tasks. These findings underscore the potential of UniPept in advancing peptide drug development and providing insights into biological and clinical applications.</p>","PeriodicalId":13670,"journal":{"name":"Interdisciplinary Sciences: Computational Life Sciences","volume":" ","pages":""},"PeriodicalIF":5.2,"publicationDate":"2026-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148812881","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"TransTCR: Integrating TCRs and Transcriptomes Through Optimal Transport for Antigen Specificity Prediction.","authors":"Wenbing Li, Yuansong Zeng, Ruipeng Huang, Yuanze Chen, Jinyun Niu, Ningyuan Shangguan, Siyuan He, Yuedong Yang","doi":"10.1007/s12539-026-00865-0","DOIUrl":"10.1007/s12539-026-00865-0","url":null,"abstract":"<p><p>Recent advances in single-cell immune profiling enable simultaneous measurement of T cell receptors (TCRs) and transcriptomes, offering unprecedented opportunities to characterize adaptive immunity at single-cell resolution. However, the substantial heterogeneity between these modalities poses challenges for effective integration, and existing approaches often rely on simplistic alignment assumptions that may overlook modality-specific biological signals. To address this challenge, we introduce TransTCR, a multimodal learning framework that integrates optimal transport (OT) with contrastive learning to align TCR and transcriptomic representations. Specifically, TransTCR first extracts informative features from each modality using pretrained foundation models, then performs OT-based projection into a shared latent space to achieve distribution-aware alignment. A bidirectional contrastive objective further refines instance-level correspondence by maximizing agreement between the paired TCR-RNA profiles. Extensive experiments demonstrate that TransTCR substantially outperforms existing single-modality and multimodal baselines across antigen specificity recognition tasks, achieving state-of-the-art performance in intra-donor antigen specificity prediction, inter-donor antigen specificity prediction, and clustering evaluations. Overall, TransTCR provides a powerful computational tool for integrating and analyzing multimodal T cell data, facilitating deeper insight into adaptive immune responses.</p>","PeriodicalId":13670,"journal":{"name":"Interdisciplinary Sciences: Computational Life Sciences","volume":" ","pages":""},"PeriodicalIF":5.2,"publicationDate":"2026-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148722595","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Novel Cancer Driver Genes Identification Method Based on Self-Supervised Dual Masked Graph Autoencoder.","authors":"Pi-Jing Wei, Xinhao Guo, Wenjun Li, Yun Ding, Rui-Fen Cao, Zhenyu Yue, Kanglin Wang, Chun-Hou Zheng","doi":"10.1007/s12539-026-00866-z","DOIUrl":"https://doi.org/10.1007/s12539-026-00866-z","url":null,"abstract":"<p><p>Uncovering genes that drive cancer is fundamental to elucidating the mechanisms underlying cancer development and to advancing cancer research. Recent years have witnessed the emergence of cancer driver gene identification from multi-omics data as a key research area, facilitated by the rapid progress of high-throughput molecular technologies. Although numerous algorithms have been proposed for cancer driver gene discovery, the precise identification of these genes continues to pose a challenge owing to the lack of labeled data. This study presents SDMGAE, a Self-supervised Dual Masked Graph AutoEncoder-based method for cancer driver gene identification. This framework integrates two components: a self-supervised graph learning module and a driver gene prediction module. During the self-supervised graph learning phase, nodes and edges of protein-protein interaction (PPI) networks are masked separately to consider both node and structural information. Subsequently, the graph autoencoder is employed to reconstruct the PPI network without using labelled data. In the driver gene prediction stage, we employ the pre-trained graph neural network encoder to obtain the embeddings, which are then processed through the logistic regression to generate prediction outcomes. To evaluate the effectiveness of SDMGAE, we performed benchmarking experiments across 10 distinct types of cancer data. Experimental outcomes reveal that SDMGAE exhibits improved performance in cancer driver gene detection compared with state-of-the-art methods.</p>","PeriodicalId":13670,"journal":{"name":"Interdisciplinary Sciences: Computational Life Sciences","volume":" ","pages":""},"PeriodicalIF":5.2,"publicationDate":"2026-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148712316","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CCVAN Leverages Conditional Molecular Generation Through Conditional VAE and Wasserstein GAN.","authors":"Jianqiang Zheng, Ziqi Xu, Junwen Huang, Xiaochuan Chen, Yuetong Li, Yanjie Wei, Huiling Zhang","doi":"10.1007/s12539-026-00860-5","DOIUrl":"https://doi.org/10.1007/s12539-026-00860-5","url":null,"abstract":"<p><p>Molecular generation plays a vital role in advancing drug discovery, materials science, and chemical exploration. In this study, we integrated the conditional variational autoencoder (CVAE) with the Wasserstein generative adversarial network (WGAN) and effectively applied this hybrid architecture to molecular generation tasks, introducing a molecular generation framework with conditional generation capabilities known as CCVAN. The model first encodes the data into a latent vector using CVAE, then shares a decoder with the generator of the WGAN to reconstruct molecular SMILES, and trains the discriminator with both the generated and real molecular SMILES to achieve the goal of conditionally generating molecules. Compared to existing methods, CCVAN can generate molecules with specific properties as needed and performs well in terms of validity and novelty. In a case study, we utilized CCVAN for ligand-based and structure-based drug design, enabling the generation of high-binding-affinity molecules for target binding. Overall, the flexibility and effectiveness of CCVAN make it a valuable tool for accelerating the compound discovery process. The source code of CCVAN is publicly available at https://github.com/mjcoo/CCVAN .</p>","PeriodicalId":13670,"journal":{"name":"Interdisciplinary Sciences: Computational Life Sciences","volume":" ","pages":""},"PeriodicalIF":5.2,"publicationDate":"2026-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148619778","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}