Interdisciplinary Sciences: Computational Life Sciences最新文献_第10页

Enabling Drug-Drug Interaction Event Prediction with Multi-view-enhanced Chemical Structural Information. 利用多视图增强的化学结构信息实现药物-药物相互作用事件预测。

IF 3.9 2区生物学

Interdisciplinary Sciences: Computational Life Sciences Pub Date : 2026-05-26 DOI: 10.1007/s12539-026-00830-x

Ge Jin, Junlin Xu, Hongxin Xiang, Xuan Yu, Zhiwei Xu, Anqi Huang, Jingyang Xia, Shuting Jin

{"title":"Enabling Drug-Drug Interaction Event Prediction with Multi-view-enhanced Chemical Structural Information.","authors":"Ge Jin, Junlin Xu, Hongxin Xiang, Xuan Yu, Zhiwei Xu, Anqi Huang, Jingyang Xia, Shuting Jin","doi":"10.1007/s12539-026-00830-x","DOIUrl":"https://doi.org/10.1007/s12539-026-00830-x","url":null,"abstract":"Predicting drug-drug interaction (DDI) events is critical for ensuring patient safety, optimizing therapeutic efficacy, and advancing drug discovery. Deep learning-based models have recently attracted considerable attention in this domain and achieved promising results. However, most existing approaches insufficiently account for both the chemical structural information of drugs and the multiplicity of interaction types, thereby limiting predictive accuracy. In this work, we present ChemDDI, a deep learning framework for DDI event prediction enabled by multi-view-enhanced chemical structural information. Specifically, ChemDDI employs multi-view graph- and image-based encoders to extract chemical structural information from three-dimensional conformations. Building on these chemically informed representations, ChemDDI incorporates multi-relational interaction information through Transformer-based graph neural networks and relational graph embeddings, while contrastive learning further aligns interaction features to enable robust DDI event prediction. Extensive experiments demonstrate that ChemDDI consistently outperforms state-of-the-art baselines, achieving substantial gains on rare interaction events. ChemDDI is available at https://github.com/gjin-DLOU/ChemDDI .","PeriodicalId":13670,"journal":{"name":"Interdisciplinary Sciences: Computational Life Sciences","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2026-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148029962","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

CDM-UNet: Content-Driven Enhanced Mamba Model for Medical Image Segmentation. CDM-UNet：用于医学图像分割的内容驱动的增强曼巴模型。

IF 3.9 2区生物学

Interdisciplinary Sciences: Computational Life Sciences Pub Date : 2026-05-21 DOI: 10.1007/s12539-026-00841-8

Fan Zhang, Hui Chen, Binjie Wang, Xinhong Zhang

{"title":"CDM-UNet: Content-Driven Enhanced Mamba Model for Medical Image Segmentation.","authors":"Fan Zhang, Hui Chen, Binjie Wang, Xinhong Zhang","doi":"10.1007/s12539-026-00841-8","DOIUrl":"https://doi.org/10.1007/s12539-026-00841-8","url":null,"abstract":"Segmenting medical images plays a pivotal role in diagnosis, treatment planning, and healthcare. Recent advancements in deep learning have significantly transformed this domain. Convolutional Neural Networks (CNNs) are proficient at extracting local image features, while Vision Transformers (ViTs) excel in capturing long-range dependencies through self-attention mechanisms. However, both approaches face limitations when dealing with intricate anatomical structures, unclear lesion boundaries, and scale variations. Additionally, they often require substantial computational resources. To tackle these challenges, this study introduces CDM-UNet, designed to improve upon the limitations of existing models in feature representation and fusion. It also investigates the potential of hybrid Mamba models for advancing their application in this domain. CDM-UNet combines Mamba's global feature modeling capabilities with lightweight attention mechanisms. The core component of CDM-UNet is Content Driven Mamba Block (CDMB), and a SCConv-Based Attention Gate (SAG) module is introduced to suppress the influence of irrelevant information. Comprehensive evaluations on the ISIC17, ISIC18, and Synapse datasets demonstrate that CDM-UNet outperforms existing mainstream models across multiple evaluation criteria, including Dice Similarity Coefficient (DSC) and mean Intersection over Union (mIoU), underscoring its excellent segmentation performance in medical image processing.","PeriodicalId":13670,"journal":{"name":"Interdisciplinary Sciences: Computational Life Sciences","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2026-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147981715","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

