BMC Bioinformatics最新文献

{"title":"BioLake: an RNA expression analysis framework for prostate cancer biomarker powered by data lakehouse.","authors":"Qiaowang Li, Yaser Gamallat, Jon George Rokne, Tarek A Bismar, Reda Alhajj","doi":"10.1186/s12859-025-06050-2","DOIUrl":"10.1186/s12859-025-06050-2","url":null,"abstract":"<p><p>Biomedical researchers must often deal with large amounts of raw data, and analysis of this data might provide significant insights. However, if the raw data size is large, it might be difficult to uncover these insights. In this paper, a data framework named BioLake is presented that provides minimalist interactive methods to help researchers conduct bioinformatics data analysis. Unlike some existing analytical tools on the market, BioLake supports a wide range of web-based bioinformatics data analysis for public datasets, while allowing researchers to analyze their private datasets instantly. The tool also significantly enhances result interpretability by providing the source code and detailed instructions. In terms of data storage design, BioLake adopts the data lakehouse architecture to provide storage scalability and analysis flexibility. To further enhance the analysis efficiency, BioLake supports online analysis for custom data, allowing researchers to upload their own data via a designed procedure without waiting for server-side approval. BioLake allows a one-time upload of custom data of up to 500 MB to ensure that researchers avoid issues with data being too large for upload. In terms of the built-in dataset, BioLake applies reactive continuous data integration, helping the analysis pipeline to get rid of most preprocessing steps. The only pre-built-in dataset of BioLake in the first public version is TCGA-PRAD mRNA expression data for prostate cancer research, which is the primary focus of the development team of BioLake. In summary, BioLake offers a lightweight online tool to facilitate bioinformatic mRNA data analysis with the support of custom online data processing.</p>","PeriodicalId":8958,"journal":{"name":"BMC Bioinformatics","volume":"26 1","pages":"37"},"PeriodicalIF":2.9,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11792420/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143187989","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Accurate assembly of full-length consensus for viral quasispecies.","authors":"Jia Tian, Ziyu Gao, Minghao Li, Ergude Bao, Jin Zhao","doi":"10.1186/s12859-025-06045-z","DOIUrl":"10.1186/s12859-025-06045-z","url":null,"abstract":"<p><strong>Background: </strong>Viruses can inhabit their hosts in the form of an ensemble of various mutant strains. Reconstructing a robust consensus representation for these diverse mutant strains is essential for recognizing the genetic variations among strains and delving into aspects like virulence, pathogenesis, and selecting therapies. Virus genomes are typically small, often composed of only a few thousand to several hundred thousand nucleotides. While constructing a high-quality consensus of virus strains might seem feasible, most current assemblers only generated fragmented contigs. It's important to emphasize the significance of assembling a single full-length consensus contig, as it's vital for identifying genetic diversity and estimating strain abundance accurately.</p><p><strong>Results: </strong>In this paper, we developed FC-Virus, a de novo genome assembly strategy specifically targeting highly diverse viral populations. FC-Virus first identifies the k-mers that are common across most viral strains, and then uses these k-mers as a backbone to build a full-length consensus sequence covering the entire genome. We benchmark FC-Virus against state-of-the-art genome assemblers.</p><p><strong>Conclusion: </strong>Experimental results confirm that FC-Virus can construct a single, accurate full-length consensus, whereas other assemblers only manage to produce fragmented contigs. FC-Virus is freely available at https://github.com/qdu-bioinfo/FC-Virus.git .</p>","PeriodicalId":8958,"journal":{"name":"BMC Bioinformatics","volume":"26 1","pages":"36"},"PeriodicalIF":2.9,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11787740/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143073632","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Flexible analysis of spatial transcriptomics data (FAST): a deconvolution approach.","authors":"Meng Zhang, Joel Parker, Lingling An, Yiwen Liu, Xiaoxiao Sun","doi":"10.1186/s12859-025-06054-y","DOIUrl":"10.1186/s12859-025-06054-y","url":null,"abstract":"<p><strong>Motivation: </strong>Spatial transcriptomics is a state-of-art technique that allows researchers to study gene expression patterns in tissues over the spatial domain. As a result of technical limitations, the majority of spatial transcriptomics techniques provide bulk data for each sequencing spot. Consequently, in order to obtain high-resolution spatial transcriptomics data, performing deconvolution becomes essential. Most existing deconvolution methods rely on reference data (e.g., single-cell data), which may not be available in real applications. Current reference-free methods encounter limitations due to their dependence on distribution assumptions, reliance on marker genes, or the absence of leveraging histology and spatial information. Consequently, there is a critical need for the development of highly flexible, robust, and user-friendly reference-free deconvolution methods capable of unifying or leveraging case-specific information in the analysis of spatial transcriptomics data.