IF 4.3 3区生物学 Q1 BIOCHEMICAL RESEARCH METHODS

Methods

Pub Date : 2025-11-28 DOI: 10.1016/j.ymeth.2025.11.009

Tejas S. Patil , Deepvardhan P. Chaudhari , Utkarsh U. Bhamare , Mahesh B. Palkar , Mahendra R. Mahajan , Sopan N. Nangare

Millions of women worldwide suffer from a variety of health conditions, including vaginal bacterial and yeast infections, sexually transmitted infections (STIs), urinary tract infections, pelvic inflammatory disorders, and hormonal abnormalities. Despite major advances in biomedical research, traditional intravaginal drug administration systems such as gels, creams, and suppositories frequently encounter issues such as fast drug clearance, leakage, and uneven mucosal retention, reducing therapeutic effectiveness. Microneedles, a painless and less invasive drug delivery technology, represent a viable alternative to standard formulations because they allow for accurate, controlled, and localized drug administration. Therefore, the present review focuses on possibility of microneedle-based techniques for intravaginal medication administration. In brief, it covers the need for breakthroughs in vaginal drug administration. It provides an overview of several types of microneedles, including solid, hollow, dissolving, coated, and hydrogel-forming, and their manufacturing procedures. Then, it delves into their use in intravaginal drug administration, highlighting their capacity to improve drug penetration and retention. Finally, it discusses future problems, prospective advancements, and the larger implications of microneedle technology in vaginal therapy. Microneedle-based intravaginal medication delivery is a huge step forward in targeted vaginal infection treatment. Notably, microneedles easily cross the cervicovaginal mucus barrier, increasing drug absorption at the target region while being minimally invasive. Future studies should focus on improving microneedle formulations, assessing long-term safety, and investigating their potential for wider clinical applications.

全世界数以百万计的妇女患有各种健康问题，包括阴道细菌和酵母菌感染、性传播感染、尿路感染、盆腔炎性疾病和激素异常。尽管生物医学研究取得了重大进展，但传统的阴道内给药系统，如凝胶、乳膏和栓剂，经常遇到药物快速清除、渗漏和粘膜保留不均匀等问题，降低了治疗效果。微针是一种无痛、无创给药技术，是标准配方的可行替代方案，因为它们允许精确、可控和局部给药。因此，本综述的重点是基于微针的阴道内给药技术的可能性。简而言之，它涵盖了在阴道给药方面取得突破的需要。它提供了几种类型的微针的概述，包括固体，空心，溶解，涂层和水凝胶形成，以及它们的制造程序。然后，深入研究了它们在阴道内给药中的应用，强调了它们提高药物渗透和保留的能力。最后，它讨论了未来的问题，前瞻性的进展，以及微针技术在阴道治疗中的更大的影响。基于微针的阴道内给药是阴道感染靶向治疗的巨大进步。值得注意的是，微针很容易穿过宫颈阴道粘液屏障，增加了靶区药物的吸收，同时微创。未来的研究应侧重于改进微针配方，评估长期安全性，并调查其更广泛临床应用的潜力。

{"title":"Fabrication of advanced microneedle-based targeted intravaginal drug delivery devices: therapeutic opportunities and translational challenges","authors":"Tejas S. Patil , Deepvardhan P. Chaudhari , Utkarsh U. Bhamare , Mahesh B. Palkar , Mahendra R. Mahajan , Sopan N. Nangare","doi":"10.1016/j.ymeth.2025.11.009","DOIUrl":"10.1016/j.ymeth.2025.11.009","url":null,"abstract":"<div><div>Millions of women worldwide suffer from a variety of health conditions, including vaginal bacterial and yeast infections, sexually transmitted infections (STIs), urinary tract infections, pelvic inflammatory disorders, and hormonal abnormalities. Despite major advances in biomedical research, traditional intravaginal drug administration systems such as gels, creams, and suppositories frequently encounter issues such as fast drug clearance, leakage, and uneven mucosal retention, reducing therapeutic effectiveness. Microneedles, a painless and less invasive drug delivery technology, represent a viable alternative to standard formulations because they allow for accurate, controlled, and localized drug administration. Therefore, the present review focuses on possibility of microneedle-based techniques for intravaginal medication administration. In brief, it covers the need for breakthroughs in vaginal drug administration. It provides an overview of several types of microneedles, including solid, hollow, dissolving, coated, and hydrogel-forming, and their manufacturing procedures. Then, it delves into their use in intravaginal drug administration, highlighting their capacity to improve drug penetration and retention. Finally, it discusses future problems, prospective advancements, and the larger implications of microneedle technology in vaginal therapy. Microneedle-based intravaginal medication delivery is a huge step forward in targeted vaginal infection treatment. Notably, microneedles easily cross the cervicovaginal mucus barrier, increasing drug absorption at the target region while being minimally invasive. Future studies should focus on improving microneedle formulations, assessing long-term safety, and investigating their potential for wider clinical applications.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"246 ","pages":"Pages 62-82"},"PeriodicalIF":4.3,"publicationDate":"2025-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145647037","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

Explainable machine learning-based prediction of psoriatic arthritis flares using heterogenous real-world data for personalised patient care 可解释的基于机器学习的银屑病关节炎耀斑预测，使用异质真实世界数据进行个性化患者护理。