BrainDEC: An M/EEG Unsupervised Representation Learning Framework with Disentangled Equivariance Constraint. 一种具有解纠缠等方差约束的M/EEG无监督表示学习框架。

IF 3.9 2区生物学

Interdisciplinary Sciences: Computational Life Sciences Pub Date : 2026-05-21 DOI: 10.1007/s12539-026-00834-7

Xingyuan Song, Qiong Li, Haokun Mao, Yongdong Fan

{"title":"BrainDEC: An M/EEG Unsupervised Representation Learning Framework with Disentangled Equivariance Constraint.","authors":"Xingyuan Song, Qiong Li, Haokun Mao, Yongdong Fan","doi":"10.1007/s12539-026-00834-7","DOIUrl":"https://doi.org/10.1007/s12539-026-00834-7","url":null,"abstract":"Magnetoencephalography (MEG) and electroencephalography (EEG) are prominent non-invasive brain imaging techniques that have attracted considerable interest in neuroscience research. Unsupervised learning of M/EEG signals has become a critical area of focus. However, existing data transformation strategies often introduce representation space biases, whether through random and mechanical methods or adaptive approaches that rely on prior knowledge, which limits the effectiveness of unsupervised M/EEG signal analysis. To overcome these challenges, we propose a novel unsupervised learning method BrainDEC that enhances the extraction of robust and generalizable M/EEG features. By employing a disentanglement framework, we disentangle invariance and equivariance features in a manner that enables more precise and transparent control over the equivariance training process. This adjustment leads to improved transparency and greater precision in the learned representations. Extensive experiments across multiple M/EEG datasets demonstrate the superior performance of our approach in both linear and semi-supervised evaluation settings. Our method holds great promise for advancing brain signal analysis in downstream tasks, all within an unsupervised learning framework.","PeriodicalId":13670,"journal":{"name":"Interdisciplinary Sciences: Computational Life Sciences","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2026-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147981660","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

HP-MoleQ: An Effective Predictive Model for High-Throughput Screening of Food-Derived Hepatoprotective Compounds. HP-MoleQ：一种高通量筛选食源性肝保护化合物的有效预测模型。

IF 3.9 2区生物学

Interdisciplinary Sciences: Computational Life Sciences Pub Date : 2026-05-11 DOI: 10.1007/s12539-026-00838-3

Qinyi Wang, Fangyuan Wang, Jiao Wang, Yunhui Zhuo, Junjie Tang, Xia Wei, Xiaoqing Guan, Ying Xu

{"title":"HP-MoleQ: An Effective Predictive Model for High-Throughput Screening of Food-Derived Hepatoprotective Compounds.","authors":"Qinyi Wang, Fangyuan Wang, Jiao Wang, Yunhui Zhuo, Junjie Tang, Xia Wei, Xiaoqing Guan, Ying Xu","doi":"10.1007/s12539-026-00838-3","DOIUrl":"https://doi.org/10.1007/s12539-026-00838-3","url":null,"abstract":"Hepatoprotective natural compounds are pivotal constituents for the formulation of functional foods and the prophylaxis of hepatic disorders. To enhance the efficiency and reliability of hepatoprotective compound discovery, we propose a new predictive framework named HP-MoleQ. It comprises a pretrained Transformer and an uncertainty quantification module. HP-MoleQ outperforms existing models and enables high-confidence screening of the FoodB database. Compounds are ranked according to 95% confidence interval width lower bound. Top 20 candidates, including 12 phenolic glucopyranosides, 5 phenolic furanosides and 3 flavonoid glycosides, were prioritized. Three candidates (1,2,6-trigalloyl-beta-D-glucopyranose, hamamelitannin, and 6-hydroxyluteolin 7-glucoside) were represented and chosen for experimental validation. In cellular models of alcohol-induced hepatotoxicity and oleic acid and palmitic acid-induced steatosis, the three candidates attenuated intracellular triglyceride, aspartate aminotransferase, and alanine transaminase, inhibited lipid droplet formation, and enhanced albumin production. These findings not only confirm the hepatoprotective efficacy of these compounds but also highlight the utility of the HP-MoleQ platform in identifying potential hepatoprotective agents.","PeriodicalId":13670,"journal":{"name":"Interdisciplinary Sciences: Computational Life Sciences","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2026-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147868304","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

Pan-cancer Distant Metastasis Prediction Based on Graph Neural Network. 基于图神经网络的泛癌远处转移预测。

