Interdisciplinary Sciences: Computational Life Sciences最新文献_第3页

Repurposing Drugs for Infectious Diseases by Graph Convolutional Network with Sensitivity-Based Graph Reduction. 基于灵敏度的图约简的图卷积网络对传染病药物的再利用。

IF 3.9 2区生物学

Interdisciplinary Sciences: Computational Life Sciences Pub Date : 2025-03-01 Epub Date: 2024-12-04 DOI: 10.1007/s12539-024-00672-5

Rongting Yue, Abhishek Dutta

{"title":"Repurposing Drugs for Infectious Diseases by Graph Convolutional Network with Sensitivity-Based Graph Reduction.","authors":"Rongting Yue, Abhishek Dutta","doi":"10.1007/s12539-024-00672-5","DOIUrl":"10.1007/s12539-024-00672-5","url":null,"abstract":"Computational systems biology employs computational algorithms and integrates diverse data sources, such as gene expression profiles, molecular interactions, and network modeling, to identify promising drug candidates through repurposing existing compounds in response to urgent healthcare needs. This study tackles the urgent need for rapid therapeutic development against emerging infectious diseases. We introduce a novel analytic expression for sensitivity analysis based on the Kronecker product and enhance model prediction performance using Graph Convolutional Networks (GCNs) with sensitivity-based graph reduction. Our algorithm refines prediction performance by leveraging sensitivity-based graph reduction. By integrating RNA-seq data, molecular interactions, and GCNs, we identify disease-related genes and pathways, construct heterogeneous graph models, and predict potential drugs. This approach involves novel analytical expressions that assess sensitivity to model loss, employing the Kronecker product approach. Subgraph analysis identifies nodes for removal, leading to a refined graph used for model retraining. This cost-effective pipeline focuses on computational methods for drug repurposing, targeting infectious diseases such as Zika virus and COVID-19 infection. Applied to these infections, our methodology integrates 659 proteins and 703 drugs for Zika virus, and 495 proteins and 468 drugs for COVID-19, along with their interactions derived from gene expression profiles. Top candidate drugs, such as Betamethasone phosphate and Bizelesin for Zika virus, and Chloroquine, Heparin Disaccharide, and Resveratrol for COVID-19, were validated through literature review or docking analysis. This scalable approach demonstrates promise in repurposing drugs for urgent healthcare challenges.","PeriodicalId":13670,"journal":{"name":"Interdisciplinary Sciences: Computational Life Sciences","volume":" ","pages":"185-199"},"PeriodicalIF":3.9,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142768515","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}

引用次数: 0

scCrab: A Reference-Guided Cancer Cell Identification Method based on Bayesian Neural Networks. scCrab：基于贝叶斯神经网络的参考引导癌细胞识别方法

IF 3.9 2区生物学

Interdisciplinary Sciences: Computational Life Sciences Pub Date : 2025-03-01 Epub Date: 2024-09-30 DOI: 10.1007/s12539-024-00655-6

Heyang Hua, Wenxin Long, Yan Pan, Siyu Li, Jianyu Zhou, Haixin Wang, Shengquan Chen

{"title":"scCrab: A Reference-Guided Cancer Cell Identification Method based on Bayesian Neural Networks.","authors":"Heyang Hua, Wenxin Long, Yan Pan, Siyu Li, Jianyu Zhou, Haixin Wang, Shengquan Chen","doi":"10.1007/s12539-024-00655-6","DOIUrl":"10.1007/s12539-024-00655-6","url":null,"abstract":"Cancer is a significant global public health concern, where early detection can greatly enhance curative outcomes. Therefore, the identification of cancer cells holds significant importance as the primary method for cancer diagnosis. The advancement of single-cell RNA sequencing (scRNA-seq) technology has made it possible to address the problem of cancer cell identification at the single-cell level more efficiently with computational methods, as opposed to the time-consuming and less reproducible manual identification methods. However, existing computational methods have shown suboptimal identification performance and a lack of capability to incorporate external reference data as prior information. Here, we propose scCrab, a reference-guided automatic cancer cell identification method, which performs ensemble learning based on a Bayesian neural network (BNN) with multi-head self-attention mechanisms and a linear regression model. Through a series of experiments on various datasets, we systematically validated the superior performance of scCrab in both intra- and inter-dataset predictions. Besides, we demonstrated the robustness of scCrab to dropout rate and sample size, and conducted ablation experiments to investigate the contributions of each component in scCrab. Furthermore, as a dedicated model for cancer cell identification, scCrab effectively captures cancer-related biological significance during the identification process.","PeriodicalId":13670,"journal":{"name":"Interdisciplinary Sciences: Computational Life Sciences","volume":" ","pages":"12-26"},"PeriodicalIF":3.9,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142346020","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}

