MethodsX最新文献_第2页

Exploring the efficacy of various CNN architectures in diagnosing oral cancer from squamous cell carcinoma 探索各种 CNN 架构在从鳞状细胞癌诊断口腔癌方面的功效

IF 1.6 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX

Pub Date : 2024-11-05 DOI: 10.1016/j.mex.2024.103034

Prerna Kulkarni , Nidhi Sarwe , Abhishek Pingale , Yash Sarolkar , Rutuja Rajendra Patil , Gitanjali Shinde , Gagandeep Kaur

Oral cancer can result from mutations in cells located in the lips or mouth. Diagnosing oral cavity squamous cell carcinoma (OCSCC) is particularly challenging, often occurring at advanced stages. To address this, computer-aided diagnosis methods are increasingly being used. In this work, a deep learning-based approach utilizing models such as VGG16, ResNet50, LeNet-5, MobileNetV2, and Inception V3 is presented. NEOR and OCSCC datasets were used for feature extraction, with virtual slide images divided into tiles and classified as normal or squamous cell cancer. Performance metrics like accuracy, F1-score, AUC, precision, and recall were analyzed to determine the prerequisites for optimal CNN performance. The proposed CNN approaches were effective for classifying OCSCC and oral dysplasia, with the highest accuracy of 95.41 % achieved using MobileNetV2.

Key findings

Deep learning models, particularly MobileNetV2, achieved high classification accuracy (95.41 %) for OCSCC.

CNN-based methods show promise for early-stage OCSCC and oral dysplasia diagnosis. Performance parameters like precision, recall, and F1-score help optimize CNN model selection for this task.

口腔癌可能是位于嘴唇或口腔内的细胞发生突变所致。口腔鳞状细胞癌（OCSCC）的诊断尤其具有挑战性，通常发生在晚期阶段。为解决这一问题，计算机辅助诊断方法正得到越来越多的应用。在这项工作中，介绍了一种利用 VGG16、ResNet50、LeNet-5、MobileNetV2 和 Inception V3 等模型的基于深度学习的方法。该方法使用 NEOR 和 OCSCC 数据集进行特征提取，将虚拟幻灯片图像划分为瓦片，并将其分类为正常或鳞状细胞癌。分析了准确率、F1-分数、AUC、精确度和召回率等性能指标，以确定实现最佳 CNN 性能的先决条件。主要发现深度学习模型，尤其是 MobileNetV2，对 OCSCC 实现了很高的分类准确率（95.41%）。精确度、召回率和 F1 分数等性能参数有助于优化该任务的 CNN 模型选择。

{"title":"Exploring the efficacy of various CNN architectures in diagnosing oral cancer from squamous cell carcinoma","authors":"Prerna Kulkarni , Nidhi Sarwe , Abhishek Pingale , Yash Sarolkar , Rutuja Rajendra Patil , Gitanjali Shinde , Gagandeep Kaur","doi":"10.1016/j.mex.2024.103034","DOIUrl":"10.1016/j.mex.2024.103034","url":null,"abstract":"<div><div>Oral cancer can result from mutations in cells located in the lips or mouth. Diagnosing oral cavity squamous cell carcinoma (OCSCC) is particularly challenging, often occurring at advanced stages. To address this, computer-aided diagnosis methods are increasingly being used. In this work, a deep learning-based approach utilizing models such as VGG16, ResNet50, LeNet-5, MobileNetV2, and Inception V3 is presented. NEOR and OCSCC datasets were used for feature extraction, with virtual slide images divided into tiles and classified as normal or squamous cell cancer. Performance metrics like accuracy, F1-score, AUC, precision, and recall were analyzed to determine the prerequisites for optimal CNN performance. The proposed CNN approaches were effective for classifying OCSCC and oral dysplasia, with the highest accuracy of 95.41 % achieved using MobileNetV2.</div></div><div><h3>Key findings</h3><div>Deep learning models, particularly MobileNetV2, achieved high classification accuracy (95.41 %) for OCSCC.</div><div>CNN-based methods show promise for early-stage OCSCC and oral dysplasia diagnosis. Performance parameters like precision, recall, and F1-score help optimize CNN model selection for this task.</div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"13 ","pages":"Article 103034"},"PeriodicalIF":1.6,"publicationDate":"2024-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142655311","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Development of rapid, efficient and cost effective screening technique for testing arecanut against Phytophthora meadii incitant of fruit rot disease 开发快速、高效和成本效益高的筛选技术，用于检测油甘花生对引起果实腐烂病的蚧壳虫的抗性

IF 1.6 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX

Pub Date : 2024-11-04 DOI: 10.1016/j.mex.2024.103032

V. H. Prathibha , N. R. Nagaraja , M. K. Rajesh , Daliyamol , K. P. Thejasri , Rajkumar , Vinayaka Hegde , Uchoi Anok

To accelerate identification of disease resistant arecanut germplasm or hybrids against Phytophthora, it is very much imperative to develop bioassays which could differentiate resistant and susceptible cultivars efficiently. Here, a cost effective and rapid technique, called the “Detached Leaf Assay”, was developed to identify resistant germplasm at the seedling stage itself. Zoospore production in highly virulent Phytophthora meadii (P19) was standardized by incubating under a 12 hours light and dark regime. Zoospore suspension was adjusted to 10⁵ spores ml^-1 in Petri plates. Subsequently, surface sterilized arecanut leaves were floated in zoospore suspension and incubated at temperature of 24±1 °C. Disease symptoms, including water-soaked lesions, were recorded three days after inoculation. Infection lesion increased from 1 to 7.3 cm². The pathogen was re-isolated and confirmed with the original culture. The assay was successfully validated to screen arecanut accessions, wild types and hybrids against P. meadii. This technique is the first to be developed, and it is simple, cost-effective, and faster. It also provides consistent infection and could be effectively utilized to screen arecanut germplasm or hybrids against P. meadii in the seedling stage itself.

