Biodata Mining最新文献

{"title":"High-dimensional mediation analysis reveals the mediating role of physical activity patterns in genetic pathways leading to AD-like brain atrophy.","authors":"Hanxiang Xu, Shizhuo Mu, Jingxuan Bao, Christos Davatzikos, Haochang Shou, Li Shen","doi":"10.1186/s13040-025-00432-1","DOIUrl":"10.1186/s13040-025-00432-1","url":null,"abstract":"<p><strong>Background: </strong>Alzheimer's disease (AD) is a complex disorder that affects multiple biological systems including cognition, behavior and physical health. Unfortunately, the pathogenic mechanisms behind AD are not yet clear and the treatment options are still limited. Despite the increasing number of studies examining the pairwise relationships between genetic factors, physical activity (PA), and AD, few have successfully integrated all three domains of data, which may help reveal mechanisms and impact of these genomic and phenomic factors on AD. We use high-dimensional mediation analysis as an integrative framework to study the relationships among genetic factors, PA and AD-like brain atrophy quantified by spatial patterns of brain atrophy.</p><p><strong>Results: </strong>We integrate data from genetics, PA and neuroimaging measures collected from 13,425 UK Biobank samples to unveil the complex relationship among genetic risk factors, behavior and brain signatures in the contexts of aging and AD. Specifically, we used a composite imaging marker, Spatial Pattern of Abnormality for Recognition of Early AD (SPARE-AD) that characterizes AD-like brain atrophy, as an outcome variable to represent AD risk. Through GWAS, we identified single nucleotide polymorphisms (SNPs) that are significantly associated with SPARE-AD as exposure variables. We employed conventional summary statistics and functional principal component analysis to extract patterns of PA as mediators. After constructing these variables, we utilized a high-dimensional mediation analysis method, Bayesian Mediation Analysis (BAMA), to estimate potential mediating pathways between SNPs, multivariate PA signatures and SPARE-AD. BAMA incorporates Bayesian continuous shrinkage prior to select the active mediators from a large pool of candidates. We identified a total of 22 mediation pathways, indicating how genetic variants can influence SPARE-AD by altering physical activity. By comparing the results with those obtained using univariate mediation analysis, we demonstrate the advantages of high-dimensional mediation analysis methods over univariate mediation analysis.</p><p><strong>Conclusion: </strong>Through integrative analysis of multi-omics data, we identified several mediation pathways of physical activity between genetic factors and SPARE-AD. These findings contribute to a better understanding of the pathogenic mechanisms of AD. Moreover, our research demonstrates the potential of the high-dimensional mediation analysis method in revealing the mechanisms of disease.</p>","PeriodicalId":48947,"journal":{"name":"Biodata Mining","volume":"18 1","pages":"24"},"PeriodicalIF":4.0,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11931790/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143701870","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":"Automatic detection and extraction of key resources from tables in biomedical papers.","authors":"Ibrahim Burak Ozyurt, Anita Bandrowski","doi":"10.1186/s13040-025-00438-9","DOIUrl":"10.1186/s13040-025-00438-9","url":null,"abstract":"<p><strong>Background: </strong>Tables are useful information artifacts that allow easy detection of missing data and have been deployed by several publishers to improve the amount of information present for key resources and reagents such as antibodies, cell lines, and other tools that constitute the inputs to a study. STAR*Methods key resource tables have increased the \"findability\" of these key resources, improving transparency of the paper by warning authors (before publication) about any problems, such as key resources that cannot be uniquely identified or those that are known to be problematic, but they have not been commonly available outside of the Cell Press journal family. We believe that processing preprints and adding these 'resource table candidates' automatically will improve the availability of structured and linked information about research resources in a broader swath of the scientific literature. However, if the authors have already added a key resource table, that table must be detected, and each entity must be correctly identified and faithfully restructured into a standard format.</p><p><strong>Methods: </strong>We introduce four end-to-end table extraction pipelines to extract and faithfully reconstruct key resource tables from biomedical papers in PDF format. The pipelines employ machine learning approaches for key resource table page identification, \"Table Transformer\" models for table detection, and table structure recognition. We also introduce a character-level generative pre-trained transformer (GPT) language model for scientific tables pre-trained on over 11 million scientific tables. We fine-tuned our table-specific language model with synthetic training data generated with a novel approach to alleviate row over-segmentation significantly improving key resource extraction performance.