Computational Biology and Chemistry最新文献_第2页

Identification and validation of miR-21 key genes in cervical cancer through an integrated bioinformatics approach 通过综合生物信息学方法鉴定和验证宫颈癌中的 miR-21 关键基因。

IF 2.6 4区生物学 Q2 BIOLOGY

Computational Biology and Chemistry

Pub Date : 2024-11-12 DOI: 10.1016/j.compbiolchem.2024.108280

Tandrima Mitra, Monica Prusty, Selvakumar Elangovan

Cervical cancer is one of the most prevalent female reproductive cancers. miR-21 is a multi-target oncomiR that has shown its potential in regulating several cancers including colon, pancreatic, breast, prostate, ovarian, and cervical cancer. However, the signaling network of miR-21 remains underexplored, and only a limited number of miR-21 gene targets in cervical cancer have been reported. In this context, the present study was undertaken to evaluate the role of miR-21 in cervical cancer by combining in silico analysis with in vitro validation in cervical cancer cells. The miR-21 target genes were predicted using four different prediction tools: miRWalk, DIANA, miRDB, and TargetScan. A total of 113 overlapping target genes, common in at least three of the prediction tools, were shortlisted and subjected to functional enrichment analysis. The analysis predicted that JAK-STAT, MAPK, neurotrophin, and Ras signaling pathways are significantly (p≤0.05) targeted by miR-21. The MCODE plugin identified the potential cluster in the protein-protein interaction network based on the highest degree of connectivity. After GEPIA2 validation of all 20 hub genes, NTF3, LIFR, and IL-6R were shortlisted for validation in cervical cancer cell lines. The results showed that NTF3, LIFR, and IL-6R were significantly upregulated in the miR-21 knockdown CaSki cell lines in 6.27, 1.92 and 1.71 folds (p≤0.01), respectively. Similarly, in HeLa cell lines expression of NTF3, LIFR, and IL-6R were overexpressed in 4.06, 5.65, 2.42 folds (p≤0.001), respectively. Findings of the study was confirming the role of miR-21 in regulating the expression of these genes. Additionally, the knockdown of miR-21 significantly inhibited the secretion of matrix metalloproteinases by CaSki cells. These results highlight that miR-21 could be a potential therapeutic target for cervical cancer, although further preclinical and clinical studies are required to validate its role and efficacy.

宫颈癌是最常见的女性生殖系统癌症之一。miR-21 是一种多靶点的癌基因，已显示出它在调节包括结肠癌、胰腺癌、乳腺癌、前列腺癌、卵巢癌和宫颈癌在内的多种癌症方面的潜力。然而，miR-21 的信号转导网络仍未得到充分探索，宫颈癌中的 miR-21 基因靶点也仅有少量报道。在此背景下，本研究通过结合硅学分析和宫颈癌细胞的体外验证，评估了 miR-21 在宫颈癌中的作用。研究人员使用四种不同的预测工具：miRWalk、DIANA、miRDB 和 TargetScan 预测了 miR-21 的靶基因。共筛选出 113 个重叠的靶基因，这些基因在至少三种预测工具中都是常见的，并对其进行了功能富集分析。分析预测，miR-21 显著靶向 JAK-STAT、MAPK、神经营养素和 Ras 信号通路（p≤0.05）。MCODE 插件根据连接度最高的蛋白质-蛋白质相互作用网络确定了潜在的群集。在对所有20个中心基因进行GEPIA2验证后，NTF3、LIFR和IL-6R入围宫颈癌细胞系的验证。结果显示，在 miR-21 敲除的 CaSki 细胞系中，NTF3、LIFR 和 IL-6R 分别显著上调了 6.27、1.92 和 1.71 倍（p≤0.01）。同样，在 HeLa 细胞系中，NTF3、LIFR 和 IL-6R 的表达分别过表达了 4.06、5.65 和 2.42 倍（p≤0.001）。研究结果证实了 miR-21 在调节这些基因表达中的作用。此外，敲除 miR-21 能显著抑制 CaSki 细胞分泌基质金属蛋白酶。这些结果突出表明，miR-21 可能是宫颈癌的潜在治疗靶点，尽管还需要进一步的临床前和临床研究来验证其作用和疗效。

{"title":"Identification and validation of miR-21 key genes in cervical cancer through an integrated bioinformatics approach","authors":"Tandrima Mitra, Monica Prusty, Selvakumar Elangovan","doi":"10.1016/j.compbiolchem.2024.108280","DOIUrl":"10.1016/j.compbiolchem.2024.108280","url":null,"abstract":"<div><div>Cervical cancer is one of the most prevalent female reproductive cancers. miR-21 is a multi-target oncomiR that has shown its potential in regulating several cancers including colon, pancreatic, breast, prostate, ovarian, and cervical cancer. However, the signaling network of miR-21 remains underexplored, and only a limited number of miR-21 gene targets in cervical cancer have been reported. In this context, the present study was undertaken to evaluate the role of miR-21 in cervical cancer by combining <em>in silico</em> analysis with <em>in vitro</em> validation in cervical cancer cells. The miR-21 target genes were predicted using four different prediction tools: miRWalk, DIANA, miRDB, and TargetScan. A total of 113 overlapping target genes, common in at least three of the prediction tools, were shortlisted and subjected to functional enrichment analysis. The analysis predicted that JAK-STAT, MAPK, neurotrophin, and Ras signaling pathways are significantly (p≤0.05) targeted by miR-21. The MCODE plugin identified the potential cluster in the protein-protein interaction network based on the highest degree of connectivity. After GEPIA2 validation of all 20 hub genes, NTF3, LIFR, and IL-6R were shortlisted for validation in cervical cancer cell lines. The results showed that NTF3, LIFR, and IL-6R were significantly upregulated in the miR-21 knockdown CaSki cell lines in 6.27, 1.92 and 1.71 folds (p≤0.01), respectively. Similarly, in HeLa cell lines expression of NTF3, LIFR, and IL-6R were overexpressed in 4.06, 5.65, 2.42 folds (p≤0.001), respectively. Findings of the study was confirming the role of miR-21 in regulating the expression of these genes. Additionally, the knockdown of miR-21 significantly inhibited the secretion of matrix metalloproteinases by CaSki cells. These results highlight that miR-21 could be a potential therapeutic target for cervical cancer, although further preclinical and clinical studies are required to validate its role and efficacy.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"113 ","pages":"Article 108280"},"PeriodicalIF":2.6,"publicationDate":"2024-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142689383","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