IF 3.9 2区生物学

Interdisciplinary Sciences: Computational Life Sciences Pub Date : 2026-05-11 DOI: 10.1007/s12539-026-00844-5

Fengyun Zhang, Qiangguo Jin, Changming Sun, Ruibing Chen, Jie Geng, Siqi Chen, Wenrun Cai, Xugang Sun, Xiaofeng Liu, Ran Su

{"title":"Pan-cancer Distant Metastasis Prediction Based on Graph Neural Network.","authors":"Fengyun Zhang, Qiangguo Jin, Changming Sun, Ruibing Chen, Jie Geng, Siqi Chen, Wenrun Cai, Xugang Sun, Xiaofeng Liu, Ran Su","doi":"10.1007/s12539-026-00844-5","DOIUrl":"https://doi.org/10.1007/s12539-026-00844-5","url":null,"abstract":"Distant metastasis (DM) is the primary driver of cancer-related mortality, and its clinical prediction remains challenging due to the lack of robust biomarkers. This study proposes a novel graph representation that effectively identifies discriminative morphological features from histopathological whole slide images (WSIs). By transforming high-resolution WSIs into topological graphs, the proposed method leverages graph neural networks (GNNs) to capture complex spatial dependencies and cellular organizations critical for metastatic progression. The study is evaluated on a large-scale pan-cancer dataset and demonstrates superior performance in distilling shared metastatic patterns across diverse malignancies. Furthermore, the cross-dataset robustness of this representation is validated by training on a specialized nasopharyngeal carcinoma cohort (TJ-NPC) and evaluating on independent public datasets. The results highlight the potential of computational pathology to provide scalable, objective risk stratification, offering a high accuracy tool for personalized clinical intervention.","PeriodicalId":13670,"journal":{"name":"Interdisciplinary Sciences: Computational Life Sciences","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2026-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147868321","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

Hybrid Encoding and Adaptive Guidance for Enhanced Single-Cell Multi-omics Clustering. 增强单细胞多组学聚类的混合编码和自适应制导。

IF 3.9 2区生物学

Interdisciplinary Sciences: Computational Life Sciences Pub Date : 2026-05-11 DOI: 10.1007/s12539-026-00827-6

Jing Li, Hong Wang, Jiafeng Yu, Cheng Liang, Xingtang Zhao, Jun Zhao, Yanshen Sun

{"title":"Hybrid Encoding and Adaptive Guidance for Enhanced Single-Cell Multi-omics Clustering.","authors":"Jing Li, Hong Wang, Jiafeng Yu, Cheng Liang, Xingtang Zhao, Jun Zhao, Yanshen Sun","doi":"10.1007/s12539-026-00827-6","DOIUrl":"https://doi.org/10.1007/s12539-026-00827-6","url":null,"abstract":"Cluster analysis is essential in single-cell multi-omics research, allowing for simultaneous analysis across different omics levels. It reveals cellular diversity and precisely differentiates cell types and their physiological states. Despite advancements in clustering methods for single-cell multi-omics, challenges persist in analyzing the complexity of multi-omics data, integrating information across dimensions, ensuring dynamic adaptability, and maintaining consistent representation. Existing methods often fall short in capturing the full complexity and diversity of the data, tend to overemphasize local details while neglecting global patterns, and lack flexible clustering objectives. To tackle these limitations, we introduce scHEAGC, a novel hybrid encoding and adaptive guidance framework for enhanced single-cell multi-omics clustering. Our model employs a hybrid encoding strategy, integrating discrete and continuous techniques with vector quantization encoders (VQ-VAEs) and graph autoencoders (GAEs) to improve data representation. Furthermore, we design a multi-layer information fusion strategy that robustly integrates multi-dimensional data at both local and global levels, leveraging diverse embedding types. Additionally, our model includes an adaptive guided clustering module that dynamically adjusts targets in response to changes in the loss function, promoting iterative optimization. The hybrid encoding and the adaptive guided information fusion strategies we present are effective for single-cell multi-omics clustering and extendable to other fields. Experimental results demonstrate that scHEAGC outperforms existing methods across six real datasets, offering a powerful new tool for single-cell multi-omics data analysis.","PeriodicalId":13670,"journal":{"name":"Interdisciplinary Sciences: Computational Life Sciences","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2026-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147868328","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

VFLING: Vertical Federated Learning for Multi-Omics Data Integration with Graphs. VFLING：多组学数据与图集成的垂直联邦学习。