</p><p><strong>Results: </strong>The extraction of key resource tables in PDF files by the popular GROBID tool resulted in a Grid Table Similarity (GriTS) score of 0.12. All of our pipelines have outperformed GROBID by a large margin. Our best pipeline with table-specific language model-based row merger achieved a GriTS score of 0.90.</p><p><strong>Conclusions: </strong>Our pipelines allow the detection and extraction of key resources from tables with much higher accuracy, enabling the deployment of automated research resource extraction tools on BioRxiv to help authors correct unidentifiable key resources detected in their articles and improve the reproducibility of their findings. The code, table-specific language model, annotated training and evaluation data are publicly available.</p>","PeriodicalId":48947,"journal":{"name":"Biodata Mining","volume":"18 1","pages":"23"},"PeriodicalIF":4.0,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11924859/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143671632","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":"Leveraging mixed-effects regression trees for the analysis of high-dimensional longitudinal data to identify the low and high-risk subgroups: simulation study with application to genetic study.","authors":"Mina Jahangiri, Anoshirvan Kazemnejad, Keith S Goldfeld, Maryam S Daneshpour, Mehdi Momen, Shayan Mostafaei, Davood Khalili, Mahdi Akbarzadeh","doi":"10.1186/s13040-025-00437-w","DOIUrl":"10.1186/s13040-025-00437-w","url":null,"abstract":"<p><strong>Background: </strong>The linear mixed-effects model (LME) is a conventional parametric method mainly used for analyzing longitudinal and clustered data in genetic studies. Previous studies have shown that this model can be sensitive to parametric assumptions and provides less predictive performance than non-parametric methods such as random effects-expectation maximization (RE-EM) and unbiased RE-EM regression tree algorithms. These longitudinal regression trees utilize classification and regression trees (CART) and conditional inference trees (Ctree) to estimate the fixed-effects components of the mixed-effects model. While CART is a well-known tree algorithm, it suffers from greediness. To mitigate this issue, we used the Evtree algorithm to estimate the fixed-effects part of the LME for handling longitudinal and clustered data in genome association studies.</p><p><strong>Methods: </strong>In this study, we propose a new non-parametric longitudinal-based algorithm called \"Ev-RE-EM\" for modeling a continuous response variable using the Evtree algorithm to estimate the fixed-effects part of the LME. We compared its predictive performance with other tree algorithms, such as RE-EM and unbiased RE-EM, with and without considering the structure for autocorrelation between errors within subjects to analyze the longitudinal data in the genetic study. The autocorrelation structures include a first-order autoregressive process, a compound symmetric structure with a constant correlation, and a general correlation matrix. The real data was obtained from the longitudinal Tehran cardiometabolic genetic study (TCGS). The data modeling used body mass index (BMI) as the phenotype and included predictor variables such as age, sex, and 25,640 single nucleotide polymorphisms (SNPs).</p><p><strong>Results: </strong>The results demonstrated that the predictive performance of Ev-RE-EM and unbiased RE-EM was nearly similar. Additionally, the Ev-RE-EM algorithm generated smaller trees than the unbiased RE-EM algorithm, enhancing tree interpretability.</p><p><strong>Conclusion: </strong>The results showed that the unbiased RE-EM and Ev-RE-EM algorithms outperformed the RE-EM algorithm. Since algorithm performance varies across datasets, researchers should test different algorithms on the dataset of interest and select the best-performing one. Accurately predicting and diagnosing an individual's genetic profile is crucial in medical studies. The model with the highest accuracy should be used to enhance understanding of the genetics of complex traits, improve disease prevention and diagnosis, and aid in treating complex human diseases.</p>","PeriodicalId":48947,"journal":{"name":"Biodata Mining","volume":"18 1","pages":"22"},"PeriodicalIF":4.0,"publicationDate":"2025-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11924713/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143665028","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":"Unsupervised clustering based coronary artery segmentation.","authors":"Belén Serrano-Antón, Manuel Insúa Villa, Santiago Pendón-Minguillón, Santiago Paramés-Estévez, Alberto Otero-Cacho, Diego López-Otero, Brais Díaz-Fernández, María Bastos-Fernández, José R González-Juanatey, Alberto P Muñuzuri","doi":"10.1186/s13040-025-00435-y","DOIUrl":"10.1186/s13040-025-00435-y","url":null,"abstract":"<p><strong>Background: </strong>The acquisition of 3D geometries of coronary arteries from computed tomography coronary angiography (CTCA) is crucial for clinicians, enabling visualization of lesions and supporting decision-making processes. Manual segmentation of coronary arteries is time-consuming and prone to errors. There is growing interest in automatic segmentation algorithms, particularly those based on neural networks, which require large datasets and significant computational resources for training. This paper proposes an automatic segmentation methodology based on clustering algorithms and a graph structure, which integrates data from both the clustering process and the original images.