Computational Biology and Chemistry最新文献_第5页

A Novel Ensemble Approach with Deep Transfer Learning for Accurate Identification of Foodborne Bacteria from Hyperspectral Microscopy 利用深度迁移学习的新型集合方法从高光谱显微镜准确识别食源性细菌

IF 2.6 4区生物学 Q2 BIOLOGY

Computational Biology and Chemistry

Pub Date : 2024-10-09 DOI: 10.1016/j.compbiolchem.2024.108238

Qurrat ul Ain , Sohaib Asif

The detection of foodborne bacteria is critical in ensuring both consumer safety and food safety. If these pathogens are not properly identified, it can lead to dangerous cross-contamination. One of the most common methods for classifying bacteria is through the examination of Hyperspectral microscope imaging (HMI). A widely used technique for measuring microbial growth is microscopic cell counting. HMI is a laborious and expensive process, producing voluminous data and needing specialized equipment, which might not be widely available. Machine learning (ML) methods are now frequently utilized to automatically interpret data from hyperspectral microscopy. The objective of our study is to devise a technique that employs deep transfer learning to address the challenge of limited data and utilizes four base classifiers - InceptionResNetV2, MobileNet, ResNet101V2, and Xception - to create an ensemble-based classification model for distinguishing live and dead bacterial cells of six pathogenic strains. In order to determine the optimal weights for the base classifiers, a Powell's optimization method was utilized in conjunction with a weighted average ensemble (WAVE) technique. We carried out an extensive experimental study to verify the efficiency of our proposed ensemble model on live and dead cell images of six different foodborne bacteria. In order to gain a better understanding of the regions, we performed a Grad-CAM analysis to explain the predictions made by our model. Through a series of experiments, our proposed framework has proven its capacity to effectively and precisely detect numerous bacterial pathogens. Specifically, it achieved a perfect identification rate of 100% for Escherichia coli (EC), Listeria innocua (LI), and Salmonella Enteritidis (SE), while achieving rates of 96.30% for Salmonella Typhimurium (ST), 87.13% for Staphylococcus aureus (SA), and 94.12% for Salmonella Heidelberg (SH). As a result, it can be considered as an effective tool for the identification of foodborne pathogens, due to its high level of efficiency.

食源性细菌的检测对于确保消费者安全和食品安全至关重要。如果不能正确识别这些病原体，就会导致危险的交叉污染。对细菌进行分类的最常用方法之一是通过高光谱显微镜成像（HMI）进行检查。显微镜细胞计数是一种广泛使用的微生物生长测量技术。高光谱显微成像是一个费力且昂贵的过程，会产生大量数据，并且需要专业设备，而这些设备可能并不普及。目前，机器学习（ML）方法经常被用来自动解释高光谱显微镜的数据。我们的研究目标是设计一种技术，利用深度迁移学习来应对数据有限的挑战，并利用四个基础分类器--InceptionResNetV2、MobileNet、ResNet101V2 和 Xception--来创建一个基于集合的分类模型，以区分六种致病菌株的活细菌细胞和死细菌细胞。为了确定基础分类器的最佳权重，我们采用了鲍威尔优化法和加权平均集合（WAVE）技术。我们进行了广泛的实验研究，以验证我们提出的集合模型在六种不同食源性细菌的活细胞和死细胞图像上的效率。为了更好地了解这些区域，我们进行了 Grad-CAM 分析，以解释我们的模型所做的预测。通过一系列实验，我们提出的框架证明了其有效、精确检测多种细菌病原体的能力。具体来说，它对大肠杆菌（EC）、无毒李斯特菌（LI）和肠炎沙门氏菌（SE）的完美识别率达到了 100%，而对鼠伤寒沙门氏菌（ST）、金黄色葡萄球菌（SA）和海德堡沙门氏菌（SH）的识别率分别为 96.30%、87.13% 和 94.12%。因此，该方法因其高效率而被视为鉴定食源性病原体的有效工具。

{"title":"A Novel Ensemble Approach with Deep Transfer Learning for Accurate Identification of Foodborne Bacteria from Hyperspectral Microscopy","authors":"Qurrat ul Ain , Sohaib Asif","doi":"10.1016/j.compbiolchem.2024.108238","DOIUrl":"10.1016/j.compbiolchem.2024.108238","url":null,"abstract":"<div><div>The detection of foodborne bacteria is critical in ensuring both consumer safety and food safety. If these pathogens are not properly identified, it can lead to dangerous cross-contamination. One of the most common methods for classifying bacteria is through the examination of Hyperspectral microscope imaging (HMI). A widely used technique for measuring microbial growth is microscopic cell counting. HMI is a laborious and expensive process, producing voluminous data and needing specialized equipment, which might not be widely available. Machine learning (ML) methods are now frequently utilized to automatically interpret data from hyperspectral microscopy. The objective of our study is to devise a technique that employs deep transfer learning to address the challenge of limited data and utilizes four base classifiers - InceptionResNetV2, MobileNet, ResNet101V2, and Xception - to create an ensemble-based classification model for distinguishing live and dead bacterial cells of six pathogenic strains. In order to determine the optimal weights for the base classifiers, a Powell's optimization method was utilized in conjunction with a weighted average ensemble (WAVE) technique. We carried out an extensive experimental study to verify the efficiency of our proposed ensemble model on live and dead cell images of six different foodborne bacteria. In order to gain a better understanding of the regions, we performed a Grad-CAM analysis to explain the predictions made by our model. Through a series of experiments, our proposed framework has proven its capacity to effectively and precisely detect numerous bacterial pathogens. Specifically, it achieved a perfect identification rate of 100% for <em>Escherichia coli (EC), Listeria innocua (LI), and Salmonella Enteritidis (SE)</em>, while achieving rates of 96.30% for <em>Salmonella Typhimurium (ST),</em> 87.13% for <em>Staphylococcus aureus (SA</em>), and 94.12% for Salmonella Heidelberg (SH). As a result, it can be considered as an effective tool for the identification of foodborne pathogens, due to its high level of efficiency.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"113 ","pages":"Article 108238"},"PeriodicalIF":2.6,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142428691","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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

Leukotriene B4 receptor 1 (BLT1) activation by leukotriene B4 (LTB4) and E resolvins (RvE1 and RvE2) 白三烯 B4 (LTB4) 和 E resolvins (RvE1 和 RvE2) 激活白三烯 B4 受体 1 (BLT1)