IF 4.3 3区生物学 Q1 BIOCHEMICAL RESEARCH METHODS

Methods

Pub Date : 2025-11-21 DOI: 10.1016/j.ymeth.2025.10.010

Pradip Moon , Weizi Li , Antoni Chan , Bing Wang , Eghosa Bazuaye

Psoriatic arthritis (PsA) is a chronic inflammatory disease characterised by unpredictable flare-ups that are difficult to forecast, particularly in patients without an acute phase response. In this paper, we propose and apply an explainable, multimodal machine learning framework that jointly leverages structured temporal electronic patient records (EPRs) – sequential blood tests, disease activity scores, comorbidity burden, medications, and demographics – and unstructured clinical referral letters pre-processed with large language models ((LLMs, (Qwen-2.5 family)) to predict PsA flares. Gradient boosting models, Light Gradient Boosting Machine (LGBM) and eXtreme Gradient Boosting (XGBoost) were used to predict PsA flares, achieving the highest predictive performance 3 months before a clinic visit (accuracy = 92.8 %, AUROC = 0.94). Model performance gradually declined for longer timeframes (6 months: 78.2 %, AUROC = 0.80; 9 months: 76.6 %, AUROC = 0.78; 12 months: 72.2 %, AUROC = 0.75). LLMs applied to unstructured GP referral letters had limited standalone predictive value, but enhanced sensitivity and specificity when combined with the structured models in an ensemble approach. SHapley Additive exPlanations (SHAP) helped explain the prediction and demonstrated comorbidity count, disease scores, and immunosuppressive medications as the top predictors. Our results show that integrating both structured longitudinal data with unstructured clinical narratives using interpretable multimodal artificial intelligence can enable time-sensitive, personalised management of PsA flares and early clinical intervention.

银屑病关节炎（PsA）是一种慢性炎症性疾病，其特征是难以预测的突然发作，特别是在没有急性期反应的患者中。在本文中，我们提出并应用了一个可解释的多模式机器学习框架，该框架联合利用结构化的时间电子病历（epr) -顺序血液检查，疾病活动评分，合并症负担，药物和人口统计学-以及用大型语言模型预处理的非结构化临床转诊信（LLMs, Qwen-2.5 family））来预测PsA发作。梯度增强模型、光梯度增强机（Light Gradient boosting Machine， LGBM）和极限梯度增强（eXtreme Gradient boosting, XGBoost）用于预测PsA耀斑，在就诊前3 个月达到最高预测效果（准确率 = 92.8 %,AUROC = 0.94）。更长时间的模型性能逐渐下降(6 个月:78.2 %,AUROC = 0.80; 9个月:76.6 %,AUROC = 0.78; 12个月:72.2 %,AUROC = 0.75)。llm应用于非结构化GP推荐信的单独预测价值有限，但当与结构化模型结合在一起时，灵敏度和特异性增强。SHapley加性解释（SHAP）有助于解释预测，并证明合并症计数、疾病评分和免疫抑制药物是最重要的预测因子。我们的研究结果表明，使用可解释的多模式人工智能将结构化的纵向数据与非结构化的临床叙述结合起来，可以实现对PsA耀斑的时间敏感、个性化管理和早期临床干预。

{"title":"Explainable machine learning-based prediction of psoriatic arthritis flares using heterogenous real-world data for personalised patient care","authors":"Pradip Moon , Weizi Li , Antoni Chan , Bing Wang , Eghosa Bazuaye","doi":"10.1016/j.ymeth.2025.10.010","DOIUrl":"10.1016/j.ymeth.2025.10.010","url":null,"abstract":"<div><div>Psoriatic arthritis (PsA) is a chronic inflammatory disease characterised by unpredictable flare-ups that are difficult to forecast, particularly in patients without an acute phase response. In this paper, we propose and apply an explainable, multimodal machine learning framework that jointly leverages structured temporal electronic patient records (EPRs) – sequential blood tests, disease activity scores, comorbidity burden, medications, and demographics – and unstructured clinical referral letters pre-processed with large language models ((LLMs, (Qwen-2.5 family)) to predict PsA flares. Gradient boosting models, Light Gradient Boosting Machine (LGBM) and eXtreme Gradient Boosting (XGBoost) were used to predict PsA flares, achieving the highest predictive performance 3 months before a clinic visit (accuracy = 92.8 %, AUROC = 0.94). Model performance gradually declined for longer timeframes (6 months: 78.2 %, AUROC = 0.80; 9 months: 76.6 %, AUROC = 0.78; 12 months: 72.2 %, AUROC = 0.75). LLMs applied to unstructured GP referral letters had limited standalone predictive value, but enhanced sensitivity and specificity when combined with the structured models in an ensemble approach. SHapley Additive exPlanations (SHAP) helped explain the prediction and demonstrated comorbidity count, disease scores, and immunosuppressive medications as the top predictors. Our results show that integrating both structured longitudinal data with unstructured clinical narratives using interpretable multimodal artificial intelligence can enable time-sensitive, personalised management of PsA flares and early clinical intervention.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"246 ","pages":"Pages 95-106"},"PeriodicalIF":4.3,"publicationDate":"2025-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145585760","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

A smoothing method for DNA methylome analysis to enhance epigenomic signature detection in epigenome-wide association studies 一种用于DNA甲基组分析的平滑方法，以增强表观基因组全关联研究中的表观基因组特征检测。

