Methods最新文献_第4页

Advances in machine learning for epigenetics and biomedical applications 表观遗传学和生物医学应用的机器学习进展。

IF 4.2 3区生物学 Q1 BIOCHEMICAL RESEARCH METHODS

Methods

Pub Date : 2025-02-01 DOI: 10.1016/j.ymeth.2025.01.018

Hao Lin, Hao Lv, Fuying Dao

引用次数: 0

Low friction hydrogel with diclofenac eluting ability for dry eye therapeutic contact lenses 具有双氯芬酸洗脱能力的低摩擦水凝胶用于干眼治疗性隐形眼镜。

IF 4.2 3区生物学 Q1 BIOCHEMICAL RESEARCH METHODS

Methods

Pub Date : 2025-02-01 DOI: 10.1016/j.ymeth.2024.11.015

Diana C. Silva , Margarida Oliveira , Carolina Marto-Costa , João Teixeira , Madalena Salema Oom , Carlos A. Pinto , Jorge A. Saraiva , Ana Clara Marques , Laurence Fitzhenry , Ana Paula Serro

When placed in the eye, contact lenses (CLs) disturb the tear fluid and affect the natural tribological behaviour of the eye. The disruption in the contact mechanics between the ocular tissues can increase frictional shear stress and ocular dryness, causing discomfort. Ultimately, continuous CLs wear can trigger inflammation which is particularly critical for people suffering from dry eye. In this work, a double strategy was followed to obtain therapeutic daily disposable CLs for dry eye: a hydroxyethyl methacrylate (HEMA) based hydrogel was coated with two natural polysaccharides, chitosan (CHI) and hyaluronic acid (HA) and posteriorly loaded with an anti-inflammatory drug (diclofenac, DCF). Material sterilisation was carried out by high hydrostatic pressure (HHP) combined with moderate temperature. The friction coefficient (μ) was determined in the presence of different tear biomolecules (cholesterol, lysozyme and albumin) using a nanotribometer. Drug release experiments were performed in static and in hydrodynamic conditions. The material was extensively characterised, regarding surface morphology/topography, optical properties, water content and swelling behaviour, wettability, ionic and oxygen permeability and mechanical properties. It was found that the coating did not impair the physico-chemical properties relevant for the material’s application in CLs. Besides, it also ensured a sustained release of DCF for 24 h in tests performed in hydrodynamic conditions that simulate those found in the eye, increasing significantly the amount of drug released. It reduced friction, improving the lubrication ability of the hydrogel, and presented antibacterial properties against S. aureus, P. aeruginosa and B. Cereus. The coated samples did not reveal any signs of cytotoxicity or potential eye irritation. Overall, the coating of the hydrogel may be useful to produce daily CLs able to alleviate dry eye symptoms and the discomfort of CLs wearers.

当戴在眼睛里时，隐形眼镜会干扰泪液，影响眼睛的自然摩擦学行为。眼组织间接触力学的破坏会增加摩擦剪切应力和眼干涩，引起不适。最终，持续佩戴CLs会引发炎症，这对患有干眼症的人来说尤其重要。在这项工作中，采用双重策略获得用于干眼症的每日一次性CLs：甲基丙烯酸羟乙酯（HEMA）为基础的水凝胶包被两种天然多糖，壳聚糖（CHI）和透明质酸（HA），后负载抗炎药（双氯芬酸，DCF）。物料灭菌采用高静水压力（HHP）结合中等温度进行。采用纳米摩擦计测定了不同撕裂生物分子（胆固醇、溶菌酶和白蛋白）存在时的摩擦系数（μ）。在静、水动力两种条件下进行药物释放实验。对材料进行了广泛的表征，包括表面形貌/形貌、光学性能、含水量和膨胀行为、润湿性、离子和氧渗透性以及机械性能。结果表明，该涂层不影响材料在CLs中的应用所需的理化性能。此外，它还确保在模拟眼睛中发现的流体动力学条件下进行的测试中DCF持续释放24 h，从而显着增加药物释放量。它减少了摩擦，提高了水凝胶的润滑能力，并表现出对金黄色葡萄球菌、铜绿假单胞菌和蜡状芽孢杆菌的抗菌性能。涂层样品没有显示任何细胞毒性或潜在的眼睛刺激的迹象。总的来说，水凝胶的涂层可能有助于产生能够减轻干眼症状和CLs佩戴者不适的日常CLs。

