首页 > 最新文献

Frontiers in Neuroinformatics最新文献

英文 中文
Effect of natural and synthetic noise data augmentation on physical action classification by brain-computer interface and deep learning.
IF 2.5 4区 医学 Q2 MATHEMATICAL & COMPUTATIONAL BIOLOGY Pub Date : 2025-02-27 eCollection Date: 2025-01-01 DOI: 10.3389/fninf.2025.1521805
Yuri Gordienko, Nikita Gordienko, Vladyslav Taran, Anis Rojbi, Sergii Telenyk, Sergii Stirenko

Analysis of electroencephalography (EEG) signals gathered by brain-computer interface (BCI) recently demonstrated that deep neural networks (DNNs) can be effectively used for investigation of time sequences for physical actions (PA) classification. In this study, the relatively simple DNN with fully connected network (FCN) components and convolutional neural network (CNN) components was considered to classify finger-palm-hand manipulations each from the grasp-and-lift (GAL) dataset. The main aim of this study was to imitate and investigate environmental influence by the proposed noise data augmentation (NDA) of two kinds: (i) natural NDA by inclusion of noise EEG data from neighboring regions by increasing the sampling size N and the different offset values for sample labeling and (ii) synthetic NDA by adding the generated Gaussian noise. The natural NDA by increasing N leads to the higher micro and macro area under the curve (AUC) for receiver operating curve values for the bigger N values than usage of synthetic NDA. The detrended fluctuation analysis (DFA) was applied to investigate the fluctuation properties and calculate the correspondent Hurst exponents H for the quantitative characterization of the fluctuation variability. H values for the low time window scales (< 2 s) are higher in comparison with ones for the bigger time window scales. For example, H more than 2-3 times higher for some PAs, i.e., it means that the shorter EEG fragments (< 2 s) demonstrate the scaling behavior of the higher complexity than the longer fragments. As far as these results were obtained by the relatively small DNN with the low resource requirements, this approach can be promising for porting such models to Edge Computing infrastructures on devices with the very limited computational resources.

{"title":"Effect of natural and synthetic noise data augmentation on physical action classification by brain-computer interface and deep learning.","authors":"Yuri Gordienko, Nikita Gordienko, Vladyslav Taran, Anis Rojbi, Sergii Telenyk, Sergii Stirenko","doi":"10.3389/fninf.2025.1521805","DOIUrl":"https://doi.org/10.3389/fninf.2025.1521805","url":null,"abstract":"<p><p>Analysis of electroencephalography (EEG) signals gathered by brain-computer interface (BCI) recently demonstrated that deep neural networks (DNNs) can be effectively used for investigation of time sequences for physical actions (PA) classification. In this study, the relatively simple DNN with fully connected network (FCN) components and convolutional neural network (CNN) components was considered to classify finger-palm-hand manipulations each from the grasp-and-lift (GAL) dataset. The main aim of this study was to imitate and investigate environmental influence by the proposed noise data augmentation (NDA) of two kinds: (i) natural NDA by inclusion of noise EEG data from neighboring regions by increasing the sampling size <i>N</i> and the different offset values for sample labeling and (ii) synthetic NDA by adding the generated Gaussian noise. The natural NDA by increasing <i>N</i> leads to the higher micro and macro area under the curve (AUC) for receiver operating curve values for the bigger <i>N</i> values than usage of synthetic NDA. The detrended fluctuation analysis (DFA) was applied to investigate the fluctuation properties and calculate the correspondent Hurst exponents <i>H</i> for the quantitative characterization of the fluctuation variability. <i>H</i> values for the low time window scales (< 2 s) are higher in comparison with ones for the bigger time window scales. For example, <i>H</i> more than 2-3 times higher for some PAs, i.e., it means that the shorter EEG fragments (< 2 s) demonstrate the scaling behavior of the higher complexity than the longer fragments. As far as these results were obtained by the relatively small DNN with the low resource requirements, this approach can be promising for porting such models to Edge Computing infrastructures on devices with the very limited computational resources.</p>","PeriodicalId":12462,"journal":{"name":"Frontiers in Neuroinformatics","volume":"19 ","pages":"1521805"},"PeriodicalIF":2.5,"publicationDate":"2025-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11903462/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143624151","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
An action decoding framework combined with deep neural network for predicting the semantics of human actions in videos from evoked brain activities. 结合深度神经网络的动作解码框架,从诱发的大脑活动中预测视频中人类动作的语义。
IF 2.5 4区 医学 Q2 MATHEMATICAL & COMPUTATIONAL BIOLOGY Pub Date : 2025-02-19 eCollection Date: 2025-01-01 DOI: 10.3389/fninf.2025.1526259
Yuanyuan Zhang, Manli Tian, Baolin Liu

Introduction: Recently, numerous studies have focused on the semantic decoding of perceived images based on functional magnetic resonance imaging (fMRI) activities. However, it remains unclear whether it is possible to establish relationships between brain activities and semantic features of human actions in video stimuli. Here we construct a framework for decoding action semantics by establishing relationships between brain activities and semantic features of human actions.