IF 4.3 3区生物学 Q1 BIOCHEMICAL RESEARCH METHODS

Methods

Pub Date : 2025-11-20 DOI: 10.1016/j.ymeth.2025.11.005

Abderrahim Oussalah , Loris Mousel , David-Alexandre Trégouët , Jean-Louis Guéant

Epigenome‐wide association studies (EWAS) are instrumental for mapping DNA methylation changes in human traits and diseases but often suffer from low statistical power and false positives, especially in small cohorts. We developed an EWAS smoothing method that exploits co‐methylation of adjacent CpG probes within CpG islands via a sliding‐window average and generalized it using Savitzky-Golay filtering. We applied the smoothing approach—with window widths of 1–3 CpGs and, for generalization, Savitzky-Golay filters of varying polynomial orders and window sizes—across five distinct EWAS settings. Performance was quantified by signal‐to‐noise ratio (SNR), noise‐variance reduction, variance ratio (VR), Bayes factors, and sample‐size sensitivity. In the MMACHC epimutation dataset, a 5‐CpG window (width, w = 2) increased SNR by 90 %, reduced noise variance by 80 %, and elevated VR by 176 % at the target CpG island, with no genome‐wide false positives. For MLH1, smoothing preserved the top association and suppressed background signals. In the aging EWAS, a “Polyepigenetic CpG aging score” was derived following smoothing. This score correlated strongly with chronological age in the discovery cohort (Spearman’s ρ = 0.89; P = 3.0 × 10⁻²¹⁹) and was independently validated in a separate dataset, significantly distinguishing newborns from nonagenarians (P = 3.4 × 10⁻⁸). Savitzky-Golay filtering of order 0 with a 5‐CpG window yielded optimal SNR across bootstrap iterations, supporting this configuration as a robust choice for methylation array smoothing. As an extension of the Savitzky-Golay-based smoothing framework, reanalysis of a liver cancer dataset identified five top loci surpassing a smoothed P-value threshold of 1 × 10⁻⁸. Among these, MIR10A within the HOXB3 locus was the only previously reported functionally relevant site. In conclusion, the smoothing method improves EWAS performance by enhancing SNR, enabling detection of meaningful associations even in small cohorts, and offers a valuable tool for reanalyzing existing Infinium methylation array datasets to uncover previously undetected epigenomic signatures.

全表观基因组关联研究（EWAS）是绘制人类特征和疾病中DNA甲基化变化的工具，但往往存在统计效力低和假阳性的问题，特别是在小队列中。我们开发了一种EWAS平滑方法，该方法通过滑动窗口平均利用CpG岛屿内相邻CpG探针的共甲基化，并使用Savitzky-Golay滤波对其进行了推广。我们在五个不同的EWAS设置中应用了平滑方法——窗宽为1-3 CpGs，并且为了一般化，使用了不同多项式阶数和窗大小的Savitzky-Golay滤波器。通过信噪比（SNR）、降噪方差、方差比（VR）、贝叶斯因子和样本量敏感性对性能进行量化。在MMACHC估计数据集中，5-CpG窗口（宽度，w = 2）使目标CpG岛的信噪比提高了90 %，噪声方差降低了80 %，VR提高了176 %，没有全基因组假阳性。对于MLH1，平滑保留了顶部关联并抑制了背景信号。在老化EWAS中，平滑后得到“聚遗传CpG老化评分”。这一点强烈的实足年龄相关发现队列(枪兵的ρ = 0.89;P = 3.0  × 10 - 219),是独立的在一个单独的数据集进行验证,显著区别新生儿中(3.4 P =  × 换。0阶Savitzky-Golay滤波与5-CpG窗口在自举迭代中产生最佳信噪比，支持该配置作为甲基化阵列平滑的鲁棒选择。作为savitzky - golay平滑框架的扩展，对肝癌数据集的再分析确定了超过1 × 10-8平滑p值阈值的五个顶级位点。其中，HOXB3基因座内的MIR10A是唯一先前报道的功能相关位点。总之，平滑方法通过提高信噪比提高了EWAS的性能，即使在小队列中也能检测到有意义的关联，并为重新分析现有的Infinium甲基化阵列数据集提供了一个有价值的工具，以揭示以前未检测到的表观基因组特征。