</p><p><strong>Results: </strong>The study compares two approaches: a 2.5D version using axial, sagittal, and coronal slices (3Axis), and a perpendicular version (Perp), which uses the cross-section of each vessel. The methodology was tested on two patient groups: a test set of 10 patients and an additional set of 22 patients with clinically diagnosed lesions. The 3Axis method achieved a Dice score of 0.88 in the test set and 0.83 in the lesion set, while the Perp method obtained Dice scores of 0.81 in the test set and 0.82 in the lesion set, decreasing to 0.79 and 0.80 in the lesion region, respectively. These results are competitive with current state-of-the-art methods.</p><p><strong>Conclusions: </strong>This clustering-based segmentation approach offers a robust framework that can be easily integrated into clinical workflows, improving both accuracy and efficiency in coronary artery analysis. Additionally, the ability to visualize clusters and graphs from any cross-section enhances the method's explainability, providing clinicians with deeper insights into vascular structures. The study demonstrates the potential of clustering algorithms for improving segmentation performance in coronary artery imaging.</p>","PeriodicalId":48947,"journal":{"name":"Biodata Mining","volume":"18 1","pages":"21"},"PeriodicalIF":4.0,"publicationDate":"2025-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11887207/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143587591","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":"EnSCAN: ENsemble Scoring for prioritizing CAusative variaNts across multiplatform GWASs for late-onset alzheimer's disease.","authors":"Onur Erdogan, Cem Iyigun, Yeşim Aydın Son","doi":"10.1186/s13040-025-00436-x","DOIUrl":"10.1186/s13040-025-00436-x","url":null,"abstract":"<p><p>Late-onset Alzheimer's disease (LOAD) is a progressive and complex neurodegenerative disorder of the aging population. LOAD is characterized by cognitive decline, such as deterioration of memory, loss of intellectual abilities, and other cognitive domains resulting from due to traumatic brain injuries. Alzheimer's Disease (AD) presents a complex genetic etiology that is still unclear, which limits its early or differential diagnosis. The Genome-Wide Association Studies (GWAS) enable the exploration of individual variants' statistical interactions at candidate loci, but univariate analysis overlooks interactions between variants. Machine learning (ML) algorithms can capture hidden, novel, and significant patterns while considering nonlinear interactions between variants to understand the genetic predisposition for complex genetic disorders. When working on different platforms, majority voting cannot be applied because the attributes differ. Hence, a new post-ML ensemble approach was developed to select significant SNVs via multiple genotyping platforms. We proposed the EnSCAN framework using a new algorithm to ensemble selected variants even from different platforms to prioritize candidate causative loci, which consequently helps improve ML results by combining the prior information captured from each dataset. The proposed ensemble algorithm utilizes the chromosomal locations of SNVs by mapping to cytogenetic bands, along with the proximities between pairs and multimodel Random Forest (RF) validations to prioritize SNVs and candidate causative genes for LOAD. The scoring method is scalable and can be applied to any multiplatform genotyping study. We present how the proposed EnSCAN scoring algorithm prioritizes candidate causative variants related to LOAD among three GWAS datasets.</p>","PeriodicalId":48947,"journal":{"name":"Biodata Mining","volume":"18 1","pages":"20"},"PeriodicalIF":4.0,"publicationDate":"2025-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11881353/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143558468","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":"Analysis of global trends and hotspots of skin microbiome in acne: a bibliometric perspective.","authors":"Lanfang Zhang, Yuan Cai, Lin Li, Jie Hu, Changsha Jia, Xu Kuang, Yi Zhou, Zhiai Lan, Chunyan Liu, Feng Jiang, Nana Sun, Ni Zeng","doi":"10.1186/s13040-025-00433-0","DOIUrl":"10.1186/s13040-025-00433-0","url":null,"abstract":"<p><strong>Background: </strong>Acne is a chronic inflammatory condition affecting the hair follicles and sebaceous glands. Recent research has revealed significant advances in the study of the acne skin microbiome. Systematic analysis of research trends and hotspots in the acne skin microbiome is lacking. This study utilized bibliometric methods to conduct in-depth research on the recognition structure of the acne skin microbiome, identifying hot trends and emerging topics.</p><p><strong>Methods: </strong>We performed a topic search to retrieve articles about skin microbiome in acne from the Web of Science Core Collection. Bibliometric research was conducted using CiteSpace, VOSviewer, and R language.