Methods最新文献

{"title":"FedKD-CPI: Combining the federated knowledge distillation technique to accomplish synergistic compound-protein interaction prediction","authors":"Xuetao Wang ,&nbsp;Qichang Zhao ,&nbsp;Jianxin Wang","doi":"10.1016/j.ymeth.2024.12.014","DOIUrl":"10.1016/j.ymeth.2024.12.014","url":null,"abstract":"<div><div>Compound-protein interaction (CPI) prediction is critical in the early stages of drug discovery, narrowing the search space for CPIs and reducing the cost and time required for traditional high-throughput screening. However, CPI-related data are usually distributed across different institutions and their sharing is restricted because of data privacy and intellectual property rights. Constructing a scheme that enhances multi-institutional collaboration to improve prediction accuracy while protecting data privacy is essential. To this end, we propose FedKD-CPI, the first framework based on federated knowledge distillation, to effectively facilitate multi-party CPI collaborative prediction and ensure data privacy and security. FedKD-CPI uses knowledge distillation technology to extract the updated knowledge of all client models and train the model on the server to achieve knowledge aggregation, which can effectively utilize the knowledge contained in public and private data. We evaluate FedKD-CPI on three benchmark datasets and compare it with four baselines. The results show that FedKD-CPI is very close to centralized learning and significantly better than localized learning. Furthermore, FedKD-CPI outperforms federated learning-based baselines on independent and identically distributed data and non-independent and identically distributed data. Overall, FedKD-CPI improves the CPI prediction while ensuring data security and promoting institutions' collaboration to accelerate drug discovery.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"234 ","pages":"Pages 275-283"},"PeriodicalIF":4.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142997925","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":"MVSLLnc: LncRNA subcellular localization prediction based on multi-source features and two-stage voting strategy","authors":"Sheng Wang ,&nbsp;Zu-Guo Yu ,&nbsp;Guo-Sheng Han","doi":"10.1016/j.ymeth.2025.01.013","DOIUrl":"10.1016/j.ymeth.2025.01.013","url":null,"abstract":"<div><div>The subcellular localization of long non-coding RNAs (lncRNAs) is crucial for understanding the function of lncRNAs. Since the traditional biological experimental methods are time-consuming and some existing computational methods rely on high computing power, we are committed to finding a simple and easy-to-implement method to achieve more efficient prediction of the subcellular localization of lncRNAs. In this work, we proposed a model based on <u>m</u>ulti-source features and two-stage <u>v</u>oting strategy for predicting the <u>s</u>ubcellular <u>l</u>ocalization of <u>lnc</u>RNAs (MVSLLnc). The multi-source features include <em>k</em>-mer frequency, features based on the coordinate values of Chaos Game Representation (CGR) and features based on physicochemical property (PhyChe). We feed the multi-source features into the traditional machine learning classifiers RF, SVM and XGBoost, respectively, and perform the final prediction task with two-stage voting strategy. Experimental results on three benchmark datasets show that the accuracy can reach 0.829, 0.793 and 0.968, respectively. The accuracy on three independent test sets is 0.642, 0.737 and 0.518, respectively, which are competitive with the existing methods. Our ablation analyses show that the two-stage voting strategy can make full use of the advantages of multi-source features and multiple classifiers, and obtain more robust results.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"234 ","pages":"Pages 324-332"},"PeriodicalIF":4.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142997931","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":"Imaging flow cytometry reveals LPS-induced changes to intracellular intensity and distribution of α-synuclein in a TLR4-dependent manner in STC-1 cells","authors":"Anastazja M. Gorecki ,&nbsp;Chidozie C. Anyaegbu ,&nbsp;Melinda Fitzgerald ,&nbsp;Kathryn A. Fuller ,&nbsp;Ryan S. Anderton","doi":"10.1016/j.ymeth.2024.10.009","DOIUrl":"10.1016/j.ymeth.2024.10.009","url":null,"abstract":"<div><h3>Background</h3><div>Parkinson’s disease is a chronic neurodegenerative disorder, where pathological protein aggregates largely composed of phosphorylated α-synuclein are implicated in disease pathogenesis and progression. Emerging evidence suggests that the interaction between pro-inflammatory microbial factors and the gut epithelium contributes to α-synuclein aggregation in the enteric nervous system. However, the cellular sources and mechanisms for α-synuclein pathology in the gut are still unclear.