Computers in biology and medicine最新文献

Machine learning guided structural dynamics identifies translation elongation factor 1 (EEF1A1) as an immunological biomarker and marine natural products as therapeutic leads for rheumatoid arthritis with major depressive disorder 机器学习引导结构动力学识别翻译延伸因子1 （EEF1A1）作为免疫生物标志物和海洋天然产物作为类风湿关节炎伴重度抑郁症的治疗线索

IF 6.3 2区医学 Q1 BIOLOGY

Computers in biology and medicine

Pub Date : 2026-01-16 DOI: 10.1016/j.compbiomed.2026.111480

Santhiya Panchalingam , Govindaraju Kasivelu , Manikandan Jayaraman , Jeyakanthan Jeyaraman

Rheumatoid arthritis (RA) is a systemic autoimmune disease that predominantly affects synovial joints, especially those of the hands, elbows, wrists, knees, and shoulders. RA frequently co-occurs with major depressive disorder (MDD), amplifying disease burden and complicating clinical outcomes. This study employed a multi-step integrative bioinformatics and structural biology framework to identify candidate molecular biomarkers for RA and MDD. Differential gene expression analysis and weighted gene co-expression network analysis (WGCNA) were performed on the epitranscriptomic dataset. These analyses identified immune-regulatory gene modules that were significantly associated with both phenotypes. Least absolute shrinkage and selection operator (LASSO) regression was applied to select strong, statistically significant biomarkers. The methylated biomarker EEF1A1 was identified, and its structure predicted via AlphaFold, was subjected to in silico structure-based virtual screening (SBVS) against the Comprehensive Marine Natural Product Database (CMNPD). Four marine natural products (CMNPD17984, CMNPD27318, CMNPD26200, and CMNPD26011) showed significant binding affinity for EEF1A1. Furthermore, EEF1A1-MNP complexes were simulated for 150 ns using GROMACS, and PCA-based free energy landscape (FEL) analyses were performed to characterize the dynamic behavior and identify energy minima. This integrated computational approach provides a comprehensive platform for biomarker discovery and validation in RA and MDD, with potential applications in early diagnosis, therapeutic targeting, and precision medicine.

类风湿性关节炎（RA）是一种系统性自身免疫性疾病，主要影响滑膜关节，特别是手、肘关节、手腕、膝盖和肩膀。RA经常与重度抑郁症（MDD）共同发生，加重了疾病负担并使临床结果复杂化。本研究采用多步骤综合生物信息学和结构生物学框架来确定RA和MDD的候选分子生物标志物。对表转录组数据集进行差异基因表达分析和加权基因共表达网络分析（WGCNA）。这些分析确定了与两种表型显著相关的免疫调节基因模块。最小绝对收缩和选择算子（LASSO）回归应用于选择强的，具有统计学意义的生物标志物。鉴定了甲基化的生物标志物EEF1A1，并通过AlphaFold预测了其结构，并针对综合海洋天然产品数据库（CMNPD）进行了基于硅结构的虚拟筛选（SBVS）。四种海洋天然产物（CMNPD17984、CMNPD27318、CMNPD26200和CMNPD26011）对EEF1A1具有显著的结合亲和力。此外，利用GROMACS对EEF1A1-MNP配合物进行了150 ns的模拟，并进行了基于pca的自由能景观（FEL）分析，以表征其动态行为并识别能量最小值。这种综合计算方法为RA和MDD的生物标志物发现和验证提供了全面的平台，在早期诊断、治疗靶向和精准医学方面具有潜在的应用前景。

{"title":"Machine learning guided structural dynamics identifies translation elongation factor 1 (EEF1A1) as an immunological biomarker and marine natural products as therapeutic leads for rheumatoid arthritis with major depressive disorder","authors":"Santhiya Panchalingam , Govindaraju Kasivelu , Manikandan Jayaraman , Jeyakanthan Jeyaraman","doi":"10.1016/j.compbiomed.2026.111480","DOIUrl":"10.1016/j.compbiomed.2026.111480","url":null,"abstract":"<div><div>Rheumatoid arthritis (RA) is a systemic autoimmune disease that predominantly affects synovial joints, especially those of the hands, elbows, wrists, knees, and shoulders. RA frequently co-occurs with major depressive disorder (MDD), amplifying disease burden and complicating clinical outcomes. This study employed a multi-step integrative bioinformatics and structural biology framework to identify candidate molecular biomarkers for RA and MDD. Differential gene expression analysis and weighted gene co-expression network analysis (WGCNA) were performed on the epitranscriptomic dataset. These analyses identified immune-regulatory gene modules that were significantly associated with both phenotypes. Least absolute shrinkage and selection operator (LASSO) regression was applied to select strong, statistically significant biomarkers. The methylated biomarker EEF1A1 was identified, and its structure predicted via AlphaFold, was subjected to <em>in silico</em> structure-based virtual screening (SBVS) against the Comprehensive Marine Natural Product Database (CMNPD). Four marine natural products (CMNPD17984, CMNPD27318, CMNPD26200, and CMNPD26011) showed significant binding affinity for EEF1A1. Furthermore, EEF1A1-MNP complexes were simulated for 150 ns using GROMACS, and PCA-based free energy landscape (FEL) analyses were performed to characterize the dynamic behavior and identify energy minima. This integrated computational approach provides a comprehensive platform for biomarker discovery and validation in RA and MDD, with potential applications in early diagnosis, therapeutic targeting, and precision medicine.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"203 ","pages":"Article 111480"},"PeriodicalIF":6.3,"publicationDate":"2026-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145976109","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

IntNet: Lightweight yet high-performance deep learning system for intuitive radar patterns analysis and human fall detection internet：轻量级但高性能的深度学习系统，用于直观的雷达模式分析和人体跌倒检测

IF 6.3 2区医学 Q1 BIOLOGY

Computers in biology and medicine

Pub Date : 2026-01-16 DOI: 10.1016/j.compbiomed.2026.111485

Malek Y. Almallah , Belal H. Sababha

The growing trend of solitary living among the elderly and young, coupled with the high risk of falls leading to injuries and death, highlights the need for fall monitoring systems. Emphasizing individuals' privacy and comfort, these systems should rely on radar sensors instead of visual-based, acoustic-based, or wearable solutions. Current radar-based systems have yet to reach satisfactory real-world performance. This work proposes a radar-based fall detection system that offers superior performance in complex real-world scenarios while maintaining edge computing capabilities and utilizing minimal hardware resources. The proposed deep learning system achieved a recall of 98.99 % and a precision of 99.32 %. These unprecedented performance numbers are measured on the proposed dataset, which is the most real-life representative dataset in the literature. The system has 211.8k parameters and ∼8.84 M Floating Point Operations (FLOPs), achieving an edge computing capability. Moreover, the efficient model construction eliminates redundant computation in real-time operation. Furthermore, this work proposes a novel performance comparison methodology that can be used in all classification problems. This methodology compares performance metrics, which are calculated based on different datasets, with a high level of fairness.