{"title":"A smoothing method for DNA methylome analysis to enhance epigenomic signature detection in epigenome-wide association studies","authors":"Abderrahim Oussalah , Loris Mousel , David-Alexandre Trégouët , Jean-Louis Guéant","doi":"10.1016/j.ymeth.2025.11.005","DOIUrl":"10.1016/j.ymeth.2025.11.005","url":null,"abstract":"<div><div>Epigenome‐wide association studies (EWAS) are instrumental for mapping DNA methylation changes in human traits and diseases but often suffer from low statistical power and false positives, especially in small cohorts. We developed an EWAS smoothing method that exploits co‐methylation of adjacent CpG probes within CpG islands via a sliding‐window average and generalized it using Savitzky-Golay filtering. We applied the smoothing approach—with window widths of 1–3 CpGs and, for generalization, Savitzky-Golay filters of varying polynomial orders and window sizes—across five distinct EWAS settings. Performance was quantified by signal‐to‐noise ratio (SNR), noise‐variance reduction, variance ratio (VR), Bayes factors, and sample‐size sensitivity. In the <em>MMACHC</em> epimutation dataset, a 5‐CpG window (width, <em>w</em> = 2) increased SNR by 90 %, reduced noise variance by 80 %, and elevated VR by 176 % at the target CpG island, with no genome‐wide false positives. For <em>MLH1</em>, smoothing preserved the top association and suppressed background signals. In the aging EWAS, a “Polyepigenetic CpG aging score” was derived following smoothing. This score correlated strongly with chronological age in the discovery cohort (Spearman’s <em>ρ</em> = 0.89; <em>P</em> = 3.0 × 10<sup>−219</sup>) and was independently validated in a separate dataset, significantly distinguishing newborns from nonagenarians (<em>P</em> = 3.4 × 10<sup>−8</sup>). Savitzky-Golay filtering of order 0 with a 5‐CpG window yielded optimal SNR across bootstrap iterations, supporting this configuration as a robust choice for methylation array smoothing. As an extension of the Savitzky-Golay-based smoothing framework, reanalysis of a liver cancer dataset identified five top loci surpassing a smoothed <em>P</em>-value threshold of 1 × 10<sup>−8</sup>. Among these, <em>MIR10A</em> within the <em>HOXB3</em> locus was the only previously reported functionally relevant site. In conclusion, the smoothing method improves EWAS performance by enhancing SNR, enabling detection of meaningful associations even in small cohorts, and offers a valuable tool for reanalyzing existing Infinium methylation array datasets to uncover previously undetected epigenomic signatures.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"246 ","pages":"Pages 34-47"},"PeriodicalIF":4.3,"publicationDate":"2025-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145581598","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

From sample to clinical insight: a review of exome sequencing in disease diagnostics 从样本到临床洞察：外显子组测序在疾病诊断中的综述。

IF 4.3 3区生物学 Q1 BIOCHEMICAL RESEARCH METHODS

Methods

Pub Date : 2025-11-19 DOI: 10.1016/j.ymeth.2025.11.007

Gowrang Kasaba Manjunath , Rohit Kumar Verma , Abhijit Berua , Shweta Mahalingam , Tikam Chand Dakal , Abhishek Kumar

Exome sequencing (ES) has transformed genomic research and clinical diagnostics by enabling precise identification of disease-associated variants within protein-coding regions, which, while representing a minority of the genome, include many well-characterized pathogenic mutations. This review provides a comprehensive overview of ES methodology, data analysis pipelines, clinical relevance, and ethical considerations. We describe the ES workflow from DNA extraction and library preparation to target enrichment, sequencing to ES data analysis. We have also evaluated major capture technologies and sequencing platforms, including short-read and emerging long-read systems. Furthermore, we discuss computational analysis tools such as GATK, FreeBayes, DeepVariant, and Platypus, and strategies to improve accuracy through rigorous quality control, coverage optimization, and orthogonal validation. Beyond rare disease and cancer genomics, ES has expanded into pharmacogenomics, population-scale studies, and integrative multi-omics frameworks that combine transcriptomic and proteomic data to enhance functional interpretation. We highlight actionable examples such as CYP2C19 variants influencing clopidogrel metabolism, illustrating ES’s growing role in personalized medicine. Challenges (including variant interpretation complexity, false positives, and data standardization) are critically discussed. The review also addresses ethical, legal, and social dimensions of ES, including informed consent, data privacy, incidental findings, and adherence to ACMG, HIPAA, and GDPR. Finally, we outline future directions emphasizing machine learning–based variant prioritization, single-cell sequencing integration, and scalable bioinformatics infrastructures to enhance accuracy and clinical translation. Collectively, these developments position ES as a pivotal tool bridging genomic discovery, disease diagnostics, and precision healthcare in the era of personalized medicine.

外显子组测序（ES）已经改变了基因组研究和临床诊断，因为它能够精确识别蛋白质编码区域内的疾病相关变异，这些变异虽然只占基因组的一小部分，但包括许多具有良好特征的致病突变。这篇综述提供了ES方法、数据分析管道、临床相关性和伦理考虑的全面概述。我们描述了从DNA提取和文库制备到目标富集，测序到ES数据分析的ES工作流程。我们还评估了主要的捕获技术和测序平台，包括短读和新兴的长读系统。此外，我们还讨论了计算分析工具，如GATK， FreeBayes， DeepVariant和Platypus，以及通过严格的质量控制，覆盖优化和正交验证来提高准确性的策略。除了罕见疾病和癌症基因组学，ES已经扩展到药物基因组学、人群规模研究和整合多组学框架，结合转录组学和蛋白质组学数据来增强功能解释。我们强调了可操作的例子，如CYP2C19变异影响氯吡格雷代谢，说明ES在个性化医疗中的作用越来越大。挑战（包括变体解释的复杂性，误报和数据标准化）进行了批判性的讨论。该审查还涉及ES的伦理、法律和社会层面，包括知情同意、数据隐私、偶然发现以及对ACMG、HIPAA和GDPR的遵守。最后，我们概述了未来的发展方向，强调基于机器学习的变异优先排序，单细胞测序整合和可扩展的生物信息学基础设施，以提高准确性和临床翻译。总的来说，这些发展使ES成为个性化医疗时代连接基因组发现、疾病诊断和精准医疗的关键工具。