Methods: To effectively use a small amount of available brain activity data, our proposed method employs a pre-trained image action recognition network model based on an expanding three-dimensional (X3D) deep neural network framework (DNN). To apply brain activities to the image action recognition network, we train regression models that learn the relationship between brain activities and deep-layer image features. To improve decoding accuracy, we join by adding the nonlocal-attention mechanism module to the X3D model to capture long-range temporal and spatial dependence, proposing a multilayer perceptron (MLP) module of multi-task loss constraint to build a more accurate regression mapping approach and performing data enhancement through linear interpolation to expand the amount of data to reduce the impact of a small sample.

Results and discussion: Our findings indicate that the features in the X3D-DNN are biologically relevant, and capture information useful for perception. The proposed method enriches the semantic decoding model. We have also conducted several experiments with data from different subsets of brain regions known to process visual stimuli. The results suggest that semantic information for human actions is widespread across the entire visual cortex.

简介最近,许多研究都在关注基于功能磁共振成像(fMRI)活动的感知图像语义解码。然而,是否有可能在大脑活动与视频刺激中人类动作的语义特征之间建立关系,目前仍不清楚。在此,我们通过建立大脑活动与人类动作语义特征之间的关系,构建了一个解码动作语义的框架:为了有效利用少量可用的大脑活动数据,我们提出的方法采用了基于扩展三维(X3D)深度神经网络框架(DNN)的预训练图像动作识别网络模型。为了将脑部活动应用于图像动作识别网络,我们训练回归模型,学习脑部活动与深层图像特征之间的关系。为了提高解码准确性,我们在 X3D 模型中加入了非局部注意机制模块,以捕捉长程时空依赖性;提出了多任务损失约束的多层感知器(MLP)模块,以构建更精确的回归映射方法;并通过线性插值进行数据增强,以扩大数据量,减少小样本的影响:我们的研究结果表明,X3D-DNN 中的特征与生物相关,并捕获了对感知有用的信息。所提出的方法丰富了语义解码模型。我们还利用已知可处理视觉刺激的不同脑区子集的数据进行了多项实验。结果表明,人类行动的语义信息广泛存在于整个视觉皮层。
{"title":"An action decoding framework combined with deep neural network for predicting the semantics of human actions in videos from evoked brain activities.","authors":"Yuanyuan Zhang, Manli Tian, Baolin Liu","doi":"10.3389/fninf.2025.1526259","DOIUrl":"10.3389/fninf.2025.1526259","url":null,"abstract":"<p><strong>Introduction: </strong>Recently, numerous studies have focused on the semantic decoding of perceived images based on functional magnetic resonance imaging (fMRI) activities. However, it remains unclear whether it is possible to establish relationships between brain activities and semantic features of human actions in video stimuli. Here we construct a framework for decoding action semantics by establishing relationships between brain activities and semantic features of human actions.</p><p><strong>Methods: </strong>To effectively use a small amount of available brain activity data, our proposed method employs a pre-trained image action recognition network model based on an expanding three-dimensional (X3D) deep neural network framework (DNN). To apply brain activities to the image action recognition network, we train regression models that learn the relationship between brain activities and deep-layer image features. To improve decoding accuracy, we join by adding the nonlocal-attention mechanism module to the X3D model to capture long-range temporal and spatial dependence, proposing a multilayer perceptron (MLP) module of multi-task loss constraint to build a more accurate regression mapping approach and performing data enhancement through linear interpolation to expand the amount of data to reduce the impact of a small sample.</p><p><strong>Results and discussion: </strong>Our findings indicate that the features in the X3D-DNN are biologically relevant, and capture information useful for perception. The proposed method enriches the semantic decoding model. We have also conducted several experiments with data from different subsets of brain regions known to process visual stimuli. The results suggest that semantic information for human actions is widespread across the entire visual cortex.</p>","PeriodicalId":12462,"journal":{"name":"Frontiers in Neuroinformatics","volume":"19 ","pages":"1526259"},"PeriodicalIF":2.5,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11880012/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143566696","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Contrastive self-supervised learning for neurodegenerative disorder classification.
IF 2.5 4区 医学 Q2 MATHEMATICAL & COMPUTATIONAL BIOLOGY Pub Date : 2025-02-17 eCollection Date: 2025-01-01 DOI: 10.3389/fninf.2025.1527582
Vadym Gryshchuk, Devesh Singh, Stefan Teipel, Martin Dyrba

Introduction: Neurodegenerative diseases such as Alzheimer's disease (AD) or frontotemporal lobar degeneration (FTLD) involve specific loss of brain volume, detectable in vivo using T1-weighted MRI scans. Supervised machine learning approaches classifying neurodegenerative diseases require diagnostic-labels for each sample. However, it can be difficult to obtain expert labels for a large amount of data. Self-supervised learning (SSL) offers an alternative for training machine learning models without data-labels.