老年人和年轻人独居的趋势日益增加，再加上跌倒导致受伤和死亡的高风险，凸显了对跌倒监测系统的需求。这些系统强调个人隐私和舒适，应该依靠雷达传感器，而不是基于视觉、声学或可穿戴的解决方案。目前基于雷达的系统尚未达到令人满意的实际性能。这项工作提出了一种基于雷达的跌倒检测系统，该系统在复杂的现实场景中提供卓越的性能，同时保持边缘计算能力并利用最少的硬件资源。所提出的深度学习系统达到了98.99%的召回率和99.32%的准确率。这些前所未有的性能数字是在提议的数据集上测量的，这是文献中最具现实代表性的数据集。该系统具有211.8k个参数和~ 8.84 M浮点运算（FLOPs），实现了边缘计算能力。此外，高效的模型构建消除了实时操作中的冗余计算。此外，这项工作提出了一种新的性能比较方法，可用于所有分类问题。这种方法比较了基于不同数据集计算的性能指标，具有高度的公平性。

{"title":"IntNet: Lightweight yet high-performance deep learning system for intuitive radar patterns analysis and human fall detection","authors":"Malek Y. Almallah , Belal H. Sababha","doi":"10.1016/j.compbiomed.2026.111485","DOIUrl":"10.1016/j.compbiomed.2026.111485","url":null,"abstract":"<div><div>The growing trend of solitary living among the elderly and young, coupled with the high risk of falls leading to injuries and death, highlights the need for fall monitoring systems. Emphasizing individuals' privacy and comfort, these systems should rely on radar sensors instead of visual-based, acoustic-based, or wearable solutions. Current radar-based systems have yet to reach satisfactory real-world performance. This work proposes a radar-based fall detection system that offers superior performance in complex real-world scenarios while maintaining edge computing capabilities and utilizing minimal hardware resources. The proposed deep learning system achieved a recall of 98.99 % and a precision of 99.32 %. These unprecedented performance numbers are measured on the proposed dataset, which is the most real-life representative dataset in the literature. The system has 211.8k parameters and ∼8.84 M Floating Point Operations (FLOPs), achieving an edge computing capability. Moreover, the efficient model construction eliminates redundant computation in real-time operation. Furthermore, this work proposes a novel performance comparison methodology that can be used in all classification problems. This methodology compares performance metrics, which are calculated based on different datasets, with a high level of fairness.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"203 ","pages":"Article 111485"},"PeriodicalIF":6.3,"publicationDate":"2026-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145976106","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Amplitude symbolic analysis: a tool for the evaluation of the autonomic function complementary to traditional symbolic approach 振幅符号分析：一种与传统符号方法互补的评价自主神经功能的工具

IF 6.3 2区医学 Q1 BIOLOGY

Computers in biology and medicine

Pub Date : 2026-01-16 DOI: 10.1016/j.compbiomed.2026.111473

Alberto Porta , Beatrice Cairo , Vlasta Bari , Chiara Arduino , Ilaria Burzo , Beatrice De Maria , Paolo Castiglioni , Luc Quintin , Aparecida Maria Catai , Franca Barbic , Raffaello Furlan

Symbolic analysis (SA) infers cardiac control from spontaneous stationary sequences of heart period (HP) by estimating the probability of symbolic pattern classes. Unfortunately, SA does not assess the fraction of HP variability associated with symbolic pattern families. This study proposes amplitude SA (ASA) accounting for absolute changes between consecutive HPs. ASA leverages uniform 6-bin quantization to symbolize HP, the delay embedding procedure to form length-3 symbolic patterns and a traditional strategy to group symbolic patterns into four classes families according to number and sign of variations between adjacent symbols. ASA computes the fraction of variance associated with symbolic pattern classes. ASA was applied to HP variability derived from: 1) healthy subjects during pharmacological challenges (n = 9; age: 25–46 yrs, 9 males); 2) healthy subjects during graded postural stimuli (n = 19; age: 21–48 yrs, 8 males); 3) Parkinson disease (PD) patients (n = 12; age: 55–79 yrs, 8 males) and matched healthy controls (n = 12; age: 58–72 yrs, 7 males). We computed both global and local ASA markers and we compared them with SA indexes. Over stationary HP series we found that: i) ASA provides a general method to decompose HP variance according to symbolic pattern classes; ii) ASA is useful to describe cardiac control; iii) ASA indexes are complementary to SA markers; iv) ASA emphasizes the link of HP variability markers expressed in absolute units with vagal control; v) global and local ASA approaches provide similar information. SA and ASA should be utilized concomitantly for a deeper characterization of cardiac control from spontaneous HP fluctuations.

符号分析（symbol analysis， SA）通过估计符号模式类的概率，从自发平稳的心期序列（HP）中推断出心脏控制。不幸的是，SA并没有评估与符号模式家族相关的HP变异的比例。本研究提出用振幅SA （ASA）来计算连续hp之间的绝对变化。ASA利用均匀6 bin量化对HP进行符号化，利用延迟嵌入程序形成长度为3的符号模式，利用传统策略根据相邻符号之间的变化数和符号将符号模式分为四类族。ASA计算与符号模式类相关的方差的分数。ASA应用于HP变异性的来源：1)健康受试者在药理学挑战期间（n = 9，年龄：25-46岁，9名男性）；2)健康受试者接受分级体位刺激（n = 19，年龄21 ~ 48岁，男性8例）；3)帕金森病（PD）患者（n = 12，年龄55-79岁，男性8人）和匹配的健康对照（n = 12，年龄58-72岁，男性7人）。我们计算了全局和局部ASA标记，并将它们与SA指数进行了比较。对于平稳HP序列，我们发现：i) ASA提供了一种按照符号模式类分解HP方差的通用方法；ii) ASA可用于描述心脏控制；iii) ASA指数与SA标记物是互补的；iv) ASA强调以绝对单位表达的HP变异性标记与迷走神经控制的联系；v)全球和本地ASA方法提供类似的信息。SA和ASA应同时使用，以更深入地表征自发HP波动引起的心脏控制。