{"title":"From sample to clinical insight: a review of exome sequencing in disease diagnostics","authors":"Gowrang Kasaba Manjunath , Rohit Kumar Verma , Abhijit Berua , Shweta Mahalingam , Tikam Chand Dakal , Abhishek Kumar","doi":"10.1016/j.ymeth.2025.11.007","DOIUrl":"10.1016/j.ymeth.2025.11.007","url":null,"abstract":"<div><div>Exome sequencing (ES) has transformed genomic research and clinical diagnostics by enabling precise identification of disease-associated variants within protein-coding regions, which, while representing a minority of the genome, include many well-characterized pathogenic mutations. This review provides a comprehensive overview of ES methodology, data analysis pipelines, clinical relevance, and ethical considerations. We describe the ES workflow from DNA extraction and library preparation to target enrichment, sequencing to ES data analysis. We have also evaluated major capture technologies and sequencing platforms, including short-read and emerging long-read systems. Furthermore, we discuss computational analysis tools such as GATK, FreeBayes, DeepVariant, and Platypus, and strategies to improve accuracy through rigorous quality control, coverage optimization, and orthogonal validation. Beyond rare disease and cancer genomics, ES has expanded into pharmacogenomics, population-scale studies, and integrative multi-omics frameworks that combine transcriptomic and proteomic data to enhance functional interpretation. We highlight actionable examples such as CYP2C19 variants influencing clopidogrel metabolism, illustrating ES’s growing role in personalized medicine. Challenges (including variant interpretation complexity, false positives, and data standardization) are critically discussed. The review also addresses ethical, legal, and social dimensions of ES, including informed consent, data privacy, incidental findings, and adherence to ACMG, HIPAA, and GDPR. Finally, we outline future directions emphasizing machine learning–based variant prioritization, single-cell sequencing integration, and scalable bioinformatics infrastructures to enhance accuracy and clinical translation. Collectively, these developments position ES as a pivotal tool bridging genomic discovery, disease diagnostics, and precision healthcare in the era of personalized medicine.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"246 ","pages":"Pages 12-33"},"PeriodicalIF":4.3,"publicationDate":"2025-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145572733","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

Toward accurate breast cancer classification: A review of multi-modal machine learning approaches 乳腺癌准确分类：多模态机器学习方法综述。

IF 4.3 3区生物学 Q1 BIOCHEMICAL RESEARCH METHODS

Methods

Pub Date : 2025-11-18 DOI: 10.1016/j.ymeth.2025.10.011

Archana Mathur , Abbas Mufaddal Dudhiyawala , Sudeepa Roy Dey , Snehanshu Saha

The innovations in classifying breast cancer into malignant and benign categories and further categorizing it into molecular subtypes have reshaped healthcare services, enabling accurate diagnosis of these complex conditions. Identification of molecular subtypes of breast cancer is one of the most important treatment challenges, as these subtypes can have an enormous effect on the prognosis and treatment approaches. Data integration from various modalities, such as transcriptomics, imaging, and genomics, has been crucial in leveraging new opportunities to increase classification accuracy and improve individualized treatment plans. These heterogeneous data sources are examined by applying deep learning algorithms, which provide further insights into the complex patterns that traditional approaches often overlook. In this paper, we explore the various modalities researchers use to investigate breast cancer and the intriguing fusion techniques employed to combine these modalities. We also review the most recent models (traditional, machine learning, and deep learning), emphasizing their improvements over traditional classification methods and the molecular subtype categorization of breast cancer. Furthermore, the emphasis of this review is to examine techniques to process the entire image of the breast tissue slide, which is challenging, particularly due to its size. We explore recent advances in multiple instance learning tasks and the use of attention-based transformers and similar architectures for annotating the WSI slides before using them for cancer classification. We additionally discuss the interpretability tools—attention maps, saliency maps and model explainability— in the context of transformers. In a nutshell, we aim to provide an in-depth look at the revolutionary capabilities of deep learning models in precision oncology and guide future research paths in this crucial field by synthesizing existing studies.

在将乳腺癌分为恶性和良性，并进一步将其分类为分子亚型方面的创新，重塑了医疗保健服务，使其能够准确诊断复杂的疾病。乳腺癌分子亚型的鉴定是最重要的治疗困难之一，因为这些亚型对预后和治疗方法有巨大的影响。来自转录组学、成像和基因组等各种模式的数据集成，对于利用新的机会提高分类准确性和改善个性化治疗计划至关重要。通过应用深度学习算法对这些异构数据源进行检查，这为传统方法经常忽略的复杂模式提供了进一步的见解。在本文中，我们探讨了研究人员用于研究乳腺癌的各种模式以及用于融合模式的有趣融合技术。我们还回顾了最新的模型（传统、机器学习和深度学习），强调了它们对传统分类和乳腺癌分子亚型分类的改进。此外，本综述的重点是研究处理乳腺组织幻灯片的整个图像的技术，这是具有挑战性的，特别是由于它的大小。我们探索了多实例学习任务的最新进展，以及在将WSI幻灯片用于癌症分类之前，使用基于注意力的转换器和类似架构对其进行注释。我们还讨论了可解释性工具-注意图，显著性图和模型可解释性在变压器的背景下。简而言之，我们的目标是深入了解深度学习模型在精确肿瘤学中的革命性能力，并通过结合现有研究指导这一关键领域的未来研究路径。