</p><p><strong>Results: </strong>We propose a novel reference-free method based on regularized non-negative matrix factorization (NMF), named Flexible Analysis of Spatial Transcriptomics (FAST), that can effectively incorporate gene expression data, spatial, and histology information into a unified deconvolution framework. Compared to existing methods, FAST imposes fewer distribution assumptions, utilizes the spatial structure information of tissues, and encourages interpretable factorization results. These features enable greater flexibility and accuracy, making FAST an effective tool for deciphering the complex cell-type composition of tissues and advancing our understanding of various biological processes and diseases. Extensive simulation studies have shown that FAST outperforms other existing reference-free methods. In real data applications, FAST is able to uncover the underlying tissue structures and identify the corresponding marker genes.</p>","PeriodicalId":8958,"journal":{"name":"BMC Bioinformatics","volume":"26 1","pages":"35"},"PeriodicalIF":2.9,"publicationDate":"2025-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11786350/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143073656","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Biomedical named entity recognition using improved green anaconda-assisted Bi-GRU-based hierarchical ResNet model.","authors":"Ram Chandra Bhushan, Rakesh Kumar Donthi, Yojitha Chilukuri, Ulligaddala Srinivasarao, Polisetty Swetha","doi":"10.1186/s12859-024-06008-w","DOIUrl":"10.1186/s12859-024-06008-w","url":null,"abstract":"<p><strong>Background: </strong>Biomedical text mining is a technique that extracts essential information from scientific articles using named entity recognition (NER). Traditional NER methods rely on dictionaries, rules, or curated corpora, which may not always be accessible. To overcome these challenges, deep learning (DL) methods have emerged. However, DL-based NER methods may need help identifying long-distance relationships within text and require significant annotated datasets.</p><p><strong>Results: </strong>This research has proposed a novel model to address the challenges in natural language processing. The Improved Green anaconda-assisted Bi-GRU based Hierarchical ResNet BNER model (IGa-BiHR BNERM) is the model. IGa-BiHR BNERM model has shown promising results in accurately identifying named entities. The MACCROBAT dataset was obtained from Kaggle and underwent several pre-processing steps such as Stop Word Filtering, WordNet processing, Removal of non-alphanumeric characters, stemming Segmentation, and Tokenization, which is standardized and improves its quality. The pre-processed text was fed into a feature extraction model like the Robustly Optimized BERT -Whole Word Masking model. This model provides word embeddings with semantic information. Then, the BNER process utilized an Improved Green Anaconda-assisted Bi-GRU-based Hierarchical ResNet BNER model (IGa-BiHR BNERM).</p><p><strong>Conclusion: </strong>To improve the training phase of the IGa-BiHR BNERM, the Improved Green Anaconda Optimization technique was used to select optimal weight parameter coefficients for training the model parameters. After the model was tested using the MACCROBAT dataset, it outperformed previous models with a tremendous accuracy rate of 99.11%. This model effectively and accurately identifies biomedical names within the text, significantly advancing this field.</p>","PeriodicalId":8958,"journal":{"name":"BMC Bioinformatics","volume":"26 1","pages":"34"},"PeriodicalIF":2.9,"publicationDate":"2025-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11780922/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143063556","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"scSMD: a deep learning method for accurate clustering of single cells based on auto-encoder.","authors":"Xiaoxu Cui, Renkai Wu, Yinghao Liu, Peizhan Chen, Qing Chang, Pengchen Liang, Changyu He","doi":"10.1186/s12859-025-06047-x","DOIUrl":"10.1186/s12859-025-06047-x","url":null,"abstract":"<p><strong>Background: </strong>Single-cell RNA sequencing (scRNA-seq) has transformed biological research by offering new insights into cellular heterogeneity, developmental processes, and disease mechanisms. As scRNA-seq technology advances, its role in modern biology has become increasingly vital. This study explores the application of deep learning to single-cell data clustering, with a particular focus on managing sparse, high-dimensional data.