IF 2.6 4区生物学 Q2 BIOLOGY

Computational Biology and Chemistry

Pub Date : 2024-10-06 DOI: 10.1016/j.compbiolchem.2024.108236

Vinicius S. Nunes , Alexandre P. Rogério , Odonírio Abrahão , Charles N. Serhan

Leukotriene B4 (LTB₄) is a lipid inﬂammatory mediator derived from arachidonic acid (AA). Leukotriene B4 receptor 1 (BLT1), a G protein-coupled receptor (GPCR), is a receptor of LTB₄. Nonetheless, the resolution of inflammation is driven by specialized pro-resolving lipid mediators (SPMs) such as resolvins E1 (RvE1) and E2 (RvE2). Both resolvins are derived from omega-3 fatty acid eicosapentaenoic acid (EPA). Here, long-term molecular dynamics simulations (MD) were performed to investigate the activation of the BLT1 receptor using two pro-resolution agonists (RvE1 and RvE2) and an inflammatory agonist (LTB₄). We have analyzed the receptor's activation state, electrostatic interactions, and the binding affinity the Molecular Mechanics Poisson-Boltzmann Surface Area (MMPBSA) approach. The results showed that LTB4 and RvE1 have kept the receptor in an active state by higher simulation time. MD showed that the ligand-receptor interactions occurred mainly through residues H94, R156, and R267. The MMPBSA calculations showed residues R156 and R267 were the two mainly hotspots. Our MMPBSA results were compatible with experimental results from other studies. Overall, the results from this study provide new insights into the activation mechanisms of the BLT1 receptor, reinforcing the role of critical residues and interactions in the binding of pro-resolution and pro-inflammatory agonists.

白三烯 B4（LTB4）是一种由花生四烯酸（AA）衍生的脂质炎症介质。白三烯 B4 受体 1（BLT1）是一种 G 蛋白偶联受体（GPCR），是 LTB4 的受体。然而，炎症的消退是由专门的促进消退脂质介质（SPMs）驱动的，如 resolvins E1（RvE1）和 E2（RvE2）。这两种溶解素都来源于欧米伽-3 脂肪酸二十碳五烯酸（EPA）。在此，我们进行了长期分子动力学模拟（MD），研究了使用两种促溶解激动剂（RvE1 和 RvE2）和一种炎症激动剂（LTB4）激活 BLT1 受体的过程。我们采用分子力学泊松-玻尔兹曼表面积（MMPBSA）方法分析了受体的活化状态、静电相互作用和结合亲和力。结果表明，LTB4 和 RvE1 在较长的模拟时间内使受体处于激活状态。MD 显示，配体与受体之间的相互作用主要通过 H94、R156 和 R267 等残基发生。MMPBSA 计算显示 R156 和 R267 残基是两个主要热点。我们的 MMPBSA 计算结果与其他研究的实验结果一致。总之，本研究的结果为 BLT1 受体的活化机制提供了新的见解，加强了关键残基和相互作用在促溶解和促炎症激动剂结合中的作用。

{"title":"Leukotriene B4 receptor 1 (BLT1) activation by leukotriene B4 (LTB4) and E resolvins (RvE1 and RvE2)","authors":"Vinicius S. Nunes , Alexandre P. Rogério , Odonírio Abrahão , Charles N. Serhan","doi":"10.1016/j.compbiolchem.2024.108236","DOIUrl":"10.1016/j.compbiolchem.2024.108236","url":null,"abstract":"<div><div>Leukotriene B4 (LTB<sub>4</sub>) is a lipid inﬂammatory mediator derived from arachidonic acid (AA). Leukotriene B4 receptor 1 (BLT1), a G protein-coupled receptor (GPCR), is a receptor of LTB<sub>4</sub>. Nonetheless, the resolution of inflammation is driven by specialized pro-resolving lipid mediators (SPMs) such as resolvins E1 (RvE1) and E2 (RvE2). Both resolvins are derived from omega-3 fatty acid eicosapentaenoic acid (EPA). Here, long-term molecular dynamics simulations (MD) were performed to investigate the activation of the BLT1 receptor using two pro-resolution agonists (RvE1 and RvE2) and an inflammatory agonist (LTB<sub>4</sub>). We have analyzed the receptor's activation state, electrostatic interactions, and the binding affinity the Molecular Mechanics Poisson-Boltzmann Surface Area (MMPBSA) approach. The results showed that LTB4 and RvE1 have kept the receptor in an active state by higher simulation time. MD showed that the ligand-receptor interactions occurred mainly through residues H94, R156, and R267. The MMPBSA calculations showed residues R156 and R267 were the two mainly hotspots. Our MMPBSA results were compatible with experimental results from other studies. Overall, the results from this study provide new insights into the activation mechanisms of the BLT1 receptor, reinforcing the role of critical residues and interactions in the binding of pro-resolution and pro-inflammatory agonists.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"113 ","pages":"Article 108236"},"PeriodicalIF":2.6,"publicationDate":"2024-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142428646","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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

Statistical analysis of the unique characteristics of secondary structures in proteins 对蛋白质二级结构独特特征的统计分析。

IF 2.6 4区生物学 Q2 BIOLOGY

Computational Biology and Chemistry

Pub Date : 2024-10-05 DOI: 10.1016/j.compbiolchem.2024.108237

Nitin Kumar Singh , Manish Agarwal , Mithun Radhakrishna

Protein folding is a complex process influenced by the primary sequence of amino acids. Early studies focused on understanding whether the specificity or the conservation of properties of amino acids was crucial for folding into secondary structures such as

α

-helices,

β

-sheets, turns, and coils. However, with the advent of artificial intelligence (AI) and machine learning (ML), the emphasis has shifted towards the precise nature and occurrence of specific amino acids. In our study, we analyzed a large set of proteins from diverse organisms to identify unique features of secondary structures, particularly in terms of the distribution of polar, non-polar, and charged amino acid residues. We found that

α

-helices tend to have a higher proportion of charged and non-polar groups compared to other secondary structures and that the presence of oppositely charged amino acid residues in helices stabilizes them, facilitating the formation of longer helices. These characteristics are distinct to

α

-helices. This study offers valuable insights for researchers in the field of protein design, enabling the de-novo creation of short helical peptides for a range of applications. We have also developed a web server for extensive analysis of proteins from different databases. The web server is housed at https://proseqanalyser.iitgn.ac.in/

蛋白质折叠是一个受氨基酸主序列影响的复杂过程。早期的研究侧重于了解氨基酸的特异性或特性保持对于折叠成二级结构（如α螺旋、β片、转折和线圈）是否至关重要。然而，随着人工智能（AI）和机器学习（ML）的出现，重点已转向特定氨基酸的精确性质和出现。在我们的研究中，我们分析了来自不同生物体的大量蛋白质，以确定二级结构的独特特征，特别是极性、非极性和带电氨基酸残基的分布。我们发现，与其他二级结构相比，α-螺旋中带电和非极性基团的比例往往较高，螺旋中存在带相反电荷的氨基酸残基可使螺旋稳定，有利于形成较长的螺旋。这些特征与α螺旋截然不同。这项研究为蛋白质设计领域的研究人员提供了宝贵的见解，使他们能够重新创造短螺旋肽，用于一系列应用。我们还开发了一个网络服务器，用于广泛分析不同数据库中的蛋白质。网络服务器设在 https://proseqanalyser.iitgn.ac.in/。

