The development of a novel zeolite-based assay for efficient and deep plasma proteomic profiling.

Plasma proteins are considered the most informative source of biomarkers for disease diagnosis and monitoring. Mass spectrometry (MS)-based proteomics has been applied to identify biomarkers in plasma, but the complexity of the plasma proteome and the extremely large dynamic range of protein abundances in plasma make the clinical application of plasma proteomics highly challenging. We designed and synthesized zeolite-based nanoparticles to deplete high-abundance plasma proteins. The resulting novel plasma proteomic assay can measure approximately 3000 plasma proteins in a 45 min chromatographic gradient. Compared to those in neat and depleted plasma, the plasma proteins identified by our assay exhibited distinct biological profiles, as validated in several public datasets. A pilot investigation of the proteomic profile of a hepatocellular carcinoma (HCC) cohort identified 15 promising protein features, highlighting the diagnostic value of the plasma proteome in distinguishing individuals with and without HCC. Furthermore, this assay can be easily integrated with all current downstream protein profiling methods and potentially extended to other biofluids. In conclusion, we established a robust and efficient plasma proteomic assay with unprecedented identification depth, paving the way for the translation of plasma proteomics into clinical applications.

IMPRINTS.CETSA and IMPRINTS.CETSA.app: an R package and a Shiny application for the analysis and interpretation of IMPRINTS-CETSA data.

IMPRINTS-CETSA (Integrated Modulation of Protein Interaction States-Cellular Thermal Shift Assay) provides a highly resolved means to systematically study the interactions of proteins with other cellular components, including metabolites, nucleic acids and other proteins, at the proteome level, but no freely available and user-friendly data analysis software has been reported. Here, we report IMPRINTS.CETSA, an R package that provides the basic data processing framework for robust analysis of the IMPRINTS-CETSA data format, from preprocessing and normalization to visualization. We also report an accompanying R package, IMPRINTS.CETSA.app, which offers a user-friendly Shiny interface for analysis and interpretation of IMPRINTS-CETSA results, with seamless features such as functional enrichment and mapping to other databases at a single site. For the hit generation part, the diverse behaviors of protein modulations have been typically segregated with a two-measure scoring method, i.e. the abundance and thermal stability changes. We present a new algorithm to classify modulated proteins in IMPRINTS-CETSA experiments by a robust single-measure scoring. In this way, both the numerical changes and the statistical significances of the IMPRINTS information can be visualized on a single plot. The IMPRINTS.CETSA and IMPRINTS.CETSA.app R packages are freely available on GitHub at https://github.com/nkdailingyun/IMPRINTS.CETSA and https://github.com/mgerault/IMPRINTS.CETSA.app, respectively. IMPRINTS.CETSA.app is also available as an executable program at https://zenodo.org/records/10636134.

Moiré Pattern Controlled Phonon Polarizer Based on Twisted Graphene.

Twisted van der Waals materials featuring Moiré patterns present new design possibilities and demonstrate unconventional behaviors in electrical, optical, spintronic, and superconducting properties. However, experimental exploration of thermal transport across Moiré patterns has not been as extensive, despite its critical role in nanoelectronics, thermal management, and energy technologies. Here, the first experimental study is conducted on thermal transport across twisted graphene, demonstrating a phonon polarizer concept from the rotational misalignment between stacked layers. The direct thermal and acoustic measurements, structural characterizations, and atomistic modeling, reveal a modulation up to 631% in thermal conductance with various Moiré angles, while maintaining a high acoustic transmission. By comparing experiments with density functional theory and molecular dynamics simulations, mode-dependent phonon transmissions are quantified based on the angle alignment of graphene band structures and attributed to the coupling among flexural phonon modes. The agreement confirms the dominant tuning mechanisms in adjusting phonon transmission from high-frequency thermal modes while having negligible effects on low-frequency acoustic modes near Brillouin zone center. This study offers crucial insights into the fundamental thermal transport in Moiré structures, opening avenues for the invention of quantum thermal devices and new design methodologies based on manipulations of vibrational band structures and phonon spectra.

HGSMDA: miRNA-Disease Association Prediction Based on HyperGCN and Sørensen-Dice Loss.