</p><p><strong>Results: </strong>We propose the SMD deep learning model, which integrates nonlinear dimensionality reduction techniques with a porous dilated attention gate component. Built upon a convolutional autoencoder and informed by the negative binomial distribution, the SMD model efficiently captures essential cell clustering features and dynamically adjusts feature weights. Comprehensive evaluation on both public datasets and proprietary osteosarcoma data highlights the SMD model's efficacy in achieving precise classifications for single-cell data clustering, showcasing its potential for advanced transcriptomic analysis.</p><p><strong>Conclusion: </strong>This study underscores the potential of deep learning-specifically the SMD model-in advancing single-cell RNA sequencing data analysis. By integrating innovative computational techniques, the SMD model provides a powerful framework for unraveling cellular complexities, enhancing our understanding of biological processes, and elucidating disease mechanisms. The code is available from  https://github.com/xiaoxuc/scSMD .</p>","PeriodicalId":8958,"journal":{"name":"BMC Bioinformatics","volume":"26 1","pages":"33"},"PeriodicalIF":2.9,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11780796/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143063557","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Marigold: a machine learning-based web app for zebrafish pose tracking.","authors":"Gregory Teicher, R Madison Riffe, Wayne Barnaby, Gabrielle Martin, Benjamin E Clayton, Josef G Trapani, Gerald B Downes","doi":"10.1186/s12859-025-06042-2","DOIUrl":"10.1186/s12859-025-06042-2","url":null,"abstract":"<p><strong>Background: </strong>High-throughput behavioral analysis is important for drug discovery, toxicological studies, and the modeling of neurological disorders such as autism and epilepsy. Zebrafish embryos and larvae are ideal for such applications because they are spawned in large clutches, develop rapidly, feature a relatively simple nervous system, and have orthologs to many human disease genes. However, existing software for video-based behavioral analysis can be incompatible with recordings that contain dynamic backgrounds or foreign objects, lack support for multiwell formats, require expensive hardware, and/or demand considerable programming expertise. Here, we introduce Marigold, a free and open source web app for high-throughput behavioral analysis of embryonic and larval zebrafish.</p><p><strong>Results: </strong>Marigold features an intuitive graphical user interface, tracks up to 10 user-defined keypoints, supports both single- and multiwell formats, and exports a range of kinematic parameters in addition to publication-quality data visualizations. By leveraging a highly efficient, custom-designed neural network architecture, Marigold achieves reasonable training and inference speeds even on modestly powered computers lacking a discrete graphics processing unit. Notably, as a web app, Marigold does not require any installation and runs within popular web browsers on ChromeOS, Linux, macOS, and Windows. To demonstrate Marigold's utility, we used two sets of biological experiments. First, we examined novel aspects of the touch-evoked escape response in techno trousers (tnt) mutant embryos, which contain a previously described loss-of-function mutation in the gene encoding Eaat2b, a glial glutamate transporter. We identified differences and interactions between touch location (head vs. tail) and genotype. Second, we investigated the effects of feeding on larval visuomotor behavior at 5 and 7 days post-fertilization (dpf). We found differences in the number and vigor of swimming bouts between fed and unfed fish at both time points, as well as interactions between developmental stage and feeding regimen.</p><p><strong>Conclusions: </strong>In both biological experiments presented here, the use of Marigold facilitated novel behavioral findings. Marigold's ease of use, robust pose tracking, amenability to diverse experimental paradigms, and flexibility regarding hardware requirements make it a powerful tool for analyzing zebrafish behavior, especially in low-resource settings such as course-based undergraduate research experiences. Marigold is available at: https://downeslab.github.io/marigold/ .