Methods最新文献

{"title":"The application of advanced deep learning in biomedical graph analysis","authors":"Wen Zhang , Shikui Tu , Xiaopeng Zhu , Shichao Liu","doi":"10.1016/j.ymeth.2024.09.013","DOIUrl":"10.1016/j.ymeth.2024.09.013","url":null,"abstract":"","PeriodicalId":390,"journal":{"name":"Methods","volume":"231 ","pages":"Pages 115-117"},"PeriodicalIF":4.2,"publicationDate":"2024-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142338566","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Model-agnostic confidence measurement for aggregating multimodal ensemble models in automatic diagnostic systems","authors":"Chan-Yang Ju,&nbsp;Dong-Ho Lee","doi":"10.1016/j.ymeth.2024.09.012","DOIUrl":"10.1016/j.ymeth.2024.09.012","url":null,"abstract":"<div><div>Automatic diagnostic systems (ADSs) have been garnering increased attention because they can alleviate the workload of clinicians by assisting in diagnosis and offering low-cost access to healthcare for people in medically underserved areas. ADS can suggest potential diseases by analyzing a patient's self-report. Previous research on ADS has leveraged diagnostic case data from various patients and medical knowledge to diagnose diseases, with multimodal ensemble methods proving particularly effective. However, the existing multimodal ensemble method combines the probabilities of different models in the aggregating process, which can not properly combine the probabilities that are produced by different criteria. To address these issues, we propose an effective aggregation framework for multimodal ensembles that can properly aggregate model-agnostic confidence scores and predictions from each model. Our framework transforms probability scores from different criteria into unified aggregation rule-based scores and reflects the gap between the probabilities that may be blurred in the aggregation process through the confidence score. In particular, The proposed confidence measurement method employs a post-analysis approach with the developed model or algorithm, making it adaptable in a model-agnostic manner and suitable for multimodal ensemble learning that utilizes heterogeneous prediction results. Our experimental results demonstrate that our framework outperforms existing approaches by more effectively leveraging the strengths of each ensemble member.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"231 ","pages":"Pages 103-114"},"PeriodicalIF":4.2,"publicationDate":"2024-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142338565","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cancer subtype identification by multi-omics clustering based on interpretable feature and latent subspace learning","authors":"Tianyi Shi,&nbsp;Xiucai Ye,&nbsp;Dong Huang,&nbsp;Tetsuya Sakurai","doi":"10.1016/j.ymeth.2024.09.014","DOIUrl":"10.1016/j.ymeth.2024.09.014","url":null,"abstract":"<div><div>In recent years, multi-omics clustering has become a powerful tool in cancer research, offering a comprehensive perspective on the diverse molecular characteristics inherent to various cancer subtypes. However, most existing multi-omics clustering methods directly integrate heterogeneous features from different omics, which may struggle to deal with the noise or redundancy of multi-omics data and lead to poor clustering results. Therefore, we propose a novel multi-omics clustering method to extract interpretable and discriminative features from various omics before data integration. The clinical information is used to supervise the process of feature extraction based on SHAP (SHapley Additive exPlanation) values. Singular value decomposition (SVD) is then applied to integrate the extracted features of different omics by constructing a latent subspace. Finally, we utilize shared nearest neighbor-based spectral clustering on the latent representation to obtain the clustering result. The proposed method is evaluated on several cancer datasets across three levels of omics, in comparison to several state-of-the-art multi-omics clustering methods. The comparison results demonstrate the superior performance of the proposed method in multi-omics data analysis for cancer subtyping. Additionally, experiments reveal the efficacy of utilizing clinical information based on SHAP values for feature extraction, enhancing the performance of clustering analyses. Moreover, enrichment analysis of the identified gene signatures in different subtypes is also performed to further demonstrate the effectiveness of the proposed method.</div><div><strong>Availability:</strong> The proposed method can be freely accessible at <span><span>https://github.com/Tianyi-Shi-Tsukuba/Multi-omics-clustering-based-on-SHAP</span><svg><path></path></svg></span>. Data will be made available on request.