Biological research has demonstrated the significance of identifying miRNA-disease associations in the context of disease prevention, diagnosis, and treatment. However, the utilization of experimental approaches involving biological subjects to infer these associations is both costly and inefficient. Consequently, there is a pressing need to devise novel approaches that offer enhanced accuracy and effectiveness. Presently, the predominant methods employed for predicting disease associations rely on Graph Convolutional Network (GCN) techniques. However, the Graph Convolutional Network algorithm, which is locally aggregated, solely incorporates information from the immediate neighboring nodes of a given node at each layer. Consequently, GCN cannot simultaneously aggregate information from multiple nodes. This constraint significantly impacts the predictive efficacy of the model. To tackle this problem, we propose a novel approach, based on HyperGCN and Sørensen-Dice loss (HGSMDA), for predicting associations between miRNAs and diseases. In the initial phase, we developed multiple networks to represent the similarity between miRNAs and diseases and employed GCNs to extract information from diverse perspectives. Subsequently, we draw into HyperGCN to construct a miRNA-disease heteromorphic hypergraph using hypernodes and train GCN on the graph to aggregate information. Finally, we utilized the Sørensen-Dice loss function to evaluate the degree of similarity between the predicted outcomes and the ground truth values, thereby enabling the prediction of associations between miRNAs and diseases. In order to assess the soundness of our methodology, an extensive series of experiments was conducted employing the Human MicroRNA Disease Database (HMDD v3.2) as the dataset. The experimental outcomes unequivocally indicate that HGSMDA exhibits remarkable efficacy when compared to alternative methodologies. Furthermore, the predictive capacity of HGSMDA was corroborated through a case study focused on colon cancer. These findings strongly imply that HGSMDA represents a dependable and valid framework, thereby offering a novel avenue for investigating the intricate association between miRNAs and diseases.

Perfluorooctanoic acid induces Leydig cell injury via inhibition of autophagosomes formation and activation of endoplasmic reticulum stress.

Perfluorooctanoic acid (PFOA) is a man-made chemical broadly distributed in various ecological environment and human bodies, which poses potential health risks. Its toxicity, especially the male reproduction toxicity has drawn increasing attention due to declining birth rates in recent years. However, how PFOA induces male reproductive toxicity remains unclear. Here, we characterize PFOA-induced cell injury and reveal the underlying mechanism in mouse Leydig cells, which are critical to spermatogenesis in the testes. We show that PFOA induces cell injury as evidenced by reduced cell viability, cell morphology changes and apoptosis induction. RNA-sequencing analysis reveals that PFOA-induced cell injury is correlated with compromised autophagy and activated endoplasmic reticulum (ER) stress, two conserved biological processes required for regulating cellular homeostasis. Mechanistic analysis shows that PFOA inhibits autophagosomes formation, and activation of autophagy rescues PFOA-induced apoptosis. Additionally, PFOA activates ER stress, and pharmacological inhibition of ER stress attenuates PFOA-induced cell injury. Taken together, these results demonstrate that PFOA induces cell injury through inhibition of autophagosomes formation and induction of ER stress in Leydig cells. Thus, our study sheds light on the cellular mechanisms of PFOA-induced Leydig cell injury, which may be suggestive to human male reproductive health risk assessment and prevention from PFOA exposure-induced reproductive toxicity.

Deep learning based CETSA feature prediction cross multiple cell lines with latent space representation.

Mass spectrometry-coupled cellular thermal shift assay (MS-CETSA), a biophysical principle-based technique that measures the thermal stability of proteins at the proteome level inside the cell, has contributed significantly to the understanding of drug mechanisms of action and the dissection of protein interaction dynamics in different cellular states. One of the barriers to the wide applications of MS-CETSA is that MS-CETSA experiments must be performed on the specific cell lines of interest, which is typically time-consuming and costly in terms of labeling reagents and mass spectrometry time. In this study, we aim to predict CETSA features in various cell lines by introducing a computational framework called CycleDNN based on deep neural network technology. For a given set of n cell lines, CycleDNN comprises n auto-encoders. Each auto-encoder includes an encoder to convert CETSA features from one cell line into latent features in a latent space [Formula: see text]. It also features a decoder that transforms the latent features back into CETSA features for another cell line. In such a way, the proposed CycleDNN creates a cyclic prediction of CETSA features across different cell lines. The prediction loss, cycle-consistency loss, and latent space regularization loss are used to guide the model training. Experimental results on a public CETSA dataset demonstrate the effectiveness of our proposed approach. Furthermore, we confirm the validity of the predicted MS-CETSA data from our proposed CycleDNN through validation in protein-protein interaction prediction.