•
Developed a cost effective, efficient and rapid screening technique
•
The technique was validated to identify resistant arecanut genotypes against Phytophthora meadii at the seedling stage.

为了加速鉴定抗病的油甘子种质或杂交种，必须开发能有效区分抗病和易感栽培品种的生物测定方法。在此，我们开发了一种成本效益高且快速的技术，称为 "分离叶片测定法"，可在幼苗阶段鉴定抗性种质。通过在 12 小时的光照和黑暗条件下进行培养，对高致病性 Phytophthora meadii（P19）的 Zoospore 生产进行了标准化。将培养皿中的 Zoospore 悬浮液调整为 105 孢子 ml-1。随后，将表面灭菌的油菜叶片漂浮在孢子悬浮液中，在 24±1 °C 的温度下培养。接种三天后记录病害症状，包括水渍状病变。病斑面积从 1 平方厘米扩大到 7.3 平方厘米。对病原体进行了重新分离，并用原始培养物进行了确认。该检测方法已成功验证，可用于筛选针对 P. meadii 的山胡桃品种、野生型和杂交种。这项技术是首次开发，它简单、经济、快速。开发出了一种成本效益高、高效、快速的筛选技术--该技术已通过验证，可在苗期鉴定出对 Pytophthora meadii 具有抗性的油甘子基因型。

{"title":"Development of rapid, efficient and cost effective screening technique for testing arecanut against Phytophthora meadii incitant of fruit rot disease","authors":"V. H. Prathibha , N. R. Nagaraja , M. K. Rajesh , Daliyamol , K. P. Thejasri , Rajkumar , Vinayaka Hegde , Uchoi Anok","doi":"10.1016/j.mex.2024.103032","DOIUrl":"10.1016/j.mex.2024.103032","url":null,"abstract":"<div><div>To accelerate identification of disease resistant arecanut germplasm or hybrids against <em>Phytophthora</em>, it is very much imperative to develop bioassays which could differentiate resistant and susceptible cultivars efficiently. Here, a cost effective and rapid technique, called the “Detached Leaf Assay”, was developed to identify resistant germplasm at the seedling stage itself. Zoospore production in highly virulent <em>Phytophthora meadii</em> (P19) was standardized by incubating under a 12 hours light and dark regime. Zoospore suspension was adjusted to 10<sup>5</sup> spores ml<sup>-1</sup> in Petri plates. Subsequently, surface sterilized arecanut leaves were floated in zoospore suspension and incubated at temperature of 24±1 °C. Disease symptoms, including water-soaked lesions, were recorded three days after inoculation. Infection lesion increased from 1 to 7.3 cm<sup>2</sup>. The pathogen was re-isolated and confirmed with the original culture. The assay was successfully validated to screen arecanut accessions, wild types and hybrids against <em>P. meadii</em>. This technique is the first to be developed, and it is simple, cost-effective, and faster. It also provides consistent infection and could be effectively utilized to screen arecanut germplasm or hybrids against <em>P. meadii</em> in the seedling stage itself.<ul><li><span>•</span><span><div>Developed a cost effective, efficient and rapid screening technique</div></span></li><li><span>•</span><span><div>The technique was validated to identify resistant arecanut genotypes against <em>Phytophthora meadii</em> at the seedling stage.</div></span></li></ul></div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"13 ","pages":"Article 103032"},"PeriodicalIF":1.6,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142654779","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Ocean wave prediction using Long Short-Term Memory (LSTM) and Extreme Gradient Boosting (XGBoost) in Tuban Regency for fisherman safety 使用长短期记忆（LSTM）和极端梯度提升（XGBoost）预测图班地区的海浪，保障渔民安全

IF 1.6 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX

Pub Date : 2024-11-02 DOI: 10.1016/j.mex.2024.103031

Riswanda Ayu Dhiya'ulhaq, Anisya Safira, Indah Fahmiyah, Mohammad Ghani

The fishing industry has a large role in the Indonesian economy, with potential profits in 2020 of around US$ 1.338 billion. Tuban Regency is one of the regions in East Java that contributes to the fisheries sector. Fisheries relate to the work of fishermen. Accidents in shipping are still a major concern. One of the natural factors that influence shipping accidents is the height of the waves. Fisherman safety regulations have been established by the Ministry of Maritime Affairs and Fisheries and the Meteorology, Climatology and Geophysics Agency. Apart from regulations, the results of wave height predictions using the Long Short-Term Memory (LSTM) and Extreme Gradient Boosting (XGBoost) methods can help fishermen determine shipping departures, thereby reducing the risk of accidents. In this study, the Grid Search hyperparameter tuning process was used for both methods which were carried out on four location coordinates. Based on the analysis results, LSTM is superior in predicting wave height for the next 30 days because it can predict wave height at all three locations, with results at the first location (RMSE 0.045; MAE 0.029; MAPE 8.671 %), second location (RMSE 0.051; MAE 0.035; MAPE 10.64 %), and third location (RMSE 0.044; MAE 0.027; MAPE 7.773 %), while XGBoost only has the best value at fourth location (RMSE 0.040; MAE 0.025; MAPE 7.286 %).