{"title":"Low friction hydrogel with diclofenac eluting ability for dry eye therapeutic contact lenses","authors":"Diana C. Silva , Margarida Oliveira , Carolina Marto-Costa , João Teixeira , Madalena Salema Oom , Carlos A. Pinto , Jorge A. Saraiva , Ana Clara Marques , Laurence Fitzhenry , Ana Paula Serro","doi":"10.1016/j.ymeth.2024.11.015","DOIUrl":"10.1016/j.ymeth.2024.11.015","url":null,"abstract":"<div><div>When placed in the eye, contact lenses (CLs) disturb the tear fluid and affect the natural tribological behaviour of the eye. The disruption in the contact mechanics between the ocular tissues can increase frictional shear stress and ocular dryness, causing discomfort. Ultimately, continuous CLs wear can trigger inflammation which is particularly critical for people suffering from dry eye. In this work, a double strategy was followed to obtain therapeutic daily disposable CLs for dry eye: a hydroxyethyl methacrylate (HEMA) based hydrogel was coated with two natural polysaccharides, chitosan (CHI) and hyaluronic acid (HA) and posteriorly loaded with an anti-inflammatory drug (diclofenac, DCF). Material sterilisation was carried out by high hydrostatic pressure (HHP) combined with moderate temperature. The friction coefficient (μ) was determined in the presence of different tear biomolecules (cholesterol, lysozyme and albumin) using a nanotribometer. Drug release experiments were performed in static and in hydrodynamic conditions. The material was extensively characterised, regarding surface morphology/topography, optical properties, water content and swelling behaviour, wettability, ionic and oxygen permeability and mechanical properties. It was found that the coating did not impair the physico-chemical properties relevant for the material’s application in CLs. Besides, it also ensured a sustained release of DCF for 24 h in tests performed in hydrodynamic conditions that simulate those found in the eye, increasing significantly the amount of drug released. It reduced friction, improving the lubrication ability of the hydrogel, and presented antibacterial properties against <em>S. aureus</em>, <em>P. aeruginosa</em> and <em>B. Cereus</em>. The coated samples did not reveal any signs of cytotoxicity or potential eye irritation. Overall, the coating of the hydrogel may be useful to produce daily CLs able to alleviate dry eye symptoms and the discomfort of CLs wearers.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"234 ","pages":"Pages 67-84"},"PeriodicalIF":4.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142765111","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

A roadmap to cysteine specific labeling of membrane proteins for single-molecule photobleaching studies 用于单分子光漂白研究的膜蛋白半胱氨酸特异性标记路线图。

IF 4.2 3区生物学 Q1 BIOCHEMICAL RESEARCH METHODS

Methods

Pub Date : 2025-02-01 DOI: 10.1016/j.ymeth.2024.10.013

Melanie Ernst, Robyn Mahoney-Kruszka, Nathan B. Zelt, Janice L. Robertson

Single-molecule photobleaching analysis is a useful approach for quantifying reactive membrane protein oligomerization in membranes. It provides a binary readout of a fluorophore attached to a protein subunit at dilute conditions. However, quantification of protein stoichiometry from this data requires information about the subunit labeling yields and whether there is non-specific background labeling. Any increases in subunit-specific labeling improves the ability to determine oligomeric states with confidence. A common strategy for site-specific labeling is by conjugation of a fluorophore bearing a thiol-reactive maleimide group to a substituted cysteine. Yet, cysteine reactivity can be difficult to predict as it depends on many factors such as solvent accessibility and electrostatics from the surrounding protein structure. Here we report a general methodology for screening potential cysteine labeling sites on purified membrane proteins. We present the results of two example systems for which the dimerization reactions in membranes have been characterized: (1) the CLC-ec1 Cl^-/H⁺ antiporter, an Escherichia coli homologue of voltage-gated chloride ion channels in humans and (2) a mutant form of a member of the family of fluoride channels Fluc from Bordetella pertussis (Fluc-Bpe-N43S). To demonstrate how we identify such sites, we first discuss considerations of residue positions hypothesized to be suitable and then describe the specific steps to rigorously assess site-specific labeling while maintaining functional activity and robust single-molecule fluorescence signals. We find that our initial, well rationalized choices are not strong predictors of success, as rigorous testing of the labeling sites shows that only ≈ 30 % of sites end up being useful for single-molecule photobleaching studies.

单分子光漂白分析是量化膜中反应性膜蛋白寡聚的有效方法。它提供了稀释条件下蛋白质亚基上荧光团的二进制读数。不过，从该数据中量化蛋白质的化学计量需要亚基标记产量以及是否存在非特异性背景标记的信息。亚基特异性标记的任何增加都能提高确定低聚物状态的可信度。位点特异性标记的常见策略是将带有硫醇反应性马来酰亚胺基团的荧光团与取代的半胱氨酸共轭。然而，半胱氨酸的反应性很难预测，因为它取决于许多因素，如周围蛋白质结构的溶剂可及性和静电。在此，我们报告了筛选纯化膜蛋白上潜在半胱氨酸标记位点的一般方法。我们介绍了两个已对膜中二聚化反应进行表征的示例系统的结果：(1) CLC-ec1 Cl-/H+ 反载体，它是人类电压门控氯离子通道的大肠杆菌同源物；(2) 百日咳杆菌氟化物通道家族成员 Fluc 的突变体形式（Fluc-Bpe-N43S）。为了展示我们是如何识别这些位点的，我们首先讨论了假设合适的残基位置的考虑因素，并描述了在保持功能活性和稳健的单分子荧光信号的同时严格评估位点特异性标记的具体步骤。我们发现，我们最初的合理选择并不是成功的有力预测因素，因为对标记位点的严格测试表明，只有≈30%的位点最终可用于单分子光漂白研究。