Methods: We investigated if the SSL models can be applied to distinguish between different neurodegenerative disorders in an interpretable manner. Our method comprises a feature extractor and a downstream classification head. A deep convolutional neural network, trained with a contrastive loss, serves as the feature extractor that learns latent representations. The classification head is a single-layer perceptron that is trained to perform diagnostic group separation. We used N = 2,694 T1-weighted MRI scans from four data cohorts: two ADNI datasets, AIBL and FTLDNI, including cognitively normal controls (CN), cases with prodromal and clinical AD, as well as FTLD cases differentiated into its phenotypes.

Results: Our results showed that the feature extractor trained in a self-supervised way provides generalizable and robust representations for the downstream classification. For AD vs. CN, our model achieves 82% balanced accuracy on the test subset and 80% on an independent holdout dataset. Similarly, the Behavioral variant of frontotemporal dementia (BV) vs. CN model attains an 88% balanced accuracy on the test subset. The average feature attribution heatmaps obtained by the Integrated Gradient method highlighted hallmark regions, i.e., temporal gray matter atrophy for AD, and insular atrophy for BV.

Conclusion: Our models perform comparably to state-of-the-art supervised deep learning approaches. This suggests that the SSL methodology can successfully make use of unannotated neuroimaging datasets as training data while remaining robust and interpretable.

{"title":"Contrastive self-supervised learning for neurodegenerative disorder classification.","authors":"Vadym Gryshchuk, Devesh Singh, Stefan Teipel, Martin Dyrba","doi":"10.3389/fninf.2025.1527582","DOIUrl":"10.3389/fninf.2025.1527582","url":null,"abstract":"<p><strong>Introduction: </strong>Neurodegenerative diseases such as Alzheimer's disease (AD) or frontotemporal lobar degeneration (FTLD) involve specific loss of brain volume, detectable <i>in vivo</i> using T1-weighted MRI scans. Supervised machine learning approaches classifying neurodegenerative diseases require diagnostic-labels for each sample. However, it can be difficult to obtain expert labels for a large amount of data. Self-supervised learning (SSL) offers an alternative for training machine learning models without data-labels.</p><p><strong>Methods: </strong>We investigated if the SSL models can be applied to distinguish between different neurodegenerative disorders in an interpretable manner. Our method comprises a feature extractor and a downstream classification head. A deep convolutional neural network, trained with a contrastive loss, serves as the feature extractor that learns latent representations. The classification head is a single-layer perceptron that is trained to perform diagnostic group separation. We used <i>N</i> = 2,694 T1-weighted MRI scans from four data cohorts: two ADNI datasets, AIBL and FTLDNI, including cognitively normal controls (CN), cases with prodromal and clinical AD, as well as FTLD cases differentiated into its phenotypes.</p><p><strong>Results: </strong>Our results showed that the feature extractor trained in a self-supervised way provides generalizable and robust representations for the downstream classification. For AD vs. CN, our model achieves 82% balanced accuracy on the test subset and 80% on an independent holdout dataset. Similarly, the Behavioral variant of frontotemporal dementia (BV) vs. CN model attains an 88% balanced accuracy on the test subset. The average feature attribution heatmaps obtained by the Integrated Gradient method highlighted hallmark regions, i.e., temporal gray matter atrophy for AD, and insular atrophy for BV.</p><p><strong>Conclusion: </strong>Our models perform comparably to state-of-the-art supervised deep learning approaches. This suggests that the SSL methodology can successfully make use of unannotated neuroimaging datasets as training data while remaining robust and interpretable.</p>","PeriodicalId":12462,"journal":{"name":"Frontiers in Neuroinformatics","volume":"19 ","pages":"1527582"},"PeriodicalIF":2.5,"publicationDate":"2025-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11873101/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143540685","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Quantitative evaluation method of stroke association based on multidimensional gait parameters by using machine learning.
IF 2.5 4区 医学 Q2 MATHEMATICAL & COMPUTATIONAL BIOLOGY Pub Date : 2025-02-12 eCollection Date: 2025-01-01 DOI: 10.3389/fninf.2025.1544372
Cheng Wang, Zhou Long, Xiang-Dong Wang, You-Qi Kong, Li-Chun Zhou, Wei-Hua Jia, Pei Li, Jing Wang, Xiao-Juan Wang, Tian Tian

Objective: NIHSS for stroke is widely used in clinical, but it is complex and subjective. The purpose of the study is to present a quantitative evaluation method of stroke association based on multi-dimensional gait parameters by using machine learning.