•
Hyperparameter tuning with gridsearch is used in LSTM and XGBoost to obtain optimal accuracy
•
LSTM outperforms in three locations, while XGBoost outperforms in the fourth location.
•
Advanced prediction techniques such as LSTM and XGBoost improve fishermen's safety by providing accurate wave height estimates, thereby reducing the possibility of shipping accidents.

渔业在印尼经济中发挥着重要作用，2020 年的潜在利润约为 13.38 亿美元。图班县是东爪哇岛渔业贡献较大的地区之一。渔业与渔民的工作有关。航运事故仍然是一个主要问题。影响航运事故的自然因素之一是海浪的高度。海洋事务和渔业部以及气象、气候和地球物理局制定了渔民安全条例。除法规外，使用长短期记忆（LSTM）和极端梯度提升（XGBoost）方法预测波高的结果可帮助渔民确定航船的出发点，从而降低事故风险。在本研究中，两种方法都使用了网格搜索超参数调整过程，并在四个位置坐标上进行了调整。根据分析结果，LSTM 在预测未来 30 天的波高方面更胜一筹，因为它可以预测所有三个地点的波高，其中第一个地点的结果（RMSE 0.045；MAE 0.029; MAPE 8.671 %）、第二地点（RMSE 0.051; MAE 0.035; MAPE 10.64 %）和第三地点（RMSE 0.044; MAE 0.027; MAPE 7.773 %）的结果，而 XGBoost 仅在第四地点具有最佳值（RMSE 0.在 LSTM 和 XGBoost 中使用了网格搜索进行超参数调整，以获得最佳精度--LSTM 在三个地点表现最佳，而 XGBoost 在第四个地点表现最佳。

{"title":"Ocean wave prediction using Long Short-Term Memory (LSTM) and Extreme Gradient Boosting (XGBoost) in Tuban Regency for fisherman safety","authors":"Riswanda Ayu Dhiya'ulhaq, Anisya Safira, Indah Fahmiyah, Mohammad Ghani","doi":"10.1016/j.mex.2024.103031","DOIUrl":"10.1016/j.mex.2024.103031","url":null,"abstract":"<div><div>The fishing industry has a large role in the Indonesian economy, with potential profits in 2020 of around US$ 1.338 billion. Tuban Regency is one of the regions in East Java that contributes to the fisheries sector. Fisheries relate to the work of fishermen. Accidents in shipping are still a major concern. One of the natural factors that influence shipping accidents is the height of the waves. Fisherman safety regulations have been established by the Ministry of Maritime Affairs and Fisheries and the Meteorology, Climatology and Geophysics Agency. Apart from regulations, the results of wave height predictions using the Long Short-Term Memory (LSTM) and Extreme Gradient Boosting (XGBoost) methods can help fishermen determine shipping departures, thereby reducing the risk of accidents. In this study, the Grid Search hyperparameter tuning process was used for both methods which were carried out on four location coordinates. Based on the analysis results, LSTM is superior in predicting wave height for the next 30 days because it can predict wave height at all three locations, with results at the first location (RMSE 0.045; MAE 0.029; MAPE 8.671 %), second location (RMSE 0.051; MAE 0.035; MAPE 10.64 %), and third location (RMSE 0.044; MAE 0.027; MAPE 7.773 %), while XGBoost only has the best value at fourth location (RMSE 0.040; MAE 0.025; MAPE 7.286 %).<ul><li><span>•</span><span><div>Hyperparameter tuning with gridsearch is used in LSTM and XGBoost to obtain optimal accuracy</div></span></li><li><span>•</span><span><div>LSTM outperforms in three locations, while XGBoost outperforms in the fourth location.</div></span></li><li><span>•</span><span><div>Advanced prediction techniques such as LSTM and XGBoost improve fishermen's safety by providing accurate wave height estimates, thereby reducing the possibility of shipping accidents.</div></span></li></ul></div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"13 ","pages":"Article 103031"},"PeriodicalIF":1.6,"publicationDate":"2024-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142655310","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Optimizing lncRNA-miRNA interaction analysis: Modified crosslinking and immunoprecipitation (M-CLIP) assay 优化 lncRNA-miRNA 相互作用分析：改良交联和免疫沉淀（M-CLIP）测定

IF 1.6 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX

Pub Date : 2024-10-30 DOI: 10.1016/j.mex.2024.103028

Revathy Nadhan , Rohini Gomathinayagam , Rangasudhagar Radhakrishnan , Ji Hee Ha , Muralidharan Jayaraman , Danny N. Dhanasekaran