</p>","PeriodicalId":8958,"journal":{"name":"BMC Bioinformatics","volume":"26 1","pages":"30"},"PeriodicalIF":2.9,"publicationDate":"2025-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11773884/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143057892","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Correcting scale distortion in RNA sequencing data.","authors":"Christopher Thron, Farhad Jafari","doi":"10.1186/s12859-025-06041-3","DOIUrl":"10.1186/s12859-025-06041-3","url":null,"abstract":"<p><p>RNA sequencing (RNA-seq) is the conventional genome-scale approach used to capture the expression levels of all detectable genes in a biological sample. This is now regularly used for population-based studies designed to identify genetic determinants of various diseases. Naturally, the accuracy of these tests should be verified and improved if possible. In this study, we aimed to detect and correct for expression level-dependent errors which are not corrected by conventional normalization techniques. We examined several RNA-seq datasets from the Cancer Genome Atlas (TCGA), Stand Up 2 Cancer (SU2C), and GTEx databases with various types of preprocessing. By applying local averaging, we found expression-level dependent biases that differ from sample to sample in all datasets studied. Using simulations, we show that these biases corrupt gene-gene correlation estimations and t tests between subpopulations. To mitigate these biases, we introduce two different nonlinear transforms based on statistical considerations that correct these observed biases. We demonstrate that these transforms effectively remove the observed per-sample biases, reduce sample-to-sample variance, and improve the characteristics of gene-gene correlation distributions. Using a novel simulation methodology that creates controlled differences between subpopulations, we show that these transforms reduce variability and increase sensitivity of two population tests. The improvements in sensitivity and specificity were of the order of 3-5% in most instances after the data was corrected for bias. Altogether, these results improve our capacity to understand gene-gene relationships, and may lead to novel ways to utilize the information derived from clinical tests.</p>","PeriodicalId":8958,"journal":{"name":"BMC Bioinformatics","volume":"26 1","pages":"32"},"PeriodicalIF":2.9,"publicationDate":"2025-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11776150/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143057890","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Metadag: a web tool to generate and analyse metabolic networks.","authors":"Pere Palmer-Rodríguez, Ricardo Alberich, Mariana Reyes-Prieto, José A Castro, Mercè Llabrés","doi":"10.1186/s12859-025-06048-w","DOIUrl":"10.1186/s12859-025-06048-w","url":null,"abstract":"<p><strong>Background: </strong>MetaDAG is a web-based tool developed to address challenges posed by big data from omics technologies, particularly in metabolic network reconstruction and analysis. The tool is capable of constructing metabolic networks for specific organisms, sets of organisms, reactions, enzymes, or KEGG Orthology (KO) identifiers. By retrieving data from the KEGG database, MetaDAG helps users visualize and analyze complex metabolic interactions efficiently.</p><p><strong>Results: </strong>MetaDAG computes two models: a reaction graph and a metabolic directed acyclic graph (m-DAG). The reaction graph represents reactions as nodes and metabolite flow between them as edges. The m-DAG simplifies the reaction graph by collapsing strongly connected components, significantly reducing the number of nodes while maintaining connectivity. MetaDAG can generate metabolic networks from various inputs, including KEGG organisms or custom data (e.g., reactions, enzymes, KOs). The tool displays these models on an interactive web page and provides downloadable files, including network visualizations. MetaDAG was tested using two datasets. In an eukaryotic analysis, it successfully classified organisms from the KEGG database at the kingdom and phylum levels. In a microbiome study, MetaDAG accurately distinguished between Western and Korean diets and categorized individuals by weight loss outcomes based on dietary interventions.</p><p><strong>Conclusion: </strong>MetaDAG offers an effective and versatile solution for metabolic network reconstruction from diverse data sources, enabling large-scale biological comparisons. Its ability to generate synthetic metabolisms and its broad application, from taxonomy classification to diet analysis, make it a valuable tool for biological research. MetaDAG is available online, with user support provided via a comprehensive guide. MetaDAG: https://bioinfo.uib.es/metadag/ User guide: https://biocom-uib.github.io/MetaDag/.