{"title":"Amplitude symbolic analysis: a tool for the evaluation of the autonomic function complementary to traditional symbolic approach","authors":"Alberto Porta , Beatrice Cairo , Vlasta Bari , Chiara Arduino , Ilaria Burzo , Beatrice De Maria , Paolo Castiglioni , Luc Quintin , Aparecida Maria Catai , Franca Barbic , Raffaello Furlan","doi":"10.1016/j.compbiomed.2026.111473","DOIUrl":"10.1016/j.compbiomed.2026.111473","url":null,"abstract":"<div><div>Symbolic analysis (SA) infers cardiac control from spontaneous stationary sequences of heart period (HP) by estimating the probability of symbolic pattern classes. Unfortunately, SA does not assess the fraction of HP variability associated with symbolic pattern families. This study proposes amplitude SA (ASA) accounting for absolute changes between consecutive HPs. ASA leverages uniform 6-bin quantization to symbolize HP, the delay embedding procedure to form length-3 symbolic patterns and a traditional strategy to group symbolic patterns into four classes families according to number and sign of variations between adjacent symbols. ASA computes the fraction of variance associated with symbolic pattern classes. ASA was applied to HP variability derived from: 1) healthy subjects during pharmacological challenges (n = 9; age: 25–46 yrs, 9 males); 2) healthy subjects during graded postural stimuli (n = 19; age: 21–48 yrs, 8 males); 3) Parkinson disease (PD) patients (n = 12; age: 55–79 yrs, 8 males) and matched healthy controls (n = 12; age: 58–72 yrs, 7 males). We computed both global and local ASA markers and we compared them with SA indexes. Over stationary HP series we found that: i) ASA provides a general method to decompose HP variance according to symbolic pattern classes; ii) ASA is useful to describe cardiac control; iii) ASA indexes are complementary to SA markers; iv) ASA emphasizes the link of HP variability markers expressed in absolute units with vagal control; v) global and local ASA approaches provide similar information. SA and ASA should be utilized concomitantly for a deeper characterization of cardiac control from spontaneous HP fluctuations.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"203 ","pages":"Article 111473"},"PeriodicalIF":6.3,"publicationDate":"2026-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145976663","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Unravelling the structural impact of progesterone receptor mutations in myoma and progesterone intolerance through computational modeling 通过计算模型揭示肌瘤和黄体酮不耐受中黄体酮受体突变的结构影响

IF 6.3 2区医学 Q1 BIOLOGY

Computers in biology and medicine

Pub Date : 2026-01-15 DOI: 10.1016/j.compbiomed.2026.111476

F. Saritha , R. Aswath Kumar , K.V. Dileep

Progesterone (P4) is a steroid hormone involved in the regulation of female reproductive functions. The endogenous progesterone receptor (PR), a member of the nuclear receptor family of ligand-dependent transcription regulators responsible for P4 action in the body through the ‘ligand binding domain’ (LBD). PR isoforms, PR-A and PR-B, are encoded by a single gene, PGR and variations in this gene can disrupt cellular signaling. In the current study, putative disease-causing mutations on PR has been identified through computationally and its mechanistic effects were explored using structural bioinformatics tools. Studies suggested that 11 of 66 missense variants (within the LBD) induce structural destabilization and were identified as potentially deleterious. Our ensemble docking suggested that these variations have a limited impact on P4 binding, however they significantly disrupt the binding of co-activators as evident by the protein-peptide docking. The binding of co-activators to the PR is the determining factor for the P4 signaling. Finally, based on the free energy of binding, we proposed two variations such as R869H and C798Y could cause myoma and progesterone tolerance conditions respectively. These findings were further validated through the use of allostery predictions. Our results reveal distinct mechanisms by which PR mutations modulate receptor function, laying the framework for future mechanistic studies and therapeutic development for PR-associated reproductive disorders.

黄体酮（P4）是一种类固醇激素，参与调节女性生殖功能。内源性孕激素受体（PR）是核受体家族的一员，是配体依赖性转录调节因子，通过“配体结合域”（LBD）在体内负责P4的作用。PR亚型PR- a和PR- b由单个基因PGR编码，该基因的变异可以破坏细胞信号传导。在目前的研究中，通过计算确定了PR上可能的致病突变，并利用结构生物信息学工具探索了其机制作用。研究表明，66个错义变异中有11个（在LBD内）诱导结构不稳定，并被确定为潜在的有害变异。我们的集合对接表明，这些变异对P4结合的影响有限，但它们显著破坏了共激活物的结合，这一点从蛋白-肽对接中可以看出。共激活剂与PR的结合是P4信号转导的决定因素。最后，基于结合自由能，我们提出了R869H和C798Y两种变异分别可引起肌瘤和黄体酮耐受条件。这些发现通过使用变构预测得到进一步验证。我们的研究结果揭示了PR突变调节受体功能的独特机制，为PR相关生殖疾病的未来机制研究和治疗开发奠定了框架。

{"title":"Unravelling the structural impact of progesterone receptor mutations in myoma and progesterone intolerance through computational modeling","authors":"F. Saritha , R. Aswath Kumar , K.V. Dileep","doi":"10.1016/j.compbiomed.2026.111476","DOIUrl":"10.1016/j.compbiomed.2026.111476","url":null,"abstract":"<div><div>Progesterone (P4) is a steroid hormone involved in the regulation of female reproductive functions. The endogenous progesterone receptor (PR), a member of the nuclear receptor family of ligand-dependent transcription regulators responsible for P4 action in the body through the ‘ligand binding domain’ (LBD). PR isoforms, PR-A and PR-B, are encoded by a single gene, PGR and variations in this gene can disrupt cellular signaling. In the current study, putative disease-causing mutations on PR has been identified through computationally and its mechanistic effects were explored using structural bioinformatics tools. Studies suggested that 11 of 66 missense variants (within the LBD) induce structural destabilization and were identified as potentially deleterious. Our ensemble docking suggested that these variations have a limited impact on P4 binding, however they significantly disrupt the binding of co-activators as evident by the protein-peptide docking. The binding of co-activators to the PR is the determining factor for the P4 signaling. Finally, based on the free energy of binding, we proposed two variations such as R869H and C798Y could cause myoma and progesterone tolerance conditions respectively. These findings were further validated through the use of allostery predictions. Our results reveal distinct mechanisms by which PR mutations modulate receptor function, laying the framework for future mechanistic studies and therapeutic development for PR-associated reproductive disorders.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"202 ","pages":"Article 111476"},"PeriodicalIF":6.3,"publicationDate":"2026-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145974290","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Accurate prediction of anticancer peptides using a stacking ensemble of convolutional and transformer models with conjoint sequence representations 使用卷积和变压器模型的叠加集合与联合序列表示精确预测抗癌肽