Defining lncRNA-miRNA interactions is critical for understanding their roles in cellular signaling and cancer biology. Capturing these interactions is challenging due to the inherent instability of RNAs. Our study focuses on the long non-coding RNA (lncRNA) UCA1, exploring its role in ovarian cancer progression through interactions with microRNAs (miRNAs). We hypothesized that UCA1 acts as a competing endogenous RNA (ceRNA), sequestering let-7 miRNAs to modulate the expression of let-7 targets, thereby driving cancer progression. Typically, miRNAs associate with ribonucleoprotein complexes that include Ago2 protein, pivotal in mediating miRNA activity and stability. Analyzing these complexes has proven effective in identifying lncRNAs and their miRNA partners. Inspired by previous RNA-protein crosslinking methodologies, we developed the Modified Crosslinking and Immunoprecipitation (M-CLIP) assay to capture UCA1-let-7 miRNA interactions through immunoprecipitation of Ago2, followed by qRT-PCR to detect the bound UCA1 and its associated let-7 miRNAs. This method includes:

•
Formaldehyde-based crosslinking followed by cell lysis
•
Immunoprecipitation and isolation of RNAs bound to bait proteins
•
Characterization of bound lncRNA and target miRNAs

Our findings demonstrate the efficacy of the M-CLIP assay in identifying UCA1-let-7 interactions, providing a robust tool to elucidate how UCA1 and similar lncRNAs influence cancer progression through miRNA sequestration.

定义 lncRNA-miRNA 相互作用对于了解它们在细胞信号传导和癌症生物学中的作用至关重要。由于 RNA 本身的不稳定性，捕捉这些相互作用具有挑战性。我们的研究聚焦于长非编码 RNA（lncRNA）UCA1，通过其与 microRNA（miRNA）的相互作用，探索其在卵巢癌进展中的作用。我们假设 UCA1 作为竞争性内源性 RNA（ceRNA），封存 let-7 miRNA，调节 let-7 靶点的表达，从而推动癌症进展。通常，miRNA 与包括 Ago2 蛋白在内的核糖核蛋白复合物结合，而 Ago2 蛋白在介导 miRNA 的活性和稳定性方面起着关键作用。事实证明，分析这些复合物能有效识别 lncRNA 及其 miRNA 伙伴。受以前的 RNA 蛋白交联方法的启发，我们开发了改良交联和免疫沉淀（M-CLIP）测定法，通过免疫沉淀 Ago2 来捕获 UCA1-let-7 miRNA 的相互作用，然后用 qRT-PCR 检测结合的 UCA1 及其相关的 let-7 miRNA。我们的研究结果表明，M-CLIP 法能有效识别 UCA1-let-7 的相互作用，为阐明 UCA1 和类似的 lncRNA 如何通过 miRNA 的螯合作用影响癌症的进展提供了有力的工具。

{"title":"Optimizing lncRNA-miRNA interaction analysis: Modified crosslinking and immunoprecipitation (M-CLIP) assay","authors":"Revathy Nadhan , Rohini Gomathinayagam , Rangasudhagar Radhakrishnan , Ji Hee Ha , Muralidharan Jayaraman , Danny N. Dhanasekaran","doi":"10.1016/j.mex.2024.103028","DOIUrl":"10.1016/j.mex.2024.103028","url":null,"abstract":"<div><div>Defining lncRNA-miRNA interactions is critical for understanding their roles in cellular signaling and cancer biology. Capturing these interactions is challenging due to the inherent instability of RNAs. Our study focuses on the long non-coding RNA (lncRNA) UCA1, exploring its role in ovarian cancer progression through interactions with microRNAs (miRNAs). We hypothesized that UCA1 acts as a competing endogenous RNA (ceRNA), sequestering let-7 miRNAs to modulate the expression of let-7 targets, thereby driving cancer progression. Typically, miRNAs associate with ribonucleoprotein complexes that include Ago2 protein, pivotal in mediating miRNA activity and stability. Analyzing these complexes has proven effective in identifying lncRNAs and their miRNA partners. Inspired by previous RNA-protein crosslinking methodologies, we developed the Modified Crosslinking and Immunoprecipitation (M-CLIP) assay to capture UCA1-let-7 miRNA interactions through immunoprecipitation of Ago2, followed by qRT-PCR to detect the bound UCA1 and its associated let-7 miRNAs. This method includes:<ul><li><span>•</span><span><div>Formaldehyde-based crosslinking followed by cell lysis</div></span></li><li><span>•</span><span><div>Immunoprecipitation and isolation of RNAs bound to bait proteins</div></span></li><li><span>•</span><span><div>Characterization of bound lncRNA and target miRNAs</div></span></li></ul>Our findings demonstrate the efficacy of the M-CLIP assay in identifying UCA1-let-7 interactions, providing a robust tool to elucidate how UCA1 and similar lncRNAs influence cancer progression through miRNA sequestration.</div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"13 ","pages":"Article 103028"},"PeriodicalIF":1.6,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142655308","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","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 GIS-toolbox for a landscape structure based Wind Erosion Risk Assessment (WERA) 基于景观结构的风蚀风险评估（WERA）地理信息系统工具箱

IF 1.6 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX

Pub Date : 2024-10-30 DOI: 10.1016/j.mex.2024.103006

Roger Funk, Lidia Völker

The landscape structure influences the local wind field by lowering the wind speed and thus reducing the wind erosion risk. An important parameter is the height of each landscape element, as this determines the length of wind protection behind it. Further determining parameters are the wind speeds above a threshold value for initiating wind erosion and the corresponding wind directions. The presented method combines heights of landscape elements and the directional transport capacities of erosive wind speeds to derive a map of the spatial wind speed reduction by landscape structures. This map can be combined with the soil-derived erodibility map to get finally a wind erosion risk map which includes landscape effects.

