IF 4.2 3区生物学

Methods Pub Date : 2025-02-01 DOI: 10.1016/j.ymeth.2024.12.004

Shilpkala Gade, Lalitkumar K. Vora, Raghu Raj Singh Thakur

{"title":"Design and characterization of hollow microneedles for localized intrascleral drug delivery of ocular formulations","authors":"Shilpkala Gade, Lalitkumar K. Vora, Raghu Raj Singh Thakur","doi":"10.1016/j.ymeth.2024.12.004","DOIUrl":"10.1016/j.ymeth.2024.12.004","url":null,"abstract":"<div><div>Effective drug delivery to the posterior segment of the eye remains a challenge owing to the limitations of conventional methods such as intravitreal injections, which are associated with significant side effects. This study explored the use of hollow microneedles (HMNs) for localized intrascleral drug delivery as a minimally invasive alternative. Stainless steel HMNs with bevel angles of 30°, 45°, 60°, and 75° were fabricated using wire electron discharge machining. The penetration force of these HMNs in ex vivo porcine sclera was assessed using a texture analyser, revealing that the 60° bevel angle required the lowest force (<2N), making it optimal for scleral penetration. To ensure precision in drug delivery, 3D-printed adapters were developed to control the injection angles and volumes. The distribution of a model dye, rhodamine B, was studied via digital imaging, multiphoton microscopy, and confocal microscopy. The results showed that HMNs with a 60° bevel angle could penetrate the sclera to a depth of approximately 450 µm at a 45° injection angle, providing enhanced distribution within the scleral layers. This study confirmed that the use of HMNs enables effective and controlled intrascleral drug delivery, resulting in the formation of localized depots with minimal tissue damage. This research demonstrates the potential of HMNs as a promising alternative to traditional ocular drug delivery methods, offering improved bioavailability and the potential to reduce patient discomfort.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"234 ","pages":"Pages 196-210"},"PeriodicalIF":4.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142880855","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}

引用次数: 0

AntiT2DMP-Pred: Leveraging feature fusion and optimization for superior machine learning prediction of type 2 diabetes mellitus AntiT2DMP-Pred：利用特征融合和优化进行2型糖尿病的卓越机器学习预测。

IF 4.2 3区生物学

Methods Pub Date : 2025-02-01 DOI: 10.1016/j.ymeth.2025.01.003

Shaherin Basith , Balachandran Manavalan , Gwang Lee

{"title":"AntiT2DMP-Pred: Leveraging feature fusion and optimization for superior machine learning prediction of type 2 diabetes mellitus","authors":"Shaherin Basith , Balachandran Manavalan , Gwang Lee","doi":"10.1016/j.ymeth.2025.01.003","DOIUrl":"10.1016/j.ymeth.2025.01.003","url":null,"abstract":"<div><div>Pancreatic α-amylase breaks down starch into isomaltose and maltose, which are further hydrolyzed by α-glucosidase in the intestine into monosaccharides, rapidly raising blood sugar levels and contributing to type 2 diabetes mellitus (T2DM). Synthetic inhibitors of carbohydrate-digesting enzymes are used to manage T2DM but may harm organ function over time. Bioactive peptides offer a safer alternative, avoiding such adverse effects. Computational methods for predicting antidiabetic peptides (ADPs) can significantly reduce the time and cost of experimental testing. While machine learning (ML) has been applied to identify ADPs, advancements in data analysis and algorithms continue to drive progress in the field. To address this, we developed AntiT2DMP-Pred, the first ML-based tool specifically designed for predicting type 2 antidiabetic peptides (T2ADPs). This tool employs a feature fusion strategy, combining ten highly discriminative feature descriptors chosen from a pool of 32 descriptors and eight ML algorithms, tested across a range of baseline models. AntiT2DMP-Pred demonstrated excellent performance, surpassing both baseline and feature-optimized models, with an accuracy (ACC) and Matthews’ correlation coefficient (MCC) of 0.976 and 0.953 on the training dataset, and an ACC and MCC of 0.957 and 0.851 on the independent dataset. The web server (<span><span>https://balalab-skku.org/AntiT2DMP-Pred</span><svg><path></path></svg></span>) is freely accessible, enabling researchers worldwide to utilize it in their experimental workflows and contribute to the discovery and understanding of T2ADPs, ultimately supporting peptide-based therapeutic development for diabetes management.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"234 ","pages":"Pages 264-274"},"PeriodicalIF":4.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142968895","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}