</div></div><div><h3>Methods</h3><div>The STC-1 cell line, which models an enteroendocrine population capable of communicating with the gut microbiota, immune and nervous systems, was treated with a TLR4 inhibitor (TAK-242) prior to microbial lipopolysaccharide (LPS) exposure to investigate the role of TLR4 signalling in α-synuclein alterations. Antibodies targeting the full-length protein (α-synuclein) and the Serine-129 phosphorylated form (pS129) were used. Complex, multi-parametric image analysis was conducted through confocal microscopy (with Zen 3.8 analysis) and imaging flow cytometry (with IDEAS® analysis).</div></div><div><h3>Results</h3><div>Confocal microscopy revealed heterogenous distribution of α-synuclein and pS129 in STC-1 cells, with prominent pS129 staining along cytoplasmic processes. Imaging flow cytometry further quantified the relationship between various α-synuclein morphometric features. Thereafter, imaging flow cytometry demonstrated a dose-specific effect of LPS, where the low (8 μg/mL), but not high dose (32 μg/mL), significantly altered measures related to α-synuclein intensity, distribution, and localisation. Pre-treatment with a TLR4 inhibitor TAK-242 alleviated some of these significant alterations.</div></div><div><h3>Conclusion</h3><div>This study demonstrates that LPS-TLR4 signalling alters the intracellular localisation of α-synuclein in enteroendocrine cells <em>in vitro</em> and showcases the utility of combining imaging flow cytometry to investigate subtle protein changes that may not be apparent through confocal microscopy alone. Further investigation is required to understand the apparent dose-dependent effects of LPS on α-synuclein in the gut epithelium in healthy states as well as conditions such as Parkinson’s disease.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"234 ","pages":"Pages 93-111"},"PeriodicalIF":4.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142563953","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":"Artificial intelligence and computer-aided drug discovery: Methods development and application","authors":"Haiping Zhang,&nbsp;Yanjie Wei,&nbsp;Konda Mani Saravanan","doi":"10.1016/j.ymeth.2025.01.009","DOIUrl":"10.1016/j.ymeth.2025.01.009","url":null,"abstract":"","PeriodicalId":390,"journal":{"name":"Methods","volume":"234 ","pages":"Pages 294-295"},"PeriodicalIF":4.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142997924","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":"Terahertz-based biosensors for biomedical applications: A review","authors":"Meraline Selvaraj ,&nbsp;Sreeja B S ,&nbsp;Mohamed Aly Saad Aly","doi":"10.1016/j.ymeth.2024.12.001","DOIUrl":"10.1016/j.ymeth.2024.12.001","url":null,"abstract":"<div><div>Biosensors have many life sciences-related applications, particularly in the healthcare sector. They are employed in a wide range of fields, including drug development, food quality management, early diagnosis of diseases, and environmental monitoring. Terahertz-based biosensing has shown great promise as a label-free, non-invasive, and non-contact method of detecting biological substances. THz Spectroscopy has achieved a remarkable advancement in biomolecule recognition providing a rapid, highly sensitive, and non-destructive approach for various biomedical applications. The significance of THz-based biosensors and the broad spectrum of biomolecules that can be detected and analyzed with biosensors are reviewed in this work. Additionally, this work summarizes several techniques that were previously reported to improve the sensitivity and selectivity of these biosensors. Furthermore, an in-depth comparison between previously developed biosensors with an emphasis on their performance is presented and highlighted in the current review. Lastly, the challenges, the potential, and the future prospects of THz-based biosensing technology are critically addressed.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"234 ","pages":"Pages 54-66"},"PeriodicalIF":4.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142783792","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":"Novel, standardized sample collection from the brain-nose interface","authors":"Marion San Nicoló ,&nbsp;Sabine Mertzig ,&nbsp;Alexander Berghaus ,&nbsp;Oliver Peters ,&nbsp;Lutz Frölich ,&nbsp;Timo Grimmer ,&nbsp;Jens Wiltfang ,&nbsp;Timo Oberstein ,&nbsp;Thomas Braun ,&nbsp;Maria Babu ,&nbsp;Hilary Wunderlich ,&nbsp;Peter Kaspar ,&nbsp;Gabriele Baur ,&nbsp;Christian Braun ,&nbsp;Mohammad Bashiri ,&nbsp;Heinz Oehl ,&nbsp;Thomas Heydler ,&nbsp;Mareike Albert","doi":"10.1016/j.ymeth.2024.12.012","DOIUrl":"10.1016/j.ymeth.2024.12.012","url":null,"abstract":"<div><h3>Background</h3><div>Diagnostics for neurodegenerative diseases lack non-invasive approaches suitable for early-stage biochemical screening and routine examination of neuropathology. Biomarkers of neurodegenerative diseases pass through the brain-nose interface (BNI) and accumulate in nasal secretion. Sample collection from the brain-nose interface presents a compelling prospect as basis for a non-invasive molecular diagnosis of neuropathologies. Here, we evaluated a novel medical device (nosecollect) that is tailored for the standardized collection of nasal secretion samples from BNI, focusing on its sample collection safety and efficiency.