IF 6.3 2区医学 Q1 BIOLOGY

Computers in biology and medicine

Pub Date : 2026-01-14 DOI: 10.1016/j.compbiomed.2026.111463

Huynh Anh Duy , Phurinut Khampasri , Pimmada Janthanet , Patlissa Pattiyamongkhonkul , Tarapong Srisongkram

We present a high-performance predictive framework for anticancer peptide (ACP) identification, based on a stacking ensemble learning approach that synergistically combines convolutional neural networks and transformer models using a random forest as a meta-classifier. This architecture is driven by conjoint sequence representations that integrate both one-hot encoding and pre-trained evolutionary scale modeling embeddings, enabling the extraction of complementary local and global features from peptide sequences. Our proposed model achieved a robust accuracy of 88.9% on the primary ACP data set, while maintaining competitive or superior performance across multiple external benchmark data sets, with accuracies ranging from 83.2% to 95.2%, highlighting its strong generalization capability on par with the state-of-the-art models. To demonstrate translational relevance, the model was applied to a curated set of clinically approved and candidate ACPs, producing probabilistic scores to support experimental prioritization. To further enhance model interpretability, SHapley Additive exPlanations analysis was employed, revealing lysine as a consistently influential residue, alongside other positively charged and hydrophobic amino acids. These findings not only corroborate known mechanistic insights into ACP-membrane interactions but also highlight the utility of model-derived feature importance in guiding peptide design. Taken together, this work introduces a robust, interpretable, and generalizable approach for computational ACP prediction, offering valuable implications for peptide-based anticancer drug discovery. To enhance the accessibility and translational potential of our model, we developed an interactive web-based prediction tool, named ACPredictor, for the identification of ACPs. This platform is freely available at https://acpredictor.streamlit.app/.

我们提出了一种用于抗癌肽（ACP）识别的高性能预测框架，该框架基于堆叠集成学习方法，该方法将卷积神经网络和变压器模型协同结合，使用随机森林作为元分类器。该结构由整合了单热编码和预训练进化尺度建模嵌入的联合序列表示驱动，能够从肽序列中提取互补的局部和全局特征。我们提出的模型在主要ACP数据集上实现了88.9%的鲁棒准确率，同时在多个外部基准数据集上保持了竞争或优越的性能，准确率范围从83.2%到95.2%，突出了其与最先进模型相当的强大泛化能力。为了证明翻译相关性，该模型被应用于一组经过筛选的临床批准和候选acp，产生概率分数以支持实验优先级。为了进一步提高模型的可解释性，采用了SHapley加性解释分析，揭示赖氨酸与其他带正电和疏水的氨基酸一起始终是有影响的残基。这些发现不仅证实了acp -膜相互作用的已知机制见解，而且强调了模型衍生特征在指导肽设计中的重要性。综上所述，这项工作为计算ACP预测引入了一种强大的、可解释的和可推广的方法，为基于肽的抗癌药物的发现提供了有价值的意义。为了提高我们模型的可及性和转化潜力，我们开发了一个交互式的基于网络的预测工具，名为ACPredictor，用于识别acp。该平台可在https://acpredictor.streamlit.app/免费获得。

{"title":"Accurate prediction of anticancer peptides using a stacking ensemble of convolutional and transformer models with conjoint sequence representations","authors":"Huynh Anh Duy , Phurinut Khampasri , Pimmada Janthanet , Patlissa Pattiyamongkhonkul , Tarapong Srisongkram","doi":"10.1016/j.compbiomed.2026.111463","DOIUrl":"10.1016/j.compbiomed.2026.111463","url":null,"abstract":"<div><div>We present a high-performance predictive framework for anticancer peptide (ACP) identification, based on a stacking ensemble learning approach that synergistically combines convolutional neural networks and transformer models using a random forest as a meta-classifier. This architecture is driven by conjoint sequence representations that integrate both one-hot encoding and pre-trained evolutionary scale modeling embeddings, enabling the extraction of complementary local and global features from peptide sequences. Our proposed model achieved a robust accuracy of 88.9% on the primary ACP data set, while maintaining competitive or superior performance across multiple external benchmark data sets, with accuracies ranging from 83.2% to 95.2%, highlighting its strong generalization capability on par with the state-of-the-art models. To demonstrate translational relevance, the model was applied to a curated set of clinically approved and candidate ACPs, producing probabilistic scores to support experimental prioritization. To further enhance model interpretability, SHapley Additive exPlanations analysis was employed, revealing lysine as a consistently influential residue, alongside other positively charged and hydrophobic amino acids. These findings not only corroborate known mechanistic insights into ACP-membrane interactions but also highlight the utility of model-derived feature importance in guiding peptide design. Taken together, this work introduces a robust, interpretable, and generalizable approach for computational ACP prediction, offering valuable implications for peptide-based anticancer drug discovery. To enhance the accessibility and translational potential of our model, we developed an interactive web-based prediction tool, named <em>ACPredictor</em>, for the identification of ACPs. This platform is freely available at <span><span>https://acpredictor.streamlit.app/</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"202 ","pages":"Article 111463"},"PeriodicalIF":6.3,"publicationDate":"2026-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145974291","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

DeeBayes: An interpretable deep Bayesian network for ECG signal restoration DeeBayes：一个用于心电信号恢复的可解释的深度贝叶斯网络

IF 6.3 2区医学 Q1 BIOLOGY

Computers in biology and medicine

Pub Date : 2026-01-14 DOI: 10.1016/j.compbiomed.2025.111424

Hazique Aetesam , Mohammad Amber Rizvi

The electrocardiogram (ECG) is a valuable and non-invasive tool for detecting and preventing arrhythmias. However, in real-world situations, ECG signals are often contaminated by various types of noise, which can lead to clinical misdiagnoses. As a result, significant attention is given to developing methods to denoise ECG signals to ensure an accurate diagnosis and prognosis. This paper aims to develop a novel variational inference method that combines noise estimation and signal denoising within a unified Bayesian framework, specifically designed to effectively denoise ECG signals from any patient. Our method, the Deep Bayesian ECG Signal Restoration Network (DeeBayes), takes advantage of data-driven deep learning techniques, enabling efficient denoising through its explicit expression of posterior probabilities. Furthermore, DeeBayes incorporates the benefits of traditional model-driven approaches, particularly the strong generalization capabilities of generative models. This ensures that DeeBayes is both interpretable and adaptive for accurately estimating and removing complex non-independent and identically distributed (non-iid) noise patterns. Qualitative and quantitative experimental results conducted on noisy ECG signals with varying input signal-to-noise ratio (SNR) levels demonstrate that the proposed approach outperforms other state-of-the-art ECG signal restoration models, including those based on fully connected neural networks and convolutional neural networks.