</p><p><strong>Results: </strong>This study analyzed 757 articles from 1362 institutions in 68 countries, the United States leading the research efforts. Notably, Brigitte Dréno from the University of Nantes emerged as the most prolific author in this field, with 19 papers and 334 co-citations. The research output on the skin microbiome of acne continues to increase, with Experimental Dermatology being the journal with the highest number of published articles. The primary focus is investigating the skin microbiome's mechanisms in acne development and exploring treatment strategies. These findings have important implications for developing microbiome-targeted therapies, which could provide new, personalized treatment options for patients with acne. Emerging research hotspots include skincare, gut microbiome, and treatment.</p><p><strong>Conclusion: </strong>The study's findings indicate a thriving research interest in the skin microbiome and its relationship to acne, focusing on acne treatment through the regulation of the skin microbiome balance. Currently, the development of skincare products targeting the regulation of the skin microbiome represents a research hotspot, reflecting the transition from basic scientific research to clinical practice.</p>","PeriodicalId":48947,"journal":{"name":"Biodata Mining","volume":"18 1","pages":"19"},"PeriodicalIF":4.0,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11874858/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143544184","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":"Inferring protein from transcript abundances using convolutional neural networks.","authors":"Patrick Maximilian Schwehn, Pascal Falter-Braun","doi":"10.1186/s13040-025-00434-z","DOIUrl":"10.1186/s13040-025-00434-z","url":null,"abstract":"<p><strong>Background: </strong>Although transcript abundance is often used as a proxy for protein abundance, it is an unreliable predictor. As proteins execute biological functions and their expression levels influence phenotypic outcomes, we developed a convolutional neural network (CNN) to predict protein abundances from mRNA abundances, protein sequence, and mRNA sequence in Homo sapiens (H. sapiens) and the reference plant Arabidopsis thaliana (A. thaliana).</p><p><strong>Results: </strong>After hyperparameter optimization and initial data exploration, we implemented distinct training modules for value-based and sequence-based data. By analyzing the learned weights, we revealed common and organism-specific sequence features that influence protein-to-mRNA ratios (PTRs), including known and putative sequence motifs. Adding condition-specific protein interaction information identified genes correlated with many PTRs but did not improve predictions, likely due to insufficient data. The integrated model predicted protein abundance on unseen genes with a coefficient of determination (r²) of 0.30 in H. sapiens and 0.32 in A. thaliana.</p><p><strong>Conclusions: </strong>For H. sapiens, our model improves prediction performance by nearly 50% compared to previous sequence-based approaches, and for A. thaliana it represents the first model of its kind. The model's learned motifs recapitulate known regulatory elements, supporting its utility in systems-level and hypothesis-driven research approaches related to protein regulation.</p>","PeriodicalId":48947,"journal":{"name":"Biodata Mining","volume":"18 1","pages":"18"},"PeriodicalIF":4.0,"publicationDate":"2025-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11866710/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143525013","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":"AI as an accelerator for defining new problems that transcends boundaries.","authors":"Tayo Obafemi-Ajayi, Steven F Jennings, Yu Zhang, Kara Li Liu, Joan Peckham, Jason H Moore","doi":"10.1186/s13040-025-00429-w","DOIUrl":"10.1186/s13040-025-00429-w","url":null,"abstract":"<p><p>Interdisciplinary, transdisciplinary, convergence, and No-Boundary Thinking (NBT) research are methodology and technology-agnostic approaches to problem solving. The focus is on defining problems informed by access to multiple knowledge sources and expert perspectives across different domains, with the goal of accessing all available knowledge sources and perspectives. While access to all available knowledge sources and perspectives could be seen as a difficult to attain objective, with the recent rise of AI we might be closer to approaching this goal. We review several examples of methodologies and technologies that have been used to put these strategies into action, but the primary focus of this paper is on how recent advances in AI now enable a quantum leap forward in defining new problems. By leveraging the capacity of AI to synthesize knowledge from multiple domains, these tools can be used to propose multiple candidate problem definitions. AI is uniquely able to draw upon many more knowledge sources than any individual-or even a very large team-could. Coupled with human intelligence, better problems can be defined to address complex scholarly or societal challenges.