{"title":"Statistical analysis of the unique characteristics of secondary structures in proteins","authors":"Nitin Kumar Singh , Manish Agarwal , Mithun Radhakrishna","doi":"10.1016/j.compbiolchem.2024.108237","DOIUrl":"10.1016/j.compbiolchem.2024.108237","url":null,"abstract":"<div><div>Protein folding is a complex process influenced by the primary sequence of amino acids. Early studies focused on understanding whether the specificity or the conservation of properties of amino acids was crucial for folding into secondary structures such as <span><math><mi>α</mi></math></span>-helices, <span><math><mi>β</mi></math></span>-sheets, turns, and coils. However, with the advent of artificial intelligence (AI) and machine learning (ML), the emphasis has shifted towards the precise nature and occurrence of specific amino acids. In our study, we analyzed a large set of proteins from diverse organisms to identify unique features of secondary structures, particularly in terms of the distribution of polar, non-polar, and charged amino acid residues. We found that <span><math><mi>α</mi></math></span>-helices tend to have a higher proportion of charged and non-polar groups compared to other secondary structures and that the presence of oppositely charged amino acid residues in helices stabilizes them, facilitating the formation of longer helices. These characteristics are distinct to <span><math><mi>α</mi></math></span>-helices. This study offers valuable insights for researchers in the field of protein design, enabling the de-novo creation of short helical peptides for a range of applications. We have also developed a web server for extensive analysis of proteins from different databases. The web server is housed at <span><span>https://proseqanalyser.iitgn.ac.in/</span><svg><path></path></svg></span></div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"113 ","pages":"Article 108237"},"PeriodicalIF":2.6,"publicationDate":"2024-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142407387","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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 novel prognostic risk score model based on RNA editing level in lower-grade glioma 基于低级别胶质瘤 RNA 编辑水平的新型预后风险评分模型。

IF 2.6 4区生物学 Q2 BIOLOGY

Computational Biology and Chemistry

Pub Date : 2024-10-05 DOI: 10.1016/j.compbiolchem.2024.108229

Bincan Jiang, Ziyang Chen, Jiajie Zhou

Background

Lower-grade glioma (LGG) refers to WHO grade 2 and 3 gliomas. Surgery combined with radiotherapy and chemotherapy can significantly improve the prognosis of LGG patients, but tumor progression is still unavoidable. As a form of posttranscriptional regulation, RNA editing (RE) has been reported to be involved in tumorigenesis and progression and has been intensively studied recently.

Methods

Survival data and RE data were subjected to univariate and multivariate Cox regression analysis and lasso regression analysis to establish an RE risk score model. A nomogram combining the risk score and clinicopathological features was built to predict the 1-, 3-, and 5-year survival probability of patients. The relationship among ADAR1, SOD2 and SOAT1 was verified by reverse transcription-quantitative polymerase chain reaction (RT-qPCR)

Results

A risk model associated with RE was constructed and patients were divided into different risk groups based on risk scores. The model demonstrated strong prognostic capability, with the area under the ROC curve (AUC) values of 0.882, 0.938, and 0.947 for 1-, 3-, and 5-year survival predictions, respectively. Through receiver operating characteristic curve (ROC) curves and calibration curves, it was verified that the constructed nomogram had better performance than age, grade, and risk score in predicting patient survival probability. Apart from this functional analysis, the results of correlation analyses between risk differentially expressed genes (RDEGs) and RE help us to understand the underlying mechanism of RE in LGG. ADAR may regulate the expression of SOD2 and SOAT1 through gene editing.

Conclusion

In conclusion, this study establishes a novel and accurate 17-RE model and a nomogram for predicting the survival probability of LGG patients. ADAR may affect the prognosis of glioma patients by influencing gene expression.

背景：低级别胶质瘤（LGG）是指WHO 2级和3级胶质瘤。手术结合放疗和化疗可显著改善 LGG 患者的预后，但肿瘤进展仍不可避免。据报道，RNA编辑（RE）作为转录后调控的一种形式，参与了肿瘤的发生和发展，最近对此进行了深入研究：方法：对生存数据和 RE 数据进行单变量和多变量 Cox 回归分析以及 lasso 回归分析，以建立 RE 风险评分模型。结合风险评分和临床病理特征，建立了预测患者1年、3年和5年生存概率的提名图。通过反转录-定量聚合酶链反应（RT-qPCR）验证了ADAR1、SOD2和SOAT1之间的关系结果：建立了与RE相关的风险模型，并根据风险评分将患者分为不同的风险组。该模型显示出很强的预后能力，预测 1 年、3 年和 5 年生存率的 ROC 曲线下面积（AUC）值分别为 0.882、0.938 和 0.947。通过接收者操作特征曲线（ROC）和校准曲线，验证了所构建的提名图在预测患者生存概率方面的性能优于年龄、分级和风险评分。除功能分析外，风险差异表达基因（RDEGs）与RE之间的相关性分析结果也有助于我们了解LGG中RE的内在机制。ADAR可能通过基因编辑调控SOD2和SOAT1的表达：总之，本研究建立了一个新颖、准确的17-RE模型和提名图，用于预测LGG患者的生存概率。ADAR可能通过影响基因表达来影响胶质瘤患者的预后。

{"title":"A novel prognostic risk score model based on RNA editing level in lower-grade glioma","authors":"Bincan Jiang, Ziyang Chen, Jiajie Zhou","doi":"10.1016/j.compbiolchem.2024.108229","DOIUrl":"10.1016/j.compbiolchem.2024.108229","url":null,"abstract":"<div><h3>Background</h3><div>Lower-grade glioma (LGG) refers to WHO grade 2 and 3 gliomas. Surgery combined with radiotherapy and chemotherapy can significantly improve the prognosis of LGG patients, but tumor progression is still unavoidable. As a form of posttranscriptional regulation, RNA editing (RE) has been reported to be involved in tumorigenesis and progression and has been intensively studied recently.</div></div><div><h3>Methods</h3><div>Survival data and RE data were subjected to univariate and multivariate Cox regression analysis and lasso regression analysis to establish an RE risk score model. A nomogram combining the risk score and clinicopathological features was built to predict the 1-, 3-, and 5-year survival probability of patients. The relationship among ADAR1, SOD2 and SOAT1 was verified by reverse transcription-quantitative polymerase chain reaction (RT-qPCR)</div></div><div><h3>Results</h3><div>A risk model associated with RE was constructed and patients were divided into different risk groups based on risk scores. The model demonstrated strong prognostic capability, with the area under the ROC curve (AUC) values of 0.882, 0.938, and 0.947 for 1-, 3-, and 5-year survival predictions, respectively. Through receiver operating characteristic curve (ROC) curves and calibration curves, it was verified that the constructed nomogram had better performance than age, grade, and risk score in predicting patient survival probability. Apart from this functional analysis, the results of correlation analyses between risk differentially expressed genes (RDEGs) and RE help us to understand the underlying mechanism of RE in LGG. ADAR may regulate the expression of SOD2 and SOAT1 through gene editing.</div></div><div><h3>Conclusion</h3><div>In conclusion, this study establishes a novel and accurate 17-RE model and a nomogram for predicting the survival probability of LGG patients. ADAR may affect the prognosis of glioma patients by influencing gene expression.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"113 ","pages":"Article 108229"},"PeriodicalIF":2.6,"publicationDate":"2024-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142395947","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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