•
The ArcGIS toolbox “WERA” allows a detailed analysis of the landscape structure on wind erosion processes,.
•
The method allows both the identification of risk areas and needs for additional plantings of LE.
•
The area-specific query determines the wind erosion risk for field blocks, districts or municipalities.

景观结构通过降低风速来影响当地风场，从而降低风蚀风险。一个重要的参数是每个景观元素的高度，因为这决定了其背后的防风长度。进一步的决定性参数是风速是否超过引发风蚀的临界值以及相应的风向。所提出的方法结合了景观元素的高度和侵蚀风速的定向传输能力，得出了景观结构降低空间风速的地图。通过 ArcGIS 工具箱 "WERA"，可以详细分析景观结构对风蚀过程的影响。

{"title":"A GIS-toolbox for a landscape structure based Wind Erosion Risk Assessment (WERA)","authors":"Roger Funk, Lidia Völker","doi":"10.1016/j.mex.2024.103006","DOIUrl":"10.1016/j.mex.2024.103006","url":null,"abstract":"<div><div>The landscape structure influences the local wind field by lowering the wind speed and thus reducing the wind erosion risk. An important parameter is the height of each landscape element, as this determines the length of wind protection behind it. Further determining parameters are the wind speeds above a threshold value for initiating wind erosion and the corresponding wind directions. The presented method combines heights of landscape elements and the directional transport capacities of erosive wind speeds to derive a map of the spatial wind speed reduction by landscape structures. This map can be combined with the soil-derived erodibility map to get finally a wind erosion risk map which includes landscape effects.<ul><li><span>•</span><span><div>The ArcGIS toolbox “WERA” allows a detailed analysis of the landscape structure on wind erosion processes,.</div></span></li><li><span>•</span><span><div>The method allows both the identification of risk areas and needs for additional plantings of LE.</div></span></li><li><span>•</span><span><div>The area-specific query determines the wind erosion risk for field blocks, districts or municipalities.</div></span></li></ul></div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"13 ","pages":"Article 103006"},"PeriodicalIF":1.6,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142586510","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

ViT-HHO: Optimized vision transformer for diabetic retinopathy detection using Harris Hawk optimization ViT-HHO：利用哈里斯-霍克优化技术检测糖尿病视网膜病变的优化视觉转换器

IF 1.6 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX

Pub Date : 2024-10-23 DOI: 10.1016/j.mex.2024.103018

Vishal Awasthi , Namita Awasthi , Hemant Kumar , Shubhendra Singh , Prabal Pratap Singh , Poonam Dixit , Rashi Agarwal

Diabetic retinopathy (DR) is a significant cause of vision impairment globally, emphasizing the importance of timely and precise detection to prevent severe consequences. This study presents an optimized Vision Transformer (ViT) model that incorporates Harris Hawk Optimization (HHO) to improve the automated detection of diabetic retinopathy (DR). The ViT architecture utilizes self-attention mechanisms to capture local and global features in retinal images. Additionally, HHO optimizes key hyperparameters to maximize the performance of the model. The proposed ViT-HHO model achieved exceptional performance on the APTOS-2019 and IDRiD datasets. Specifically, it achieved 99.83 % accuracy, 99.78 % sensitivity, 99.85 % specificity, and 99.80 % AUC-ROC on the APTOS-2019 dataset, surpassing traditional CNNs and alternative optimization techniques. The model exhibited strong generalization on the IDRiID dataset, achieving an accuracy of 99.11 % and an AUC-ROC of 99.12 %. The ViT-HHO model demonstrates the potential for enhancing the clinical detection of diabetic retinopathy (DR), providing high precision and reliability.

•
An optimized Vision Transformer (ViT) model was developed using HHO for improved detection of Diabetic Retinopathy (DR).
•
The model was validated on the APTOS-2019 and IDRiID datasets, demonstrating superior accuracy and AUC-ROC metrics.
•
The model's generalization and robustness were demonstrated through comprehensive performance evaluations.

糖尿病视网膜病变（DR）是全球视力受损的重要原因之一，因此必须及时、精确地检测以防止严重后果的发生。本研究提出了一种优化的视觉转换器（ViT）模型，该模型结合了哈里斯鹰优化（HHO）技术，以改进糖尿病视网膜病变（DR）的自动检测。ViT 架构利用自我注意机制捕捉视网膜图像中的局部和全局特征。此外，HHO 还优化了关键超参数，以最大限度地提高模型的性能。所提出的 ViT-HHO 模型在 APTOS-2019 和 IDRiD 数据集上取得了优异的性能。具体来说，它在 APTOS-2019 数据集上实现了 99.83 % 的准确率、99.78 % 的灵敏度、99.85 % 的特异性和 99.80 % 的 AUC-ROC，超越了传统的 CNN 和其他优化技术。该模型在 IDRiID 数据集上表现出很强的泛化能力，准确率达到 99.11%，AUC-ROC 达到 99.12%。该模型在 APTOS-2019 和 IDRiID 数据集上进行了验证，显示出卓越的准确性和 AUC-ROC 指标。