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"231 ","pages":"Pages 144-153"},"PeriodicalIF":4.2,"publicationDate":"2024-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142338563","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Production, analysis, and safety assessment of a soil and plant-based natural material with microbiome- and immune-modulatory effects","authors":"Anirudra Parajuli ,&nbsp;Iida Mäkelä ,&nbsp;Marja I. Roslund ,&nbsp;Emma Ringqvist ,&nbsp;Juulia Manninen ,&nbsp;Yan Sun ,&nbsp;Noora Nurminen ,&nbsp;Sami Oikarinen ,&nbsp;Olli H. Laitinen ,&nbsp;Heikki Hyöty ,&nbsp;Malin Flodström-Tullberg ,&nbsp;Aki Sinkkonen","doi":"10.1016/j.ymeth.2024.09.011","DOIUrl":"10.1016/j.ymeth.2024.09.011","url":null,"abstract":"<div><div>It has been suggested that reduced contact with microbiota from the natural environment contributes to the rising incidence of immune-mediated inflammatory disorders (IMIDs) in western, highly urbanized societies. In line with this, we have previously shown that exposure to environmental microbiota in the form of a blend comprising of soil and plant-based material (biodiversity blend; BDB) enhances the diversity of human commensal microbiota and promotes immunoregulation that may be associated with a reduced risk for IMIDs. To provide a framework for future preclinical studies and clinical trials, this study describes how the preparation of BDB was standardized, its microbial content analysed and safety assessments performed. Multiple batches of BDB were manufactured and microbial composition analysed using 16S rRNA gene sequencing. We observed a consistently high alpha diversity and relative abundance of bacteria normally found in soil and vegetation. We also found that inactivation of BDB by autoclaving effectively inactivates human and murine bacteria, viruses and parasites. Finally, we demonstrate that experimental mice prone to develop IMIDs (non-obese diabetic, NOD, mouse model) can be exposed to BDB without causing adverse effects on animal health and welfare. Our study provides insights into a potentially safe, sustainable, and cost-effective approach for simulating exposure to natural microbiota, which could have substantial impacts on health and socio-economic factors.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"231 ","pages":"Pages 94-102"},"PeriodicalIF":4.2,"publicationDate":"2024-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1046202324002093/pdfft?md5=bd4f9846358c697b0dd4799224c609ba&pid=1-s2.0-S1046202324002093-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142278230","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":"GATDE: A graph attention network with diffusion-enhanced protein-protein interaction for cancer classification","authors":"Ruike Song ,&nbsp;Xiaofeng Wang ,&nbsp;Jiahao Zhang ,&nbsp;Shengquan Chen ,&nbsp;Jianyu Zhou","doi":"10.1016/j.ymeth.2024.09.003","DOIUrl":"10.1016/j.ymeth.2024.09.003","url":null,"abstract":"<div><p>Cancer classification is crucial for effective patient treatment, and recent years have seen various methods emerge based on protein expression levels. However, existing methods oversimplify by assuming uniform interaction strengths and neglecting intermediate influences among proteins. Addressing these limitations, GATDE employs a graph attention network enhanced with diffusion on protein-protein interactions. By constructing a weighted protein-protein interaction network, GATDE captures the diversity of these interactions and uses a diffusion process to assess multi-hop influences between proteins. This information is subsequently incorporated into the graph attention network, resulting in precise cancer classification. Experimental results on breast cancer and pan-cancer datasets demonstrate that GATDE surpasses current leading methods. Additionally, in-depth case studies further validate the effectiveness of the diffusion process and the attention mechanism, highlighting GATDE's robustness and potential for real-world applications.</p></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"231 ","pages":"Pages 70-77"},"PeriodicalIF":4.2,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142272154","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AtML: An Arabidopsis thaliana root cell identity recognition tool for medicinal ingredient accumulation","authors":"Shicong Yu ,&nbsp;Lijia Liu ,&nbsp;Hao Wang ,&nbsp;Shen Yan ,&nbsp;Shuqin Zheng ,&nbsp;Jing Ning ,&nbsp;Ruxian Luo ,&nbsp;Xiangzheng Fu ,&nbsp;Xiaoshu Deng","doi":"10.1016/j.ymeth.2024.09.010","DOIUrl":"10.1016/j.ymeth.2024.09.010","url":null,"abstract":"<div><p><em>Arabidopsis thaliana</em> synthesizes various medicinal compounds, and serves as a model plant for medicinal plant research. Single-cell transcriptomics technologies are essential for understanding the developmental trajectory of plant roots, facilitating the analysis of synthesis and accumulation patterns of medicinal compounds in different cell subpopulations. Although methods for interpreting single-cell transcriptomics data are rapidly advancing in Arabidopsis, challenges remain in precisely annotating cell identity due to the lack of marker genes for certain cell types. In this work, we trained a machine learning system, AtML, using sequencing datasets from six cell subpopulations, comprising a total of 6000 cells, to predict Arabidopsis root cell stages and identify biomarkers through complete model interpretability. Performance testing using an external dataset revealed that AtML achieved 96.50% accuracy and 96.51% recall. Through the interpretability provided by AtML, our model identified 160 important marker genes, contributing to the understanding of cell type annotations. In conclusion, we trained AtML to efficiently identify Arabidopsis root cell stages, providing a new tool for elucidating the mechanisms of medicinal compound accumulation in Arabidopsis roots.