引用次数: 0

CEL: A Continual Learning Model for Disease Outbreak Prediction by Leveraging Domain Adaptation via Elastic Weight Consolidation. CEL：通过弹性权重整合利用领域适应的疾病爆发预测的持续学习模型。

IF 3.9 2区生物学

Interdisciplinary Sciences: Computational Life Sciences Pub Date : 2025-02-28 DOI: 10.1007/s12539-024-00675-2

Saba Aslam, Abdur Rasool, Xiaoli Li, Hongyan Wu

{"title":"CEL: A Continual Learning Model for Disease Outbreak Prediction by Leveraging Domain Adaptation via Elastic Weight Consolidation.","authors":"Saba Aslam, Abdur Rasool, Xiaoli Li, Hongyan Wu","doi":"10.1007/s12539-024-00675-2","DOIUrl":"https://doi.org/10.1007/s12539-024-00675-2","url":null,"abstract":"Continual learning is the ability of a model to learn over time without forgetting previous knowledge. Therefore, adapting new data in dynamic fields like disease outbreak prediction is paramount. Deep neural networks are prone to error due to catastrophic forgetting. This study introduces a novel CEL model for Continual Learning by leveraging domain adaptation via Elastic weight consolidation (EWC). This model aims to mitigate the catastrophic forgetting phenomenon in a domain incremental setting. The Fisher information matrix (FIM) is constructed with EWC to develop a regularization term that penalizes changes to essential parameters. We conducted experiments on three distinct diseases, influenza, mpox, and measles, with customized metrics. The high R-squared values during evaluation and reevaluation outperform the other state-of-the-art models in several contexts. The results indicate that CEL adapts well to incremental data. CEL's robustness emphasizes its minimal 65% forgetting rate and 18% higher memory stability compared to existing benchmark studies. This study highlights CEL's versatility in disease outbreak prediction by addressing evolving data with temporal patterns. It offers a valuable model for proactive disease control with accurate and timely predictions.","PeriodicalId":13670,"journal":{"name":"Interdisciplinary Sciences: Computational Life Sciences","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143523276","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}

引用次数: 0

MultiKD-DTA: Enhancing Drug-Target Affinity Prediction Through Multiscale Feature Extraction. MultiKD-DTA：通过多尺度特征提取增强药物-靶标亲和力预测。

IF 3.9 2区生物学

Interdisciplinary Sciences: Computational Life Sciences Pub Date : 2025-02-28 DOI: 10.1007/s12539-025-00697-4

Riqian Hu, Ruiquan Ge, Guojian Deng, Jin Fan, Bowen Tang, Changmiao Wang

{"title":"MultiKD-DTA: Enhancing Drug-Target Affinity Prediction Through Multiscale Feature Extraction.","authors":"Riqian Hu, Ruiquan Ge, Guojian Deng, Jin Fan, Bowen Tang, Changmiao Wang","doi":"10.1007/s12539-025-00697-4","DOIUrl":"https://doi.org/10.1007/s12539-025-00697-4","url":null,"abstract":"The discovery and development of novel pharmaceutical agents is characterized by high costs, lengthy timelines, and significant safety concerns. Traditional drug discovery involves pharmacologists manually screening drug molecules against protein targets, focusing on binding within protein cavities. However, this manual process is slow and inherently limited. Given these constraints, the use of deep learning techniques to predict drug-target interaction (DTI) affinities is both significant and promising for future applications. This paper introduces an innovative deep learning architecture designed to enhance the prediction of DTI affinities. The model ingeniously combines graph neural networks, pre-trained large-scale protein models, and attention mechanisms to improve performance. In this framework, molecular structures are represented as graphs and processed through graph neural networks and multiscale convolutional networks to facilitate feature extraction. Simultaneously, protein sequences are encoded using pre-trained ESM-2 large models and processed with bidirectional long short-term memory networks. Subsequently, the molecular and protein embeddings derived from these processes are integrated within a fusion module to compute affinity scores. Experimental results demonstrate that our proposed model outperforms existing methods on two publicly available datasets.","PeriodicalId":13670,"journal":{"name":"Interdisciplinary Sciences: Computational Life Sciences","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143523301","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}

引用次数: 0

NTMFF-DTA: Prediction of Drug-Target Affinity Based on Network Topology and Multi-feature Fusion. NTMFF-DTA：基于网络拓扑和多特征融合的药物-靶标亲和力预测。