Deep learning enables the discovery of a novel cuproptosis-inducing molecule for the inhibition of hepatocellular carcinoma.

Hepatocellular carcinoma (HCC) is one of the most common and deadly cancers in the world. The therapeutic outlook for HCC patients has significantly improved with the advent and development of systematic and targeted therapies such as sorafenib and lenvatinib; however, the rise of drug resistance and the high mortality rate necessitate the continuous discovery of effective targeting agents. To discover novel anti-HCC compounds, we first constructed a deep learning-based chemical representation model to screen more than 6 million compounds in the ZINC15 drug-like library. We successfully identified LGOd1 as a novel anticancer agent with a characteristic levoglucosenone (LGO) scaffold. The mechanistic studies revealed that LGOd1 treatment leads to HCC cell death by interfering with cellular copper homeostasis, which is similar to a recently reported copper-dependent cell death named cuproptosis. While the prototypical cuproptosis is brought on by copper ionophore-induced copper overload, mechanistic studies indicated that LGOd1 does not act as a copper ionophore, but most likely by interacting with the copper chaperone protein CCS, thus LGOd1 represents a potentially new class of compounds with unique cuproptosis-inducing property. In summary, our findings highlight the critical role of bioavailable copper in the regulation of cell death and represent a novel route of cuproptosis induction.

New insights into the oscillations of the nucleon electromagnetic form factors.

The electromagnetic form factors of the proton and the neutron in the timelike region are investigated. Electron-positron annihilation into antinucleon-nucleon (N¯N) pairs is treated in distorted wave Born approximation, including the final-state interaction in the N¯N system. The latter is obtained by a Lippmann-Schwinger equation for N¯N potentials derived within SU(3) chiral effective field theory. By fitting to the phase shifts and (differential) cross section data, a high quality description is achieved. With these amplitudes, the oscillations of the electromagnetic form factors of the proton and the neutron are studied. It is found that each of them can be described by two fractional oscillators. One is characterized as "overdamped" and dominates near the threshold, while the other is "underdamped" and plays an important role in the high-energy region. These two oscillators are essential to understand the distributions of polarized electric charges induced by hard photons for the nucleons.

Systematic thermal analysis of the Arabidopsis proteome: Thermal tolerance, organization, and evolution.

Understanding the thermal stability of the plant proteome in the context of the native cellular environment would aid the design of crops with high thermal tolerance, but only limited such data are available. Here, we applied quantitative mass spectrometry to profile the thermal stability of the Arabidopsis proteome and identify thermo-sensitive and thermo-resilient protein networks in Arabidopsis, providing a basis for understanding heat-induced damage. We also show that the similarities of the protein-melting curves can be used as a proxy to evaluate system-wide protein-protein interactions in non-engineered plants and enable the identification of transient interactions exhibited by metabolons in the context of the cellular environment. Finally, we report a systematic comparison of the thermal stability of paralogs in Arabidopsis to aid the investigation and understanding of gene duplication and protein evolution. Taken together, our results could have broad implications for the fields of plant thermal tolerance, plant protein assemblies, and evolution.

Network embedding framework for driver gene discovery by combining functional and structural information.