引用次数: 0

Deepstack-ACE: A deep stacking-based ensemble learning framework for the accelerated discovery of ACE inhibitory peptides Deepstack-ACE：一个基于深度堆栈的集成学习框架，用于加速发现ACE抑制肽。

IF 4.2 3区生物学

Methods Pub Date : 2025-02-01 DOI: 10.1016/j.ymeth.2024.12.005

Phasit Charoenkwan , Pramote Chumnanpuen , Nalini Schaduangrat , Watshara Shoombuatong

{"title":"Deepstack-ACE: A deep stacking-based ensemble learning framework for the accelerated discovery of ACE inhibitory peptides","authors":"Phasit Charoenkwan , Pramote Chumnanpuen , Nalini Schaduangrat , Watshara Shoombuatong","doi":"10.1016/j.ymeth.2024.12.005","DOIUrl":"10.1016/j.ymeth.2024.12.005","url":null,"abstract":"<div><div>Identifying angiotensin-I-converting enzyme (ACE) inhibitory peptides accurately is crucial for understanding the primary factor that regulates the renin-angiotensin system and for providing guidance in developing new potential drugs. Given the inherent experimental complexities, using computational methods for <em>in silico</em> peptide identification could be indispensable for facilitating the high-throughput characterization of ACE inhibitory peptides. In this paper, we propose a novel deep stacking-based ensemble learning framework, termed Deepstack-ACE, to precisely identify ACE inhibitory peptides. In Deepstack-ACE, the input peptide sequences are fed into the word2vec embedding technique to generate sequence representations. Then, these representations were employed to train five powerful deep learning methods, including long short-term memory, convolutional neural network, multi-layer perceptron, gated recurrent unit network, and recurrent neural network, for the construction of base-classifiers. Finally, the optimized stacked model was constructed based on the best combination of selected base-classifiers. Benchmarking experiments showed that Deepstack-ACE attained a more accurate and robust identification of ACE inhibitory peptides compared to its base-classifiers and several conventional machine learning classifiers. Remarkably, in the independent test, our proposed model significantly outperformed the current state-of-the-art methods, with a balanced accuracy of 0.916, sensitivity of 0.911, and Matthews correlation coefficient scores of 0.826. Moreover, we developed a user-friendly web server for Deepstack-ACE, which is freely available at <span><span>https://pmlabqsar.pythonanywhere.com/Deepstack-ACE</span><svg><path></path></svg></span>. We anticipate that our proposed Deepstack-ACE model can provide a faster and reasonably accurate identification of ACE inhibitory peptides.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"234 ","pages":"Pages 131-140"},"PeriodicalIF":4.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142870920","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}

引用次数: 0

Integrated analyses of prognostic and immunotherapeutic significance of EZH2 in uveal melanoma EZH2对葡萄膜黑色素瘤预后和免疫治疗意义的综合分析。

IF 4.2 3区生物学

Methods Pub Date : 2025-02-01 DOI: 10.1016/j.ymeth.2025.01.004

Junfang Li , Yifei Zhang , Qiu Yang , Yi Qu

{"title":"Integrated analyses of prognostic and immunotherapeutic significance of EZH2 in uveal melanoma","authors":"Junfang Li , Yifei Zhang , Qiu Yang , Yi Qu","doi":"10.1016/j.ymeth.2025.01.004","DOIUrl":"10.1016/j.ymeth.2025.01.004","url":null,"abstract":"<div><div>The EZH2 expression shows significantly associated with immunotherapeutic resistance in several tumors. A comprehensive analysis of the predictive values of EZH2 for immune checkpoint blockade (ICB) effectiveness in uveal melanoma (UM) remains unclear. We analyzed UM data from The Cancer Genome Atlas (TCGA) database, identified 888 differentially expressed genes (DEGs) associated with EZH2 expression, then conducted Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analyses to elucidate biological features of EZH2 in UM assays. The correlation of the expression of EZH2 with tumor immunity related factors such as immune-related pathways, infiltration of various immune cells, immune score and immune checkpoints were explored. The evaluation of EZH2′s capability to predict immune therapy outcomes in UM was assessed by incorporating the Tumor Immune Dysfunction and Exclusion (TIDE) score. Lastly, programmed death-ligand 1 (PD-L1) expression was detected in an independent UM patient cohort by immunohistochemical analyses, the correlation of EZH2 with PD-L1 was evaluated. Results highlighted that the EZH2 expression was correlated with immune-related pathways, infiltration of various immune cells, immune score, the expression of immune checkpoints and immunotherapy sensitivity. Collectively, we suggested that EZH2 might be considered as predictor on the therapeutic effects of ICBs on UM patients, and a potential target for combined immunotherapy.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"234 ","pages":"Pages 242-252"},"PeriodicalIF":4.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142942260","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}