{"title":"Toward accurate breast cancer classification: A review of multi-modal machine learning approaches","authors":"Archana Mathur , Abbas Mufaddal Dudhiyawala , Sudeepa Roy Dey , Snehanshu Saha","doi":"10.1016/j.ymeth.2025.10.011","DOIUrl":"10.1016/j.ymeth.2025.10.011","url":null,"abstract":"<div><div>The innovations in classifying breast cancer into malignant and benign categories and further categorizing it into molecular subtypes have reshaped healthcare services, enabling accurate diagnosis of these complex conditions. Identification of molecular subtypes of breast cancer is one of the most important treatment challenges, as these subtypes can have an enormous effect on the prognosis and treatment approaches. Data integration from various modalities, such as transcriptomics, imaging, and genomics, has been crucial in leveraging new opportunities to increase classification accuracy and improve individualized treatment plans. These heterogeneous data sources are examined by applying deep learning algorithms, which provide further insights into the complex patterns that traditional approaches often overlook. In this paper, we explore the various modalities researchers use to investigate breast cancer and the intriguing fusion techniques employed to combine these modalities. We also review the most recent models (traditional, machine learning, and deep learning), emphasizing their improvements over traditional classification methods and the molecular subtype categorization of breast cancer. Furthermore, the emphasis of this review is to examine techniques to process the entire image of the breast tissue slide, which is challenging, particularly due to its size. We explore recent advances in multiple instance learning tasks and the use of attention-based transformers and similar architectures for annotating the WSI slides before using them for cancer classification. We additionally discuss the interpretability tools—attention maps, saliency maps and model explainability— in the context of transformers. In a nutshell, we aim to provide an in-depth look at the revolutionary capabilities of deep learning models in precision oncology and guide future research paths in this crucial field by synthesizing existing studies.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"246 ","pages":"Pages 48-61"},"PeriodicalIF":4.3,"publicationDate":"2025-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145562223","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

Unravelling cell heterogeneity and gene regulation mechanisms in multiple myeloma through single-cell RNA-seq 通过单细胞RNA-seq揭示多发性骨髓瘤细胞异质性和基因调控机制

IF 4.3 3区生物学 Q1 BIOCHEMICAL RESEARCH METHODS

Methods

Pub Date : 2025-11-16 DOI: 10.1016/j.ymeth.2025.11.006

Jing Jiang , Junlin Xu , Peng Wang , Yuansheng Liu , Yiping Liu

Multiple myeloma (MM) is the second most common blood cancer in the world, yet its genetic pathology is not fully understood and MM cells have highly heterogeneous regulatory mechanisms. Single-cell RNA-Sequencing (scRNA-Seq) technologies provide an unprecedented opportunity to investigate cell heterogeneity and understand regulatory mechanisms at the single-cell level. Four MM scRNA-Seq datasets were retrieved from the public domain containing 597, 172, 477, and 51,840 cells, respectively. First, they were integrated and jointly analyzed to accurately identify 24 MM cell clusters, using a normal hematopoiesis cells atlas as a control. Then we predicted 651 regulons within the 24 MM cell clusters. The identified regulons can substantially improve the elucidation of heterogeneous gene regulation mechanisms across various cell clusters, and hence can serve as a reference for diagnosis in MM.

多发性骨髓瘤（MM）是世界上第二常见的血癌，但其遗传病理尚不完全清楚，MM细胞具有高度异质性的调节机制。单细胞rna测序（scRNA-Seq）技术为研究细胞异质性和了解单细胞水平的调控机制提供了前所未有的机会。从公共领域检索到4个MM scRNA-Seq数据集，分别包含597、172、477和51840个细胞。首先，将它们整合并联合分析，以准确识别24个MM细胞簇，使用正常造血细胞图谱作为对照。然后我们预测了24个MM细胞簇中的651个调控子。这些确定的调控可以大大提高对不同细胞簇间异质基因调控机制的阐明，因此可以作为MM诊断的参考。

引用次数: 0

Natural language processing 自然语言处理

IF 4.3 3区生物学 Q1 BIOCHEMICAL RESEARCH METHODS

Methods

Pub Date : 2025-11-12 DOI: 10.1016/j.ymeth.2025.11.004

Nguyen Quoc Khanh Le , Matthew Chin Heng Chua

引用次数: 0

Scale-adjusted distance transform and its applications to segmentation of multimodal images 尺度调整距离变换及其在多模态图像分割中的应用。