Source code is available at: https://github.com/marizvi/DeeBayes.

心电图（ECG）是一种有价值的、无创的检测和预防心律失常的工具。然而，在现实世界中，心电信号经常被各种类型的噪声污染，这可能导致临床误诊。因此，为了保证准确的诊断和预后，对心电信号进行降噪的方法得到了极大的重视。本文旨在开发一种新的变分推理方法，在统一的贝叶斯框架内将噪声估计和信号去噪结合起来，专门用于对任何患者的心电信号进行有效的去噪。我们的方法，深度贝叶斯心电信号恢复网络（DeeBayes），利用数据驱动的深度学习技术，通过其后验概率的显式表达实现有效的去噪。此外，DeeBayes结合了传统模型驱动方法的优点，特别是生成模型的强大泛化能力。这确保了DeeBayes对于准确估计和去除复杂的非独立和同分布（非id）噪声模式既可解释又自适应。在不同输入信噪比（SNR）水平的有噪声心电信号上进行的定性和定量实验结果表明，该方法优于其他最先进的心电信号恢复模型，包括基于全连接神经网络和卷积神经网络的模型。源代码可从https://github.com/marizvi/DeeBayes获得。

{"title":"DeeBayes: An interpretable deep Bayesian network for ECG signal restoration","authors":"Hazique Aetesam , Mohammad Amber Rizvi","doi":"10.1016/j.compbiomed.2025.111424","DOIUrl":"10.1016/j.compbiomed.2025.111424","url":null,"abstract":"<div><div>The electrocardiogram (ECG) is a valuable and non-invasive tool for detecting and preventing arrhythmias. However, in real-world situations, ECG signals are often contaminated by various types of noise, which can lead to clinical misdiagnoses. As a result, significant attention is given to developing methods to denoise ECG signals to ensure an accurate diagnosis and prognosis. This paper aims to develop a novel variational inference method that combines noise estimation and signal denoising within a unified Bayesian framework, specifically designed to effectively denoise ECG signals from any patient. Our method, the Deep Bayesian ECG Signal Restoration Network <em>(DeeBayes)</em>, takes advantage of data-driven deep learning techniques, enabling efficient denoising through its explicit expression of posterior probabilities. Furthermore, <em>DeeBayes</em> incorporates the benefits of traditional model-driven approaches, particularly the strong generalization capabilities of generative models. This ensures that <em>DeeBayes</em> is both interpretable and adaptive for accurately estimating and removing complex non-independent and identically distributed (non-iid) noise patterns. Qualitative and quantitative experimental results conducted on noisy ECG signals with varying input signal-to-noise ratio (SNR) levels demonstrate that the proposed approach outperforms other state-of-the-art ECG signal restoration models, including those based on fully connected neural networks and convolutional neural networks.</div><div><strong>Source code is available at:</strong> <span><span>https://github.com/marizvi/DeeBayes</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"202 ","pages":"Article 111424"},"PeriodicalIF":6.3,"publicationDate":"2026-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145974289","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The halophile protein database 2.0: A comprehensive resource of physico-chemical properties of halophilic proteins 嗜盐蛋白数据库2.0：一个关于嗜盐蛋白理化性质的综合资源

IF 6.3 2区医学 Q1 BIOLOGY

Computers in biology and medicine

Pub Date : 2026-01-14 DOI: 10.1016/j.compbiomed.2026.111477

Sudhir Srivastava , Mohammad Samir Farooqi , Deepa Bhatt, Priyanka Balley, Jyotika Bhati, Anu Sharma, Dwijesh Chandra Mishra, Krishna Kumar Chaturvedi, Shashi Bhushan Lal, Girish Kumar Jha

Halophilic organisms are among the oldest microorganisms on earth which thrive in extreme saline environments through unique physiological and biochemical mechanisms. Halophiles are classified into extreme, moderate, and mild groups based on their salt tolerance. Proteins play a crucial role in their adaptation by undergoing structural modifications and cellular alterations and allowing them to maintain stability and functionality in high-saline conditions. To support research on halophilic adaptations, we have developed an advanced Halophile Protein Database 2.0 (HProtDB 2.0) which serves as a comprehensive resource for analyzing the physicochemical properties of halophilic proteins. This database provides extensive data on diverse physicochemical properties, including molecular weight, theoretical pI, amino acid composition, atomic composition, instability index, aliphatic index, extinction coefficients, estimated half-life, and the grand average of the hydropathicity index. These properties help researchers understand how halophilic proteins maintain their structure and function by influencing salt-ion interaction, solubility and protein folding. HProtDB 2.0 significantly expands the earlier version by increasing its dataset from 59,897 protein sequences (21 strains) to 777,979 protein sequences (54 strains) with enhanced precision in physicochemical properties. We developed R programs to compute physicochemical properties of halophilic proteins. Additionally, we designed the database using a three-tier web architecture, integrating HTML, CSS, and JavaScript for the front-end, PHP for server-side scripting, and MySQL for data storage. Researchers can access HProtDB 2.0 at: http://proteindb2.iari.res.in; http://webapp.cabgrid.res.in/proteindb2.0/. This database will serve as valuable tool for researchers seeking information on the characteristics and features of proteins adapted to salt conditions.

嗜盐生物是地球上最古老的微生物之一，它们通过独特的生理和生化机制在极端盐环境中茁壮成长。根据嗜盐菌的耐盐性，可分为极端、中等和温和三类。蛋白质通过结构修饰和细胞改变，使其在高盐条件下保持稳定性和功能，在适应中起着至关重要的作用。为了支持对嗜盐适应性的研究，我们开发了一个先进的亲盐蛋白数据库2.0 (HProtDB 2.0)，作为分析亲盐蛋白的物理化学性质的综合资源。该数据库提供了各种物理化学性质的广泛数据，包括分子量、理论pI、氨基酸组成、原子组成、不稳定性指数、脂肪族指数、消光系数、估计半衰期和亲水性指数的大平均值。这些特性有助于研究人员了解嗜盐蛋白如何通过影响盐离子相互作用、溶解度和蛋白质折叠来维持其结构和功能。HProtDB 2.0大大扩展了早期版本，将其数据集从59,897个蛋白质序列（21个菌株）增加到777,979个蛋白质序列（54个菌株），提高了物理化学性质的精度。我们开发了R程序来计算嗜盐蛋白的物理化学性质。此外，我们使用三层web架构设计数据库，将HTML、CSS和JavaScript集成为前端，PHP用于服务器端脚本，MySQL用于数据存储。研究人员可以访问HProtDB 2.0: http://proteindb2.iari.res.in；http://webapp.cabgrid.res.in/proteindb2.0/。该数据库将为研究人员寻找适应盐条件的蛋白质的特征和特征的信息提供有价值的工具。