引用次数: 0

Predicting cyclins based on key features and machine learning methods 基于关键特征和机器学习方法预测周期蛋白。

IF 4.2 3区生物学

Methods Pub Date : 2025-02-01 DOI: 10.1016/j.ymeth.2024.12.009

Cheng-Yan Wu , Zhi-Xue Xu , Nan Li , Dan-Yang Qi , Hong-Ye Wu , Hui Ding , Yan-Ting Jin

{"title":"Predicting cyclins based on key features and machine learning methods","authors":"Cheng-Yan Wu , Zhi-Xue Xu , Nan Li , Dan-Yang Qi , Hong-Ye Wu , Hui Ding , Yan-Ting Jin","doi":"10.1016/j.ymeth.2024.12.009","DOIUrl":"10.1016/j.ymeth.2024.12.009","url":null,"abstract":"<div><div>Cyclins are a group of proteins that regulate the cell cycle process by modulating various stages of cell division to ensure correct cell proliferation, differentiation, and apoptosis. Research on cyclins is crucial for understanding the biological functions and pathological states of cells. However, current research on cyclin identification based on machine learning only focuses on accuracy ignoring the interpretability of features. Therefore, in this study, we pay more attention to the interpretation and analysis of key features associated with cyclins. Firstly, we developed an SVM-based model for identifying cyclins with an accuracy of 92.8% through 5-fold. Then we analyzed the physicochemical properties of the 14 key features used in the model construction and identified the G and charged C1 features that are critical for distinguishing cyclins from non-cyclins. Furthermore, we constructed an SVM-based model using only these two features with an accuracy of 81.3% through the leave-one-out cross-validation. Our study shows that cyclins differ from non-cyclins in their physicochemical properties and that using only two features can achieve good prediction accuracy.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"234 ","pages":"Pages 112-119"},"PeriodicalIF":4.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142851969","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}

引用次数: 0

Ins-ATP: Deep estimation of ATP for organoid based on high throughput microscope images

IF 4.2 3区生物学

Methods Pub Date : 2025-01-31 DOI: 10.1016/j.ymeth.2025.01.012

Xuesheng Bian , Shuting Chen , Weiquan Liu

{"title":"Ins-ATP: Deep estimation of ATP for organoid based on high throughput microscope images","authors":"Xuesheng Bian , Shuting Chen , Weiquan Liu","doi":"10.1016/j.ymeth.2025.01.012","DOIUrl":"10.1016/j.ymeth.2025.01.012","url":null,"abstract":"<div><div>Adenosine triphosphate (ATP) is a high-energy phosphate compound, the most direct energy source in organisms. ATP is an important biomarker for evaluating cell viability in biology. Researchers often use ATP bioluminescence to measure the ATP of organoid after drug to evaluate the drug efficacy. However, ATP bioluminescence has limitations, leading to unreliable drug screening results. ATP bioluminescence measurement requires the lysis of organoid cells, making it impossible to continuously monitor the long-term viability changes of organoids after drug administration. To overcome the disadvantages of ATP bioluminescence, we propose Ins-ATP, a non-invasive strategy, the first organoid ATP estimation model based on the high-throughput microscope image. Ins-ATP directly estimates the ATP of organoids from high-throughput microscope images so that it does not influence the drug reactions of organoids. Therefore, the ATP change of organoids can be observed for a long time to obtain more stable results. Experimental results show that the ATP estimation by Ins-ATP is in good agreement with those determined by ATP bioluminescence. Specifically, the predictions of Ins-ATP are consistent with the results measured by ATP bioluminescence in the efficacy evaluation experiments of different drugs.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"235 ","pages":"Pages 34-44"},"PeriodicalIF":4.2,"publicationDate":"2025-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143073381","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}