IF 3.9 2区生物学

Interdisciplinary Sciences: Computational Life Sciences Pub Date : 2025-02-25 DOI: 10.1007/s12539-025-00692-9

Yuandong Liu, Youzhi Liu, Haoqin Yang, Longbo Zhang, Kai Che, Linlin Xing

{"title":"NTMFF-DTA: Prediction of Drug-Target Affinity Based on Network Topology and Multi-feature Fusion.","authors":"Yuandong Liu, Youzhi Liu, Haoqin Yang, Longbo Zhang, Kai Che, Linlin Xing","doi":"10.1007/s12539-025-00692-9","DOIUrl":"https://doi.org/10.1007/s12539-025-00692-9","url":null,"abstract":"Predicting drug-target binding affinity (DTA) is an important step in the complex process of drug discovery or drug repositioning. A large number of computational methods proposed for the task of DTA prediction utilize single features of proteins to measure drug-protein or protein-protein interactions, ignoring multi-feature fusion between protein-related features (e.g., solvent accessibility, protein pockets, secondary structures, and distance maps, etc.). To address the aforementioned constraints, we propose a new network topology and multi-feature fusion based approach for DTA prediction (NTMFF-DTA), which deeply mines protein multiple types of data and propagates drug information across domains. Data in drug-target interactions are often sparse, and multi-feature fusion can enrich data information by integrating multiple features, thus overcoming the data sparsity problem to some extent. The proposed approach offers two main contributions: (1) constructing a relationship-aware GAT that selectively focuses on the connections between nodes and edges in the molecular graph to capture the more central roles of nodes and edges in DTA prediction and (2) constructing an information propagation channel between different feature domains of drug proteins to achieve the sharing of the importance weight of drug atoms and edges, and combining with a multi-head self-attention mechanism to capture residue-enhancing features. The NTMFF-DTA model was comparatively tested against several leading baseline technologies on commonly used datasets. Experimental show that NTMFF-DTA can effectively and accurately predict DTA and outperform existing comparative models.","PeriodicalId":13670,"journal":{"name":"Interdisciplinary Sciences: Computational Life Sciences","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143491929","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}

引用次数: 0

scRDiT: Generating Single-cell RNA-seq Data by Diffusion Transformers and Accelerating Sampling. scdit：通过扩散变压器和加速采样生成单细胞RNA-seq数据。

IF 3.9 2区生物学

Interdisciplinary Sciences: Computational Life Sciences Pub Date : 2025-02-21 DOI: 10.1007/s12539-025-00688-5

Shengze Dong, Zhuorui Cui, Ding Liu, Jinzhi Lei

{"title":"scRDiT: Generating Single-cell RNA-seq Data by Diffusion Transformers and Accelerating Sampling.","authors":"Shengze Dong, Zhuorui Cui, Ding Liu, Jinzhi Lei","doi":"10.1007/s12539-025-00688-5","DOIUrl":"https://doi.org/10.1007/s12539-025-00688-5","url":null,"abstract":"Single-cell RNA sequencing (scRNA-seq) is a groundbreaking technology extensively utilized in biological research, facilitating the examination of gene expression at the individual cell level within a given tissue sample. While numerous tools have been developed for scRNA-seq data analysis, the challenge persists in capturing the distinct features of such data and replicating virtual datasets that share analogous statistical properties. Our study introduces a generative approach termed scRNA-seq Diffusion Transformer (scRDiT). This method generates virtual scRNA-seq data by leveraging a real dataset. The method is a neural network constructed based on Denoising Diffusion Probabilistic Models (DDPMs) and Diffusion Transformers (DiTs). This involves subjecting Gaussian noises to the real dataset through iterative noise-adding steps and ultimately restoring the noises to form scRNA-seq samples. This scheme allows us to learn data features from actual scRNA-seq samples during model training. Our experiments, conducted on two distinct scRNA-seq datasets, demonstrate superior performance. Additionally, the model sampling process is expedited by incorporating Denoising Diffusion Implicit Models (DDIMs). scRDiT presents a unified methodology empowering users to train neural network models with their unique scRNA-seq datasets, enabling the generation of numerous high-quality scRNA-seq samples.","PeriodicalId":13670,"journal":{"name":"Interdisciplinary Sciences: Computational Life Sciences","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143468010","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}

引用次数: 0

NPI-HGNN: A Heterogeneous Graph Neural Network-Based Approach for Predicting ncRNA-Protein Interactions. NPI-HGNN：一种基于异质图神经网络的预测ncrna -蛋白相互作用的方法。