{"title":"ViT-HHO: Optimized vision transformer for diabetic retinopathy detection using Harris Hawk optimization","authors":"Vishal Awasthi , Namita Awasthi , Hemant Kumar , Shubhendra Singh , Prabal Pratap Singh , Poonam Dixit , Rashi Agarwal","doi":"10.1016/j.mex.2024.103018","DOIUrl":"10.1016/j.mex.2024.103018","url":null,"abstract":"<div><div>Diabetic retinopathy (DR) is a significant cause of vision impairment globally, emphasizing the importance of timely and precise detection to prevent severe consequences. This study presents an optimized Vision Transformer (ViT) model that incorporates Harris Hawk Optimization (HHO) to improve the automated detection of diabetic retinopathy (DR). The ViT architecture utilizes self-attention mechanisms to capture local and global features in retinal images. Additionally, HHO optimizes key hyperparameters to maximize the performance of the model. The proposed ViT-HHO model achieved exceptional performance on the APTOS-2019 and IDRiD datasets. Specifically, it achieved 99.83 % accuracy, 99.78 % sensitivity, 99.85 % specificity, and 99.80 % AUC-ROC on the APTOS-2019 dataset, surpassing traditional CNNs and alternative optimization techniques. The model exhibited strong generalization on the IDRiID dataset, achieving an accuracy of 99.11 % and an AUC-ROC of 99.12 %. The ViT-HHO model demonstrates the potential for enhancing the clinical detection of diabetic retinopathy (DR), providing high precision and reliability.<ul><li><span>•</span><span><div>An optimized Vision Transformer (ViT) model was developed using HHO for improved detection of Diabetic Retinopathy (DR).</div></span></li><li><span>•</span><span><div>The model was validated on the APTOS-2019 and IDRiID datasets, demonstrating superior accuracy and AUC-ROC metrics.</div></span></li><li><span>•</span><span><div>The model's generalization and robustness were demonstrated through comprehensive performance evaluations.</div></span></li></ul></div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"13 ","pages":"Article 103018"},"PeriodicalIF":1.6,"publicationDate":"2024-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142529066","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The TOPSIS method: Figuring the landslide susceptibility using Excel and GIS TOPSIS 方法：使用 Excel 和 GIS 计算滑坡易发性

IF 1.6 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX

Pub Date : 2024-10-17 DOI: 10.1016/j.mex.2024.103005

Jonmenjoy Barman , Brototi Biswas , Syed Sadath Ali , Mohamed Zhran

The current study introduced Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) to enhance landslide susceptibility. It determines the relative distance of each alternative from the ideal best and ideal worst value. The ArcGIS environment was used to prepare eleven landslide conditioning factors, while raster values were extracted for the decision matrix preparation. We utilized subjective expert judgment to create a weighted matrix that considers the roles of each conditioning component. In addition, a Euclidean distance was measured from each alternative to the ideal best and worst values. The relative closeness value (R_i) has been used to prepare the landslide susceptibility index by the inverse distance weighting (IDW) interpolation. Furthermore, the precision of the landslide susceptibility was justified by area under curve-receiver operating characteristic (AUC-ROC) which was 0.987. Hence, multi-criteria decision-making (MCDM) techniques like the TOPSIS method are very useful for natural hazard mapping.

•
The simplified TOPSIS approach described by Hwang and Yoon (1981) is applied in this study. The criteria have been categorized and assigned weights based on expert judgment and previously published material.
•
The TOPSIS approach and GIS integration has significantly enhanced the creation of a landslide susceptibility map for a sensitive area.
•
The method is easiest and suitable for short term operation research.

目前的研究引入了 "与理想方案相似度排序偏好技术"（TOPSIS），以提高滑坡的易发性。它确定了每个备选方案与理想最佳值和理想最坏值的相对距离。我们使用 ArcGIS 环境编制了 11 个滑坡条件因子，并提取了栅格值用于编制决策矩阵。我们利用专家的主观判断创建了一个加权矩阵，该矩阵考虑了每个调节因素的作用。此外，我们还测量了每个备选方案与理想的最佳值和最坏值之间的欧氏距离。通过反距离加权（IDW）插值法，利用相对接近值（Ri）来编制滑坡易感性指数。此外，曲线下面积-接收器工作特征（AUC-ROC）为 0.987，证明了滑坡易感性的精确性。因此，像 TOPSIS 方法这样的多标准决策（MCDM）技术对于绘制自然灾害地图非常有用。本研究采用了 Hwang 和 Yoon（1981 年）描述的简化 TOPSIS 方法，并根据专家判断和以前发表的资料对标准进行了分类和权重分配。

{"title":"The TOPSIS method: Figuring the landslide susceptibility using Excel and GIS","authors":"Jonmenjoy Barman , Brototi Biswas , Syed Sadath Ali , Mohamed Zhran","doi":"10.1016/j.mex.2024.103005","DOIUrl":"10.1016/j.mex.2024.103005","url":null,"abstract":"<div><div>The current study introduced Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) to enhance landslide susceptibility. It determines the relative distance of each alternative from the ideal best and ideal worst value. The ArcGIS environment was used to prepare eleven landslide conditioning factors, while raster values were extracted for the decision matrix preparation. We utilized subjective expert judgment to create a weighted matrix that considers the roles of each conditioning component. In addition, a Euclidean distance was measured from each alternative to the ideal best and worst values. The relative closeness value (R<sub>i</sub>) has been used to prepare the landslide susceptibility index by the inverse distance weighting (IDW) interpolation. Furthermore, the precision of the landslide susceptibility was justified by area under curve-receiver operating characteristic (AUC-ROC) which was 0.987. Hence, multi-criteria decision-making (MCDM) techniques like the TOPSIS method are very useful for natural hazard mapping.</div><div><ul><li><span>•</span><span><div>The simplified TOPSIS approach described by Hwang and Yoon (1981) is applied in this study. The criteria have been categorized and assigned weights based on expert judgment and previously published material.</div></span></li><li><span>•</span><span><div>The TOPSIS approach and GIS integration has significantly enhanced the creation of a landslide susceptibility map for a sensitive area.</div></span></li><li><span>•</span><span><div>The method is easiest and suitable for short term operation research.</div></span></li></ul></div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"13 ","pages":"Article 103005"},"PeriodicalIF":1.6,"publicationDate":"2024-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142529067","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Standardized lab-scale production of the recombinant fusion protein HUG for the nanoscale analysis of bilirubin 用于胆红素纳米级分析的重组融合蛋白 HUG 的标准化实验室规模生产