引用次数: 0

ZeRPI: A graph neural network model for zero-shot prediction of RNA-protein interactions

IF 4.2 3区生物学

Methods Pub Date : 2025-01-30 DOI: 10.1016/j.ymeth.2025.01.014

Yifei Gao , Runhan Shi , Gufeng Yu , Yuyang Huang , Yang Yang

{"title":"ZeRPI: A graph neural network model for zero-shot prediction of RNA-protein interactions","authors":"Yifei Gao , Runhan Shi , Gufeng Yu , Yuyang Huang , Yang Yang","doi":"10.1016/j.ymeth.2025.01.014","DOIUrl":"10.1016/j.ymeth.2025.01.014","url":null,"abstract":"<div><div>RNA-protein interactions are crucial for biological functions across multiple levels. RNA binding proteins (RBPs) intricately engage in diverse biological processes through specific RNA molecule interactions. Previous studies have revealed the indispensable role of RBPs in both health and disease development. With the increase of experimental data, machine-learning methods have been widely used to predict RNA-protein interactions. However, most current methods either train models for individual RBPs or develop multi-task models for a fixed set of multiple RBPs. These approaches are incapable of predicting interactions with previously unseen RBPs. In this study, we present ZeRPI, a zero-shot method for predicting RNA-protein interactions. Based on a graph neural network model, ZeRPI integrates RNA and protein information to generate detailed representations, using a novel loss function based on contrastive learning principles to augment the alignment between interacting pairs in feature space. ZeRPI demonstrates competitive performance in predicting RNA-protein interactions across a wide array of RBPs. Notably, our model exhibits remarkable versatility in accurately predicting interactions for unseen RBPs, demonstrating its capacity to transfer knowledge learned from known RBPs.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"235 ","pages":"Pages 45-52"},"PeriodicalIF":4.2,"publicationDate":"2025-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143073378","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}

引用次数: 0

CSSEC: An adaptive approach integrating consensus and specific self-expressive coefficients for multi-omics cancer subtyping

IF 4.2 3区生物学

Methods Pub Date : 2025-01-27 DOI: 10.1016/j.ymeth.2025.01.016

Yueyi Cai, Nan Zhou, Junran Zhao, Weihua Li, Shunfang Wang

{"title":"CSSEC: An adaptive approach integrating consensus and specific self-expressive coefficients for multi-omics cancer subtyping","authors":"Yueyi Cai, Nan Zhou, Junran Zhao, Weihua Li, Shunfang Wang","doi":"10.1016/j.ymeth.2025.01.016","DOIUrl":"10.1016/j.ymeth.2025.01.016","url":null,"abstract":"<div><div>Cancer is a complex and heterogeneous disease, and accurate cancer subtyping can significantly improve patient survival rates. The complexity of cancer spans multiple omics levels, and analyzing multi-omics data for cancer subtyping has become a major focus of research. However, extracting complementary information from different omics data sources and adaptively integrating them remains a major challenge. To address this, we proposed an adaptive approach integrating consensus and specific self-expressive coefficients for multi-omics cancer subtyping (CSSEC). First, independent self-expressive networks are applied to each omics to calculate coefficient matrices to measure patient similarity. Then, two feature graph convolutional network modules capture consensus and specific similarity features using the topK relevant features. Finally, the multi-omics self-expression coefficient matrix is constructed by consensus and specific similarity features. Furthermore, joint consistency and disparity constraints are applied to regularize the fusion of the self-expressive coefficients. Experimental results demonstrate that CSSEC outperforms existing state-of-the-art methods in survival analysis. Moreover, case studies on kidney cancer confirm that the cancer subtypes identified by CSSEC are biologically significant. The complete code can be available at <span><span>https://github.com/ykxhs/CSSEC</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"235 ","pages":"Pages 26-33"},"PeriodicalIF":4.2,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143063046","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}