IF 3.9 2区生物学

Interdisciplinary Sciences: Computational Life Sciences Pub Date : 2026-05-08 DOI: 10.1007/s12539-026-00825-8

Xiaoli Li, Qi Li, Dedao Lu, Yue Lin, Saba Aslam, Huijun Li, Zequn Zhang, Yuxi Chen, Ruey-Song Huang, Hongyan Wu

{"title":"VFLING: Vertical Federated Learning for Multi-Omics Data Integration with Graphs.","authors":"Xiaoli Li, Qi Li, Dedao Lu, Yue Lin, Saba Aslam, Huijun Li, Zequn Zhang, Yuxi Chen, Ruey-Song Huang, Hongyan Wu","doi":"10.1007/s12539-026-00825-8","DOIUrl":"https://doi.org/10.1007/s12539-026-00825-8","url":null,"abstract":"Modern machine learning models leveraging multi-omics data face significant privacy challenges due to the sensitive nature of patient information. Communication overhead and missing features in each institution can lead to a substantial decline in federated learning performance. In response to these concerns, we propose VFLING-Federated Learning for Multi-Omics Data Integration with Graphs-a secure one-shot communication federated learning framework. We note that medical data reflects disease characteristics from different omics, while the relationships between samples exhibit relative stability across these omics. To minimize data transmission while maximizing the utilization of each participant's feature information we develop a strategy that transmits not only the local features but also the relationships or topology in one-shot communication. By fusing the omics based on the locally learned graph structure instead of features, VFLING enables improved performance even when some features are missing from individual parties. Extensive experiments demonstrate that VFLING outperforms existing frameworks, paving the way for applications in the medical field. Local features and graph topology are shared to the trainable server in a single communication, enhancing model accuracy through integrated data. This approach improves robustness despite incomplete information. Local Parties and Server Integration: Local parties learn and transmit both local features and graph topology to the server in a single communication, maximizing effective information transfer. The trainable server then integrates data across parties using graph relationships, enhancing model robustness and accuracy despite incomplete feature sets.","PeriodicalId":13670,"journal":{"name":"Interdisciplinary Sciences: Computational Life Sciences","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2026-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147837345","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 Bimodal Graph Neural Network with Transfer Learning and Contrastive Learning for Protein-Protein Interaction Site Prediction. 基于迁移学习和对比学习的双峰图神经网络在蛋白质相互作用位点预测中的应用。

IF 3.9 2区生物学

Interdisciplinary Sciences: Computational Life Sciences Pub Date : 2026-05-05 DOI: 10.1007/s12539-026-00842-7

Sheng Chang, Boyan Zhang, Changbo Li, Fan Zhang

{"title":"A Bimodal Graph Neural Network with Transfer Learning and Contrastive Learning for Protein-Protein Interaction Site Prediction.","authors":"Sheng Chang, Boyan Zhang, Changbo Li, Fan Zhang","doi":"10.1007/s12539-026-00842-7","DOIUrl":"https://doi.org/10.1007/s12539-026-00842-7","url":null,"abstract":"Accurate prediction of protein-protein interaction sites (PPIS) is crucial for understanding molecular mechanisms and advancing precision medicine. However, due to the complexity of protein structure and function, as well as the sequential and spatial heterogeneity of PPIS, accurately predicting these sites remains a major challenge. To address the limitations of existing methods in feature representation and class imbalance, this paper proposes TransPPIS, a transfer learning and contrastive learning based method for predicting PPIS using bimodal graphs. Specifically, TransPPIS constructs a structural graph from the three-dimensional structure of a protein and models its sequence as a de Bruijn graph. Then, an unsupervised pretraining combined with a transfer learning strategy is employed, transferring a graph convolutional network pre-trained on a large-scale protein dataset to the PPIS prediction task. In addition, we design a supervised contrastive learning module, which optimizes cross-modal feature consistency and class discriminability through a dual mechanism of collaborative contrast and positive-negative sample contrast, effectively mitigating class imbalance. Experimental results demonstrate that TransPPIS consistently outperforms state-of-the-art methods on multiple independent test sets, exhibiting superior prediction accuracy, robustness, and generalization. Ablation studies further confirm the effectiveness of each module and validate the synergistic benefits of structured modeling, transfer learning, and supervised contrastive learning. These results suggest that TransPPIS provides a powerful tool for efficiently and accurately deciphering complex protein interaction networks. The source code of TransPPIS is available at https://github.com/houyichi6-netizen/transppis .","PeriodicalId":13670,"journal":{"name":"Interdisciplinary Sciences: Computational Life Sciences","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2026-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147836959","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