Methods: 39 ischemic stroke patients with hemiplegia were selected as the stroke group and 187 healthy adults from the community as the control group. Gaitboter system was used for gait analysis. Through the labeling of stroke patients by clinicians with NIHSS score, all gait parameters obtained were used to select appropriate gait parameters. By using machine learning algorithm, a discriminant model and a hierarchical model were trained.

Results: The discriminant model was used to distinguish between healthy people and stroke patients. The overall detection accuracy of the model based on KNN, SVM and Randomforest algorithms is 92.86, 92.86 and 90.00%, respectively. The hierarchical model was used to judge the severity of stroke in stroke patients. The model based on Randomforest, SVM and AdaBoost algorithm had an overall detection accuracy of 71.43, 85.71 and 85.71%, respectively.

Conclusion: The proposed stroke association quantitative evaluation method based on multi-dimensional gait parameters has the characteristics of high accuracy, objectivity, and quantification.

{"title":"Quantitative evaluation method of stroke association based on multidimensional gait parameters by using machine learning.","authors":"Cheng Wang, Zhou Long, Xiang-Dong Wang, You-Qi Kong, Li-Chun Zhou, Wei-Hua Jia, Pei Li, Jing Wang, Xiao-Juan Wang, Tian Tian","doi":"10.3389/fninf.2025.1544372","DOIUrl":"10.3389/fninf.2025.1544372","url":null,"abstract":"<p><strong>Objective: </strong>NIHSS for stroke is widely used in clinical, but it is complex and subjective. The purpose of the study is to present a quantitative evaluation method of stroke association based on multi-dimensional gait parameters by using machine learning.</p><p><strong>Methods: </strong>39 ischemic stroke patients with hemiplegia were selected as the stroke group and 187 healthy adults from the community as the control group. Gaitboter system was used for gait analysis. Through the labeling of stroke patients by clinicians with NIHSS score, all gait parameters obtained were used to select appropriate gait parameters. By using machine learning algorithm, a discriminant model and a hierarchical model were trained.</p><p><strong>Results: </strong>The discriminant model was used to distinguish between healthy people and stroke patients. The overall detection accuracy of the model based on KNN, SVM and Randomforest algorithms is 92.86, 92.86 and 90.00%, respectively. The hierarchical model was used to judge the severity of stroke in stroke patients. The model based on Randomforest, SVM and AdaBoost algorithm had an overall detection accuracy of 71.43, 85.71 and 85.71%, respectively.</p><p><strong>Conclusion: </strong>The proposed stroke association quantitative evaluation method based on multi-dimensional gait parameters has the characteristics of high accuracy, objectivity, and quantification.</p>","PeriodicalId":12462,"journal":{"name":"Frontiers in Neuroinformatics","volume":"19 ","pages":"1544372"},"PeriodicalIF":2.5,"publicationDate":"2025-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11861528/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143515164","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
The classification of absence seizures using power-to-power cross-frequency coupling analysis with a deep learning network.
IF 2.5 4区 医学 Q2 MATHEMATICAL & COMPUTATIONAL BIOLOGY Pub Date : 2025-02-10 eCollection Date: 2025-01-01 DOI: 10.3389/fninf.2025.1513661
A V Medvedev, B Lehmann

High frequency oscillations are important novel biomarkers of epileptic tissue. The interaction of oscillations across different time scales is revealed as cross-frequency coupling (CFC) representing a high-order structure in the functional organization of brain rhythms. Power-to-power coupling (PPC) is one form of coupling with significant research attesting to its neurobiological significance as well as its computational efficiency, yet has been hitherto unexplored within seizure classification literature. New artificial intelligence methods such as deep learning neural networks can provide powerful tools for automated analysis of EEG. Here we present a Stacked Sparse Autoencoder (SSAE) trained to classify absence seizure activity based on this important form of cross-frequency patterns within scalp EEG. The analysis is done on the EEG records from the Temple University Hospital database. Absence seizures (n = 94) from 12 patients were taken into analysis along with segments of background activity. Power-to-power coupling was calculated between all frequencies 2-120 Hz pairwise using the EEGLAB toolbox. The resulting CFC matrices were used as training or testing inputs to the autoencoder. The trained network was able to recognize background and seizure segments (not used in training) with a sensitivity of 93.1%, specificity of 99.5% and overall accuracy of 96.8%. The results provide evidence both for (1) the relevance of PPC for seizure classification, as well as (2) the efficacy of an approach combining PPC with SSAE neural networks for automated classification of absence seizures within scalp EEG.