IF 3.9 2区生物学

Interdisciplinary Sciences: Computational Life Sciences Pub Date : 2025-02-21 DOI: 10.1007/s12539-025-00689-4

Xin Zhang, Haofeng Ma, Sizhe Wang, Hao Wu, Yu Jiang, Quanzhong Liu

{"title":"NPI-HGNN: A Heterogeneous Graph Neural Network-Based Approach for Predicting ncRNA-Protein Interactions.","authors":"Xin Zhang, Haofeng Ma, Sizhe Wang, Hao Wu, Yu Jiang, Quanzhong Liu","doi":"10.1007/s12539-025-00689-4","DOIUrl":"https://doi.org/10.1007/s12539-025-00689-4","url":null,"abstract":"Accurate identification of ncRNA-protein interactions (NPIs) is critical for understanding various cellular activities and biological functions of ncRNAs and proteins. Many sequence- and/or structure- and graph-based computational approaches have been developed to identify NPIs from large-scale ncRNA and protein data in a high-throughput manner. However, many sequence- and/or structure- and graph-based computational approaches often ignore either the topological information in NPIs or the influence of other molecule networks on NPI prediction. In this work, we propose NPI-HGNN, an end-to-end graph neural network (GNN)-based approach for the identification of NPIs from a large heterogeneous network, consisting of the ncRNA-protein interaction network, the ncRNA-ncRNA similarity network, and the protein-protein interaction network. To our knowledge, NPI-HGNN is the first GNN-based predictor that integrates related heterogeneous networks for NPI prediction. Experiments on five benchmarking datasets demonstrate that NPI-HGNN outperformed several state-of-the-art sequence- and/or structure- and graph-based predictors. In addition, we showcased the prediction power of NPI-HGNN by identifying 12 interacting ncRNAs of the pre-mRNA 3' end processing protein, which indicates the effectiveness of the proposed model. The source code of NPI-HGNN is freely available for academic purposes at https://github.com/zhangxin11111/NPI-HGNN .","PeriodicalId":13670,"journal":{"name":"Interdisciplinary Sciences: Computational Life Sciences","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143467996","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}

引用次数: 0

MVGNCDA: Identifying Potential circRNA-Disease Associations Based on Multi-view Graph Convolutional Networks and Network Embeddings. MVGNCDA：基于多视图图卷积网络和网络嵌入识别潜在的circrna -疾病关联。

IF 3.9 2区生物学

Interdisciplinary Sciences: Computational Life Sciences Pub Date : 2025-02-17 DOI: 10.1007/s12539-025-00690-x

Guicong Sun, Mengxin Zheng, Yongxian Fan, Xiaoyong Pan

{"title":"MVGNCDA: Identifying Potential circRNA-Disease Associations Based on Multi-view Graph Convolutional Networks and Network Embeddings.","authors":"Guicong Sun, Mengxin Zheng, Yongxian Fan, Xiaoyong Pan","doi":"10.1007/s12539-025-00690-x","DOIUrl":"https://doi.org/10.1007/s12539-025-00690-x","url":null,"abstract":"Increasing evidences have indicated that circular RNAs play a crucial role in the onset and progression of various diseases. However, exploring potential disease-associated circRNAs using conventional experimental techniques remains both time-intensive and costly. Recently, various computational approaches have been developed to detect the circRNA-disease associations. Nevertheless, due to the sparsity of the data and the inefficient utilization of similarity representation, it is still a challenge to effectively detect unknown circRNA-disease associations using multisource data. In this work, we propose an innovative computational framework, MVGNCDA, which merges a multi-view graph convolutional network (GCN) and biased random walk-based network embeddings to evaluate potential circRNA-disease associations from multisource data. First, we calculate disease semantic similarity, circRNA functional similarity, and their Gaussian interaction profile (GIP) kernel and cosine similarity. MVGNCDA utilizes multi-view GCNs to extract local node embeddings of diseases and circRNAs in the context of multisource information. Then, we construct a heterogeneous network utilizing integrated similarity and verified circRNA-disease associations, which is subsequently used to learn global node embeddings. Furthermore, the final fused local and global node embeddings are decoded to evaluate the circRNA-disease associations using a bilinear decoder. The fivefold cross-validation results demonstrate that MVGNCDA outperforms existing methods across five public datasets. Moreover, case study also confirms that MVGNCDA is capable of efficiently identifying unknown circRNA-disease associations.","PeriodicalId":13670,"journal":{"name":"Interdisciplinary Sciences: Computational Life Sciences","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2025-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143440761","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}