</p>","PeriodicalId":8958,"journal":{"name":"BMC Bioinformatics","volume":"26 1","pages":"31"},"PeriodicalIF":2.9,"publicationDate":"2025-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11776228/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143057843","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hybrid generative adversarial network based on frequency and spatial domain for histopathological image synthesis.","authors":"Qifeng Liu, Tao Zhou, Chi Cheng, Jin Ma, Marzia Hoque Tania","doi":"10.1186/s12859-025-06057-9","DOIUrl":"10.1186/s12859-025-06057-9","url":null,"abstract":"<p><strong>Background: </strong>Due to the complexity and cost of preparing histopathological slides, deep learning-based methods have been developed to generate high-quality histological images. However, existing approaches primarily focus on spatial domain information, neglecting the periodic information in the frequency domain and the complementary relationship between the two domains. In this paper, we proposed a generative adversarial network that employs a cross-attention mechanism to extract and fuse features across spatial and frequency domains. The method optimizes frequency domain features using spatial domain guidance and refines spatial features with frequency domain information, preserving key details while eliminating redundancy to generate high-quality histological images.</p><p><strong>Results: </strong>Our model incorporates a variable-window mixed attention module to dynamically adjust attention window sizes, capturing both local details and global context. A spectral filtering module enhances the extraction of repetitive textures and periodic structures, while a cross-attention fusion module dynamically weights features from both domains, focusing on the most critical information to produce realistic and detailed images.</p><p><strong>Conclusions: </strong>The proposed method achieves efficient spatial-frequency domain fusion, significantly improving image generation quality. Experiments on the Patch Camelyon dataset show superior performance over eight state-of-the-art models across five metrics. This approach advances automated histopathological image generation with potential for clinical applications.</p>","PeriodicalId":8958,"journal":{"name":"BMC Bioinformatics","volume":"26 1","pages":"29"},"PeriodicalIF":2.9,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11773846/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143051354","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"HDN-DDI: a novel framework for predicting drug-drug interactions using hierarchical molecular graphs and enhanced dual-view representation learning.","authors":"Jinchen Sun, Haoran Zheng","doi":"10.1186/s12859-025-06052-0","DOIUrl":"10.1186/s12859-025-06052-0","url":null,"abstract":"<p><strong>Background: </strong>Drug-drug interactions (DDIs) especially antagonistic ones present significant risks to patient safety, underscoring the urgent need for reliable prediction methods. Recently, substructure-based DDI prediction has garnered much attention due to the dominant influence of functional groups and substructures on drug properties. However, existing approaches face challenges regarding the insufficient interpretability of identified substructures and the isolation of chemical substructures.</p><p><strong>Results: </strong>This study introduces a novel framework for DDI prediction termed HDN-DDI. HDN-DDI integrates an explainable substructure extraction module to decompose drug molecules and represents them using innovative hierarchical molecular graphs, which effectively incorporates information from real chemical substructures and improves molecules encoding efficiency. Furthermore, the enhanced dual-view learning method inspired by the underlying mechanisms of DDIs enables HDN-DDI to comprehensively capture both hierarchical structure and interaction information. Experimental results demonstrate that HDN-DDI has achieved state-of-the-art performance with accuracies of 97.90% and 99.38% on the two widely-used datasets in the warm-start setting. Moreover, HDN-DDI exhibits substantial improvements in the cold-start setting with boosts of 4.96% in accuracy and 7.08% in F1 score on previously unseen drugs. Real-world applications further highlight HDN-DDI's robust generalization capabilities towards newly approved drugs.</p><p><strong>Conclusion: </strong>With its accurate predictions and robust generalization across different settings, HDN-DDI shows promise for enhancing drug safety and efficacy. Future research will focus on refining decomposition rules as well as integrating external knowledge while preserving the model's generalization capabilities.</p>","PeriodicalId":8958,"journal":{"name":"BMC Bioinformatics","volume":"26 1","pages":"28"},"PeriodicalIF":2.9,"publicationDate":"2025-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11765940/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143036651","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}