{"title":"The halophile protein database 2.0: A comprehensive resource of physico-chemical properties of halophilic proteins","authors":"Sudhir Srivastava , Mohammad Samir Farooqi , Deepa Bhatt, Priyanka Balley, Jyotika Bhati, Anu Sharma, Dwijesh Chandra Mishra, Krishna Kumar Chaturvedi, Shashi Bhushan Lal, Girish Kumar Jha","doi":"10.1016/j.compbiomed.2026.111477","DOIUrl":"10.1016/j.compbiomed.2026.111477","url":null,"abstract":"<div><div>Halophilic organisms are among the oldest microorganisms on earth which thrive in extreme saline environments through unique physiological and biochemical mechanisms. Halophiles are classified into extreme, moderate, and mild groups based on their salt tolerance. Proteins play a crucial role in their adaptation by undergoing structural modifications and cellular alterations and allowing them to maintain stability and functionality in high-saline conditions. To support research on halophilic adaptations, we have developed an advanced Halophile Protein Database 2.0 (HProtDB 2.0) which serves as a comprehensive resource for analyzing the physicochemical properties of halophilic proteins. This database provides extensive data on diverse physicochemical properties, including molecular weight, theoretical pI, amino acid composition, atomic composition, instability index, aliphatic index, extinction coefficients, estimated half-life, and the grand average of the hydropathicity index. These properties help researchers understand how halophilic proteins maintain their structure and function by influencing salt-ion interaction, solubility and protein folding. HProtDB 2.0 significantly expands the earlier version by increasing its dataset from 59,897 protein sequences (21 strains) to 777,979 protein sequences (54 strains) with enhanced precision in physicochemical properties. We developed R programs to compute physicochemical properties of halophilic proteins. Additionally, we designed the database using a three-tier web architecture, integrating HTML, CSS, and JavaScript for the front-end, PHP for server-side scripting, and MySQL for data storage. Researchers can access HProtDB 2.0 at: <span><span>http://proteindb2.iari.res.in</span><svg><path></path></svg></span>; <span><span>http://webapp.cabgrid.res.in/proteindb2.0/</span><svg><path></path></svg></span>. This database will serve as valuable tool for researchers seeking information on the characteristics and features of proteins adapted to salt conditions.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"202 ","pages":"Article 111477"},"PeriodicalIF":6.3,"publicationDate":"2026-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145974292","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Demystifying the implications of disease-susceptible missense SNPs within CTLA-4 ligand binding domain and its interaction towards B7-1 protein complex: Bioinformatics-driven evidence 揭开CTLA-4配体结合域内疾病易感错义snp的含义及其与B7-1蛋白复合物的相互作用：生物信息学驱动的证据

IF 6.3 2区医学 Q1 BIOLOGY

Computers in biology and medicine

Pub Date : 2026-01-14 DOI: 10.1016/j.compbiomed.2026.111459

V. Shamala , S. Preethi , V. Hemamalini , S. Asha Devi

Alteration of a nucleotide within a triplet codon results in substitution of a different amino acid in the protein sequence, collectively termed as missense or non-synonymous Single-Nucleotide Polymorphisms (nsSNPs). Cytoplasmic T Lymphocytes Antigen-4 (CTLA-4) gene encodes a transmembrane protein expressed on activated T cells. CTLA-4 receptor acts as an immunoregulatory molecule that prompts immunological self-tolerance by rapidly inhibiting T cell-mediated immune responses, via inactivation and elimination of T cells. Polymorphism within CTLA-4 coding region could efficiently disrupt trans-endocytosis process by decreasing its interaction towards B7 ligands (B7-1: CD80 and B7-2: CD86) molecules expressed on Antigen Presenting Cells (APCs). In the present study, we utilized several computational techniques to predict the highly disease-susceptible nsSNPs that potentially impact on structure and function of CTLA-4 protein. Followed by computational docking and Molecular Dynamics (MD) simulations for CTLA-4/CD80 protein complex were conducted. Our research findings reveal that seventeen nsSNPs were found to be highly pathogenic and structurally destabilizing CTLA-4 protein. Subsequently, an evolutionary ConSurf profile reveals that nine nsSNPs were highly conserved and also affect bio-physicochemical properties, three-dimensional RNA structure, post-translational modification sites, secondary and tertiary structure of CTLA-4 protein. Molecular docking of CTLA-4/CD80 protein complex indicates that rs1553657429-P137L and rs1356678649-N145H nsSNPs have efficiently decreased the binding affinity towards B7-1 protein. The MD simulation also reveal CTLA-4 P137L, located within ligand-binding domain (MYPPPY motif) and N145H at N-glycosylation site, were significantly considered to be high-risk nsSNPs that interfere association with B7-1 protein by decreasing structural stability and flexibility of CTLA-4 protein.

三联体密码子内核苷酸的改变导致蛋白质序列中不同氨基酸的替代，统称为错义或非同义单核苷酸多态性（nsSNPs）。细胞质T淋巴细胞抗原-4 （CTLA-4）基因编码一种在活化T细胞上表达的跨膜蛋白。CTLA-4受体作为一种免疫调节分子，通过灭活和消除T细胞，快速抑制T细胞介导的免疫反应，从而促进免疫自身耐受。CTLA-4编码区的多态性通过降低其与抗原呈递细胞（APCs）上表达的B7配体（B7-1: CD80和B7-2: CD86）分子的相互作用，有效地破坏了反式内吞过程。在本研究中，我们利用几种计算技术来预测可能影响CTLA-4蛋白结构和功能的高度疾病易感的nssnp。然后进行CTLA-4/CD80蛋白复合物的计算对接和分子动力学（MD）模拟。我们的研究结果显示，17个nssnp被发现是高致病性和结构不稳定的CTLA-4蛋白。随后，进化的ConSurf图谱显示，9个nssnp高度保守，并影响CTLA-4蛋白的生物物理化学性质、三维RNA结构、翻译后修饰位点、二级和三级结构。CTLA-4/CD80蛋白复合物的分子对接表明，rs1553657429-P137L和rs1356678649-N145H nssnp有效降低了对B7-1蛋白的结合亲和力。MD模拟还显示，位于配体结合域（MYPPPY基序）和n -糖基化位点N145H的CTLA-4 P137L被认为是通过降低CTLA-4蛋白的结构稳定性和灵活性来干扰B7-1蛋白结合的高风险非单核苷酸多态性。