Hybrid prediction model with improved score level fusion for heart disease diagnosis 混合预测模型与改进的分数级融合用于心脏病诊断。

IF 2.6 4区生物学 Q2 BIOLOGY

Computational Biology and Chemistry

Pub Date : 2024-11-12 DOI: 10.1016/j.compbiolchem.2024.108278

Shaik Ghouhar Taj, K. Kalaivani

Heart disease diagnosis is a challenging task, which provides an automated forecast of the patient's heart illness to make future treatment simpler. This has led to extensive interest in heart disease diagnostics in the medical sector. However, as there are various risks, the prediction must be more appropriate to avoid death. This work intends to develop the Hybrid Prediction Model with Improved Score Level Fusion (HPISLF) for Heart Disease Prediction. Preprocessing is the first process, where improved min-max normalization is done to preprocess the input data. Feature extraction plays a major role as it extracts additional information from the input data via extracting HOS, Improved Holoentropy-based features, and MI are extracted. Also, proposing a hybrid classification model for diagnosis, which trains the model with the extracted feature set. The final classification outcome is determined by the improved score level fusion that fuses the classification outcomes from both the classifiers, CNN and DeepMaxout. The performance of the proposed work is validated and compared over the conventional methods in terms of accuracy, precision, and other measures.

心脏病诊断是一项极具挑战性的任务，它能自动预测患者的心脏疾病，使未来的治疗更加简单。因此，医学界对心脏病诊断产生了广泛的兴趣。然而，由于存在各种风险，预测必须更加适当，以避免死亡。这项工作旨在开发用于心脏病预测的改进分数级融合混合预测模型（HPISLF）。预处理是第一道工序，通过改进的最小-最大归一化对输入数据进行预处理。特征提取起着重要作用，因为它通过提取 HOS、基于全熵的改进特征和 MI 从输入数据中提取额外信息。此外，还提出了一种用于诊断的混合分类模型，该模型利用提取的特征集进行训练。最终的分类结果由改进的分数级融合决定，它融合了 CNN 和 DeepMaxout 这两种分类器的分类结果。在准确度、精确度和其他衡量标准方面，对所提出的工作性能进行了验证，并与传统方法进行了比较。

{"title":"Hybrid prediction model with improved score level fusion for heart disease diagnosis","authors":"Shaik Ghouhar Taj, K. Kalaivani","doi":"10.1016/j.compbiolchem.2024.108278","DOIUrl":"10.1016/j.compbiolchem.2024.108278","url":null,"abstract":"<div><div>Heart disease diagnosis is a challenging task, which provides an automated forecast of the patient's heart illness to make future treatment simpler. This has led to extensive interest in heart disease diagnostics in the medical sector. However, as there are various risks, the prediction must be more appropriate to avoid death. This work intends to develop the Hybrid Prediction Model with Improved Score Level Fusion (HPISLF) for Heart Disease Prediction. Preprocessing is the first process, where improved min-max normalization is done to preprocess the input data. Feature extraction plays a major role as it extracts additional information from the input data via extracting HOS, Improved Holoentropy-based features, and MI are extracted. Also, proposing a hybrid classification model for diagnosis, which trains the model with the extracted feature set. The final classification outcome is determined by the improved score level fusion that fuses the classification outcomes from both the classifiers, CNN and DeepMaxout. The performance of the proposed work is validated and compared over the conventional methods in terms of accuracy, precision, and other measures.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"113 ","pages":"Article 108278"},"PeriodicalIF":2.6,"publicationDate":"2024-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142683892","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

IoT based healthcare system using fractional dung beetle optimization enabled deep learning for breast cancer classification 基于物联网的医疗保健系统利用分数蜣螂优化深度学习进行乳腺癌分类

IF 2.6 4区生物学 Q2 BIOLOGY

Computational Biology and Chemistry

Pub Date : 2024-11-10 DOI: 10.1016/j.compbiolchem.2024.108277

Vaddadi Vasudha Rani , G. Vasavi , P. Mano Paul , K. Sandhya Rani

Breast cancer classification plays a crucial role in healthcare, especially in the diagnosis and monitoring of patients. Traditional methods for classifying breast cancer based on histopathological images often suffer from limited accuracy, which can hinder early detection and treatment. Hence, this paper devises a novel Internet of Things (IoT) based healthcare system using SqueezeNet_Fractional Dung Beetle Optimization (Squeeze_FDBO) for breast cancer detection. Initially, IoT network is simulated, and routing of the histopathological images to the Base Station (BS) is established utilizing FDBO, which is obtained by combining Dung Beetle Optimizer (DBO), and the Fractional Calculus (FC). At BS, breast cancer classification is done, where input is first processed by a bilateral filter. Then, blood cell segmentation is effectuated using LadderNet, and then, feature extraction is performed. Finally, the multigrade classification of breast cancer is executed utilizing SqueezeNet tuned by FDBO. The efficiency of Squeeze_FDBO is validated using various performance measures, and it is found to record an accuracy of 0.919, sensitivity of 0.913, specificity of 0.923, Negative Predictive Value (NPV) of 0.920, and Positive Predictive Value (PPV) of 0.908, and a better routing performance with energy of 0.405 J, distance of 6.901 m, and delay of 0.650mS.