MOFR: Multi-omics Feature Reconstruction for Cancer Classification and Metastasis Prediction. MOFR：多组学特征重建用于肿瘤分类和转移预测。

IF 5.2 2区生物学

Interdisciplinary Sciences: Computational Life Sciences Pub Date : 2026-05-05 DOI: 10.1007/s12539-025-00804-5

Yun Tie, Dalong Zhang, Lei Shi, Ying Wang, Xin Chen, YiPeng Wang, Song Wang

{"title":"MOFR: Multi-omics Feature Reconstruction for Cancer Classification and Metastasis Prediction.","authors":"Yun Tie, Dalong Zhang, Lei Shi, Ying Wang, Xin Chen, YiPeng Wang, Song Wang","doi":"10.1007/s12539-025-00804-5","DOIUrl":"10.1007/s12539-025-00804-5","url":null,"abstract":"Deep learning for cancer intelligent diagnosis based on multi-omics data has achieved enormous advance in the condition of sufficient samples. However, these methods can’t generalize to circumstances that certain cancer samples are few, which poses a challenge for few-shot learning to apply in it. Therefore, we propose a few-shot learning algorithm, called the multi-omics feature reconstruction (MOFR), to realize the cancer classification and the metastasis prediction. Specifically, MOFR transforms the classification problem into a feature reconstruction issue in latent space. This approach needs fewer learning parameters, which facilitates model fitting in such environment. By directly regressing the ’distance’ between the support feature set and the query feature, it achieves classification tasks. Additionally, we also design a tailored feature extractor to effectively map raw data into high-level and informative features. It draws inspiration from the Transformer architecture but overcomes the need for extensive training data to train the model. According to extensive experimental results, the proposed few-shot learning algorithm surpasses homogeneous approaches in both classification and metastasis prediction performance. We provide detailed code for the new model proposed in this paper on https://github.com/vbfeobveofn/Code.git . ","PeriodicalId":13670,"journal":{"name":"Interdisciplinary Sciences: Computational Life Sciences","volume":" ","pages":""},"PeriodicalIF":5.2,"publicationDate":"2026-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147837328","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

Spatial Mapping of Single Cells via Correlation and Importance Between Cells and Spots. 基于细胞与点之间相关性和重要性的单细胞空间映射。

IF 3.9 2区生物学

Interdisciplinary Sciences: Computational Life Sciences Pub Date : 2026-04-29 DOI: 10.1007/s12539-026-00837-4

Juntao Li, Mengyuan Wang, Chenxi Xi, Shan Xiang, Yun Wang, Dongqing Wei

{"title":"Spatial Mapping of Single Cells via Correlation and Importance Between Cells and Spots.","authors":"Juntao Li, Mengyuan Wang, Chenxi Xi, Shan Xiang, Yun Wang, Dongqing Wei","doi":"10.1007/s12539-026-00837-4","DOIUrl":"https://doi.org/10.1007/s12539-026-00837-4","url":null,"abstract":"Mapping cells to spatial locations is crucial for understanding biological processes, disease mechanisms, and therapeutic strategies. However, dropout events in both spatial transcriptomics and scRNA-seq data, along with intercellular interactions and spatial dependencies among spots, challenge the accuracy of spatial mapping. This study proposes a novel method termed Spatial Mapping of single cells via Correlation and Importance between cells and spots (SM-CI). We introduce dropout handling strategies specifically designed for both spatial transcriptomics and scRNA-seq data. Imputation index sets and dropout imputation functions tailored to each data type are developed: the first effectively utilizes spatial location and gene expression information, while the second leverages data from neighboring cell types. Furthermore, we establish criteria for assessing the importance of spots (or cells) in relation to others and construct a linear programming model that integrates these criteria with correlation measures to enhance spatial mapping accuracy. Benchmarking on simulated datasets shows that SM-CI consistently outperforms existing methods across four metrics, while applications to real datasets demonstrate its effectiveness in reconstructing spatial distributions of diverse cell types across tissues. Additionally, ablation experiments validate the effectiveness of the dropout handling strategies and importance assessment criteria.","PeriodicalId":13670,"journal":{"name":"Interdisciplinary Sciences: Computational Life Sciences","volume":" ","pages":""},"PeriodicalIF":3.9,"publicationDate":"2026-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147770629","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