Comprehensive analysis of multiple data sets can identify potential driver genes for various cancers. In recent years, driver gene discovery based on massive mutation data and gene interaction networks has attracted increasing attention, but there is still a need to explore combining functional and structural information of genes in protein interaction networks to identify driver genes. Therefore, we propose a network embedding framework combining functional and structural information to identify driver genes. Firstly, we combine the mutation data and gene interaction networks to construct mutation integration network using network propagation algorithm. Secondly, the struc2vec model is used for extracting gene features from the mutation integration network, which contains both gene's functional and structural information. Finally, machine learning algorithms are utilized to identify the driver genes. Compared with the previous four excellent methods, our method can find gene pairs that are distant from each other through structural similarities and has better performance in identifying driver genes for 12 cancers in the cancer genome atlas. At the same time, we also conduct a comparative analysis of three gene interaction networks, three gene standard sets, and five machine learning algorithms. Our framework provides a new perspective for feature selection to identify novel driver genes.

Beyond canonical PROTAC: biological targeted protein degradation (bioTPD).

Targeted protein degradation (TPD) is an emerging therapeutic strategy with the potential to modulate disease-associated proteins that have previously been considered undruggable, by employing the host destruction machinery. The exploration and discovery of cellular degradation pathways, including but not limited to proteasomes and lysosome pathways as well as their degraders, is an area of active research. Since the concept of proteolysis-targeting chimeras (PROTACs) was introduced in 2001, the paradigm of TPD has been greatly expanded and moved from academia to industry for clinical translation, with small-molecule TPD being particularly represented. As an indispensable part of TPD, biological TPD (bioTPD) technologies including peptide-, fusion protein-, antibody-, nucleic acid-based bioTPD and others have also emerged and undergone significant advancement in recent years, demonstrating unique and promising activities beyond those of conventional small-molecule TPD. In this review, we provide an overview of recent advances in bioTPD technologies, summarize their compositional features and potential applications, and briefly discuss their drawbacks. Moreover, we present some strategies to improve the delivery efficacy of bioTPD, addressing their challenges in further clinical development.

ARGLRR: A Sparse Low-Rank Representation Single-Cell RNA-Sequencing Data Clustering Method Combined with a New Graph Regularization.

The development of single-cell transcriptome sequencing technologies has opened new ways to study biological phenomena at the cellular level. A key application of such technologies involves the employment of single-cell RNA sequencing (scRNA-seq) data to identify distinct cell types through clustering, which in turn provides evidence for revealing heterogeneity. Despite the promise of this approach, the inherent characteristics of scRNA-seq data, such as higher noise levels and lower coverage, pose major challenges to existing clustering methods and compromise their accuracy. In this study, we propose a method called Adjusted Random walk Graph regularization Sparse Low-Rank Representation (ARGLRR), a practical sparse subspace clustering method, to identify cell types. The fundamental low-rank representation (LRR) model is concerned with the global structure of data. To address the limited ability of the LRR method to capture local structure, we introduced adjusted random walk graph regularization in its framework. ARGLRR allows for the capture of both local and global structures in scRNA-seq data. Additionally, the imposition of similarity constraints into the LRR framework further improves the ability of the proposed model to estimate cell-to-cell similarity and capture global structural relationships between cells. ARGLRR surpasses other advanced comparison approaches on nine known scRNA-seq data sets judging by the results. In the normalized mutual information and Adjusted Rand Index metrics on the scRNA-seq data sets clustering experiments, ARGLRR outperforms the best-performing comparative method by 6.99% and 5.85%, respectively. In addition, we visualize the result using Uniform Manifold Approximation and Projection. Visualization results show that the usage of ARGLRR enhances the separation of different cell types within the similarity matrix.

Deep Profiling of the Proteome Dynamics of Pseudomonas aeruginosa Reference Strain PAO1 under Different Growth Conditions.

As one of the most common bacterial pathogens causing nosocomial infections, Pseudomonas aeruginosa is highly adaptable to survive under various conditions. Here, we profiled the abundance dynamics of 3489 proteins across different growth stages in the P. aeruginosa reference strain PAO1 using data-independent acquisition-based quantitative proteomics. The proteins differentially expressed during the planktonic growth exhibit several distinct patterns of expression profiles and are relevant to various biological processes, highlighting the continuous adaptation of the PAO1 proteome during the transition from the acceleration phase to the stationary phase. By contrasting the protein expressions in a biofilm to planktonic cells, the known roles of T6SS, phenazine biosynthesis, quorum sensing, and c-di-GMP signaling in the biofilm formation process were confirmed. Additionally, we also discovered several new functional proteins that may play roles in the biofilm formation process. Lastly, we demonstrated the general concordance of protein expressions within operons across various growth states, which permits the study of coexpression protein units, and reversely, the study of regulatory components in the operon structure. Taken together, we present a high-quality and valuable resource on the proteomic dynamics of the P. aeruginosa reference strain PAO1, with the potential of advancing our understanding of the overall physiology of Pseudomonas bacteria.