乳腺癌分类在医疗保健中发挥着至关重要的作用，尤其是在诊断和监测患者方面。传统的基于组织病理学图像的乳腺癌分类方法往往准确性有限，这可能会阻碍早期检测和治疗。因此，本文利用 SqueezeNet_Fractional Dung Beetle Optimization（Squeeze_FDBO）设计了一种基于物联网（IoT）的新型医疗系统，用于乳腺癌检测。首先，模拟物联网网络，并利用分数蜣螂优化器（DBO）和分数微积分（FC）建立组织病理学图像到基站（BS）的路由。在 BS 上进行乳腺癌分类，输入首先经过双边滤波器处理。然后，使用 LadderNet 进行血细胞分割，再进行特征提取。最后，利用经 FDBO 调整的 SqueezeNet 对乳腺癌进行多级分类。使用各种性能指标验证了 Squeeze_FDBO 的效率，发现它的准确率为 0.919，灵敏度为 0.913，特异性为 0.923，负预测值（NPV）为 0.920，正预测值（PPV）为 0.908，路由性能更好，能量为 0.405 J，距离为 6.901 m，延迟为 0.650mS。

{"title":"IoT based healthcare system using fractional dung beetle optimization enabled deep learning for breast cancer classification","authors":"Vaddadi Vasudha Rani , G. Vasavi , P. Mano Paul , K. Sandhya Rani","doi":"10.1016/j.compbiolchem.2024.108277","DOIUrl":"10.1016/j.compbiolchem.2024.108277","url":null,"abstract":"<div><div>Breast cancer classification plays a crucial role in healthcare, especially in the diagnosis and monitoring of patients. Traditional methods for classifying breast cancer based on histopathological images often suffer from limited accuracy, which can hinder early detection and treatment. Hence, this paper devises a novel Internet of Things (IoT) based healthcare system using SqueezeNet_Fractional Dung Beetle Optimization (Squeeze_FDBO) for breast cancer detection. Initially, IoT network is simulated, and routing of the histopathological images to the Base Station (BS) is established utilizing FDBO, which is obtained by combining Dung Beetle Optimizer (DBO), and the Fractional Calculus (FC). At BS, breast cancer classification is done, where input is first processed by a bilateral filter. Then, blood cell segmentation is effectuated using LadderNet, and then, feature extraction is performed. Finally, the multigrade classification of breast cancer is executed utilizing SqueezeNet tuned by FDBO. The efficiency of Squeeze_FDBO is validated using various performance measures, and it is found to record an accuracy of 0.919, sensitivity of 0.913, specificity of 0.923, Negative Predictive Value (NPV) of 0.920, and Positive Predictive Value (PPV) of 0.908, and a better routing performance with energy of 0.405 J, distance of 6.901 m, and delay of 0.650mS.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"114 ","pages":"Article 108277"},"PeriodicalIF":2.6,"publicationDate":"2024-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142706773","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

Pharmacophore-guided in-silico discovery of SIRT1 inhibitors for targeted cancer therapy 以药理为指导，在硅内发现用于癌症靶向治疗的 SIRT1 抑制剂。

IF 2.6 4区生物学 Q2 BIOLOGY

Computational Biology and Chemistry

Pub Date : 2024-11-09 DOI: 10.1016/j.compbiolchem.2024.108275

Deepak Sharma, Rajiniraja Muniyan

Epigenetic modifier, Sirtuin (SIRTs) is a family of seven isoforms (SIRT1‐7) and nicotinamide adenine dinucleotide (NAD+) dependent class III histone deacetylase (HDACs) protein. SIRT1 in association with the p53 protein can regulate crucial cell processes such as glucose metabolism, lipid metabolism, mitochondrial biogenesis, DNA repair, oxidative stress, apoptosis, and inflammation through the process of deacetylation. When SIRT1 deacetylates p53, it loses its tumor suppression property. To promote apoptosis and decrease cell proliferation by inhibiting SIRT1 protein and ultimately raising the acetylation of p53 to regain its tumor suppressor function. Though we have many SIRT1 protein inhibitors, they exhibited off-target effects and inefficiency at the clinical trial stage. This study has been executed to identify more potentially effective and reliable SIRT1 inhibitors that can perform better than the existing options. To do so, pharmacophore-based screening of compound libraries followed by virtual screening, pharmacokinetic, drug-likeness, and toxicity studies were conducted which gave 42 compounds to evaluate further. Subsequently, exhaustive molecular docking and molecular dynamics simulation predicted four potential hits to inhibit the SIRT1 protein better than the reference compound. Further studies such as principal components analysis, free energy landscape, and estimation of binding free energy were done which concluded Hit4 (PubChem ID: 55753455) to be a novel and potent SIRT1 small molecule inhibitor among the others. The total binding free energy for Hit4 was found to be −44.68 kcal/mol much better than the reference complex i.e., −29.38 kcal/mol.

表观遗传修饰因子 Sirtuin（SIRTs）是一个由七种同工酶（SIRT1-7）和依赖于烟酰胺腺嘌呤二核苷酸（NAD+）的第三类组蛋白去乙酰化酶（HDACs）蛋白组成的家族。SIRT1 与 p53 蛋白结合，可通过去乙酰化过程调控葡萄糖代谢、脂质代谢、线粒体生物生成、DNA 修复、氧化应激、细胞凋亡和炎症等关键细胞过程。当 SIRT1 对 p53 进行去乙酰化作用时，它就会失去抑制肿瘤的特性。通过抑制 SIRT1 蛋白，促进细胞凋亡，减少细胞增殖，最终提高 p53 的乙酰化水平，恢复其抑肿瘤功能。虽然我们已经有了很多 SIRT1 蛋白抑制剂，但它们在临床试验阶段表现出脱靶效应和低效性。本研究旨在找出更多潜在有效且可靠的 SIRT1 抑制剂，使其性能优于现有选择。为此，研究人员对化合物库进行了基于药效学的筛选，然后进行了虚拟筛选、药代动力学、药物相似性和毒性研究，最终得到了 42 个化合物供进一步评估。随后，通过详尽的分子对接和分子动力学模拟，预测出 4 个潜在化合物比参考化合物更能抑制 SIRT1 蛋白。通过主成分分析、自由能分布和结合自由能估算等进一步研究，Hit4（PubChem ID：55753455）被认为是一种新型且有效的 SIRT1 小分子抑制剂。研究发现，Hit4 的总结合自由能为 -44.68 kcal/mol，远高于参照复合物的 -29.38 kcal/mol。