In silico profiling, docking analysis, and protein interactions of secondary metabolites in Musa spp. Against the SGE1 protein of Fusarium oxysporum f. sp. cubense 针对 Fusarium oxysporum f. sp. cubense 的 SGE1 蛋白的硅学剖析、对接分析以及麝香树次生代谢物与蛋白质的相互作用

IF 2.6 4区生物学 Q2 BIOLOGY

Computational Biology and Chemistry

Pub Date : 2024-10-05 DOI: 10.1016/j.compbiolchem.2024.108230

Preeti Sonkar , Shalini Purwar , Prachi Bhargva , Ravindra Pratap Singh , Jawaher Alkahtani , Abdulrahman Al-hashimi , Yheni Dwiningsih , Salim Khan

Banana Fusarium Wilt (BFW), caused by Fusarium oxysporum f. sp. cubense (Foc), threatens banana crops globally, with the pathogen's virulence partially regulated by the Sge1 transcription factor, which enhances disease severity. Certain Musa species display resistance to Foc, suggesting inherent genetic traits that confer immunity against Sge1Foc. This study utilized bioinformatics tools to investigate the mechanisms underlying this resistance in Musa accuminata subsp. aalaccensis. Through in silico analyses, we explored interactions between Musa spp. and Foc, focusing on the Sge1 protein. Tools such as Anti-SMASH, AutoDockVina 4.0, STRING, and Phoenix facilitated the profiling of secondary metabolites in Musa spp. and the identification of biosynthetic gene clusters involved in defense. Our results indicate that secondary metabolites, including saccharides, terpenes, and polyketides, are crucial to the plant's immune response. Molecular docking studies of selected Musa metabolites, such as 3-Phenylphenol, Catechin, and Epicatechin, revealed 3-Phenylphenol as having the highest binding affinity to the Sge1Foc protein (-6.7 kcal/mol).Further analysis of gene clusters associated with secondary metabolite biosynthesis in Musa spp. identified key domains like Chalcone synthase, Phenylalanine ammonia-lyase, Aminotran 1–2, and CoA-ligase, which are integral to phenylpropanoid production—a critical pathway for secondary metabolites. The study highlights that the phenylpropanoid pathway and secondary metabolite biosynthesis are vital for Musa spp. resistance to Foc. Flavonoids and lignin may inhibit Sge1 protein formation, potentially disrupting Foc's cellular processes. These findings emphasize the role of phenylpropanoid pathways and secondary metabolites in combating BFW and suggest that targeting these pathways could offer innovative strategies for enhancing resistance and controlling BFW in banana crops. This research lays the groundwork for developing sustainable methods to protect banana cultivation and ensure food security.

由 Fusarium oxysporum f. sp. cubense（Foc）引起的香蕉镰刀菌枯萎病（Banana Fusarium Wilt，BFW）威胁着全球的香蕉作物，病原体的毒力部分受 Sge1 转录因子的调控，而 Sge1 转录因子会增强病害的严重性。某些蕈蚊物种对 Foc 具有抗性，这表明其固有的遗传特性赋予了对 Sge1Foc 的免疫力。本研究利用生物信息学工具研究了茄子亚种（Musa accuminata subsp.通过硅学分析，我们探索了麝香草属植物与 Foc 之间的相互作用，重点是 Sge1 蛋白。Anti-SMASH、AutoDockVina 4.0、STRING 和 Phoenix 等工具有助于分析穆萨属植物的次生代谢物，并确定参与防御的生物合成基因簇。我们的研究结果表明，次生代谢物（包括糖类、萜烯类和多酮类化合物）对植物的免疫反应至关重要。对 3-苯基苯酚、儿茶素和表儿茶素等选定的麝香草代谢物进行的分子对接研究显示，3-苯基苯酚与 Sge1Foc 蛋白的结合亲和力最高（-6.7 kcal/mol）。进一步分析与麝香草次生代谢物生物合成相关的基因簇，发现了查耳酮合成酶、苯丙氨酸氨解酶、氨基曲霉 1-2 和 CoA 连接酶等关键域，它们是苯丙类化合物生产不可或缺的部分--这是次生代谢物的关键途径。该研究强调，苯丙酮途径和次生代谢物的生物合成对麝香草属植物抵抗 Foc 至关重要。类黄酮和木质素可能会抑制 Sge1 蛋白的形成，从而可能破坏 Foc 的细胞过程。这些发现强调了苯丙类途径和次生代谢物在抗BFW中的作用，并表明针对这些途径可提供创新战略，增强香蕉作物的抗性并控制BFW。这项研究为开发保护香蕉种植和确保粮食安全的可持续方法奠定了基础。

{"title":"In silico profiling, docking analysis, and protein interactions of secondary metabolites in Musa spp. Against the SGE1 protein of Fusarium oxysporum f. sp. cubense","authors":"Preeti Sonkar , Shalini Purwar , Prachi Bhargva , Ravindra Pratap Singh , Jawaher Alkahtani , Abdulrahman Al-hashimi , Yheni Dwiningsih , Salim Khan","doi":"10.1016/j.compbiolchem.2024.108230","DOIUrl":"10.1016/j.compbiolchem.2024.108230","url":null,"abstract":"<div><div>Banana Fusarium Wilt (BFW), caused by <em>Fusarium oxysporum</em> f. sp. <em>cubense</em> (Foc), threatens banana crops globally, with the pathogen's virulence partially regulated by the Sge1 transcription factor, which enhances disease severity. Certain Musa species display resistance to Foc, suggesting inherent genetic traits that confer immunity against Sge1Foc. This study utilized bioinformatics tools to investigate the mechanisms underlying this resistance in <em>Musa accuminata</em> subsp. a<em>alaccensis</em>. Through in silico analyses, we explored interactions between <em>Musa</em> spp. and Foc, focusing on the Sge1 protein. Tools such as Anti-SMASH, AutoDockVina 4.0, STRING, and Phoenix facilitated the profiling of secondary metabolites in <em>Musa</em> spp. and the identification of biosynthetic gene clusters involved in defense. Our results indicate that secondary metabolites, including saccharides, terpenes, and polyketides, are crucial to the plant's immune response. Molecular docking studies of selected <em>Musa</em> metabolites, such as 3-Phenylphenol, Catechin, and Epicatechin, revealed 3-Phenylphenol as having the highest binding affinity to the Sge1Foc protein (-6.7 kcal/mol).Further analysis of gene clusters associated with secondary metabolite biosynthesis in <em>Musa</em> spp. identified key domains like Chalcone synthase, Phenylalanine ammonia-lyase, Aminotran 1–2, and CoA-ligase, which are integral to phenylpropanoid production—a critical pathway for secondary metabolites. The study highlights that the phenylpropanoid pathway and secondary metabolite biosynthesis are vital for <em>Musa</em> spp. resistance to Foc. Flavonoids and lignin may inhibit Sge1 protein formation, potentially disrupting Foc's cellular processes. These findings emphasize the role of phenylpropanoid pathways and secondary metabolites in combating BFW and suggest that targeting these pathways could offer innovative strategies for enhancing resistance and controlling BFW in banana crops. This research lays the groundwork for developing sustainable methods to protect banana cultivation and ensure food security.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"113 ","pages":"Article 108230"},"PeriodicalIF":2.6,"publicationDate":"2024-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142444593","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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