IF 4.3 3区生物学 Q1 BIOCHEMICAL RESEARCH METHODS

Methods

Pub Date : 2025-11-07 DOI: 10.1016/j.ymeth.2025.11.003

Nirmal Das , Subhadip Basu , Punam K. Saha

Distance transform (DT) is widely used for structural analysis of multi-dimensional (mainly 2-D and 3-D) objects. Association of DT values with local structure scale, often, adds challenges and limits the scope of applications of DT in relative structural analysis among multiple objects with varying scales. In this paper, we introduce a new notion of scale-adjusted distance transform (SADT), conceptually different from traditional DT, which is independent of object scale and offers DT values of scale varying objects on a uniform scale with the value of ‘1’ at ridges. It has been shown that scale-adjusted distance is a metric function in a continuous Euclidean space, and SADT generates a normalized field that is invariant under translation, rotation, and isotropic scaling. The computational method for digital objects traces gradient flow paths on a conventional DT field and uses the change in velocity along a digital path to detect local ridges, which are then used to generate a scale-adjusted density (SAD) field. Finally, SADT is computed using the SAD value. The results of applying the method on 2-D and 3-D multimodal image datasets are presented. Two real-life applications of SADT are shown: 1) segmentation of conjoined nuclei from 2-D microscopic images, and 2) multi-scale separation of conjoined artery–vein in 3-D pulmonary CT image of a pig lung phantom. SADT outperforms the traditional marker-controlled watershed algorithm in conjoined nuclei segmentation from 2-D images and achieves highly accurate multi-scale artery–vein separation in the pig lung phantom experiment. The performance of SADT is invariant to image dimension and imaging modality. Unlike modern deep learning methods, the proposed fuzzy method is transparent and data modality independent. The source code and sample data are freely available at: https://github.com/CMATERJU-BIOINFO/Scale-Adjusted-Distance-Transform.

距离变换（DT）广泛应用于多维（主要是二维和三维）物体的结构分析。将DT值与局部结构尺度相关联，往往会给DT在不同尺度的多物体相对结构分析中的应用范围带来挑战和限制。在本文中，我们引入了一种新的概念，即尺度调整距离变换（SADT），它与传统的DT在概念上有所不同，它不依赖于物体的尺度，并提供了在脊上以1为值的均匀尺度上变化尺度的物体的DT值。尺度调整距离是连续欧几里得空间中的度量函数，SADT生成的归一化域在平移、旋转和各向同性尺度下都是不变的。数字物体的计算方法在传统的DT场上跟踪梯度流动路径，并利用沿数字路径的速度变化来检测局部脊，然后使用这些脊来生成缩放密度（SAD）场。最后，使用SAD值计算SADT。给出了该方法在二维和三维多模态图像数据集上的应用结果。本文给出了SADT在现实生活中的两个应用：1)从二维显微图像中分割连体核；2)在猪肺幻象的三维肺CT图像中多尺度分离连体动静脉。SADT算法在二维图像的连核分割中优于传统的标记控制分水岭算法，在猪肺幻象实验中实现了高精度的多尺度动静脉分离。SADT的性能不受图像维数和成像模态的影响。与现代深度学习方法不同，本文提出的模糊方法具有透明性和数据模态无关性。源代码和示例数据可在https://github.com/CMATERJU-BIOINFO/Scale-Adjusted-Distance-Transform免费获得。

{"title":"Scale-adjusted distance transform and its applications to segmentation of multimodal images","authors":"Nirmal Das , Subhadip Basu , Punam K. Saha","doi":"10.1016/j.ymeth.2025.11.003","DOIUrl":"10.1016/j.ymeth.2025.11.003","url":null,"abstract":"<div><div>Distance transform (DT) is widely used for structural analysis of multi-dimensional (mainly 2-D and 3-D) objects. Association of DT values with local structure scale, often, adds challenges and limits the scope of applications of DT in relative structural analysis among multiple objects with varying scales. In this paper, we introduce a new notion of scale-adjusted distance transform (SADT), conceptually different from traditional DT, which is independent of object scale and offers DT values of scale varying objects on a uniform scale with the value of ‘1’ at ridges. It has been shown that scale-adjusted distance is a metric function in a continuous Euclidean space, and SADT generates a normalized field that is invariant under translation, rotation, and isotropic scaling. The computational method for digital objects traces gradient flow paths on a conventional DT field and uses the change in velocity along a digital path to detect local ridges, which are then used to generate a scale-adjusted density (SAD) field. Finally, SADT is computed using the SAD value. The results of applying the method on 2-D and 3-D multimodal image datasets are presented. Two real-life applications of SADT are shown: 1) segmentation of conjoined nuclei from 2-D microscopic images, and 2) multi-scale separation of conjoined artery–vein in 3-D pulmonary CT image of a pig lung phantom. SADT outperforms the traditional marker-controlled watershed algorithm in conjoined nuclei segmentation from 2-D images and achieves highly accurate multi-scale artery–vein separation in the pig lung phantom experiment. The performance of SADT is invariant to image dimension and imaging modality. Unlike modern deep learning methods, the proposed fuzzy method is transparent and data modality independent. The source code and sample data are freely available at: <span><span>https://github.com/CMATERJU-BIOINFO/Scale-Adjusted-Distance-Transform</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"245 ","pages":"Pages 55-68"},"PeriodicalIF":4.3,"publicationDate":"2025-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145480462","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

Disease-related omics data analysis 疾病相关组学数据分析。

IF 4.3 3区生物学 Q1 BIOCHEMICAL RESEARCH METHODS

Methods

Pub Date : 2025-11-03 DOI: 10.1016/j.ymeth.2025.11.001

Wei Peng , Zhipeng Cai

引用次数: 0

Carboxyl-PEG modified Fe3O4 nanoparticles as an ultrasensitive SERS substrate for multiplex detection of exogenous hormones related to endometrial cancer 羧基聚乙二醇修饰的Fe3O4纳米颗粒作为超灵敏SERS底物用于子宫内膜癌相关外源激素的多重检测。