{"title":"Pharmacophore-guided in-silico discovery of SIRT1 inhibitors for targeted cancer therapy","authors":"Deepak Sharma, Rajiniraja Muniyan","doi":"10.1016/j.compbiolchem.2024.108275","DOIUrl":"10.1016/j.compbiolchem.2024.108275","url":null,"abstract":"<div><div>Epigenetic modifier, Sirtuin (SIRTs) is a family of seven isoforms (SIRT1‐7) and nicotinamide adenine dinucleotide (NAD+) dependent class III histone deacetylase (HDACs) protein. SIRT1 in association with the p53 protein can regulate crucial cell processes such as glucose metabolism, lipid metabolism, mitochondrial biogenesis, DNA repair, oxidative stress, apoptosis, and inflammation through the process of deacetylation. When SIRT1 deacetylates p53, it loses its tumor suppression property. To promote apoptosis and decrease cell proliferation by inhibiting SIRT1 protein and ultimately raising the acetylation of p53 to regain its tumor suppressor function. Though we have many SIRT1 protein inhibitors, they exhibited off-target effects and inefficiency at the clinical trial stage. This study has been executed to identify more potentially effective and reliable SIRT1 inhibitors that can perform better than the existing options. To do so, pharmacophore-based screening of compound libraries followed by virtual screening, pharmacokinetic, drug-likeness, and toxicity studies were conducted which gave 42 compounds to evaluate further. Subsequently, exhaustive molecular docking and molecular dynamics simulation predicted four potential hits to inhibit the SIRT1 protein better than the reference compound. Further studies such as principal components analysis, free energy landscape, and estimation of binding free energy were done which concluded Hit4 (PubChem ID: 55753455) to be a novel and potent SIRT1 small molecule inhibitor among the others. The total binding free energy for Hit4 was found to be −44.68 kcal/mol much better than the reference complex i.e., −29.38 kcal/mol.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"113 ","pages":"Article 108275"},"PeriodicalIF":2.6,"publicationDate":"2024-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142640494","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 multi-layer neural network approach for the stability analysis of the Hepatitis B model 用于乙型肝炎模型稳定性分析的多层神经网络方法。

IF 2.6 4区生物学 Q2 BIOLOGY

Computational Biology and Chemistry

Pub Date : 2024-11-08 DOI: 10.1016/j.compbiolchem.2024.108256

Muhammad Farhan , Zhi Ling , Zahir Shah , Saeed Islam , Mansoor H. Alshehri , Elisabeta Antonescu

In the present study, we explore the dynamics of Hepatitis B virus infection, a significant global health issue, through a newly developed dynamics system. This model is distinguished by its inclusion of asymptomatic carriers and the impact of vaccination and treatment strategies. Compared to Hepatitis A, Hepatitis B poses a more serious health risk, with some cases progressing from acute to chronic. To diagnose and predict disease recurrence, the basic reproduction number (

R_{0}

) is calculated. We investigate the stability of the disease’s dynamics under different conditions, using the Lyapunov function to confirm our model’s global stability. Our findings highlight the relevance of vaccination and early treatment in reducing Hepatitis B virus spread, making them a useful tool for public health efforts aiming at eradicating Hepatitis B virus. In our research, we investigate the dynamics of a specific model that is characterized by a system of differential equations. This work uses deep neural networks (DNNs) technique to improve model accuracy, proving the use of DNNs in epidemiological modeling. Additionally, we want to find the curves that suit the target solutions with the minimum residual errors. The simulations we conducted demonstrate our methodology’s capability to accurately predict the behavior of systems across various conditions. We rigorously test the solutions obtained via the DNNs by comparing them to benchmark solutions and undergoing stages of testing, validation, and training. To determine the accuracy and reliability of our approach, we perform a series of analyses, including convergence studies, error distribution evaluations, regression analyses, and detailed curve fitting for each equation.

在本研究中，我们通过一个新开发的动力学系统，探讨了乙型肝炎病毒感染这一重大全球健康问题的动态变化。该模型的独特之处在于纳入了无症状携带者以及疫苗接种和治疗策略的影响。与甲型肝炎相比，乙型肝炎对健康的危害更为严重，有些病例会从急性发展为慢性。为了诊断和预测疾病复发，需要计算基本繁殖数（R0）。我们利用 Lyapunov 函数研究了不同条件下疾病动力学的稳定性，以确认我们模型的全局稳定性。我们的研究结果凸显了疫苗接种和早期治疗在减少乙肝病毒传播方面的重要性，使其成为旨在根除乙肝病毒的公共卫生工作的有用工具。在我们的研究中，我们研究了一个以微分方程系统为特征的特定模型的动力学。这项工作利用深度神经网络（DNN）技术提高了模型的准确性，证明了 DNN 在流行病学建模中的应用。此外，我们希望以最小的残余误差找到适合目标解决方案的曲线。我们进行的模拟证明了我们的方法能够准确预测各种条件下的系统行为。我们将 DNN 获得的解决方案与基准解决方案进行比较，并经历测试、验证和训练等阶段，从而对其进行严格测试。为了确定我们方法的准确性和可靠性，我们进行了一系列分析，包括收敛性研究、误差分布评估、回归分析以及每个方程的详细曲线拟合。

{"title":"A multi-layer neural network approach for the stability analysis of the Hepatitis B model","authors":"Muhammad Farhan , Zhi Ling , Zahir Shah , Saeed Islam , Mansoor H. Alshehri , Elisabeta Antonescu","doi":"10.1016/j.compbiolchem.2024.108256","DOIUrl":"10.1016/j.compbiolchem.2024.108256","url":null,"abstract":"<div><div>In the present study, we explore the dynamics of Hepatitis B virus infection, a significant global health issue, through a newly developed dynamics system. This model is distinguished by its inclusion of asymptomatic carriers and the impact of vaccination and treatment strategies. Compared to Hepatitis A, Hepatitis B poses a more serious health risk, with some cases progressing from acute to chronic. To diagnose and predict disease recurrence, the basic reproduction number (<span><math><msub><mrow><mi>R</mi></mrow><mrow><mn>0</mn></mrow></msub></math></span>) is calculated. We investigate the stability of the disease’s dynamics under different conditions, using the Lyapunov function to confirm our model’s global stability. Our findings highlight the relevance of vaccination and early treatment in reducing Hepatitis B virus spread, making them a useful tool for public health efforts aiming at eradicating Hepatitis B virus. In our research, we investigate the dynamics of a specific model that is characterized by a system of differential equations. This work uses deep neural networks (DNNs) technique to improve model accuracy, proving the use of DNNs in epidemiological modeling. Additionally, we want to find the curves that suit the target solutions with the minimum residual errors. The simulations we conducted demonstrate our methodology’s capability to accurately predict the behavior of systems across various conditions. We rigorously test the solutions obtained via the DNNs by comparing them to benchmark solutions and undergoing stages of testing, validation, and training. To determine the accuracy and reliability of our approach, we perform a series of analyses, including convergence studies, error distribution evaluations, regression analyses, and detailed curve fitting for each equation.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"113 ","pages":"Article 108256"},"PeriodicalIF":2.6,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142633363","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