Drug repositioning identifies potential autophagy inhibitors for the LIR motif p62/SQSTM1 protein 药物重新定位为 LIR motif p62/SQSTM1 蛋白确定了潜在的自噬抑制剂。

IF 2.6 4区生物学 Q2 BIOLOGY

Computational Biology and Chemistry

Pub Date : 2024-10-03 DOI: 10.1016/j.compbiolchem.2024.108235

Narjes Asghari , Ali Kian Saei , Marco Cordani , Zahra Nayeri , Mohammad Amin Moosavi

Autophagy is a critical cellular process for degrading damaged organelles and proteins under stressful conditions and has casually been shown to contribute to tumor survival and drug resistance. Sequestosome-1 (SQSTM1/p62) is an autophagy receptor that interacts with its binding partners via the LC3-interacting region (LIR). The p62 protein has been a highly researched target for its critical role in selective autophagy. In this study, we aimed to identify FDA-approved drugs that bind to the LIR motif of p62 and inhibit its LIR function, which could be useful targets for modulating autophagy. To this, the homology model of the p62 protein was predicted using biological data, and docking analysis was performed using Molegro Virtual Docker and PyRx softwares. We further assessed the toxicity profile of the drugs using the ProTox-II server and performed dynamics simulations on the effective candidate drugs identified. The results revealed that the kanamycin, velpatasvir, verteporfin, and temoporfin significantly decreased the binding of LIR to the p62 protein. Finally, we experimentally confirmed that Kanamycin can inhibit autophagy-associated acidic vesicular formation in breast cancer MCF-7 and MDA-MB 231 cells. These repositioned drugs may represent novel autophagy modulators in clinical management, warranting further investigation.

自噬是在应激条件下降解受损细胞器和蛋白质的关键细胞过程，已被证明有助于肿瘤的存活和耐药性。Sequestosome-1（SQSTM1/p62）是一种自噬受体，它通过 LC3 结合区（LIR）与其结合伙伴相互作用。p62 蛋白因其在选择性自噬中的关键作用而成为备受研究的靶标。在本研究中，我们旨在找出与 p62 的 LIR 矩阵结合并抑制其 LIR 功能的 FDA 批准药物，这些药物可能是调节自噬的有用靶点。为此，我们利用生物数据预测了 p62 蛋白的同源模型，并使用 Molegro Virtual Docker 和 PyRx 软件进行了对接分析。我们使用 ProTox-II 服务器进一步评估了药物的毒性特征，并对确定的有效候选药物进行了动力学模拟。结果显示，卡那霉素、velpatasvir、verteporfin 和 temoporfin 能显著减少 LIR 与 p62 蛋白的结合。最后，我们通过实验证实，卡那霉素能抑制乳腺癌 MCF-7 和 MDA-MB 231 细胞中与自噬相关的酸性囊泡的形成。这些重新定位的药物可能是临床治疗中新型的自噬调节剂，值得进一步研究。

{"title":"Drug repositioning identifies potential autophagy inhibitors for the LIR motif p62/SQSTM1 protein","authors":"Narjes Asghari , Ali Kian Saei , Marco Cordani , Zahra Nayeri , Mohammad Amin Moosavi","doi":"10.1016/j.compbiolchem.2024.108235","DOIUrl":"10.1016/j.compbiolchem.2024.108235","url":null,"abstract":"<div><div>Autophagy is a critical cellular process for degrading damaged organelles and proteins under stressful conditions and has casually been shown to contribute to tumor survival and drug resistance. Sequestosome-1 (SQSTM1/p62) is an autophagy receptor that interacts with its binding partners via the LC3-interacting region (LIR). The p62 protein has been a highly researched target for its critical role in selective autophagy. In this study, we aimed to identify FDA-approved drugs that bind to the LIR motif of p62 and inhibit its LIR function, which could be useful targets for modulating autophagy. To this, the homology model of the p62 protein was predicted using biological data, and docking analysis was performed using Molegro Virtual Docker and PyRx softwares. We further assessed the toxicity profile of the drugs using the ProTox-II server and performed dynamics simulations on the effective candidate drugs identified. The results revealed that the kanamycin, velpatasvir, verteporfin, and temoporfin significantly decreased the binding of LIR to the p62 protein. Finally, we experimentally confirmed that Kanamycin can inhibit autophagy-associated acidic vesicular formation in breast cancer MCF-7 and MDA-MB 231 cells. These repositioned drugs may represent novel autophagy modulators in clinical management, warranting further investigation.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"113 ","pages":"Article 108235"},"PeriodicalIF":2.6,"publicationDate":"2024-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142382778","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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

Intelligent computing framework to analyze the transmission risk of COVID-19: Meyer wavelet artificial neural networks 分析 COVID-19 传播风险的智能计算框架：迈耶小波人工神经网络

IF 2.6 4区生物学 Q2 BIOLOGY

Computational Biology and Chemistry

Pub Date : 2024-10-02 DOI: 10.1016/j.compbiolchem.2024.108234

Kottakkaran Sooppy Nisar , Iqra Naz , Muhammad Asif Zahoor Raja , Muhammad Shoaib

The optimum control methods for the epidemiology of the COVID-19 model are acknowledged using a novel advanced intelligent computing infrastructure that joins artificial neural networks with unsupervised learning-based optimizers i.e., Genetic Algorithms (GA) and sequential quadratic programming (SQP). Unsupervised learning strategy is provided which depends on the wavelet basis's sequential deconstruction of stochastic data. The weights or selection values of neural networks are utilizing cumulative algorithms of Meyer wavelet artificial neural networks (MWANNs) optimized with global search Genetic Algorithms (GAs) and Sequential Quadratic Programming (SQP), referred to as MWANNs-GA-SQP and the design technique is utilized to determine the COVID-19 model for five different scenarios employing different step sizes and input intervals. The findings of this research article examined that in order to minimize the total disease transmission at the lowest cost and complexity, safety, focused medical care, and exterior sterilization methods applicability. The provided data is validated through various graphical simulations, which surely authenticate the effectiveness and robustness of the proposed solver. The suggested solver, MWANNs-GA-SQP, is tested in a variety of circumstances to examine that how reliable, safe, and tolerant. Using the proposed MWANNs hubristic intelligent approach, an objective optimization function is created in feed forward neural networking to minimize the mean square error. An investigation of the hybrid GA-SQP is used to confirm the accuracy and dependability of the MWANNs model results. Mean absolute graphs have been constructed to assess the integrity and efficiency of the proposed methodology. The accuracy and reliability of the suggested method are demonstrated by constantly achieving maximum variables of analytical assessment criteria computed for a large appropriate variety of distinct trials.