IF 1.6 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX

Pub Date : 2024-10-17 DOI: 10.1016/j.mex.2024.103001

Paola Sist, Suman Saeed, Federica Tramer, Antonella Bandiera, Sabina Passamonti

The recombinant bifunctional protein HELP-UnaG (HUG) is a fusion product of the Human Elastin-like Polypeptide (HELP) with the bilirubin-binding fluorescent protein UnaG. HUG is used for the fluorometric detection of bilirubin in serum and a variety of biological fluids and extracts. Here we describe a detailed method for the standardized production and purification of HUG from E. coli extracts on a laboratory scale. This method takes advantage of the HELP-specific thermoreactive behavior that enables the separation of HUG from complex E. coli extracts by repeated precipitation/re-dissolution steps at near physiological temperature.

•
The method is based on the inverse thermal transition process.
•
The “green” method is affordable for basic laboratories and can be easily transferred to new users.

重组双功能蛋白 HELP-UnaG (HUG) 是人弹性蛋白样多肽 (HELP) 与胆红素结合荧光蛋白 UnaG 的融合产物。HUG 可用于血清、各种生物液体和提取物中胆红素的荧光检测。在此，我们介绍了一种在实验室规模上从大肠杆菌提取物中标准化生产和纯化 HUG 的详细方法。这种方法利用了 HELP 特有的热反应行为，在接近生理温度的条件下，通过重复沉淀/再溶解步骤，从复杂的大肠杆菌提取物中分离出 HUG。

引用次数: 0

Automated prediction of phosphorus concentration in soils using reflectance spectroscopy and machine learning algorithms 利用反射光谱学和机器学习算法自动预测土壤中的磷浓度

IF 1.6 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX

Pub Date : 2024-10-15 DOI: 10.1016/j.mex.2024.102996

Fabio Eliveny Rivadeneira-Bolaños , Sandra Esperanza Nope-Rodríguez , Martha Isabel Páez-Melo , Carlos Rafael Pinedo-Jaramillo

A method is presented for predicting total phosphorus concentration in soils from Santander de Quilichao, Colombia, using a UV-VIS V-750 Spectrophotometer and machine learning techniques. A total of 152 soil samples, prepared with varying proportions of P₂O₅ fertilizer and soil, were analyzed, obtaining reflectance spectra in the 200 to 900 nm range with 3501 wavelengths. Additionally, 152 laboratory results of total phosphorus concentration were used to train the prediction model. The spectra were filtered using a Savitzky-Golay filter. Key wavelengths were identified using Variable Importance in Projection - Partial Least Squares (VIP-PLS) and Random Forest (RF), reducing the spectral bands to 1085. Principal Component Analysis (PCA) further reduced data dimensionality. A feedforward artificial neural network was then trained to predict phosphorus concentration. This method is faster than traditional lab tests by leveraging advanced data analysis and machine learning, offering results in less time. While sample preparation remains consistent with standard spectroscopic analysis, the value added by the proposed method lies in its data processing and interpretation. Currently applied to a single soil type, future improvements will include more soil types and other macronutrients, enhancing nutrient management in agriculture. Accurate macronutrient measurements aid in better fertilizer uses planning.

• Filtering spectra and determining relevant wavelengths using VIP-PLS and RF.

• Dimensionality reduction with PCA.

• Training feedforward artificial neural networks.

本文介绍了一种利用 UV-VIS V-750 分光光度计和机器学习技术预测哥伦比亚桑坦德德基利乔土壤中总磷浓度的方法。共分析了 152 份土壤样本，这些样本是用不同比例的 P2O5 肥料和土壤制备的，获得了 200 到 900 纳米范围内 3501 个波长的反射光谱。此外，152 项实验室总磷浓度结果也用于训练预测模型。光谱使用 Savitzky-Golay 过滤器进行过滤。使用投影中的变量重要性--偏最小二乘法（VIP-PLS）和随机森林（RF）确定了关键波长，将光谱波段减少到 1085 个。主成分分析（PCA）进一步降低了数据维度。然后训练一个前馈人工神经网络来预测磷浓度。这种方法利用先进的数据分析和机器学习技术，比传统的实验室测试更快，能在更短的时间内得出结果。虽然样品制备与标准光谱分析保持一致，但拟议方法的附加值在于其数据处理和解释。目前，该方法只适用于单一土壤类型，未来的改进将包括更多土壤类型和其他宏量营养元素，从而加强农业养分管理。精确的宏量营养元素测量有助于更好地规划肥料使用。