Single-cell transcriptomic dissection of the cellular and molecular events underlying the triclosan-induced liver fibrosis in mice.

BACKGROUND: Triclosan [5-chloro-2-(2,4-dichlorophenoxy) phenol, TCS], a common antimicrobial additive in many personal care and health care products, is frequently detected in human blood and urine. Therefore, it has been considered an emerging and potentially toxic pollutant in recent years. Long-term exposure to TCS has been suggested to exert endocrine disruption effects, and promote liver fibrogenesis and tumorigenesis. This study was aimed at clarifying the underlying cellular and molecular mechanisms of hepatotoxicity effect of TCS at the initiation stage. METHODS: C57BL/6 mice were exposed to different dosages of TCS for 2 weeks and the organ toxicity was evaluated by various measurements including complete blood count, histological analysis and TCS quantification. Single cell RNA sequencing (scRNA-seq) was then carried out on TCS- or mock-treated mouse livers to delineate the TCS-induced hepatotoxicity. The acquired single-cell transcriptomic data were analyzed from different aspects including differential gene expression, transcription factor (TF) regulatory network, pseudotime trajectory, and cellular communication, to systematically dissect the molecular and cellular events after TCS exposure. To verify the TCS-induced liver fibrosis, the expression levels of key fibrogenic proteins were examined by Western blotting, immunofluorescence, Masson's trichrome and Sirius red staining. In addition, normal hepatocyte cell MIHA and hepatic stellate cell LX-2 were used as in vitro cell models to experimentally validate the effects of TCS by immunological, proteomic and metabolomic technologies. RESULTS: We established a relatively short term TCS exposure murine model and found the TCS mainly accumulated in the liver. The scRNA-seq performed on the livers of the TCS-treated and control group profiled the gene expressions of > 76,000 cells belonging to 13 major cell types. Among these types, hepatocytes and hepatic stellate cells (HSCs) were significantly increased in TCS-treated group. We found that TCS promoted fibrosis-associated proliferation of hepatocytes, in which Gata2 and Mef2c are the key driving TFs. Our data also suggested that TCS induced the proliferation and activation of HSCs, which was experimentally verified in both liver tissue and cell model. In addition, other changes including the dysfunction and capillarization of endothelial cells, an increase of fibrotic characteristics in B plasma cells, and M2 phenotype-skewing of macrophage cells, were also deduced from the scRNA-seq analysis, and these changes are likely to contribute to the progression of liver fibrosis. Lastly, the key differential ligand-receptor pairs involved in cellular communications were identified and we confirmed the role of GAS6_AXL interaction-mediated cellular communication in promoting liver fibrosis. CONCLUSIONS: TCS modulates the cellular activities and fates of several specific cell types (including hepatocytes, HSCs, endothelial cells, B cells, Kupffer cells and liver capsular macrophages) in the liver, and regulates the ligand-receptor interactions between these cells, thereby promoting the proliferation and activation of HSCs, leading to liver fibrosis. Overall, we provide the first comprehensive single-cell atlas of mouse livers in response to TCS and delineate the key cellular and molecular processes involved in TCS-induced hepatotoxicity and fibrosis.

Transcription factor E2F8 is a therapeutic target in the basal-like subtype of breast cancer.