Unveiling the distinctive variations in multi-omics triggered by TP53 mutation in lung cancer subtypes: An insight from interaction among intratumoral microbiota, tumor microenvironment, and pathology 揭示肺癌亚型中 TP53 突变引发的多组学独特变化：洞察瘤内微生物群、肿瘤微环境和病理学之间的相互作用。

IF 2.6 4区生物学 Q2 BIOLOGY

Computational Biology and Chemistry

Pub Date : 2024-11-07 DOI: 10.1016/j.compbiolchem.2024.108274

Shanhe Tong , Kenan Huang , Weipeng Xing , Yuwen Chu , Chuanqi Nie , Lei Ji , Wenyan Wang , Geng Tian , Bing Wang , Jialiang Yang

The TP53 mutation is one of the most common gene mutations in non-small cell lung cancer (NSCLC) and plays a significant role in the occurrence, development, and prognosis of both lung adenocarcinoma (LUAD) and lung squamous cell carcinoma (LUSC). Recent studies have also suggested the predictive value of TP53 mutations in the response to immunotherapy for NSCLC. It is known that intratumoral microbiota, tumor immune microenvironment (TIME) and histology are associated with the roles of TP53 mutation in NSCLC. However, the intrinsic associations among these three factors and their underlying interaction with TP53 mutation are not well understood. Additionally, the potential of predicting TP53 mutations using deep learning methods has not yet been fully evaluated. In this paper, we comprehensively evaluated the tissue microbiome, host gene expression characteristics, and histopathological slides of 992 NSCLC patients obtained from the cancer genome atlas (TCGA) and validated the findings using multi-omics data of 332 NSCLC patients from the Clinical Proteomic Tumor Analysis Consortium (CPTAC). Compared to LUSC, LUAD exhibited more substantial differences between patients with and without TP53 mutation in all three aspects. In LUAD, our results imply underlying links between the tissue microbiome and immune cell components in the TIME, and show that the abundance of immune cells is reflected in histology slides. Furthermore, we propose a novel multimodal deep learning model that focuses on histopathology images, which achieves an area under the curve (AUC) of 0.84 in LUAD. In summary, TP53 mutation of LUAD resulted more significant changes in intratumoral microbiota, TIME and histology than that of LUSC. And histopathology images can be used to predict TP53 mutation in LUAD with reasonable accuracy.

TP53 突变是非小细胞肺癌（NSCLC）中最常见的基因突变之一，在肺腺癌（LUAD）和肺鳞癌（LUSC）的发生、发展和预后中起着重要作用。最近的研究还表明，TP53 基因突变对 NSCLC 免疫疗法的反应具有预测价值。众所周知，瘤内微生物群、肿瘤免疫微环境（TIME）和组织学与 TP53 突变在 NSCLC 中的作用有关。然而，这三个因素之间的内在联系及其与 TP53 基因突变之间的潜在相互作用还不十分清楚。此外，利用深度学习方法预测 TP53 突变的潜力尚未得到充分评估。在本文中，我们全面评估了从癌症基因组图谱（TCGA）中获得的992名NSCLC患者的组织微生物组、宿主基因表达特征和组织病理学切片，并利用临床蛋白质组肿瘤分析联盟（CPTAC）中332名NSCLC患者的多组学数据验证了这些发现。与LUSC相比，有TP53基因突变和没有TP53基因突变的LUAD患者在所有三个方面都表现出更大的差异。在LUAD中，我们的研究结果表明组织微生物组与TIME中的免疫细胞成分之间存在潜在联系，并显示免疫细胞的丰度反映在组织学切片中。此外，我们还提出了一种新型多模态深度学习模型，该模型侧重于组织病理学图像，在 LUAD 中的曲线下面积（AUC）达到了 0.84。总之，TP53突变导致LUAD的瘤内微生物群、TIME和组织学发生了比LUSC更显著的变化。组织病理学图像可用于预测LUAD的TP53突变，准确性较高。

{"title":"Unveiling the distinctive variations in multi-omics triggered by TP53 mutation in lung cancer subtypes: An insight from interaction among intratumoral microbiota, tumor microenvironment, and pathology","authors":"Shanhe Tong , Kenan Huang , Weipeng Xing , Yuwen Chu , Chuanqi Nie , Lei Ji , Wenyan Wang , Geng Tian , Bing Wang , Jialiang Yang","doi":"10.1016/j.compbiolchem.2024.108274","DOIUrl":"10.1016/j.compbiolchem.2024.108274","url":null,"abstract":"<div><div>The TP53 mutation is one of the most common gene mutations in non-small cell lung cancer (NSCLC) and plays a significant role in the occurrence, development, and prognosis of both lung adenocarcinoma (LUAD) and lung squamous cell carcinoma (LUSC). Recent studies have also suggested the predictive value of TP53 mutations in the response to immunotherapy for NSCLC. It is known that intratumoral microbiota, tumor immune microenvironment (TIME) and histology are associated with the roles of TP53 mutation in NSCLC. However, the intrinsic associations among these three factors and their underlying interaction with TP53 mutation are not well understood. Additionally, the potential of predicting TP53 mutations using deep learning methods has not yet been fully evaluated. In this paper, we comprehensively evaluated the tissue microbiome, host gene expression characteristics, and histopathological slides of 992 NSCLC patients obtained from the cancer genome atlas (TCGA) and validated the findings using multi-omics data of 332 NSCLC patients from the Clinical Proteomic Tumor Analysis Consortium (CPTAC). Compared to LUSC, LUAD exhibited more substantial differences between patients with and without TP53 mutation in all three aspects. In LUAD, our results imply underlying links between the tissue microbiome and immune cell components in the TIME, and show that the abundance of immune cells is reflected in histology slides. Furthermore, we propose a novel multimodal deep learning model that focuses on histopathology images, which achieves an area under the curve (AUC) of 0.84 in LUAD. In summary, TP53 mutation of LUAD resulted more significant changes in intratumoral microbiota, TIME and histology than that of LUSC. And histopathology images can be used to predict TP53 mutation in LUAD with reasonable accuracy.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"113 ","pages":"Article 108274"},"PeriodicalIF":2.6,"publicationDate":"2024-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142633396","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