{"title":"The classification of absence seizures using power-to-power cross-frequency coupling analysis with a deep learning network.","authors":"A V Medvedev, B Lehmann","doi":"10.3389/fninf.2025.1513661","DOIUrl":"10.3389/fninf.2025.1513661","url":null,"abstract":"<p><p>High frequency oscillations are important novel biomarkers of epileptic tissue. The interaction of oscillations across different time scales is revealed as cross-frequency coupling (CFC) representing a high-order structure in the functional organization of brain rhythms. Power-to-power coupling (PPC) is one form of coupling with significant research attesting to its neurobiological significance as well as its computational efficiency, yet has been hitherto unexplored within seizure classification literature. New artificial intelligence methods such as deep learning neural networks can provide powerful tools for automated analysis of EEG. Here we present a Stacked Sparse Autoencoder (SSAE) trained to classify absence seizure activity based on this important form of cross-frequency patterns within scalp EEG. The analysis is done on the EEG records from the Temple University Hospital database. Absence seizures (<i>n</i> = 94) from 12 patients were taken into analysis along with segments of background activity. Power-to-power coupling was calculated between all frequencies 2-120 Hz pairwise using the EEGLAB toolbox. The resulting CFC matrices were used as training or testing inputs to the autoencoder. The trained network was able to recognize background and seizure segments (not used in training) with a sensitivity of 93.1%, specificity of 99.5% and overall accuracy of 96.8%. The results provide evidence both for (1) the relevance of PPC for seizure classification, as well as (2) the efficacy of an approach combining PPC with SSAE neural networks for automated classification of absence seizures within scalp EEG.</p>","PeriodicalId":12462,"journal":{"name":"Frontiers in Neuroinformatics","volume":"19 ","pages":"1513661"},"PeriodicalIF":2.5,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11847813/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143491525","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Identifying natural inhibitors against FUS protein in dementia through machine learning, molecular docking, and dynamics simulation.
IF 2.5 4区 医学 Q2 MATHEMATICAL & COMPUTATIONAL BIOLOGY Pub Date : 2025-02-05 eCollection Date: 2024-01-01 DOI: 10.3389/fninf.2024.1439090
Darwin Li

Dementia, a complex and debilitating spectrum of neurodegenerative diseases, presents a profound challenge in the quest for effective treatments. The FUS protein is well at the center of this problem, as it is frequently dysregulated in the various disorders. We chose a route of computational work that involves targeting natural inhibitors of the FUS protein, offering a novel treatment strategy. We first reviewed the FUS protein's framework; early forecasting models using the AlphaFold2 and SwissModel algorithms indicated a loop-rich protein-a structure component correlating with flexibility. However, these models showed limitations, as reflected by inadequate ERRAT and Verify3D scores. Seeking enhanced accuracy, we turned to the I-TASSER suite, which delivered a refined structural model affirmed by robust validation metrics. With a reliable model in hand, our study utilized machine learning techniques, particularly the Random Forest algorithm, to navigate through a vast dataset of phytochemicals. This led to the identification of nimbinin, dehydroxymethylflazine, and several other compounds as potential FUS inhibitors. Notably, dehydroxymethylflazine and cleroindicin C identified during molecular docking analyses-facilitated by AutoDock Vina-for their high binding affinities and stability in interaction with the FUS protein, as corroborated by extensive molecular dynamics simulations. Originating from medicinal plants, these compounds are not only structurally compatible with the target protein but also adhere to pharmacokinetic profiles suitable for drug development, including optimal molecular weight and LogP values conducive to blood-brain barrier penetration. This computational exploration paves the way for subsequent experimental validation and highlights the potential of these natural compounds as innovative agents in the treatment of dementia.

{"title":"Identifying natural inhibitors against FUS protein in dementia through machine learning, molecular docking, and dynamics simulation.","authors":"Darwin Li","doi":"10.3389/fninf.2024.1439090","DOIUrl":"10.3389/fninf.2024.1439090","url":null,"abstract":"<p><p>Dementia, a complex and debilitating spectrum of neurodegenerative diseases, presents a profound challenge in the quest for effective treatments. The FUS protein is well at the center of this problem, as it is frequently dysregulated in the various disorders. We chose a route of computational work that involves targeting natural inhibitors of the FUS protein, offering a novel treatment strategy. We first reviewed the FUS protein's framework; early forecasting models using the AlphaFold2 and SwissModel algorithms indicated a loop-rich protein-a structure component correlating with flexibility. However, these models showed limitations, as reflected by inadequate ERRAT and Verify3D scores. Seeking enhanced accuracy, we turned to the I-TASSER suite, which delivered a refined structural model affirmed by robust validation metrics. With a reliable model in hand, our study utilized machine learning techniques, particularly the Random Forest algorithm, to navigate through a vast dataset of phytochemicals. This led to the identification of nimbinin, dehydroxymethylflazine, and several other compounds as potential FUS inhibitors. Notably, dehydroxymethylflazine and cleroindicin C identified during molecular docking analyses-facilitated by AutoDock Vina-for their high binding affinities and stability in interaction with the FUS protein, as corroborated by extensive molecular dynamics simulations. Originating from medicinal plants, these compounds are not only structurally compatible with the target protein but also adhere to pharmacokinetic profiles suitable for drug development, including optimal molecular weight and LogP values conducive to blood-brain barrier penetration. This computational exploration paves the way for subsequent experimental validation and highlights the potential of these natural compounds as innovative agents in the treatment of dementia.</p>","PeriodicalId":12462,"journal":{"name":"Frontiers in Neuroinformatics","volume":"18 ","pages":"1439090"},"PeriodicalIF":2.5,"publicationDate":"2025-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11835945/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143457473","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Enhanced heart sound anomaly detection via WCOS: a semi-supervised framework integrating wavelet, autoencoder and SVM.
IF 2.5 4区 医学 Q2 MATHEMATICAL & COMPUTATIONAL BIOLOGY Pub Date : 2025-01-29 eCollection Date: 2025-01-01 DOI: 10.3389/fninf.2025.1530047
Peipei Zeng, Shuimiao Kang, Fan Fan, Jiyuan Liu

