Advancing single-cell RNA-seq data analysis through the fusion of multi-layer perceptron and graph neural network.

The advancement of single-cell sequencing technology has smoothed the ability to do biological studies at the cellular level. Nevertheless, single-cell RNA sequencing (scRNA-seq) data presents several obstacles due to the considerable heterogeneity, sparsity and complexity. Although many machine-learning models have been devised to tackle these difficulties, there is still a need to enhance their efficiency and accuracy. Current deep learning methods often fail to fully exploit the intrinsic interconnections within cells, resulting in unsatisfactory results. Given these obstacles, we propose a unique approach for analyzing scRNA-seq data called scMPN. This methodology integrates multi-layer perceptron and graph neural network, including attention network, to execute gene imputation and cell clustering tasks. In order to evaluate the gene imputation performance of scMPN, several metrics like cosine similarity, median L1 distance and root mean square error are used. These metrics are utilized to compare the efficacy of scMPN with other existing approaches. This research utilizes criteria such as adjusted mutual information, normalized mutual information and integrity score to assess the efficacy of cell clustering across different approaches. The superiority of scMPN over current single-cell data processing techniques in cell clustering and gene imputation investigations is shown by the experimental findings obtained from four datasets with gold-standard cell labels. This observation demonstrates the efficacy of our suggested methodology in using deep learning methodologies to enhance the interpretation of scRNA-seq data.

DGSIST: Clustering spatial transcriptome data based on deep graph structure Infomax.

Although spatial transcriptomics data provide valuable insights into gene expression profiles and the spatial structure of tissues, most studies rely solely on gene expression information, underutilizing the spatial data. To fully leverage the potential of spatial transcriptomics and graph neural networks, the DGSI (Deep Graph Structure Infomax) model is proposed. This innovative graph data processing model uses graph convolutional neural networks and employs an unsupervised learning approach. It maximizes the mutual information between graph-level and node-level representations, emphasizing flexible sampling and aggregation of nodes and their neighbors. This effectively captures and incorporates local information from nodes into the overall graph structure. Additionally, this paper developed the DGSIST framework, an unsupervised cell clustering method that integrates the DGSI model, SVD dimensionality reduction algorithm, and k-means++ clustering algorithm. This aims to identify cell types accurately. DGSIST fully uses spatial transcriptomics data and outperforms existing methods in accuracy. Demonstrations of DGSIST's capability across various tissue types and technological platforms have shown its effectiveness in accurately identifying spatial domains in multiple tissue sections. Compared to other spatial clustering methods, DGSIST excels in cell clustering and effectively eliminates batch effects without needing batch correction. DGSIST excels in spatial clustering analysis, spatial variation identification, and differential gene expression detection and directly applies to graph analysis tasks, such as node classification, link prediction, or graph clustering. Anticipation lies in the contribution of the DGSIST framework to a deeper understanding of the spatial organizational structures of diseases such as cancer.

Improved Intrusion Detection Based on Hybrid Deep Learning Models and Federated Learning.

The security of the Industrial Internet of Things (IIoT) is of vital importance, and the Network Intrusion Detection System (NIDS) plays an indispensable role in this. Although there is an increasing number of studies on the use of deep learning technology to achieve network intrusion detection, the limited local data of the device may lead to poor model performance because deep learning requires large-scale datasets for training. Some solutions propose to centralize the local datasets of devices for deep learning training, but this may involve user privacy issues. To address these challenges, this study proposes a novel federated learning (FL)-based approach aimed at improving the accuracy of network intrusion detection while ensuring data privacy protection. This research combines convolutional neural networks with attention mechanisms to develop a new deep learning intrusion detection model specifically designed for the IIoT. Additionally, variational autoencoders are incorporated to enhance data privacy protection. Furthermore, an FL framework enables multiple IIoT clients to jointly train a shared intrusion detection model without sharing their raw data. This strategy significantly improves the model's detection capability while effectively addressing data privacy and security issues. To validate the effectiveness of the proposed method, a series of experiments were conducted on a real-world Internet of Things (IoT) network intrusion dataset. The experimental results demonstrate that our model and FL approach significantly improve key performance metrics such as detection accuracy, precision, and false-positive rate (FPR) compared to traditional local training methods and existing models.

Ethereum Phishing Scam Detection Based on Data Augmentation Method and Hybrid Graph Neural Network Model.