{"title":"A roadmap to cysteine specific labeling of membrane proteins for single-molecule photobleaching studies","authors":"Melanie Ernst, Robyn Mahoney-Kruszka, Nathan B. Zelt, Janice L. Robertson","doi":"10.1016/j.ymeth.2024.10.013","DOIUrl":"10.1016/j.ymeth.2024.10.013","url":null,"abstract":"<div><div>Single-molecule photobleaching analysis is a useful approach for quantifying reactive membrane protein oligomerization in membranes. It provides a binary readout of a fluorophore attached to a protein subunit at dilute conditions. However, quantification of protein stoichiometry from this data requires information about the subunit labeling yields and whether there is non-specific background labeling. Any increases in subunit-specific labeling improves the ability to determine oligomeric states with confidence. A common strategy for site-specific labeling is by conjugation of a fluorophore bearing a thiol-reactive maleimide group to a substituted cysteine. Yet, cysteine reactivity can be difficult to predict as it depends on many factors such as solvent accessibility and electrostatics from the surrounding protein structure. Here we report a general methodology for screening potential cysteine labeling sites on purified membrane proteins. We present the results of two example systems for which the dimerization reactions in membranes have been characterized: (1) the CLC-ec1 Cl<sup>-</sup>/H<sup>+</sup> antiporter, an <em>Escherichia coli</em> homologue of voltage-gated chloride ion channels in humans and (2) a mutant form of a member of the family of fluoride channels Fluc from <em>Bordetella pertussis</em> (Fluc-Bpe-N43S). To demonstrate how we identify such sites, we first discuss considerations of residue positions hypothesized to be suitable and then describe the specific steps to rigorously assess site-specific labeling while maintaining functional activity and robust single-molecule fluorescence signals. We find that our initial, well rationalized choices are not strong predictors of success, as rigorous testing of the labeling sites shows that only ≈ 30 % of sites end up being useful for single-molecule photobleaching studies.</div></div>","PeriodicalId":390,"journal":{"name":"Methods","volume":"234 ","pages":"Pages 21-35"},"PeriodicalIF":4.2,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142714807","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

Design and characterization of hollow microneedles for localized intrascleral drug delivery of ocular formulations 眼制剂局部巩膜内给药中空微针的设计与表征。

IF 4.2 3区生物学 Q1 BIOCHEMICAL RESEARCH METHODS

Methods

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

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

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.

由于玻璃体内注射等传统方法的局限性，有效地将药物输送到眼后段仍然是一个挑战，这与显著的副作用有关。本研究探讨了将空心微针（HMNs）作为一种微创替代方法用于局部巩膜内给药。采用线束电火花加工技术制备了不锈钢HMNs，其斜角分别为30°、45°、60°和75°。利用纹理分析仪评估这些HMNs在离体猪巩膜中的穿透力，发现60°斜角所需的力最小(

{"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 Q1 BIOCHEMICAL RESEARCH METHODS

Methods

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

Shaherin Basith , Balachandran Manavalan , Gwang Lee

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 (https://balalab-skku.org/AntiT2DMP-Pred) 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.

胰腺α-淀粉酶将淀粉分解成异麦芽糖和麦芽糖，在肠道内α-葡萄糖苷酶进一步水解成单糖，迅速升高血糖水平，导致2型糖尿病（T2DM）。碳水化合物消化酶的合成抑制剂用于控制2型糖尿病，但随着时间的推移可能会损害器官功能。生物活性肽提供了一个更安全的选择，避免了这样的副作用。预测抗糖尿病肽（ADPs）的计算方法可以显著减少实验测试的时间和成本。虽然机器学习（ML）已被应用于识别adp，但数据分析和算法的进步继续推动该领域的进步。为了解决这个问题，我们开发了AntiT2DMP-Pred，这是第一个专门用于预测2型抗糖尿病肽（T2ADPs）的基于ml的工具。该工具采用特征融合策略，结合从32个描述符和8个ML算法中选择的10个高度判别性的特征描述符，并在一系列基线模型中进行了测试。AntiT2DMP-Pred表现出优异的性能，超过了基线模型和特征优化模型，在训练数据集上的准确率（ACC）和马修斯相关系数（MCC）分别为0.976和0.953，在独立数据集上的ACC和MCC分别为0.957和0.851。web服务器（https://balalab-skku.org/AntiT2DMP-Pred）是免费访问的，使世界各地的研究人员能够在他们的实验工作流程中使用它，并有助于发现和了解t2adp，最终支持基于肽的糖尿病治疗开发。

{"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 Q1 BIOCHEMICAL RESEARCH METHODS

Methods

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

Phasit Charoenkwan , Pramote Chumnanpuen , Nalini Schaduangrat , Watshara Shoombuatong

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 in silico 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 https://pmlabqsar.pythonanywhere.com/Deepstack-ACE. We anticipate that our proposed Deepstack-ACE model can provide a faster and reasonably accurate identification of ACE inhibitory peptides.