引用次数: 0

Prediction of Multimorbidity Network Evolution in Middle-Aged and Elderly Population Based on CE-GCN. 基于CE-GCN的中老年人群多病网络演化预测

IF 3.9 2区生物学

Interdisciplinary Sciences: Computational Life Sciences Pub Date : 2025-02-10 DOI: 10.1007/s12539-024-00685-0

Yushi Che, Yiqiao Wang

{"title":"Prediction of Multimorbidity Network Evolution in Middle-Aged and Elderly Population Based on CE-GCN.","authors":"Yushi Che, Yiqiao Wang","doi":"10.1007/s12539-024-00685-0","DOIUrl":"https://doi.org/10.1007/s12539-024-00685-0","url":null,"abstract":"Purpose: With the evolving disease spectrum, chronic diseases have emerged as a primary burden and a leading cause of mortality. Due to the aging population and the nature of chronic illnesses, patients often suffer from multimorbidity. Predicting the likelihood of these patients developing specific diseases in the future based on their current health status and age factors is a crucial task in multimorbidity research.Methods: We propose an algorithm, CE-GCN, which integrates age sequence and embeds Graph Convolutional Network (GCN) into Gated Recurrent Unit (GRU), utilizing the topological feature of network common neighbors to predict links in dynamic complex networks. First, we constructed a disease evolution network spanning from ages 45 to 90 years old using disease information from 3333 patients. Then, we introduced an innovative approach for link prediction aimed at uncovering relationships between various diseases. This method takes into account patients' age to construct the evolutionary structure of the disease network, thereby predicting the connections between chronic diseases.Results: Results from experiments conducted on real networks indicate that our model surpasses others regarding both MRR and MAP. The proposed method accurately reveals associations between diseases and effectively captures future disease risks.Conclusion: Our model can serve as an objective and convenient computer-aided tool to identify hidden relationships between diseases in order to assist healthcare professionals in taking early disease interventions, which can substantially lower the costs associated with treating multimorbidity and enhance the quality of life for patients suffering from chronic conditions.","PeriodicalId":13670,"journal":{"name":"Interdisciplinary Sciences: Computational Life Sciences","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143390373","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}

引用次数: 0

A Multi-View Feature-Based Interpretable Deep Learning Framework for Drug-Drug Interaction Prediction. 基于多视图特征的药物-药物相互作用预测可解释深度学习框架。

IF 3.9 2区生物学

Interdisciplinary Sciences: Computational Life Sciences Pub Date : 2025-02-03 DOI: 10.1007/s12539-025-00687-6

Zihui Cheng, Zhaojing Wang, Xianfang Tang, Xinrong Hu, Fei Yang, Xiaoyun Yan

{"title":"A Multi-View Feature-Based Interpretable Deep Learning Framework for Drug-Drug Interaction Prediction.","authors":"Zihui Cheng, Zhaojing Wang, Xianfang Tang, Xinrong Hu, Fei Yang, Xiaoyun Yan","doi":"10.1007/s12539-025-00687-6","DOIUrl":"https://doi.org/10.1007/s12539-025-00687-6","url":null,"abstract":"Drug-drug interactions (DDIs) can result in deleterious consequences when patients take multiple medications simultaneously, emphasizing the critical need for accurate DDI prediction. Computational methods for DDI prediction have garnered recent attention. However, current approaches concentrate solely on single-view features, such as atomic-view or substructure-view features, limiting predictive capacity. The scarcity of research on interpretability studies based on multi-view features is crucial for tracing interactions. Addressing this gap, we present MI-DDI, a multi-view feature-based interpretable deep learning framework for DDI. To fully extract multi-view features, we employ a Message Passing Neural Network (MPNN) to learn atomic features from molecular graphs generated by RDkit, and transformer encoders are used to learn substructure-view embeddings from drug SMILES simultaneously. These atomic-view and substructure-view features are then amalgamated into a holistic drug embedding matrix. Subsequently, an intricately designed interaction module not only establishes a tractable path for understanding interactions but also directly informs the construction of weight matrices, enabling precise and interpretable interaction predictions. Validation on the BIOSNAP dataset and DrugBank dataset demonstrates MI-DDI's superiority. It surpasses the current benchmarks by a substantial average of 3% on BIOSNAP and 1% on DrugBank. Additional experiments underscore the significance of atomic-view information for DDI prediction and confirm that our interaction module indeed learns more effective information for DDI prediction. The source codes are available at https://github.com/ZihuiCheng/MI-DDI .","PeriodicalId":13670,"journal":{"name":"Interdisciplinary Sciences: Computational Life Sciences","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2025-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143079679","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}

引用次数: 0