Autoencoder-based drug synergy framework for malignant diseases 基于自动编码器的恶性疾病药物协同作用框架。

IF 2.6 4区生物学 Q2 BIOLOGY

Computational Biology and Chemistry

Pub Date : 2024-11-06 DOI: 10.1016/j.compbiolchem.2024.108273

Pooja Rani , Kamlesh Dutta , Vijay Kumar

Drug combination emerges as a viable option for the treatment of malignant diseases. Drug combination outperforms monotherapy by improving therapeutic efficacy, reducing toxicity, and overcoming drug resistance. To find viable drug combinations it is difficult to traverse empirically because of enormous combinational space. Machine learning and deep learning approaches are used to uncover novel synergistic drug combinations in enormous combinational space. Here, AESyn, a novel autoencoder-based drug synergy framework for malignant diseases using a bag of words encoding is proposed. The bag of word encoding technique is used to extract drug-targeted genes. The framework utilized screening data from NCI-ALMANAC, and O’Neil datasets. Autoencoders take drug embeddings with drug-targeted genes as input for processing. The autoencoder in the proposed framework is used to extract drug features. The proposed framework is evaluated on classification and regression metrics. The performance of the proposed framework is compared with existing methods of drug synergy. According to the findings, the proposed framework achieved high performance with an accuracy of 95%, AUROC of 94.2%, and MAPE of 7.2. The autoencoder-based framework for malignant diseases using an encoding technique provides a stable, order-independent drug synergy prediction.

联合用药已成为治疗恶性疾病的可行方案。通过提高疗效、降低毒性和克服耐药性，联合用药优于单一疗法。由于存在巨大的组合空间，要找到可行的药物组合很难通过经验进行追踪。机器学习和深度学习方法可用于在巨大的组合空间中发现新型协同药物组合。在此，我们提出了一种基于自动编码器的新型药物协同框架 AESyn，该框架采用词袋编码技术，适用于恶性疾病。词袋编码技术用于提取药物靶向基因。该框架利用了 NCI-ALMANAC 和 O'Neil 数据集的筛选数据。自动编码器将带有药物靶向基因的药物嵌入作为输入进行处理。拟议框架中的自动编码器用于提取药物特征。拟议框架在分类和回归指标上进行了评估。将拟议框架的性能与现有的药物协同方法进行了比较。结果表明，拟议框架的准确率高达 95%，AUROC 为 94.2%，MAPE 为 7.2。基于自动编码器的恶性疾病框架使用编码技术提供了一种稳定的、与阶次无关的药物协同作用预测方法。

{"title":"Autoencoder-based drug synergy framework for malignant diseases","authors":"Pooja Rani , Kamlesh Dutta , Vijay Kumar","doi":"10.1016/j.compbiolchem.2024.108273","DOIUrl":"10.1016/j.compbiolchem.2024.108273","url":null,"abstract":"<div><div>Drug combination emerges as a viable option for the treatment of malignant diseases. Drug combination outperforms monotherapy by improving therapeutic efficacy, reducing toxicity, and overcoming drug resistance. To find viable drug combinations it is difficult to traverse empirically because of enormous combinational space. Machine learning and deep learning approaches are used to uncover novel synergistic drug combinations in enormous combinational space. Here, AESyn, a novel autoencoder-based drug synergy framework for malignant diseases using a bag of words encoding is proposed. The bag of word encoding technique is used to extract drug-targeted genes. The framework utilized screening data from NCI-ALMANAC, and O’Neil datasets. Autoencoders take drug embeddings with drug-targeted genes as input for processing. The autoencoder in the proposed framework is used to extract drug features. The proposed framework is evaluated on classification and regression metrics. The performance of the proposed framework is compared with existing methods of drug synergy. According to the findings, the proposed framework achieved high performance with an accuracy of 95%, AUROC of 94.2%, and MAPE of 7.2. The autoencoder-based framework for malignant diseases using an encoding technique provides a stable, order-independent drug synergy prediction.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"113 ","pages":"Article 108273"},"PeriodicalIF":2.6,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142633367","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

HiMolformer: Integrating graph and sequence representations for predicting liver microsome stability with SMILES HiMolformer：整合图形和序列表示法，利用 SMILES 预测肝脏微粒体的稳定性。

IF 2.6 4区生物学 Q2 BIOLOGY

Computational Biology and Chemistry

Pub Date : 2024-11-05 DOI: 10.1016/j.compbiolchem.2024.108263

Seokwoo Yun , Gibeom Nam , Jahwan Koo

In the initial stages of drug discovery or pre-clinical studies, understanding the metabolic stability of new molecules is crucial. Recently, research on pre-trained deep learning for molecular property prediction has been actively progressing, with various models being made open-source. However, most of these models rely on either 2D graph or 1D sequence for training, and the representation varies depending on the data format used. Consequently, combining multiple representations can broaden the scope of learning and may potentially be a manageable and most effective method to enhance performance.

Therefore, we propose a novel hybrid model for predicting metabolic stability, which integrates representations from both graph-based and sequence-based models pre-trained for molecular features. This approach utilizes the combined strengths of 2D topological and 1D sequential information of molecules. HiMol, a graph-based graph neural network (GNN) model, and Molformer, a sequence-based Transformer model, were selected for integration, thus we named it HiMolformer. HiMolformer demonstrated superior performance compared to other models. We also focus on regression task for prediction with a empirical dataset from Korea Chemical Bank (KCB), comprising 3,498 molecules with mouse liver microsome (MLM) and human liver microsome (HLM) data obtained from actual metabolic reaction experiments. To the best of our knowledge, it is the first attempt to develop MLM and HLM prediction models using regression with a single SMILES input. The source code of this model is available at https://github.com/YUNSEOKWOO/HiMolformer.