</p>","PeriodicalId":48947,"journal":{"name":"Biodata Mining","volume":"18 1","pages":"17"},"PeriodicalIF":4.0,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11837601/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143450623","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":"Machine learning models for reinjury risk prediction using cardiopulmonary exercise testing (CPET) data: optimizing athlete recovery.","authors":"Arezoo Abasi, Ahmad Nazari, Azar Moezy, Seyed Ali Fatemi Aghda","doi":"10.1186/s13040-025-00431-2","DOIUrl":"10.1186/s13040-025-00431-2","url":null,"abstract":"<p><strong>Background: </strong>Cardiopulmonary Exercise Testing (CPET) provides detailed insights into athletes' cardiovascular and pulmonary function, making it a valuable tool in assessing recovery and injury risks. However, traditional statistical models often fail to leverage the full potential of CPET data in predicting reinjury. Machine learning (ML) algorithms offer promising capabilities in uncovering complex patterns within this data, allowing for more accurate injury risk assessment.</p><p><strong>Objective: </strong>This study aimed to develop machine learning models to predict reinjury risk among elite soccer players using CPET data. Specifically, we sought to identify key physiological and performance variables that correlate with reinjury and to evaluate the performance of various ML algorithms in generating accurate predictions.</p><p><strong>Methods: </strong>A dataset of 256 elite soccer players from 16 national and top-tier teams in Iran was analyzed, incorporating physiological variables and categorical data. Several machine learning models, including CatBoost, SVM, Random Forest, and XGBoost, were employed to predict reinjury risk. Model performance was assessed using metrics such as accuracy, precision, recall, F1-score, AUC, and SHAP values to ensure robust evaluation and interpretability.</p><p><strong>Results: </strong>CatBoost and SVM exhibited the best performance, with CatBoost achieving the highest accuracy (0.9138) and F1-score (0.9148), and SVM achieving the highest AUC (0.9725). A significant association was found between a history of concussion and reinjury risk (χ² = 13.0360, p = 0.0015), highlighting the importance of neurological recovery in preventing future injuries. Heart rate metrics, particularly HRmax and HR2, were also significantly lower in players who experienced reinjury, indicating reduced cardiovascular capacity in this group.</p><p><strong>Conclusion: </strong>Machine learning models, particularly CatBoost and SVM, provide promising tools for predicting reinjury risk using CPET data. These models offer clinicians more precise, data-driven insights into athlete recovery and risk management. Future research should explore the integration of external factors such as training load and psychological readiness to further refine these predictions and enhance injury prevention protocols.</p>","PeriodicalId":48947,"journal":{"name":"Biodata Mining","volume":"18 1","pages":"16"},"PeriodicalIF":4.0,"publicationDate":"2025-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11834553/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143442544","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":"Feature graphs for interpretable unsupervised tree ensembles: centrality, interaction, and application in disease subtyping.","authors":"Christel Sirocchi, Martin Urschler, Bastian Pfeifer","doi":"10.1186/s13040-025-00430-3","DOIUrl":"10.1186/s13040-025-00430-3","url":null,"abstract":"<p><p>Explainable and interpretable machine learning has emerged as essential in leveraging artificial intelligence within high-stakes domains such as healthcare to ensure transparency and trustworthiness. Feature importance analysis plays a crucial role in improving model interpretability by pinpointing the most relevant input features, particularly in disease subtyping applications, aimed at stratifying patients based on a small set of signature genes and biomarkers. While clustering methods, including unsupervised random forests, have demonstrated good performance, approaches for evaluating feature contributions in an unsupervised regime are notably scarce. To address this gap, we introduce a novel methodology to enhance the interpretability of unsupervised random forests by elucidating feature contributions through the construction of feature graphs, both over the entire dataset and individual clusters, that leverage parent-child node splits within the trees. Feature selection strategies to derive effective feature combinations from these graphs are presented and extensively evaluated on synthetic and benchmark datasets against state-of-the-art methods, standing out for performance, computational efficiency, reliability, versatility and ability to provide cluster-specific insights. In a disease subtyping application, clustering kidney cancer gene expression data over a feature subset selected with our approach reveals three patient groups with different survival outcomes. Cluster-specific analysis identifies distinctive feature contributions and interactions, essential for devising targeted interventions, conducting personalised risk assessments, and enhancing our understanding of the underlying molecular complexities.</p>","PeriodicalId":48947,"journal":{"name":"Biodata Mining","volume":"18 1","pages":"15"},"PeriodicalIF":4.0,"publicationDate":"2025-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11829558/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143426202","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}