Anomaly detection is a typical binary classification problem under the condition of unbalanced samples, which has been widely used in various fields of data mining. For example, it can help detect heart murmurs when the heart is structurally abnormal, to tell if a newborn has congenital heart disease. Due to the low time and high efficiency, most work focuses on the semi- supervised anomaly detection method. However, the anomaly detection effect of this method is not high because of massive data with uneven samples and different noise. To improve the accuracy of anomaly detection under unbalanced sample conditions, we propose a new semi-supervised anomaly detection method (WCOS) based on semi-supervised clustering, which combines wavelet reconstruction, convolutional autoencoder, and one classification support vector machine. In this way, we can not only distinguish a small proportion of abnormal heart sounds in the huge data scale but also filter the noise through the noise reduction network, thus significantly improving the detection accuracy. In addition, we evaluated our method using real datasets. When the noise of sigma = 0.5, the AUC standard deviation of the WR-CAE-OCSVM is 19.2, 54.1, and 29.8% lower than that of WR-OCSVM, CAE-OCSVM and OCSVM, respectively. The results confirmed the higher accuracy of anomaly detection in WCOS compared to other state-of-the-art methods.

{"title":"Enhanced heart sound anomaly detection via WCOS: a semi-supervised framework integrating wavelet, autoencoder and SVM.","authors":"Peipei Zeng, Shuimiao Kang, Fan Fan, Jiyuan Liu","doi":"10.3389/fninf.2025.1530047","DOIUrl":"10.3389/fninf.2025.1530047","url":null,"abstract":"<p><p>Anomaly detection is a typical binary classification problem under the condition of unbalanced samples, which has been widely used in various fields of data mining. For example, it can help detect heart murmurs when the heart is structurally abnormal, to tell if a newborn has congenital heart disease. Due to the low time and high efficiency, most work focuses on the semi- supervised anomaly detection method. However, the anomaly detection effect of this method is not high because of massive data with uneven samples and different noise. To improve the accuracy of anomaly detection under unbalanced sample conditions, we propose a new semi-supervised anomaly detection method (WCOS) based on semi-supervised clustering, which combines wavelet reconstruction, convolutional autoencoder, and one classification support vector machine. In this way, we can not only distinguish a small proportion of abnormal heart sounds in the huge data scale but also filter the noise through the noise reduction network, thus significantly improving the detection accuracy. In addition, we evaluated our method using real datasets. When the noise of sigma = 0.5, the AUC standard deviation of the WR-CAE-OCSVM is 19.2, 54.1, and 29.8% lower than that of WR-OCSVM, CAE-OCSVM and OCSVM, respectively. The results confirmed the higher accuracy of anomaly detection in WCOS compared to other state-of-the-art methods.</p>","PeriodicalId":12462,"journal":{"name":"Frontiers in Neuroinformatics","volume":"19 ","pages":"1530047"},"PeriodicalIF":2.5,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11813893/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143406035","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Editorial: Recent applications of noninvasive physiological signals and artificial intelligence.
IF 2.5 4区 医学 Q2 MATHEMATICAL & COMPUTATIONAL BIOLOGY Pub Date : 2025-01-16 eCollection Date: 2025-01-01 DOI: 10.3389/fninf.2025.1543103
Irma N Angulo, Eduardo Iáñez, Andres Ubeda
{"title":"Editorial: Recent applications of noninvasive physiological signals and artificial intelligence.","authors":"Irma N Angulo, Eduardo Iáñez, Andres Ubeda","doi":"10.3389/fninf.2025.1543103","DOIUrl":"https://doi.org/10.3389/fninf.2025.1543103","url":null,"abstract":"","PeriodicalId":12462,"journal":{"name":"Frontiers in Neuroinformatics","volume":"19 ","pages":"1543103"},"PeriodicalIF":2.5,"publicationDate":"2025-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11779702/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143079233","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Power spectral analysis of voltage-gated channels in neurons.
IF 2.5 4区 医学 Q2 MATHEMATICAL & COMPUTATIONAL BIOLOGY Pub Date : 2025-01-15 eCollection Date: 2024-01-01 DOI: 10.3389/fninf.2024.1472499
Christophe Magnani, Lee E Moore