COVID-19 模型的流行病学最佳控制方法是通过一种新型的先进智能计算基础设施来实现的，该基础设施将人工神经网络与基于无监督学习的优化器（即遗传算法（GA）和顺序二次编程（SQP））结合在一起。提供的无监督学习策略取决于小波基对随机数据的顺序解构。神经网络的权重或选择值是利用迈耶小波人工神经网络（MWANNs）的累积算法与全局搜索遗传算法（GA）和顺序二次编程（SQP）进行优化的，称为 MWANNs-GA-SQP。本文的研究结果表明，为了以最低的成本和复杂性、安全性、重点医疗护理和外部消毒方法的适用性最大限度地减少疾病传播总量。所提供的数据通过各种图形模拟进行了验证，这无疑证明了所建议的求解器的有效性和鲁棒性。建议的求解器 MWANNs-GA-SQP 在各种情况下进行测试，以检验其可靠性、安全性和容错性。利用提出的 MWANNs hubristic 智能方法，在前馈神经网络中创建了一个目标优化函数，以最小化均方误差。通过对混合 GA-SQP 的研究，确认了 MWANNs 模型结果的准确性和可靠性。构建了平均绝对图，以评估所建议方法的完整性和效率。所建议方法的准确性和可靠性体现在对大量不同试验计算的分析评估标准变量不断达到最大值。

{"title":"Intelligent computing framework to analyze the transmission risk of COVID-19: Meyer wavelet artificial neural networks","authors":"Kottakkaran Sooppy Nisar , Iqra Naz , Muhammad Asif Zahoor Raja , Muhammad Shoaib","doi":"10.1016/j.compbiolchem.2024.108234","DOIUrl":"10.1016/j.compbiolchem.2024.108234","url":null,"abstract":"<div><div>The optimum control methods for the epidemiology of the COVID-19 model are acknowledged using a novel advanced intelligent computing infrastructure that joins artificial neural networks with unsupervised learning-based optimizers i.e., Genetic Algorithms (GA) and sequential quadratic programming (SQP). Unsupervised learning strategy is provided which depends on the wavelet basis's sequential deconstruction of stochastic data. The weights or selection values of neural networks are utilizing cumulative algorithms of Meyer wavelet artificial neural networks (MWANNs) optimized with global search Genetic Algorithms (GAs) and Sequential Quadratic Programming (SQP), referred to as MWANNs-GA-SQP and the design technique is utilized to determine the COVID-19 model for five different scenarios employing different step sizes and input intervals. The findings of this research article examined that in order to minimize the total disease transmission at the lowest cost and complexity, safety, focused medical care, and exterior sterilization methods applicability. The provided data is validated through various graphical simulations, which surely authenticate the effectiveness and robustness of the proposed solver. The suggested solver, MWANNs-GA-SQP, is tested in a variety of circumstances to examine that how reliable, safe, and tolerant. Using the proposed MWANNs hubristic intelligent approach, an objective optimization function is created in feed forward neural networking to minimize the mean square error. An investigation of the hybrid GA-SQP is used to confirm the accuracy and dependability of the MWANNs model results. Mean absolute graphs have been constructed to assess the integrity and efficiency of the proposed methodology. The accuracy and reliability of the suggested method are demonstrated by constantly achieving maximum variables of analytical assessment criteria computed for a large appropriate variety of distinct trials.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"113 ","pages":"Article 108234"},"PeriodicalIF":2.6,"publicationDate":"2024-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142428690","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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

Investigation of dual inhibition of antibacterial and antiarthritic drug candidates using combined approach including molecular dynamics, docking and quantum chemical methods 利用分子动力学、对接和量子化学方法等综合方法研究抗菌和抗关节炎候选药物的双重抑制作用。

IF 2.6 4区生物学 Q2 BIOLOGY

Computational Biology and Chemistry

Pub Date : 2024-09-30 DOI: 10.1016/j.compbiolchem.2024.108218

Shabbir Muhammad , Amina Faiz , Shamsa Bibi , Shafiq Ur Rehman , Mohammad Y. Alshahrani

Emerging antibiotic resistance in bacteria threatens immune efficacy and increases susceptibility to bone degradation and arthritic disorders. In our current study, we utilized a three-layer in-silico screening approach, employing quantum chemical methods, molecular docking, and molecular dynamic methods to explore the novel drug candidates similar in structure to floroquinolone (ciprofloxacin). We investigated the interaction of novel similar compounds of ciprofloxacin with both a bacterial protein S. aureus TyrRS (1JIJ) and a protein associated with gout arthritis Neutrophil collagenase (3DPE). UTIs and gout are interconnected through the elevation of uric acid levels. We aimed to identify compounds with dual functionality: antibacterial activity against UTIs and antirheumatic properties. Our screening based on several methods, sorted out six promising ligands. Four of these (L1, L2, L3, and L6) demonstrated favorable hydrogen bonding with both proteins and were selected for further analysis. These ligands showed binding affinities of −8.3 to −9.1 kcal/mol with both proteins, indicating strong interaction potential. Notably, L6 exhibited highest binding energies of −9.10 and −9.01 kcal/mol with S. aureus TyrRS and Neutrophil collagenase respectively. Additionally, the pkCSM online database conducted ADMET analysis on all lead ligand suggested that L6 might exhibit the highest intestinal absorption and justified total clearance rate. Moreover, L6 showed a best predicted inhibition constant with both proteins. The average RMSF values for all complex systems, namely L1, L2, L3 and L6 are 0.43 Å, 0.57 Å, 0.55 Å, and 0.51 Å, respectively where the ligand residues show maximum stability. The smaller energy gap of 3.85 eV between the HOMO and LUMO of the optimized molecule L1 and L6 suggests that these are biologically active compound. All the selected four drugs show considerable stabilization energy ranging from 44.78 to 103.87 kcal/mol, which means all four compounds are chemically and physically stable. Overall, this research opens exciting avenues for the development of new therapeutic agents with dual functionalities for antibacterial and antiarthritic drug designing.