{"title":"Demystifying the implications of disease-susceptible missense SNPs within CTLA-4 ligand binding domain and its interaction towards B7-1 protein complex: Bioinformatics-driven evidence","authors":"V. Shamala , S. Preethi , V. Hemamalini , S. Asha Devi","doi":"10.1016/j.compbiomed.2026.111459","DOIUrl":"10.1016/j.compbiomed.2026.111459","url":null,"abstract":"<div><div>Alteration of a nucleotide within a triplet codon results in substitution of a different amino acid in the protein sequence, collectively termed as missense or non-synonymous Single-Nucleotide Polymorphisms (nsSNPs). Cytoplasmic T Lymphocytes Antigen-4 (CTLA-4) gene encodes a transmembrane protein expressed on activated T cells. CTLA-4 receptor acts as an immunoregulatory molecule that prompts immunological self-tolerance by rapidly inhibiting T cell-mediated immune responses, via inactivation and elimination of T cells. Polymorphism within CTLA-4 coding region could efficiently disrupt trans-endocytosis process by decreasing its interaction towards B7 ligands (B7-1: CD80 and B7-2: CD86) molecules expressed on Antigen Presenting Cells (APCs). In the present study, we utilized several computational techniques to predict the highly disease-susceptible nsSNPs that potentially impact on structure and function of CTLA-4 protein. Followed by computational docking and Molecular Dynamics (MD) simulations for CTLA-4/CD80 protein complex were conducted. Our research findings reveal that seventeen nsSNPs were found to be highly pathogenic and structurally destabilizing CTLA-4 protein. Subsequently, an evolutionary ConSurf profile reveals that nine nsSNPs were highly conserved and also affect bio-physicochemical properties, three-dimensional RNA structure, post-translational modification sites, secondary and tertiary structure of CTLA-4 protein. Molecular docking of CTLA-4/CD80 protein complex indicates that rs1553657429-P137L and rs1356678649-N145H nsSNPs have efficiently decreased the binding affinity towards B7-1 protein. The MD simulation also reveal CTLA-4 P137L, located within ligand-binding domain (MYPPPY motif) and N145H at N-glycosylation site, were significantly considered to be high-risk nsSNPs that interfere association with B7-1 protein by decreasing structural stability and flexibility of CTLA-4 protein.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"202 ","pages":"Article 111459"},"PeriodicalIF":6.3,"publicationDate":"2026-01-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145974216","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-subunit vaccine design against Neoehrlichia mikurensis by applying structure-based in silico approach 应用基于结构的计算机方法设计抗mikurenicerlichia多亚单位疫苗

IF 6.3 2区医学 Q1 BIOLOGY

Computers in biology and medicine

Pub Date : 2026-01-13 DOI: 10.1016/j.compbiomed.2025.111429

Atakan Vatansever

Candidatus Neoehrlichia mikurensis, an emerging tick-borne pathogen linked to systemic inflammatory syndromes, poses significant risk to immunocompromised individuals due to its intracellular nature, diagnostic limitations, and lack of targeted vaccines. In this study, immunoinformatics-based methods were applied to design a multi-epitope subunit vaccine targeting surface and conserved immunogenic proteins of N. mikurensis. Virtual screening of 237 proteins identified 377 T-cell and 177 B-cell high-affinity epitopes, prioritized based on antigenicity, non-allergenicity, non-toxicity, and global HLA coverage. T4SS and Pdr-DsbD proteins demonstrated the highest immunological relevance, with T4SS epitopes achieving 100 % global population coverage. Structural modeling revealed stable protein folds, accessible epitopes, and functional ligand-binding pockets, supporting vaccine design reliability. Inclusion of globally effective, high-affinity epitopes is a useful strategy for the creation of subunit vaccines against N. mikurensis. These findings revealed the value of reverse vaccinology and structural bioinformatics for accelerating vaccine development for intracellular bacteria. In conclusion, this in silico approach to vaccine design provides a promising method for guiding subsequent experimental validation and preventive action against neoehrlichiosis.

mikurensis候选菌是一种与全身性炎症综合征相关的新发蜱传病原体，由于其细胞内性质、诊断局限性和缺乏靶向疫苗，对免疫功能低下的个体构成重大风险。本研究应用免疫信息学方法设计了一种多表位亚单位疫苗，该疫苗针对mikurensis的表面和保守的免疫原性蛋白。237个蛋白的虚拟筛选鉴定出377个t细胞和177个b细胞高亲和力表位，根据抗原性、非过敏原性、无毒性和全球HLA覆盖率进行优先排序。T4SS和Pdr-DsbD蛋白表现出最高的免疫学相关性，T4SS表位在全球人口中覆盖率达到100%。结构模型揭示了稳定的蛋白质折叠、可接近的表位和功能性配体结合口袋，支持疫苗设计的可靠性。包含全球有效的，高亲和力的表位是一种有用的策略，用于创建亚单位疫苗对抗奈瑟菌。这些发现揭示了反向疫苗学和结构生物信息学对加速细胞内细菌疫苗开发的价值。总之，这种基于计算机的疫苗设计方法为指导后续的实验验证和针对新立克体病的预防行动提供了一种有希望的方法。

{"title":"Multi-subunit vaccine design against Neoehrlichia mikurensis by applying structure-based in silico approach","authors":"Atakan Vatansever","doi":"10.1016/j.compbiomed.2025.111429","DOIUrl":"10.1016/j.compbiomed.2025.111429","url":null,"abstract":"<div><div><em>Candidatus Neoehrlichia mikurensis</em>, an emerging tick-borne pathogen linked to systemic inflammatory syndromes, poses significant risk to immunocompromised individuals due to its intracellular nature, diagnostic limitations, and lack of targeted vaccines. In this study, immunoinformatics-based methods were applied to design a multi-epitope subunit vaccine targeting surface and conserved immunogenic proteins of <em>N. mikurensis</em>. Virtual screening of 237 proteins identified 377 T-cell and 177 B-cell high-affinity epitopes, prioritized based on antigenicity, non-allergenicity, non-toxicity, and global HLA coverage. T4SS and Pdr-DsbD proteins demonstrated the highest immunological relevance, with T4SS epitopes achieving 100 % global population coverage. Structural modeling revealed stable protein folds, accessible epitopes, and functional ligand-binding pockets, supporting vaccine design reliability. Inclusion of globally effective, high-affinity epitopes is a useful strategy for the creation of subunit vaccines against <em>N. mikurensis</em>. These findings revealed the value of reverse vaccinology and structural bioinformatics for accelerating vaccine development for intracellular bacteria. In conclusion, this <em>in silico</em> approach to vaccine design provides a promising method for guiding subsequent experimental validation and preventive action against neoehrlichiosis.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"202 ","pages":"Article 111429"},"PeriodicalIF":6.3,"publicationDate":"2026-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145974293","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Development of a multi-epitope vaccine candidate against Sindbis virus through integrated immunoinformatics approaches and molecular dynamics simulations 通过综合免疫信息学方法和分子动力学模拟开发针对Sindbis病毒的多表位候选疫苗