{"title":"Automated prediction of phosphorus concentration in soils using reflectance spectroscopy and machine learning algorithms","authors":"Fabio Eliveny Rivadeneira-Bolaños , Sandra Esperanza Nope-Rodríguez , Martha Isabel Páez-Melo , Carlos Rafael Pinedo-Jaramillo","doi":"10.1016/j.mex.2024.102996","DOIUrl":"10.1016/j.mex.2024.102996","url":null,"abstract":"<div><div>A method is presented for predicting total phosphorus concentration in soils from Santander de Quilichao, Colombia, using a UV-VIS V-750 Spectrophotometer and machine learning techniques. A total of 152 soil samples, prepared with varying proportions of P<sub>2</sub>O<sub>5</sub> fertilizer and soil, were analyzed, obtaining reflectance spectra in the 200 to 900 nm range with 3501 wavelengths. Additionally, 152 laboratory results of total phosphorus concentration were used to train the prediction model. The spectra were filtered using a Savitzky-Golay filter. Key wavelengths were identified using Variable Importance in Projection - Partial Least Squares (VIP-PLS) and Random Forest (RF), reducing the spectral bands to 1085. Principal Component Analysis (PCA) further reduced data dimensionality. A feedforward artificial neural network was then trained to predict phosphorus concentration. This method is faster than traditional lab tests by leveraging advanced data analysis and machine learning, offering results in less time. While sample preparation remains consistent with standard spectroscopic analysis, the value added by the proposed method lies in its data processing and interpretation. Currently applied to a single soil type, future improvements will include more soil types and other macronutrients, enhancing nutrient management in agriculture. Accurate macronutrient measurements aid in better fertilizer uses planning.</div><div>• Filtering spectra and determining relevant wavelengths using VIP-PLS and RF.</div><div>• Dimensionality reduction with PCA.</div><div>• Training feedforward artificial neural networks.</div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"13 ","pages":"Article 102996"},"PeriodicalIF":1.6,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142529065","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","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 method to improve binary forecast skill verification 改进二进制预报技能验证的方法。

IF 1.6 Q2 MULTIDISCIPLINARY SCIENCES

MethodsX

Pub Date : 2024-10-15 DOI: 10.1016/j.mex.2024.103010

Thitithep Sitthiyot , Kanyarat Holasut

To overcome the limitations of existing deterministic binary forecast skill verification methods that award a perfect score for forecasting events considered easy to forecast, an improvement factor is introduced. It comprises two components which are 1) a measure of the ease with which an event can be accurately forecasted and 2) a measure of frequency of event. By using two hypothetical datasets, this study demonstrates that an improvement factor could enhance the performance of existing deterministic binary forecast skill verification methods by awarding score that is close to score for no-skill forecast for the perfect forecasts of events considered easy to forecast. In addition, the forecast and actual data on annual inflation rate are used to demonstrate how an improvement factor could be used together with the existing deterministic binary forecast skill verification methods in order to assess skills of the forecasters in practice.

•
Existing deterministic binary forecast skill verification methods fail to award correct score for events considered easy to forecast.
•
An improvement factor is developed in order to enhance performance of existing deterministic binary forecast skill verification methods.
•
Hypothetical and empirical data are used to validate how an improvement factor works.

现有的确定性二元预报技能验证方法对容易预报的事件给予满分，为了克服这种方法的局限性，我们引入了一个改进因子。它由两部分组成：1）事件准确预报难易程度的度量；2）事件发生频率的度量。通过使用两个假设数据集，本研究证明了改进因子可以提高现有确定性二元预测技能验证方法的性能，即对被认为容易预测的事件的完美预测给予接近无技能预测的分数。现有的确定性二元预测技能验证方法无法对被认为容易预测的事件给出正确的分数。

{"title":"A method to improve binary forecast skill verification","authors":"Thitithep Sitthiyot , Kanyarat Holasut","doi":"10.1016/j.mex.2024.103010","DOIUrl":"10.1016/j.mex.2024.103010","url":null,"abstract":"<div><div>To overcome the limitations of existing deterministic binary forecast skill verification methods that award a perfect score for forecasting events considered easy to forecast, an improvement factor is introduced. It comprises two components which are 1) a measure of the ease with which an event can be accurately forecasted and 2) a measure of frequency of event. By using two hypothetical datasets, this study demonstrates that an improvement factor could enhance the performance of existing deterministic binary forecast skill verification methods by awarding score that is close to score for no-skill forecast for the perfect forecasts of events considered easy to forecast. In addition, the forecast and actual data on annual inflation rate are used to demonstrate how an improvement factor could be used together with the existing deterministic binary forecast skill verification methods in order to assess skills of the forecasters in practice.<ul><li><span>•</span><span><div>Existing deterministic binary forecast skill verification methods fail to award correct score for events considered easy to forecast.</div></span></li><li><span>•</span><span><div>An improvement factor is developed in order to enhance performance of existing deterministic binary forecast skill verification methods.</div></span></li><li><span>•</span><span><div>Hypothetical and empirical data are used to validate how an improvement factor works.</div></span></li></ul></div></div>","PeriodicalId":18446,"journal":{"name":"MethodsX","volume":"13 ","pages":"Article 103010"},"PeriodicalIF":1.6,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11513477/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142522301","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0