</p></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"231 ","pages":"Pages 61-69"},"PeriodicalIF":4.2,"publicationDate":"2024-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1046202324002081/pdfft?md5=3b64d8bc9dc85039798d03e6014db597&pid=1-s2.0-S1046202324002081-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142253896","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":"A novel methodology for mapping interstitial fluid dynamics in murine brain tumors using DCE-MRI","authors":"Cora Carman-Esparza ,&nbsp;Kathryn Kingsmore ,&nbsp;Andrea Vaccari ,&nbsp;Skylar Davis ,&nbsp;Jessica Cunningham ,&nbsp;Maosen Wang ,&nbsp;Jennifer Munson","doi":"10.1016/j.ymeth.2024.09.008","DOIUrl":"10.1016/j.ymeth.2024.09.008","url":null,"abstract":"<div><div>We present a comprehensive methodology for measuring heterogeneous interstitial fluid flow in murine brain tumors using dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) coupled with the computational tool, <em>Lymph4D</em>. This four-part protocol encompasses glioma cell preparation, tumor inoculation, MRI imaging protocol, and histological verification using Evans Blue. While conventional DCE-MRI analysis primarily focuses on vascular perfusion, our methods reveal untapped potential to extract crucial information about interstitial fluid dynamics, including directions, velocities, and diffusion coefficients. This methodology extends beyond glioma research, with applicability to conditions routinely imaged with DCE-MRI, thereby offering a versatile tool for investigating interstitial fluid dynamics across a wide range of diseases and conditions. Our methodology holds promise for accelerating discoveries and advancements in biomedical research, ultimately enhancing diagnostic and therapeutic strategies for a wide range of diseases and conditions.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"231 ","pages":"Pages 78-93"},"PeriodicalIF":4.2,"publicationDate":"2024-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142278228","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Digital Intervention for behaviouR changE and Chronic disease prevenTION (DIRECTION): Study protocol for a randomized controlled trial of a web-based platform integrating nutrition, physical activity, and mindfulness for individuals with obesity","authors":"Camila E. Orsso ,&nbsp;Teresita Gormaz ,&nbsp;Sabina Valentine ,&nbsp;Claire F. Trottier ,&nbsp;Iasmin Matias de Sousa ,&nbsp;Martin Ferguson-Pell ,&nbsp;Steven T. Johnson ,&nbsp;Amy A. Kirkham ,&nbsp;Douglas Klein ,&nbsp;Nathanial Maeda ,&nbsp;João F. Mota ,&nbsp;Sarah E. Neil-Sztramko ,&nbsp;Maira Quintanilha ,&nbsp;Bukola Oladunni Salami ,&nbsp;Carla M. Prado","doi":"10.1016/j.ymeth.2024.09.009","DOIUrl":"10.1016/j.ymeth.2024.09.009","url":null,"abstract":"<div><p>Excess body weight, suboptimal diet, physical inactivity, alcohol consumption, sleep disruption, and elevated stress are modifiable risk factors associated with the development of chronic diseases. Digital behavioural interventions targeting these factors have shown promise in improving health and reducing chronic disease risk. The <em>Digital Intervention for behaviouR changE and Chronic disease prevenTION</em> (<em>DIRECTION</em>) study is a parallel group, two-arm, randomized controlled trial evaluating the effects of adding healthcare professional guidance and peer support via group-based sessions to a web-based wellness platform (experimental group, n = 90) compared to a self-guided use of the platform (active control group, n = 90) among individuals with a body mass index (BMI) of 30 to &lt;35 kg/m² and aged 40–65 years. Obesity is defined by a high BMI. The web-based wellness platform employed in this study is My Viva Plan (MVP)®, which holistically integrates nutrition, physical activity, and mindfulness programs. Over 16 weeks, the experimental group uses the web-based wellness platform daily and engages in weekly online support group sessions. The active control group exclusively uses the web-based wellness platform daily. Assessments are conducted at baseline and weeks 8 and 16. The primary outcome is between-group difference in weight loss (kg) at week 16, and secondary outcomes are BMI, percent weight change, proportion of participants achieving 5% or more weight loss, dietary intake, physical activity, alcohol consumption, sleep, and stress across the study. A web-based wellness platform may be a scalable approach to promote behavioural changes that positively impact health. This study will inform the development and implementation of interventions using web-based wellness platforms and personalized digital interventions to improve health outcomes and reduce chronic disease risk among individuals with obesity.