Introduction: Tumorigenesis in breast cancers usually accompanied by the dysregulation of transcription factors (TFs). Abnormal amplification of TFs leads aberrant expression of its downstream target genes. However, breast cancers are heterogeneous disease with different subtypes that have distinguished clinical behaviours, and the identification of prognostic TFs may enable to provide diagnosis and treatment of breast cancer based on subtypes, especially in Basal-like breast cancer. Methods: The RNA-sequencing was performed to screen differential TFs in breast cancer subtypes. The GEPIA dataset analysis was used to analyze the genes expression in invasive breast carcinoma. The expression of MYBL2, HOXC13, and E2F8 was verified by qRT-PCR assay in breast cancers. The depiction analysis of co-expressed proteins was revealed using the STRING datasets. The cellular infiltration level analysis by the TISIDB and TIMER databases. The transwell assay was performed to analyze cellular migration and invasion. CCK-8 assay was used to evaluate cellular drug susceptibility for docetaxel treatment. Predicted targeted drugs in breast cancers by GSCA Lite database online. Results: Kaplan-Meier plotter suggested that high expression of both E2F8 and MYBL2 in Basal-like subtype had a poor relapse-free survival. Functional enrichment results identified that apoptosis, cell cycle, and hormone ER pathway were represented the crucial regulation pathways by both E2F8 and MYBL2. In the meantime, database analysis indicated that high expression of E2F8 responded to chemotherapy, while those patients of high expression of MYBL2 responded to endocrinotherapy, and a positive correlation between the expression of E2F8 and PD-L1/CTLA4. Our cell line experiments confirmed the importance of E2F8 and MYBL2 in proliferation and chemotherapy sensitivity, possibly, the relationship with PD-L1. Additionally, we also observed that the up-regulation of E2F8 was accompanied with higher enrichments of CD4+ T cells and CD8+ T cells in breast cancers. Conclusion: Taken together, our findings elucidated a prospective target in Basal-like breast cancer, providing underlying molecular biomarkers for the development of breast cancer treatment.

A network-based method for identifying cancer driver genes based on node control centrality.

Cancer is one of the major contributors to human mortality and has a serious influence on human survival and health. In biomedical research, the identification of cancer driver genes (cancer drivers for short) is an important task; cancer drivers can promote the progression and generation of cancer. To identify cancer drivers, many methods have been developed. These computational models only identify coding cancer drivers; however, non-coding drivers likewise play significant roles in the progression of cancer. Hence, we propose a Network-based Method for identifying cancer Driver Genes based on node Control Centrality (NMDGCC), which can identify coding and non-coding cancer driver genes. The process of NMDGCC for identifying driver genes mainly includes the following two steps. In the first step, we construct a gene interaction network by using mRNAs and miRNAs expression data in the cancer state. In the second step, the control centrality of the node is used to identify cancer drivers in the constructed network. We use the breast cancer dataset from The Cancer Genome Atlas (TCGA) to verify the effectiveness of NMDGCC. Compared with the existing methods of cancer driver genes identification, NMDGCC has a better performance. NMDGCC also identifies 295 miRNAs as non-coding cancer drivers, of which 158 are related to tumorigenesis of BRCA. We also apply NMDGCC to identify driver genes related to the different breast cancer subtypes. The result shows that NMDGCC detects many cancer drivers of specific cancer subtypes.

Non-negative low-rank representation based on dictionary learning for single-cell RNA-sequencing data analysis.

In the analysis of single-cell RNA-sequencing (scRNA-seq) data, how to effectively and accurately identify cell clusters from a large number of cell mixtures is still a challenge. Low-rank representation (LRR) method has achieved excellent results in subspace clustering. But in previous studies, most LRR-based methods usually choose the original data matrix as the dictionary. In addition, the methods based on LRR usually use spectral clustering algorithm to complete cell clustering. Therefore, there is a matching problem between the spectral clustering method and the affinity matrix, which is difficult to ensure the optimal effect of clustering. Considering the above two points, we propose the DLNLRR method to better identify the cell type. First, DLNLRR can update the dictionary during the optimization process instead of using the predefined fixed dictionary, so it can realize dictionary learning and LRR learning at the same time. Second, DLNLRR can realize subspace clustering without relying on spectral clustering algorithm, that is, we can perform clustering directly based on the low-rank matrix. Finally, we carry out a large number of experiments on real single-cell datasets and experimental results show that DLNLRR is superior to other scRNA-seq data analysis algorithms in cell type identification.