细菌中新出现的抗生素耐药性威胁着免疫功效，并增加了骨质退化和关节炎疾病的易感性。在目前的研究中，我们采用了量子化学方法、分子对接方法和分子动力学方法等三层内分子筛选方法，探索与氟喹诺酮类药物（环丙沙星）结构相似的新型候选药物。我们研究了环丙沙星的新型相似化合物与细菌蛋白金黄色葡萄球菌 TyrRS（1JIJ）和痛风关节炎相关蛋白中性粒细胞胶原酶（3DPE）的相互作用。尿毒症和痛风通过尿酸水平的升高相互关联。我们的目标是找出具有双重功能的化合物：对 UTIs 的抗菌活性和抗风湿特性。我们采用多种方法进行筛选，选出了六种有前景的配体。其中四种配体（L1、L2、L3 和 L6）与这两种蛋白质都有良好的氢键结合，因此被选为进一步分析的对象。这些配体与两种蛋白质的结合亲和力为 -8.3 至 -9.1 kcal/mol，显示出很强的相互作用潜力。值得注意的是，L6 与金黄色葡萄球菌 TyrRS 和中性粒细胞胶原酶的结合能最高，分别为 -9.10 和 -9.01 kcal/mol。此外，pkCSM 在线数据库对所有先导配体进行的 ADMET 分析表明，L6 可能具有最高的肠道吸收率和合理的总清除率。此外，L6 对这两种蛋白质都显示出最佳预测抑制常数。所有复合物系统，即 L1、L2、L3 和 L6 的平均 RMSF 值分别为 0.43 Å、0.57 Å、0.55 Å 和 0.51 Å，其中配体残基显示出最大的稳定性。优化分子 L1 和 L6 的 HOMO 与 LUMO 之间的能隙较小，仅为 3.85 eV，这表明它们是具有生物活性的化合物。所有选定的四种药物都显示出相当大的稳定能，范围在 44.78 至 103.87 kcal/mol 之间，这意味着所有四种化合物都具有化学和物理稳定性。总之，这项研究为开发具有抗菌和抗关节炎双重功能的新型治疗药物开辟了令人兴奋的途径。

{"title":"Investigation of dual inhibition of antibacterial and antiarthritic drug candidates using combined approach including molecular dynamics, docking and quantum chemical methods","authors":"Shabbir Muhammad , Amina Faiz , Shamsa Bibi , Shafiq Ur Rehman , Mohammad Y. Alshahrani","doi":"10.1016/j.compbiolchem.2024.108218","DOIUrl":"10.1016/j.compbiolchem.2024.108218","url":null,"abstract":"<div><div>Emerging antibiotic resistance in bacteria threatens immune efficacy and increases susceptibility to bone degradation and arthritic disorders. In our current study, we utilized a three-layer in-silico screening approach, employing quantum chemical methods, molecular docking, and molecular dynamic methods to explore the novel drug candidates similar in structure to floroquinolone (ciprofloxacin). We investigated the interaction of novel similar compounds of ciprofloxacin with both a bacterial protein S. aureus TyrRS (1JIJ) and a protein associated with gout arthritis Neutrophil collagenase (3DPE). UTIs and gout are interconnected through the elevation of uric acid levels. We aimed to identify compounds with dual functionality: antibacterial activity against UTIs and antirheumatic properties. Our screening based on several methods, sorted out six promising ligands. Four of these (<strong>L1</strong>, <strong>L2</strong>, <strong>L3</strong>, and <strong>L6</strong>) demonstrated favorable hydrogen bonding with both proteins and were selected for further analysis. These ligands showed binding affinities of −8.3 to −9.1 kcal/mol with both proteins, indicating strong interaction potential. Notably, <strong>L6</strong> exhibited highest binding energies of −9.10 and −9.01 kcal/mol with S. aureus TyrRS and Neutrophil collagenase respectively. Additionally, the pkCSM online database conducted ADMET analysis on all lead ligand suggested that <strong>L6</strong> might exhibit the highest intestinal absorption and justified total clearance rate. Moreover, <strong>L6</strong> showed a best predicted inhibition constant with both proteins. The average RMSF values for all complex systems, namely <strong>L1</strong>, <strong>L2</strong>, <strong>L3</strong> and <strong>L6</strong> are 0.43 Å, 0.57 Å, 0.55 Å, and 0.51 Å, respectively where the ligand residues show maximum stability. The smaller energy gap of 3.85 eV between the HOMO and LUMO of the optimized molecule <strong>L1</strong> and <strong>L6</strong> suggests that these are biologically active compound. All the selected four drugs show considerable stabilization energy ranging from 44.78 to 103.87 kcal/mol, which means all four compounds are chemically and physically stable. Overall, this research opens exciting avenues for the development of new therapeutic agents with dual functionalities for antibacterial and antiarthritic drug designing.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"113 ","pages":"Article 108218"},"PeriodicalIF":2.6,"publicationDate":"2024-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142395949","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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

Prediction of Crohn's disease based on deep feature recognition 基于深度特征识别的克罗恩病预测。

IF 2.6 4区生物学 Q2 BIOLOGY

Computational Biology and Chemistry

Pub Date : 2024-09-30 DOI: 10.1016/j.compbiolchem.2024.108231

Hui Tian , Ran Tang

Background

Crohn's disease is a complex genetic disease that involves chronic gastrointestinal inflammation and results from a complex set of genetic, environmental, and immunological factors. By analyzing data from the human microbiome, genetic information can be used to predict Crohn's disease. Recent advances in deep learning have demonstrated its effectiveness in feature extraction and the use of deep learning to decode genetic information for disease prediction.

Methods

In this paper, we present a deep learning-based model that utilizes a sequential convolutional attention network (SCAN) for feature extraction, incorporates adaptive additive interval losses to enhance these features, and employs support vector machines (SVM) for classification. To address the challenge of unbalanced Crohn's disease samples, we propose a random noise one-hot encoding data augmentation method.

Results

Data augmentation with random noise accelerates training convergence, while SCAN-SVM effectively extracts features with adaptive additive interval loss enhancing differentiation. Our approach outperforms benchmark methods, achieving an average accuracy of 0.80 and a kappa value of 0.76, and we validate the effectiveness of feature enhancement.

Conclusions

In summary, we use deep feature recognition to effectively analyze the potential information in genes, which has a good application potential for gene analysis and prediction of Crohn's disease.