IF 4.3 3区生物学 Q1 BIOCHEMICAL RESEARCH METHODS

Methods

Pub Date : 2025-11-03 DOI: 10.1016/j.ymeth.2025.11.002

Biqing Chen, Jiayin Gao, Haizhu Sun, Yinghan Zhao, Yan Liu, Xiaohong Qiu

Traditional surface-enhanced Raman scattering (SERS) technology often struggles to achieve high-precision discrimination in the simultaneous detection of multiple exogenous hormones due to complex spectral overlap and matrix interference, limiting its application in trace analyte analysis within complex matrices (e.g., biological samples). This study developed a SERS substrate based on carboxyl-terminal polyethylene glycol (PEG)-modified iron oxide (Fe₃O₄) nanoparticles (Fe₃O₄@PEG), integrated with artificial intelligence (AI)-driven high-throughput spectral analysis algorithms. This approach successfully enabled ultrasensitive detection and precise discrimination of multiple typical exogenous hormonal drugs, including tamoxifen, drospirenone, cyproterone acetate, medroxyprogesterone acetate, estradiol ester derivatives, and dydrogesterone. By optimizing the surface enhancement effect of Fe₃O₄@PEG nanocomposites and employing machine learning models (e.g., convolutional neural networks, CNN) for collaborative analysis, the weak Raman fingerprint features of target hormones in complex mixtures were effectively extracted and classified, achieving a detection limit at the corresponding to 10⁻⁷–10⁻⁸ mg/mL level. In matrix-spiked serum and urine samples, which mimic complex biological matrices validations, the AI-SERS platform demonstrated exceptional performance in the identification and quantitative analysis of target exogenous hormones. This research provides an intelligent analytical strategy for rapid and highly sensitive detection of multiple trace exogenous hormones in complex matrices.

传统的表面增强拉曼散射（SERS）技术在同时检测多种外源激素时，由于复杂的光谱重叠和基质干扰，往往难以实现高精度的区分，限制了其在复杂基质（如生物样品）内痕量分析物分析中的应用。本研究开发了一种基于羧基末端聚乙二醇（PEG）修饰的氧化铁（Fe3O4）纳米颗粒（Fe3O4@PEG）的SERS底物，并集成了人工智能（AI）驱动的高通量光谱分析算法。该方法成功实现了他莫昔芬、屈螺酮、醋酸环丙孕酮、醋酸甲羟孕酮、雌二醇酯衍生物、地屈孕酮等多种典型外源性激素药物的超灵敏检测和精确鉴别。通过优化Fe3O4@PEG纳米复合材料的表面增强效果，利用卷积神经网络（CNN）等机器学习模型协同分析，有效提取并分类了复杂混合物中目标激素的弱拉曼指纹特征，达到了对应于10-7-10-8 mg/mL水平的检出限。在模拟复杂生物基质验证的基质加标血清和尿液样本中，AI-SERS平台在目标外源激素的鉴定和定量分析中表现出卓越的性能。本研究为复杂基质中多种微量外源激素的快速、高灵敏度检测提供了一种智能分析策略。

{"title":"Carboxyl-PEG modified Fe3O4 nanoparticles as an ultrasensitive SERS substrate for multiplex detection of exogenous hormones related to endometrial cancer","authors":"Biqing Chen, Jiayin Gao, Haizhu Sun, Yinghan Zhao, Yan Liu, Xiaohong Qiu","doi":"10.1016/j.ymeth.2025.11.002","DOIUrl":"10.1016/j.ymeth.2025.11.002","url":null,"abstract":"<div><div>Traditional surface-enhanced Raman scattering (SERS) technology often struggles to achieve high-precision discrimination in the simultaneous detection of multiple exogenous hormones due to complex spectral overlap and matrix interference, limiting its application in trace analyte analysis within complex matrices (e.g., biological samples). This study developed a SERS substrate based on carboxyl-terminal polyethylene glycol (PEG)-modified iron oxide (Fe<sub>3</sub>O<sub>4</sub>) nanoparticles (Fe<sub>3</sub>O<sub>4</sub>@PEG), integrated with artificial intelligence (AI)-driven high-throughput spectral analysis algorithms. This approach successfully enabled ultrasensitive detection and precise discrimination of multiple typical exogenous hormonal drugs, including tamoxifen, drospirenone, cyproterone acetate, medroxyprogesterone acetate, estradiol ester derivatives, and dydrogesterone. By optimizing the surface enhancement effect of Fe<sub>3</sub>O<sub>4</sub>@PEG nanocomposites and employing machine learning models (e.g., convolutional neural networks, CNN) for collaborative analysis, the weak Raman fingerprint features of target hormones in complex mixtures were effectively extracted and classified, achieving a detection limit at the corresponding to 10<sup>−7</sup>–10<sup>−8</sup> mg/mL level. In matrix-spiked serum and urine samples, which mimic complex biological matrices validations, the AI-SERS platform demonstrated exceptional performance in the identification and quantitative analysis of target exogenous hormones. This research provides an intelligent analytical strategy for rapid and highly sensitive detection of multiple trace exogenous hormones in complex matrices.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"245 ","pages":"Pages 35-52"},"PeriodicalIF":4.3,"publicationDate":"2025-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145450534","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