引用次数: 0

LiteMamba-Bound: A lightweight Mamba-based model with boundary-aware and normalized active contour loss for skin lesion segmentation

IF 4.2 3区生物学

Methods Pub Date : 2025-01-27 DOI: 10.1016/j.ymeth.2025.01.008

Quang-Huy Ho, Thi-Nhu-Quynh Nguyen, Thi-Thao Tran, Van-Truong Pham

{"title":"LiteMamba-Bound: A lightweight Mamba-based model with boundary-aware and normalized active contour loss for skin lesion segmentation","authors":"Quang-Huy Ho, Thi-Nhu-Quynh Nguyen, Thi-Thao Tran, Van-Truong Pham","doi":"10.1016/j.ymeth.2025.01.008","DOIUrl":"10.1016/j.ymeth.2025.01.008","url":null,"abstract":"<div><div>In the field of medical science, skin segmentation has gained significant importance, particularly in dermatology and skin cancer research. This domain demands high precision in distinguishing critical regions (such as lesions or moles) from healthy skin in medical images. With growing technological advancements, deep learning models have emerged as indispensable tools in addressing these challenges. One of the state-of-the-art modules revealed in recent years, the 2D Selective Scan (SS2D), based on state-space models that have already seen great success in natural language processing, has been increasingly adopted and is gradually replacing Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs). Leveraging the strength of this module, this paper introduces LiteMamba-Bound, a lightweight model with approximately 957K parameters, designed for skin image segmentation tasks. Notably, the Channel Attention Dual Mamba (CAD-Mamba) block is proposed within both the encoder and decoder alongside the Mix Convolution with Simple Attention bottleneck block to emphasize key features. Additionally, we propose the Reverse Attention Boundary Module to highlight challenging boundary features. Also, the Normalized Active Contour loss function presented in this paper significantly improves the model's performance compared to other loss functions. To validate performance, we conducted tests on two skin image datasets, ISIC2018 and PH2, with results consistently showing superior performance compared to other models. Our code will be made publicly available at: <span><span>https://github.com/kwanghwi242/A-new-segmentation-model</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"235 ","pages":"Pages 10-25"},"PeriodicalIF":4.2,"publicationDate":"2025-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143045193","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}

引用次数: 0

MPEMDA: A multi-similarity integration approach with pre-completion and error correction for predicting microbe-drug associations

IF 4.2 3区生物学

Methods Pub Date : 2025-01-23 DOI: 10.1016/j.ymeth.2024.12.013

Yuxiang Li , Haochen Zhao , Jianxin Wang

{"title":"MPEMDA: A multi-similarity integration approach with pre-completion and error correction for predicting microbe-drug associations","authors":"Yuxiang Li , Haochen Zhao , Jianxin Wang","doi":"10.1016/j.ymeth.2024.12.013","DOIUrl":"10.1016/j.ymeth.2024.12.013","url":null,"abstract":"<div><div>Exploring the associations between microbes and drugs offers valuable insights into their underlying mechanisms. Traditional wet lab experiments, while reliable, are often time-consuming and labor-intensive, making computational approaches an attractive alternative. Existing similarity-based machine learning models for predicting microbe-drug associations typically rely on integrated similarities as input, neglecting the unique contributions of individual similarities, which can compromise predictive accuracy. To overcome these limitations, we develop MPEMDA, a novel method that pre-completes the microbe-drug association matrix using various similarity combinations and employs a label propagation algorithm with error correction to predict microbe-drug associations. Compared with existing methods, MPEMDA simultaneously utilizes the integrated and individual similarities obtained through the Similarity Network Fusion (SNF) method to pre-complete the known drug-microbe association matrix, followed by error correction to optimize the predictive scores generated by the label propagation algorithm. Experimental results on three benchmark datasets show that MPEMDA outperforms state-of-the-art methods in both the 5-fold cross-validation and <em>de novo</em> test. Additionally, case studies on drugs and microbes highlight the method's strong potential to identify novel microbe-drug associations. The MPEMDA code is available at <span><span>https://github.com/lyx8527/MPEMDA</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"235 ","pages":"Pages 1-9"},"PeriodicalIF":4.2,"publicationDate":"2025-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143035727","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}

引用次数: 0

Methods最新文献