</div></div><div><h3>Method</h3><div>A class I medical device (nosecollect) was developed, to enable the standardized collection of nasal secretion exclusively from BNI in a user-friendly, safe, and comfortable manner. We performed a clinical study to test the collection device on a heterogenous cohort (n = 923) at 8 study centers and evaluated its performance to collect sufficient sample volume from the targeted BNI area, its safety and tolerability. Samples were collected by trained medical personnel (medical doctors and nurses).</div></div><div><h3>Results</h3><div>Nosecollect gathered a mean volume of 452 ± 317 μl from the BNI. Successful positioning of the absorption material (AM) in the BNI was observed in 95 % of the cases. Pain level/level of discomfort and occurrences of adverse events remained minimal (visual analogue scale (VAS) = 1.97 ± 1.99 (range 0–10), adverse events: 1 %, no serious adverse events). Analysis of the nasal secretion sample identified detectable levels of CNS biomarkers in it.</div></div><div><h3>Conclusions</h3><div>The precision and ergonomic design of nosecollect ensures a standardized, targeted and safe collection of non-diluted nasal secretion samples from BNI, thus outperforming traditional methods such as swabs, lavage etc which are not customized for accessing undiluted samples from BNI. In addition, the device offers a non-invasive and accessible approach for the acquisition of nasal secretion samples from BNI, signifying a crucial step in the future development of a BNI-based non-invasive diagnostic platform for neurodegenerative diseases.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"234 ","pages":"Pages 233-241"},"PeriodicalIF":4.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142926194","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":"Pathophysiological characterization of the ApoE−/−;db/db mouse: A model of diabetes and atherosclerosis","authors":"María Paniagua-Sancho ,&nbsp;Alfredo G. Casanova ,&nbsp;Lucía Rodríguez-Estévez ,&nbsp;Ignacio Cruz-González ,&nbsp;Francisco J. López-Hernández ,&nbsp;Carlos Martínez-Salgado","doi":"10.1016/j.ymeth.2025.01.002","DOIUrl":"10.1016/j.ymeth.2025.01.002","url":null,"abstract":"<div><div>The high prevalence of type 2 diabetes and atherosclerosis makes essential the availability of in vivo experimental models that accurately replicate the pathophysiological mechanisms of these diseases. Apolipoprotein E knockout mice (ApoE^-/-) have been used in atherosclerosis studies, and the db/db mice show hyperphagia and obesity. Mice harbouring both alterations (i.e., ApoE^{−/−;db/db}) are expected to develop combined features of type 2 diabetes, obesity and accelerated atherosclerosis. To deepen into their pathophysiological profile and further assess their potential as an experimental model, we studied their mortality and their pancreatic, cardiac, and renal phenotype. We analysed during 6 months the glycemic and lipid profile, pancreatic, cardiac and renal structure and function and atherosclerosis in ApoE^{−/−;db/db} mice. ApoE^{−/−;db/db} mice show increases in plasma glucose (although without statistical significance) and glucagon levels, total cholesterol, triglycerides and HDL-cholesterol and in both insulin-producing β and glucagon producing α cells, and in the tissue expression of both hormones with respect to control (C57BL/6) mice; they show a remarkably high degree of atherosclerosis, higher left ventricular ejection fraction. Although renal function is normal, glucose, sodium and albumin excretion and urinary flow are increased with respect to control mice. Summarizing, ApoE^{−/−;db/db} mice constitute a suitable experimental model for the study of type 2 diabetes associated with atherosclerosis.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"234 ","pages":"Pages 223-232"},"PeriodicalIF":4.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142963522","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":"Innovative PBMC-derived humanized mouse model reveals CD8+ T cell-intrinsic regulation during antitumor immunity","authors":"Xiaojun Yan,&nbsp;Donglai Wang","doi":"10.1016/j.ymeth.2025.01.011","DOIUrl":"10.1016/j.ymeth.2025.01.011","url":null,"abstract":"<div><div>The PBMC-derived humanized mouse model (PBMC model) may serve as an excellent tool in the field of immunology for both preclinical research and personalized therapeutic strategy development. However, single transplantation of complete PBMCs without modifications prevents the identification of cell type-specific factors that are potentially involved in modulating cell-intrinsic functions for the immune response. Here, we establish an innovative strategy for PBMC model generation, where two-step transplantations coupled with cell type-specific gene manipulation were conducted to evaluate the potential role of CD8⁺ T cell-intrinsic factors in regulating antitumor immunity toward PDX-based tumors. This method readily yields over 10 % of human CD45⁺ cells within the PBMCs of humanized mice with high editing efficiency of gene expression in CD8⁺ T cells that can be subsequently detected in the tumor microenvironment (TME). Our work provides a new method to generate a PBMC-derived humanized mouse model for investigating regulators of interest during antitumor immunity in a cell type-specific manner.