背景：克罗恩病是一种复杂的遗传性疾病，涉及慢性胃肠道炎症，由一系列复杂的遗传、环境和免疫因素引起。通过分析人类微生物组的数据，可以利用遗传信息来预测克罗恩病。深度学习的最新进展证明了其在特征提取和利用深度学习解码遗传信息进行疾病预测方面的有效性：在本文中，我们提出了一种基于深度学习的模型，该模型利用连续卷积注意力网络（SCAN）进行特征提取，结合自适应加法区间损失来增强这些特征，并采用支持向量机（SVM）进行分类。为了应对克罗恩病样本不平衡的挑战，我们提出了一种随机噪声单次编码数据增强方法：结果：随机噪声数据增强加速了训练收敛，而 SCAN-SVM 能有效提取特征，自适应加法区间损失增强了区分度。我们的方法优于基准方法，实现了 0.80 的平均准确率和 0.76 的卡帕值，并验证了特征增强的有效性：综上所述，我们利用深度特征识别有效地分析了基因中的潜在信息，在克罗恩病的基因分析和预测方面具有良好的应用前景。

{"title":"Prediction of Crohn's disease based on deep feature recognition","authors":"Hui Tian , Ran Tang","doi":"10.1016/j.compbiolchem.2024.108231","DOIUrl":"10.1016/j.compbiolchem.2024.108231","url":null,"abstract":"<div><h3>Background</h3><div>Crohn's disease is a complex genetic disease that involves chronic gastrointestinal inflammation and results from a complex set of genetic, environmental, and immunological factors. By analyzing data from the human microbiome, genetic information can be used to predict Crohn's disease. Recent advances in deep learning have demonstrated its effectiveness in feature extraction and the use of deep learning to decode genetic information for disease prediction.</div></div><div><h3>Methods</h3><div>In this paper, we present a deep learning-based model that utilizes a sequential convolutional attention network (SCAN) for feature extraction, incorporates adaptive additive interval losses to enhance these features, and employs support vector machines (SVM) for classification. To address the challenge of unbalanced Crohn's disease samples, we propose a random noise one-hot encoding data augmentation method.</div></div><div><h3>Results</h3><div>Data augmentation with random noise accelerates training convergence, while SCAN-SVM effectively extracts features with adaptive additive interval loss enhancing differentiation. Our approach outperforms benchmark methods, achieving an average accuracy of 0.80 and a kappa value of 0.76, and we validate the effectiveness of feature enhancement.</div></div><div><h3>Conclusions</h3><div>In summary, we use deep feature recognition to effectively analyze the potential information in genes, which has a good application potential for gene analysis and prediction of Crohn's disease.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"113 ","pages":"Article 108231"},"PeriodicalIF":2.6,"publicationDate":"2024-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142373819","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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

Recursive dynamics of GspE through machine learning enabled identification of inhibitors 通过机器学习识别 GspE 的递归动态抑制剂。

IF 2.6 4区生物学 Q2 BIOLOGY

Computational Biology and Chemistry

Pub Date : 2024-09-28 DOI: 10.1016/j.compbiolchem.2024.108217

Aliza Naz, Fouzia Gul, Syed Sikander Azam

Type II secretion System has been increasingly recognized as a key driver of virulence in many pathogenic bacteria including Achromobacter xylosoxidans. ATPase GspE is the powerhouse of the T2SS. It powers the entire secretion process by binding with ATP and hydrolyzing it. Therefore, targeting it was thought to have a profound effect on the normal functioning of the whole T2SS. A. xylosoxidans is a Gram-negative bacterium that poses a rising concern to immunocompromised people. It is responsible for many opportunistic infections mostly in people with cystic fibrosis. Due to its intrinsic and acquired resistance mechanisms, it is challenging to treat. In this current study, an extensive machine learning-enabled computational investigation was carried out. Drug libraries were screened using machine learning random forest algorithm trained on non-redundant dataset of 8722 antibacterial compounds with reported IC₅₀ values. Active compounds were then further subjected to molecular docking. To unravel the dynamics and better understand the stability of complexes, the top complexes were subjected to MD Simulations followed by various post-simulation analyses including Trajectory analysis, Atom Contacts, SASA, Hydrogen Bond, RDF, binding free energy calculations, PCA, and AFD analysis. Findings from the study unanimously unveiled Asinex-BAS00263070–28551 as the best inhibitor as it instigated the recursive dynamics of the target by making key hydrogen bond interactions with Walker A motif, suggesting it could serve as the promising drug candidate against GspE. Further experimental in-vivo and in-vitro validation is still required to authenticate the therapeutic effects of these drugs.

人们越来越认识到，II 型分泌系统是许多致病细菌（包括木糖酸 Achromobacter xylosoxidans）毒力的关键驱动因素。ATP 酶 GspE 是 T2SS 的动力源。它通过与 ATP 结合并水解 ATP，为整个分泌过程提供动力。因此，针对它的攻击被认为会对整个 T2SS 的正常运作产生深远影响。木糖酵母菌是一种革兰氏阴性菌，对免疫力低下的人群造成的危害日益严重。它主要导致囊性纤维化患者的许多机会性感染。由于其固有的和后天获得的抗药性机制，它的治疗具有挑战性。在本研究中，我们进行了广泛的机器学习计算调查。利用机器学习随机森林算法，对 8722 种已报告 IC50 值的抗菌化合物的非冗余数据集进行了筛选。然后进一步对活性化合物进行分子对接。为了揭示动力学并更好地了解复合物的稳定性，对顶级复合物进行了 MD 模拟，然后进行了各种模拟后分析，包括轨迹分析、原子接触、SASA、氢键、RDF、结合自由能计算、PCA 和 AFD 分析。研究结果表明，Asinex-BAS00263070-28551 是最佳抑制剂，因为它通过与 Walker A 动机进行关键的氢键相互作用，激发了目标的递归动力学，这表明它可以作为抗 GspE 的候选药物。要验证这些药物的治疗效果，还需要进一步的体内和体外实验验证。

{"title":"Recursive dynamics of GspE through machine learning enabled identification of inhibitors","authors":"Aliza Naz, Fouzia Gul, Syed Sikander Azam","doi":"10.1016/j.compbiolchem.2024.108217","DOIUrl":"10.1016/j.compbiolchem.2024.108217","url":null,"abstract":"<div><div>Type II secretion System has been increasingly recognized as a key driver of virulence in many pathogenic bacteria including <em>Achromobacter xylosoxidans</em>. ATPase GspE is the powerhouse of the T2SS. It powers the entire secretion process by binding with ATP and hydrolyzing it. Therefore, targeting it was thought to have a profound effect on the normal functioning of the whole T2SS. <em>A. xylosoxidans</em> is a Gram-negative bacterium that poses a rising concern to immunocompromised people. It is responsible for many opportunistic infections mostly in people with cystic fibrosis. Due to its intrinsic and acquired resistance mechanisms, it is challenging to treat. In this current study, an extensive machine learning-enabled computational investigation was carried out. Drug libraries were screened using machine learning random forest algorithm trained on non-redundant dataset of 8722 antibacterial compounds with reported IC<sub>50</sub> values. Active compounds were then further subjected to molecular docking. To unravel the dynamics and better understand the stability of complexes, the top complexes were subjected to MD Simulations followed by various post-simulation analyses including Trajectory analysis, Atom Contacts, SASA, Hydrogen Bond, RDF, binding free energy calculations, PCA, and AFD analysis. Findings from the study unanimously unveiled Asinex-BAS00263070–28551 as the best inhibitor as it instigated the recursive dynamics of the target by making key hydrogen bond interactions with Walker A motif, suggesting it could serve as the promising drug candidate against GspE. Further experimental in-vivo and in-vitro validation is still required to authenticate the therapeutic effects of these drugs.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"113 ","pages":"Article 108217"},"PeriodicalIF":2.6,"publicationDate":"2024-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142382791","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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