MSF-UBRW: An Improved Unbalanced Bi-Random Walk Method to Infer Human lncRNA-Disease Associations.

Long-non-coding RNA (lncRNA) is a transcription product that exerts its biological functions through a variety of mechanisms. The occurrence and development of a series of human diseases are closely related to abnormal expression levels of lncRNAs. Scientists have developed many computational models to identify the lncRNA-disease associations (LDAs). However, many potential LDAs are still unknown. In this paper, a novel method, namely MSF-UBRW (multiple similarities fusion based on unbalanced bi-random walk), is designed to explore new LDAs. First, two similarities (functional similarity and Gaussian Interaction Profile kernel similarity) of lncRNAs are calculated and fused linearly, also for disease data. Then, the known association matrix is preprocessed. Next, the linear neighbor similarities of lncRNAs and diseases are calculated, respectively. After that, the potential associations are predicted based on unbalanced bi-random walk. The fusion of multiple similarities improves the prediction performance of MSF-UBRW to a large extent. Finally, the prediction ability of the MSF-UBRW algorithm is measured by two statistical methods, leave-one-out cross-validation (LOOCV) and 5-fold cross-validation (5-fold CV). The AUCs of 0.9391 in LOOCV and 0.9183 (±0.0054) in 5-fold CV confirmed the reliable prediction ability of the MSF-UBRW method. Case studies of three common diseases also show that the MSF-UBRW method can infer new LDAs effectively.

Epileptic Seizure Detection Based on Variational Mode Decomposition and Deep Forest Using EEG Signals.

Electroencephalography (EEG) records the electrical activity of the brain, which is an important tool for the automatic detection of epileptic seizures. It is certainly a very heavy burden to only recognize EEG epilepsy manually, so the method of computer-assisted treatment is of great importance. This paper presents a seizure detection algorithm based on variational modal decomposition (VMD) and a deep forest (DF) model. Variational modal decomposition is performed on EEG recordings, and the first three variational modal functions (VMFs) are selected to construct the time-frequency distribution of the EEG signals. Then, the log-Euclidean covariance matrix (LECM) is computed to represent the EEG properties and form EEG features. The deep forest model is applied to complete the EEG signal classification, which is a non-neural network deep model with a cascade structure that performs feature learning through the forest. In addition, to improve the classification accuracy, postprocessing techniques are performed to generate the discriminant results by moving average filtering and adaptive collar expansion. The algorithm was evaluated on the Bonn EEG dataset and the Freiburg long-term EEG dataset, and the former achieved a sensitivity and specificity of 99.32% and 99.31%, respectively. The mean sensitivity and specificity of this method for the 21 patients in the Freiburg dataset were 95.2% and 98.56%, respectively, with a false detection rate of 0.36/h. These results demonstrate the superior performance advantage of our algorithm and indicate its great research potential in epilepsy detection.

Automatic Epileptic Seizure Detection Using Graph-Regularized Non-Negative Matrix Factorization and Kernel-Based Robust Probabilistic Collaborative Representation.

Automatic seizure detection system can serve as a meaningful clinical tool for the treatment and analysis of epilepsy using electroencephalogram (EEG) and has obtained rapid development. An automatic detection of epileptic seizure method based on kernel-based robust probabilistic collaborative representation (ProCRC) combined with graph-regularized non-negative matrix factorization (GNMF) is proposed in this work. The raw EEG signals are pre-processed through the wavelet transform to obtain time-frequency distribution of EEG signals as preliminary feature information and GNMF is further employed for dimension reduction, retaining and enhancing the productive feature information of EEG signals. Then, the test sample is represented using robust ProCRC that can decide whether the testing sample belongs to each class (seizure or non-seizure) by jointly maximizing the likelihood. In addition, the kernel trick is applied to improve the separability of non-linear high dimensional EEG signals in robust ProCRC. Finally, post-processing techniques are introduced to generate more accurate and reliable results. The average epoch-based sensitivity of 96.48%, event-based sensitivity of 93.65% and specificity of 98.55% are acquired in this method, which is evaluated on the public Freiburg EEG database.