This article develops a fundamental insight into the behavior of neuronal membranes, focusing on their responses to stimuli measured with power spectra in the frequency domain. It explores the use of linear and nonlinear (quadratic sinusoidal analysis) approaches to characterize neuronal function. It further delves into the random theory of internal noise of biological neurons and the use of stochastic Markov models to investigate these fluctuations. The text also discusses the origin of conductance noise and compares different power spectra for interpreting this noise. Importantly, it introduces a novel sequential chemical state model, named p 2, which is more general than the Hodgkin-Huxley formulation, so that the probability for an ion channel to be open does not imply exponentiation. In particular, it is demonstrated that the p 2 (without exponentiation) and n 4 (with exponentiation) models can produce similar neuronal responses. A striking relationship is also shown between fluctuation and quadratic power spectra, suggesting that voltage-dependent random mechanisms can have a significant impact on deterministic nonlinear responses, themselves known to have a crucial role in the generation of action potentials in biological neural networks.

{"title":"Power spectral analysis of voltage-gated channels in neurons.","authors":"Christophe Magnani, Lee E Moore","doi":"10.3389/fninf.2024.1472499","DOIUrl":"https://doi.org/10.3389/fninf.2024.1472499","url":null,"abstract":"<p><p>This article develops a fundamental insight into the behavior of neuronal membranes, focusing on their responses to stimuli measured with power spectra in the frequency domain. It explores the use of linear and nonlinear (quadratic sinusoidal analysis) approaches to characterize neuronal function. It further delves into the random theory of internal noise of biological neurons and the use of stochastic Markov models to investigate these fluctuations. The text also discusses the origin of conductance noise and compares different power spectra for interpreting this noise. Importantly, it introduces a novel sequential chemical state model, named <i>p</i> <sub>2</sub>, which is more general than the Hodgkin-Huxley formulation, so that the probability for an ion channel to be open does not imply exponentiation. In particular, it is demonstrated that the <i>p</i> <sub>2</sub> (without exponentiation) and <i>n</i> <sup>4</sup> (with exponentiation) models can produce similar neuronal responses. A striking relationship is also shown between fluctuation and quadratic power spectra, suggesting that voltage-dependent random mechanisms can have a significant impact on deterministic nonlinear responses, themselves known to have a crucial role in the generation of action potentials in biological neural networks.</p>","PeriodicalId":12462,"journal":{"name":"Frontiers in Neuroinformatics","volume":"18 ","pages":"1472499"},"PeriodicalIF":2.5,"publicationDate":"2025-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11774927/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143064901","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
The Multicentre Acute ischemic stroke imaGIng and Clinical data (MAGIC) repository: rationale and blueprint. 多中心急性缺血性卒中成像和临床数据(MAGIC)存储库:原理和蓝图。
IF 2.5 4区 医学 Q2 MATHEMATICAL & COMPUTATIONAL BIOLOGY Pub Date : 2025-01-07 eCollection Date: 2024-01-01 DOI: 10.3389/fninf.2024.1508161
Hakim Baazaoui, Stefan T Engelter, Henrik Gensicke, Lukas S Enz, Marios Psychogios, Matthias Mutke, Patrik Michel, Davide Strambo, Alexander Salerno, Henk A Marquering, Paul J Nederkoorn, Nabila Wali, Stephanie Tanadini-Lang, Björn Menze, Ezequiel de la Rosa, Kaiyuan Yang, Gian Marco De Marchis, Tolga D Dittrich, Francesco Valletta, Manon Germann, Carlo W Cereda, João Pedro Marto, Lisa Herzog, Patrick Hirschi, Zsolt Kulcsar, Susanne Wegener

Purpose: The Multicentre Acute ischemic stroke imaGIng and Clinical data (MAGIC) repository is a collaboration established in 2024 by seven stroke centres in Europe. MAGIC consolidates clinical and radiological data from acute ischemic stroke (AIS) patients who underwent endovascular therapy, intravenous thrombolysis, a combination of both, or conservative management.

Participants: All centres ensure accuracy and completeness of the data. Only patients who did not refuse use of their routine data collected during or after their hospital stay are included in the repository. Approvals or waivers are obtained from the responsible ethics committees before data exchange. A formal data transfer agreement (DTA) is signed by all contributing centres. The centres then share their data, and files are stored centrally on a safe server at the University Hospital Zurich. There, patient identifiers are removed and images are algorithmically de-faced. De-identified structured clinical data are connected to the imaging data by a new identifier. Data are made available to participating centres which have entered into a DTA for stroke research projects.