</p></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"231 ","pages":"Pages 45-54"},"PeriodicalIF":4.2,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S104620232400207X/pdfft?md5=787b2ff333611543fa5dd8dde7ef9999&pid=1-s2.0-S104620232400207X-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142241847","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":"Gluconeogenesis unraveled: A proteomic Odyssey with machine learning","authors":"Seher Ansar Khawaja ,&nbsp;Fahad Alturise ,&nbsp;Tamim Alkhalifah ,&nbsp;Sher Afzal Khan ,&nbsp;Yaser Daanial Khan","doi":"10.1016/j.ymeth.2024.09.002","DOIUrl":"10.1016/j.ymeth.2024.09.002","url":null,"abstract":"<div><div>The metabolic pathway known as gluconeogenesis, which produces glucose from non-carbohydrate substrates, is essential for maintaining balanced blood sugar levels while fasting. It's extremely important to anticipate gluconeogenesis rates accurately to recognize metabolic disorders and create efficient treatment strategies. The implementation of deep learning and machine learning methods to forecast complex biological processes has been gaining popularity in recent years. The recognition of both the regulation of the pathway and possible therapeutic applications of proteins depends on accurate identification associated with their gluconeogenesis patterns. This article analyzes the uses of machine learning and deep learning models, to predict gluconeogenesis efficiency. The study also discusses the challenges that come with restricted data availability and model interpretability, as well as possible applications in personalized healthcare, metabolic disease treatment, and the discovery of drugs. The predictor utilizes statistics moments on the structures of gluconeogenesis and their enzymes, while Random Forest is utilized as a classifier to ensure the accuracy of this model in identifying the best outcomes. The method was validated utilizing the independent test, self-consistency, 10k fold cross-validations, and jackknife test which achieved 92.33 %, 91.87%, 87.88%, and 87.02%. An accurate prediction of gluconeogenesis has significant implications for understanding metabolic disorders and developing targeted therapies. This study contributes to the rising field of predictive biology by mixing algorithms for deep learning, and machine learning, with metabolic pathways.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"232 ","pages":"Pages 29-42"},"PeriodicalIF":4.2,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142278229","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DeepDBS: Identification of DNA-binding sites in protein sequences by using deep representations and random forest","authors":"Yaser Daanial Khan ,&nbsp;Tamim Alkhalifah ,&nbsp;Fahad Alturise ,&nbsp;Ahmad Hassan Butt","doi":"10.1016/j.ymeth.2024.09.004","DOIUrl":"10.1016/j.ymeth.2024.09.004","url":null,"abstract":"<div><p>Interactions of biological molecules in organisms are considered to be primary factors for the lifecycle of that organism. Various important biological functions are dependent on such interactions and among different kinds of interactions, the protein DNA interactions are very important for the processes of transcription, regulation of gene expression, DNA repairing and packaging. Thus, keeping the knowledge of such interactions and the sites of those interactions is necessary to study the mechanism of various biological processes. As experimental identification through biological assays is quite resource-demanding, costly and error-prone, scientists opt for the computational methods for efficient and accurate identification of such DNA-protein interaction sites. Thus, herein, we propose a novel and accurate method namely DeepDBS for the identification of DNA-binding sites in proteins, using primary amino acid sequences of proteins under study. From protein sequences, deep representations were computed through a one-dimensional convolution neural network (1D-CNN), recurrent neural network (RNN) and long short-term memory (LSTM) network and were further used to train a Random Forest classifier. Random Forest with LSTM-based features outperformed the other models, as well as the existing state-of-the-art methods with an accuracy score of 0.99 for self-consistency test, 10-fold cross-validation, 5-fold cross-validation, and jackknife validation while 0.92 for independent dataset testing. It is concluded based on results that the DeepDBS can help accurate and efficient identification of DNA binding sites (DBS) in proteins.</p></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"231 ","pages":"Pages 26-36"},"PeriodicalIF":4.2,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142241846","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}