准确鉴定血管紧张素- i转换酶（ACE）抑制肽对于理解肾素-血管紧张素系统的主要调控因子以及为开发新的潜在药物提供指导至关重要。鉴于固有的实验复杂性，使用计算方法进行硅肽鉴定对于促进ACE抑制肽的高通量表征是必不可少的。在本文中，我们提出了一种新的基于深度堆叠的集成学习框架，称为Deepstack-ACE，以精确识别ACE抑制肽。在Deepstack-ACE中，输入的肽序列被输入到word2vec嵌入技术中生成序列表示。然后，利用这些表征训练长短期记忆、卷积神经网络、多层感知器、门控递归单元网络和递归神经网络五种强大的深度学习方法，构建基分类器。最后，根据所选基分类器的最佳组合，构建优化后的叠加模型。基准实验表明，与基础分类器和几种传统机器学习分类器相比，Deepstack-ACE对ACE抑制肽的识别更加准确和稳健。值得注意的是，在独立检验中，我们提出的模型显著优于目前最先进的方法，平衡精度为0.916，灵敏度为0.911，马修斯相关系数得分为0.826。此外，我们为Deepstack-ACE开发了一个用户友好的web服务器，可以在https://pmlabqsar.pythonanywhere.com/Deepstack-ACE上免费获得。我们期望我们提出的Deepstack-ACE模型能够提供更快、更合理准确的ACE抑制肽鉴定。

{"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 Q1 BIOCHEMICAL RESEARCH METHODS

Methods

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

Junfang Li , Yifei Zhang , Qiu Yang , Yi Qu

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.

在多种肿瘤中，EZH2表达与免疫治疗耐药显著相关。EZH2对葡萄膜黑色素瘤（UM）免疫检查点阻断（ICB）有效性的预测价值的综合分析仍不清楚。我们分析了来自癌症基因组图谱（TCGA）数据库的UM数据，确定了888个与EZH2表达相关的差异表达基因（DEGs），然后进行了基因本体（GO）和京都基因与基因组百科全书（KEGG）途径分析，以阐明EZH2在UM检测中的生物学特征。探讨EZH2表达与肿瘤免疫相关因素如免疫相关通路、各种免疫细胞浸润、免疫评分、免疫检查点等的相关性。通过结合肿瘤免疫功能障碍和排斥（TIDE）评分来评估EZH2预测UM免疫治疗结果的能力。最后，通过免疫组化分析在独立的UM患者队列中检测程序性死亡配体1 （PD-L1）的表达，并评估EZH2与PD-L1的相关性。结果提示EZH2表达与免疫相关通路、各种免疫细胞浸润、免疫评分、免疫检查点表达及免疫治疗敏感性相关。综上所述，我们认为EZH2可能被认为是ICBs对UM患者治疗效果的预测因子，也是联合免疫治疗的潜在靶点。

{"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 Q1 BIOCHEMICAL RESEARCH METHODS

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

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.

细胞周期蛋白是一组通过调节细胞分裂的各个阶段来调节细胞周期过程的蛋白质，以确保正确的细胞增殖、分化和凋亡。细胞周期蛋白的研究对于理解细胞的生物学功能和病理状态至关重要。然而，目前基于机器学习的周期蛋白识别研究只注重准确性，忽略了特征的可解释性。因此，在本研究中，我们将更多地关注与细胞周期蛋白相关的关键特征的解释和分析。首先，我们开发了一个基于支持向量机的模型来识别周期蛋白，准确率为92.8%。然后，我们分析了模型构建中使用的14个关键特征的物理化学性质，并确定了区分细胞周期蛋白和非细胞周期蛋白的关键特征G和带电C1。此外，我们通过留一交叉验证，仅使用这两个特征构建了基于svm的模型，准确率为81.3%。我们的研究表明，周期蛋白与非周期蛋白在物理化学性质上有所不同，仅使用两个特征就可以获得良好的预测精度。

{"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 Q1 BIOCHEMICAL RESEARCH METHODS

Methods

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

Xuesheng Bian , Shuting Chen , Weiquan Liu

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.

{"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 Q1 BIOCHEMICAL RESEARCH METHODS

Methods

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

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

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.

{"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