在药物发现或临床前研究的初始阶段，了解新分子的代谢稳定性至关重要。最近，用于分子性质预测的预训练深度学习研究取得了积极进展，各种模型已被开源。然而，这些模型大多依赖于二维图或一维序列进行训练，而且所使用的数据格式不同，表示方法也不尽相同。因此，结合多种表示方法可以拓宽学习范围，并有可能成为一种易于管理且最有效的提高性能的方法。因此，我们提出了一种预测代谢稳定性的新型混合模型，该模型综合了基于图和基于序列的模型的表征，并针对分子特征进行了预先训练。这种方法综合利用了分子的二维拓扑信息和一维序列信息。我们选择了基于图的图神经网络（GNN）模型 HiMol 和基于序列的 Transformer 模型 Molformer 进行整合，因此将其命名为 HiMolformer。与其他模型相比，HiMolformer 表现出了卓越的性能。我们还重点利用韩国化学库（KCB）的经验数据集进行回归预测，该数据集包括从实际代谢反应实验中获得的小鼠肝脏微粒体（MLM）和人类肝脏微粒体（HLM）数据，共 3498 个分子。据我们所知，这是首次尝试利用单一 SMILES 输入使用回归法开发 MLM 和 HLM 预测模型。该模型的源代码见 https://github.com/YUNSEOKWOO/HiMolformer。

{"title":"HiMolformer: Integrating graph and sequence representations for predicting liver microsome stability with SMILES","authors":"Seokwoo Yun , Gibeom Nam , Jahwan Koo","doi":"10.1016/j.compbiolchem.2024.108263","DOIUrl":"10.1016/j.compbiolchem.2024.108263","url":null,"abstract":"<div><div>In the initial stages of drug discovery or pre-clinical studies, understanding the metabolic stability of new molecules is crucial. Recently, research on pre-trained deep learning for molecular property prediction has been actively progressing, with various models being made open-source. However, most of these models rely on either 2D graph or 1D sequence for training, and the representation varies depending on the data format used. Consequently, combining multiple representations can broaden the scope of learning and may potentially be a manageable and most effective method to enhance performance.</div><div>Therefore, we propose a novel hybrid model for predicting metabolic stability, which integrates representations from both graph-based and sequence-based models pre-trained for molecular features. This approach utilizes the combined strengths of 2D topological and 1D sequential information of molecules. HiMol, a graph-based graph neural network (GNN) model, and Molformer, a sequence-based Transformer model, were selected for integration, thus we named it HiMolformer. HiMolformer demonstrated superior performance compared to other models. We also focus on regression task for prediction with a empirical dataset from Korea Chemical Bank (KCB), comprising 3,498 molecules with mouse liver microsome (MLM) and human liver microsome (HLM) data obtained from actual metabolic reaction experiments. To the best of our knowledge, it is the first attempt to develop MLM and HLM prediction models using regression with a single SMILES input. The source code of this model is available at <span><span>https://github.com/YUNSEOKWOO/HiMolformer</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"113 ","pages":"Article 108263"},"PeriodicalIF":2.6,"publicationDate":"2024-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142633383","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

Genome-wide identification of alternative splicing related with transcription factors and splicing regulators in breast cancer stem cells responding to fasting-mimicking diet 全基因组范围内鉴定乳腺癌干细胞对禁食模拟饮食反应中与转录因子和剪接调节因子相关的替代剪接

IF 2.6 4区生物学 Q2 BIOLOGY

Computational Biology and Chemistry

Pub Date : 2024-11-02 DOI: 10.1016/j.compbiolchem.2024.108272

Hongshuang Qin, Qian Zhang, Yanxiang Guo

Fasting-mimicking diet (FMD) can effectively inhibit the viability of breast cancer stem cells (CSCs). However, the molecular mechanisms underlying the inhibitory function of FMD on breast CSCs remain largely unknown. Elucidating the mechanisms by which FMD suppresses breast CSCs is beneficial to targeting breast CSCs. Herein, we systematically analyze alternative splicing and RNA binding protein (RBP) expression in breast CSCs during FMD. The analysis results show that a large number of regulated alternative splicing (RAS) and differentially expressed genes (DEGs) appear responding to FMD. Further studies show that there are potential regulatory relationships between transcription factors (TFs) with RAS (RAS-TFs) and their differentially expressed target genes (RAS-TF-DEGs). Moreover, differentially expressed RNA binding proteins (DERBPs) exhibit potential regulatory functions on RAS-TFs. In short, DERBPs potentially control the alternative splicing of TFs (RAS-TFs), regulating their target gene (RAS-TF-DEG) expression, which leads to the regulation of biological processes in breast CSCs during FMD. In addition, the alternative splicing and DEGs are compared between breast CSCs and differentiated cancer cells during FMD, providing new interpretations for the different responses of the two types of cells. Our studies will shed light on the understanding of the molecular mechanisms underlying breast CSC inhibition induced by FMD.

模拟空腹饮食（FMD）能有效抑制乳腺癌干细胞（CSCs）的活力。然而，FMD抑制乳腺癌干细胞的分子机制仍不为人知。阐明FMD抑制乳腺癌干细胞的机制有利于靶向治疗乳腺癌干细胞。在此，我们系统分析了FMD过程中乳腺CSCs的替代剪接和RNA结合蛋白（RBP）表达。分析结果显示，大量受调控的替代剪接（RAS）和差异表达基因（DEGs）出现了对FMD的响应。进一步的研究表明，带有 RAS 的转录因子（TFs）（RAS-TFs）与其差异表达的靶基因（RAS-TF-DEGs）之间存在潜在的调控关系。此外，差异表达的 RNA 结合蛋白（DERBPs）对 RAS-TFs 具有潜在的调控功能。简而言之，DERBPs 有可能控制 TFs（RAS-TFs）的替代剪接，调节其靶基因（RAS-TF-DEGs）的表达，从而调控 FMD 期间乳腺 CSCs 的生物学过程。此外，我们还比较了乳腺癌 CSCs 和分化癌细胞在 FMD 期间的替代剪接和 DEGs，为这两类细胞的不同反应提供了新的解释。我们的研究将有助于了解 FMD 诱导乳腺癌 CSC 抑制的分子机制。