Repository setup: Initially, MAGIC is set to comprise initial and first follow-up imaging of 2,500 AIS patients. Clinical data consist of a comprehensive set of patient characteristics and routine prehospital metrics, treatment and laboratory variables.

Outlook: Our repository will support research by leveraging the entire range of routinely collected imaging and clinical data. This dataset reflects the current state of practice in stroke patient evaluation and management and will enable researchers to retrospectively study clinically relevant questions outside the scope of randomized controlled clinical trials. New centres are invited to join MAGIC if they meet the requirements outlined here. We aim to reach approximately 10,000 cases by 2026.

目的:多中心急性缺血性卒中成像和临床数据(MAGIC)存储库是由欧洲7个卒中中心于2024年合作建立的。MAGIC整合了急性缺血性卒中(AIS)患者的临床和放射学数据,这些患者接受了血管内治疗、静脉溶栓、两者联合治疗或保守治疗。参加者:各中心确保资料的准确性及完整性。只有不拒绝使用住院期间或住院后收集的常规数据的患者才被纳入存储库。在数据交换之前,必须获得负责任的伦理委员会的批准或豁免。所有提供数据的中心签署了正式的数据转移协议。然后,这些中心共享他们的数据,文件集中存储在苏黎世大学医院的一台安全服务器上。在那里,患者标识符被删除,图像被算法删除。去识别的结构化临床数据通过一个新的标识符连接到成像数据。数据提供给已签订中风研究项目数据交换协议的参与中心。存储库设置:最初,MAGIC将包括2500名AIS患者的初始和首次随访成像。临床数据包括一套全面的患者特征和常规院前指标、治疗和实验室变量。展望:我们的知识库将通过利用常规收集的所有影像和临床数据来支持研究。该数据集反映了卒中患者评估和管理的现状,并将使研究人员能够回顾性地研究随机对照临床试验范围之外的临床相关问题。新中心如符合以下要求,可获邀请加入MAGIC。我们的目标是到2026年达到约1万例。
{"title":"The Multicentre Acute ischemic stroke imaGIng and Clinical data (MAGIC) repository: rationale and blueprint.","authors":"Hakim Baazaoui, Stefan T Engelter, Henrik Gensicke, Lukas S Enz, Marios Psychogios, Matthias Mutke, Patrik Michel, Davide Strambo, Alexander Salerno, Henk A Marquering, Paul J Nederkoorn, Nabila Wali, Stephanie Tanadini-Lang, Björn Menze, Ezequiel de la Rosa, Kaiyuan Yang, Gian Marco De Marchis, Tolga D Dittrich, Francesco Valletta, Manon Germann, Carlo W Cereda, João Pedro Marto, Lisa Herzog, Patrick Hirschi, Zsolt Kulcsar, Susanne Wegener","doi":"10.3389/fninf.2024.1508161","DOIUrl":"10.3389/fninf.2024.1508161","url":null,"abstract":"<p><strong>Purpose: </strong>The Multicentre Acute ischemic stroke imaGIng and Clinical data (MAGIC) repository is a collaboration established in 2024 by seven stroke centres in Europe. MAGIC consolidates clinical and radiological data from acute ischemic stroke (AIS) patients who underwent endovascular therapy, intravenous thrombolysis, a combination of both, or conservative management.</p><p><strong>Participants: </strong>All centres ensure accuracy and completeness of the data. Only patients who did not refuse use of their routine data collected during or after their hospital stay are included in the repository. Approvals or waivers are obtained from the responsible ethics committees before data exchange. A formal data transfer agreement (DTA) is signed by all contributing centres. The centres then share their data, and files are stored centrally on a safe server at the University Hospital Zurich. There, patient identifiers are removed and images are algorithmically de-faced. De-identified structured clinical data are connected to the imaging data by a new identifier. Data are made available to participating centres which have entered into a DTA for stroke research projects.</p><p><strong>Repository setup: </strong>Initially, MAGIC is set to comprise initial and first follow-up imaging of 2,500 AIS patients. Clinical data consist of a comprehensive set of patient characteristics and routine prehospital metrics, treatment and laboratory variables.</p><p><strong>Outlook: </strong>Our repository will support research by leveraging the entire range of routinely collected imaging and clinical data. This dataset reflects the current state of practice in stroke patient evaluation and management and will enable researchers to retrospectively study clinically relevant questions outside the scope of randomized controlled clinical trials. New centres are invited to join MAGIC if they meet the requirements outlined here. We aim to reach approximately 10,000 cases by 2026.</p>","PeriodicalId":12462,"journal":{"name":"Frontiers in Neuroinformatics","volume":"18 ","pages":"1508161"},"PeriodicalIF":2.5,"publicationDate":"2025-01-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11747442/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143002715","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
期刊
Frontiers in Neuroinformatics
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1