IF 6.3 2区医学 Q1 BIOLOGY

Computers in biology and medicine

Pub Date : 2026-01-13 DOI: 10.1016/j.compbiomed.2026.111456

Nabila Ishaque Ira , Nishika Jaishee , Ayan Saha , Devashan Naidoo , Shazneen Tasnim Islam , Tazneen Hossain Tani , Neeta Raj Sharma , Akash Anandraj , Syed Mohammad Lokman , Claudio Angione , Ayan Roy

Sindbis virus (SINV), belonging to the genus Alphavirus, is the causative agent of Pogosta disease in humans. The clinical infection is characterized by fever, malaise, rash, myalgia, and arthralgia, which is generally self-limiting. Chronic infection with SINV triggers autoimmune conditions that lead to persistent arthritis. Despite its clinical relevance, no licensed vaccine is currently available for the prevention of SINV infection. To the best of our knowledge, this study presents the first in silico design and evaluation of a multi-epitope vaccine candidate against SINV. Using an integrated immunoinformatics framework, the SINV structural polyprotein was systematically screened, leading to the identification of twelve highly antigenic immunological hotspots, derived from both experimentally validated and computationally predicted B-cell and T-cell epitopes. These epitopes were rationally assembled into a 317–amino acid multi-epitope vaccine construct using suitable linkers and the human β-defensin 2 as an immunostimulatory adjuvant. The designed construct exhibited favorable antigenicity, non-toxicity, stability, and physicochemical properties. Molecular docking and molecular dynamics simulations demonstrated encouraging interactions between the vaccine construct and innate immune receptors TLR-2 and TLR-4, highlighting its potential to trigger immune responses. Immune simulation predicted robust humoral and cell-mediated immune responses, while codon optimization and in silico cloning into the pETite vector indicated expression feasibility in Escherichia coli K12. This work proposes a novel immunoinformatics and molecular dynamics–based vaccine design pipeline for Sindbis virus and presents a computationally validated multi-epitope vaccine candidate, providing a foundation for future experimental validation toward effective vaccine development.

辛比斯病毒（SINV）属于甲病毒属，是人类波戈斯塔病的病原体。临床感染表现为发热、不适、皮疹、肌痛和关节痛，一般为自限性。慢性感染SINV会引发自身免疫性疾病，导致持续性关节炎。尽管具有临床意义，但目前尚无获得许可的疫苗可用于预防SINV感染。据我们所知，这项研究首次提出了针对SINV的多表位候选疫苗的硅设计和评估。利用综合免疫信息学框架，对SINV结构多蛋白进行系统筛选，鉴定出12个高抗原免疫热点，这些热点来自实验验证和计算预测的b细胞和t细胞表位。利用合适的连接体和人β-防御素2作为免疫刺激佐剂，将这些表位合理地组装成317个氨基酸的多表位疫苗结构。所设计的结构具有良好的抗原性、无毒性、稳定性和理化性质。分子对接和分子动力学模拟表明，疫苗结构与先天免疫受体TLR-2和TLR-4之间存在令人鼓舞的相互作用，突出了其引发免疫反应的潜力。免疫模拟预测了强大的体液和细胞介导的免疫应答，而密码子优化和在pETite载体上的硅克隆表明了在大肠杆菌K12中表达的可行性。本工作提出了一种新的基于免疫信息学和分子动力学的Sindbis病毒疫苗设计管道，并提出了一种计算验证的多表位候选疫苗，为未来有效疫苗开发的实验验证奠定了基础。

{"title":"Development of a multi-epitope vaccine candidate against Sindbis virus through integrated immunoinformatics approaches and molecular dynamics simulations","authors":"Nabila Ishaque Ira , Nishika Jaishee , Ayan Saha , Devashan Naidoo , Shazneen Tasnim Islam , Tazneen Hossain Tani , Neeta Raj Sharma , Akash Anandraj , Syed Mohammad Lokman , Claudio Angione , Ayan Roy","doi":"10.1016/j.compbiomed.2026.111456","DOIUrl":"10.1016/j.compbiomed.2026.111456","url":null,"abstract":"<div><div>Sindbis virus (SINV), belonging to the genus <em>Alphavirus</em>, is the causative agent of Pogosta disease in humans. The clinical infection is characterized by fever, malaise, rash, myalgia, and arthralgia, which is generally self-limiting. Chronic infection with SINV triggers autoimmune conditions that lead to persistent arthritis. Despite its clinical relevance, no licensed vaccine is currently available for the prevention of SINV infection. To the best of our knowledge, this study presents the first <em>in silico</em> design and evaluation of a multi-epitope vaccine candidate against SINV. Using an integrated immunoinformatics framework, the SINV structural polyprotein was systematically screened, leading to the identification of twelve highly antigenic immunological hotspots, derived from both experimentally validated and computationally predicted B-cell and T-cell epitopes. These epitopes were rationally assembled into a 317–amino acid multi-epitope vaccine construct using suitable linkers and the human β-defensin 2 as an immunostimulatory adjuvant. The designed construct exhibited favorable antigenicity, non-toxicity, stability, and physicochemical properties. Molecular docking and molecular dynamics simulations demonstrated encouraging interactions between the vaccine construct and innate immune receptors TLR-2 and TLR-4, highlighting its potential to trigger immune responses. Immune simulation predicted robust humoral and cell-mediated immune responses, while codon optimization and <em>in silico</em> cloning into the pETite vector indicated expression feasibility in <em>Escherichia coli</em> K12. This work proposes a novel immunoinformatics and molecular dynamics–based vaccine design pipeline for Sindbis virus and presents a computationally validated multi-epitope vaccine candidate, providing a foundation for future experimental validation toward effective vaccine development.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"202 ","pages":"Article 111456"},"PeriodicalIF":6.3,"publicationDate":"2026-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145974217","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0