{"title":"Genome-wide identification of alternative splicing related with transcription factors and splicing regulators in breast cancer stem cells responding to fasting-mimicking diet","authors":"Hongshuang Qin, Qian Zhang, Yanxiang Guo","doi":"10.1016/j.compbiolchem.2024.108272","DOIUrl":"10.1016/j.compbiolchem.2024.108272","url":null,"abstract":"<div><div>Fasting-mimicking diet (FMD) can effectively inhibit the viability of breast cancer stem cells (CSCs). However, the molecular mechanisms underlying the inhibitory function of FMD on breast CSCs remain largely unknown. Elucidating the mechanisms by which FMD suppresses breast CSCs is beneficial to targeting breast CSCs. Herein, we systematically analyze alternative splicing and RNA binding protein (RBP) expression in breast CSCs during FMD. The analysis results show that a large number of regulated alternative splicing (RAS) and differentially expressed genes (DEGs) appear responding to FMD. Further studies show that there are potential regulatory relationships between transcription factors (TFs) with RAS (RAS-TFs) and their differentially expressed target genes (RAS-TF-DEGs). Moreover, differentially expressed RNA binding proteins (DERBPs) exhibit potential regulatory functions on RAS-TFs. In short, DERBPs potentially control the alternative splicing of TFs (RAS-TFs), regulating their target gene (RAS-TF-DEG) expression, which leads to the regulation of biological processes in breast CSCs during FMD. In addition, the alternative splicing and DEGs are compared between breast CSCs and differentiated cancer cells during FMD, providing new interpretations for the different responses of the two types of cells. Our studies will shed light on the understanding of the molecular mechanisms underlying breast CSC inhibition induced by FMD.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"113 ","pages":"Article 108272"},"PeriodicalIF":2.6,"publicationDate":"2024-11-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142592935","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Design and characterization of defined alpha-helix mini-proteins with intrinsic cell permeability 设计并鉴定具有内在细胞渗透性的定义α-螺旋小蛋白。

IF 2.6 4区生物学 Q2 BIOLOGY

Computational Biology and Chemistry

Pub Date : 2024-10-31 DOI: 10.1016/j.compbiolchem.2024.108271

Xin-Chun Chen , Xiang-Wei Kong , Pin Chen , Zi-Qian Li , Nan Huang , Zheng Zhao , Jie Yang , Ge-Xin Zhao , Qing Mo , Yu-Tong Lu , Xiao-Ming Huang , Guo-Kai Feng , Mu-Sheng Zeng

Proteins with intrinsic cell permeability that can access intracellular targets represent a promising strategy for novel drug development; however, a general design principle is still lacking. Here, we established a library of 46,678 de novo-designed mini-proteins and performed cell permeability screening via phage display. Analyses revealed a characteristic neighboring distribution of positive charges across helices among enriched mini-proteins of CPP7, CPP11, CPP55, CPP109 and CPP112. Compared with the state-of-the-art cell-penetrating mini-protein ZF5.3, the optimized mini-protein CPP11D36R exhibited a sevenfold increase in cell permeability. Endocytosis uptake and early endosome release are the key penetrating mechanisms. A machine learning model with high-throughput data achieved an F1 score of 0.41, significantly outperforming the previously reported CPP prediction models, including MLACP, CPPpred and CellPPD, by 41 %. Overall, our findings validate the effectiveness of a helical structure with a cationic distribution as a design principle on a large scale and present a robust approach for the development of cell-permeable mini-protein drugs.

具有内在细胞渗透性并能进入细胞内靶点的蛋白质是一种很有前景的新型药物开发策略；然而，目前仍缺乏一种通用的设计原则。在这里，我们建立了一个包含 46,678 个全新设计的迷你蛋白质库，并通过噬菌体展示进行了细胞渗透性筛选。分析表明，在 CPP7、CPP11、CPP55、CPP109 和 CPP112 的富集迷你蛋白中，正电荷在各螺旋之间呈邻近分布。与最先进的细胞穿透小蛋白 ZF5.3 相比，优化后的小蛋白 CPP11D36R 的细胞渗透性提高了七倍。内吞摄取和早期内质体释放是关键的穿透机制。利用高通量数据建立的机器学习模型的 F1 得分为 0.41，比之前报道的 CPP 预测模型（包括 MLACP、CPPpred 和 CellPPD）高出 41%。总之，我们的研究结果验证了具有阳离子分布的螺旋结构作为大规模设计原则的有效性，并为开发细胞渗透性微型蛋白药物提供了一种稳健的方法。

{"title":"Design and characterization of defined alpha-helix mini-proteins with intrinsic cell permeability","authors":"Xin-Chun Chen , Xiang-Wei Kong , Pin Chen , Zi-Qian Li , Nan Huang , Zheng Zhao , Jie Yang , Ge-Xin Zhao , Qing Mo , Yu-Tong Lu , Xiao-Ming Huang , Guo-Kai Feng , Mu-Sheng Zeng","doi":"10.1016/j.compbiolchem.2024.108271","DOIUrl":"10.1016/j.compbiolchem.2024.108271","url":null,"abstract":"<div><div>Proteins with intrinsic cell permeability that can access intracellular targets represent a promising strategy for novel drug development; however, a general design principle is still lacking. Here, we established a library of 46,678 <em>de novo</em>-designed mini-proteins and performed cell permeability screening via phage display. Analyses revealed a characteristic neighboring distribution of positive charges across helices among enriched mini-proteins of CPP7, CPP11, CPP55, CPP109 and CPP112. Compared with the state-of-the-art cell-penetrating mini-protein ZF5.3, the optimized mini-protein CPP11D36R exhibited a sevenfold increase in cell permeability. Endocytosis uptake and early endosome release are the key penetrating mechanisms. A machine learning model with high-throughput data achieved an F1 score of 0.41, significantly outperforming the previously reported CPP prediction models, including MLACP, CPPpred and CellPPD, by 41 %. Overall, our findings validate the effectiveness of a helical structure with a cationic distribution as a design principle on a large scale and present a robust approach for the development of cell-permeable mini-protein drugs.</div></div>","PeriodicalId":10616,"journal":{"name":"Computational Biology and Chemistry","volume":"113 ","pages":"Article 108271"},"PeriodicalIF":2.6,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142591223","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