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"234 ","pages":"Pages 286-293"},"PeriodicalIF":4.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142997927","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":"Deep self-representation learning with hyper-laplacian regularization for brain imaging genetics association analysis","authors":"Jin-Xing Liu ,&nbsp;Shuang-Qing Wang ,&nbsp;Cui-Na Jiao ,&nbsp;Tian-Ru Wu ,&nbsp;Xin-Chun Cui ,&nbsp;Chun-Hou Zheng","doi":"10.1016/j.ymeth.2025.01.017","DOIUrl":"10.1016/j.ymeth.2025.01.017","url":null,"abstract":"<div><div>Brain imaging genetics aims to explore the association between genetic factors such as single nucleotide polymorphisms (SNPs) and brain imaging quantitative traits (QTs). However, most existing methods do not consider the nonlinear correlations between genotypic and phenotypic data, as well as potential higher-order relationships among subjects when identifying bi-multivariate associations. In this paper, a novel method called deep hyper-Laplacian regularized self-representation learning based structured association analysis (DHRSAA) is proposed which can learn genotype-phenotype associations and obtain relevant biomarkers. Specifically, a deep neural network is used first to explore the nonlinear relationships among samples. Secondly, self-representation learning based on hyper-Laplacian regularization is utilized to reconstruct the original data. In particular, the introduction of hyper-Laplacian regularization ensures the local structure of the high-dimensional spatial embedding and explores the higher-order relationships among the samples. Moreover, the structural regularization term in the association analysis uncovers chain relationships among SNPs and graphical relationships among imaging QTs, thus making the obtained markers more interpretable and enhancing the biological significance of the method. The performance of the proposed method is validated on real neuroimaging genetics data. Experimental results show that DHRSAA displays better canonical correlation coefficients and recognizes clearer canonical weight patterns compared to several state-of-the-art methods, which suggests that the proposed DHRSAA achieves better performance and identifies disease-related biomarkers.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"234 ","pages":"Pages 333-341"},"PeriodicalIF":4.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142997930","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":"Lead-grouped multi-stage learning for myocardial infarction localization","authors":"Lin Guo ,&nbsp;Qianyun Zhan ,&nbsp;Jichao Yang ,&nbsp;Ying An ,&nbsp;Jun Long ,&nbsp;Nan Ma","doi":"10.1016/j.ymeth.2025.01.015","DOIUrl":"10.1016/j.ymeth.2025.01.015","url":null,"abstract":"<div><div>The electrocardiogram (ECG) is a ubiquitous medical diagnostic tool employed to localize myocardial infarction (MI) that is characterized by abnormal waveform patterns on the ECG. MI is a serious cardiovascular disease, and accurate, timely diagnosis is crucial for preventing severe outcomes. Current ECG analysis methods mainly rely on intra- and inter-lead feature extraction, but most models overlook the medical knowledge relevant to disease diagnosis. Moreover, existing models often fail to effectively utilize the global spatial relationships within multi-lead ECGs, limiting their ability to comprehensively understand and accurately localize the complex pathological mechanisms of MI. To address these issues, we propose a knowledge-driven overlapping lead grouping method. Based on clinical diagnostic knowledge, we group the 12 leads according to their relevance to MI localization while retaining the full set of 12 leads as a unified group. Additionally, we design a multi-stage learning network that first extracts basic features through initial convolutional layer and progressive convolutional block, followed by SE-enhanced multi-scale residual block and positional Transformer block to gradually learn deeper intra- and inter-lead features. Furthermore, we propose a branch-level weighted feature integration mechanism to effectively fuse the features extracted from each group. The proposed method was thoroughly evaluated on the publicly available multi-label PTB-XL dataset and achieved over 80% prediction accuracy for MI localization tasks. The results demonstrated significant improvements across several metrics compared to current state-of-the-art methods, confirming its exceptional performance.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"234 ","pages":"Pages 315-323"},"PeriodicalIF":4.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143027495","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}