The rapid advancement of blockchain technology has fueled the prosperity of the cryptocurrency market. Unfortunately, it has also facilitated certain criminal activities, particularly the increasing issue of phishing scams on blockchain platforms such as Ethereum. Consequently, developing an efficient phishing detection system is critical for ensuring the security and reliability of cryptocurrency transactions. However, existing methods have shortcomings in dealing with sample imbalance and effective feature extraction. To address these issues, this study proposes an Ethereum phishing scam detection method based on DA-HGNN (Data Augmentation Method and Hybrid Graph Neural Network Model), validated by real Ethereum datasets to prove its effectiveness. Initially, basic node features consisting of 11 attributes were designed. This study applied a sliding window sampling method based on node transactions for data augmentation. Since phishing nodes often initiate numerous transactions, the augmented samples tended to balance. Subsequently, the Temporal Features Extraction Module employed Conv1D (One-Dimensional Convolutional neural network) and GRU-MHA (GRU-Multi-Head Attention) models to uncover intrinsic relationships between features from the time sequences and to mine adequate local features, culminating in the extraction of temporal features. The GAE (Graph Autoencoder) concept was then leveraged, with SAGEConv (Graph SAGE Convolution) as the encoder. In the SAGEConv reconstruction module, by reconstructing the relationships between transaction graph nodes, the structural features of the nodes were learned, obtaining reconstructed node embedding representations. Ultimately, phishing fraud nodes were further identified by integrating temporal features, basic features, and embedding representations. A real Ethereum dataset was collected for evaluation, and the DA-HGNN model achieved an AUC-ROC (Area Under the Receiver Operating Characteristic Curve) of 0.994, a Recall of 0.995, and an F1-score of 0.994, outperforming existing methods and baseline models.

Prediction of miRNAs and diseases association based on sparse autoencoder and MLP.

Introduction: MicroRNAs (miRNAs) are small and non-coding RNA molecules which have multiple important regulatory roles within cells. With the deepening research on miRNAs, more and more researches show that the abnormal expression of miRNAs is closely related to various diseases. The relationship between miRNAs and diseases is crucial for discovering the pathogenesis of diseases and exploring new treatment methods. Methods: Therefore, we propose a new sparse autoencoder and MLP method (SPALP) to predict the association between miRNAs and diseases. In this study, we adopt advanced deep learning technologies, including sparse autoencoder and multi-layer perceptron (MLP), to improve the accuracy of predicting miRNA-disease associations. Firstly, the SPALP model uses a sparse autoencoder to perform feature learning and extract the initial features of miRNAs and diseases separately, obtaining the latent features of miRNAs and diseases. Then, the latent features combine miRNAs functional similarity data with diseases semantic similarity data to construct comprehensive miRNAs-diseases datasets. Subsequently, the MLP model can predict the unknown association among miRNAs and diseases. Result: To verify the performance of our model, we set up several comparative experiments. The experimental results show that, compared with traditional methods and other deep learning prediction methods, our method has significantly improved the accuracy of predicting miRNAs-disease associations, with 94.61% accuracy and 0.9859 AUC value. Finally, we conducted case study of SPALP model. We predicted the top 30 miRNAs that might be related to Lupus Erythematosus, Ecute Myeloid Leukemia, Cardiovascular, Stroke, Diabetes Mellitus five elderly diseases and validated that 27, 29, 29, 30, and 30 of the top 30 are indeed associated. Discussion: The SPALP approach introduced in this study is adept at forecasting the links between miRNAs and diseases, addressing the complexities of analyzing extensive bioinformatics datasets and enriching the comprehension contribution to disease progression of miRNAs.

[Efficacy evaluation of high intensity focused ultrasound combined with intra-arterial infusion of gemcitabine in the treatment of pancreatic cancer].

OBJECTIVE: The aim of this study was to discuss the clinical effectiveness of high intensity focused ultrasound (HIFU) combined with gemcitabine administered by intra-arterial infusion on intermediate and advanced pancreatic cancer. METHODS: Forty-eight patients with intermediate and advanced pancreatic cancer were divided into two groups. Twenty-four patients of the experimental group were treated by HIFU combined with gemcitabine, and 24 patients of the the HIFU group were treated by HIFU alone. Then the curative effect, extent of pain relief, and survival time were compared in the course of the treatment between the two groups. RESULTS: As compared with those in the control group, the overall response rate, level of pain relief, and 12-month survival rate after therapy were higher and the median survival time was longer in the joint group (P < 0.05). CONCLUSIONS: Ultrasound imaging, CT and associated tumor marker detection can make effective measurement to evaluate curative effect on pancreatic carcinoma. HIFU plus gemcitabine administered by intra-arterial infusion can improve the clinical therapeutic efficacy, pain relief, quality of life and long-term survival rate of patients with pancreatic cancer.

[Isolation and identification of cancer stem cells from primary human ovarian cancer tissues].

OBJECTIVE: To isolate and identify the cancer stem cells from primary human ovarian cancer tissues. METHODS: Fresh tumor tissues from five cases of pathologically diagnosed ovarian cancers were taken, minced and then digested with collagenase and hyaluronidase to obtain single cell suspension. The erythrocytes were removed with ACK Lysis buffer. The suspensions were sorted by magnetic activated cell sorting (MACS) using CD133-binding microbeads. Then the sorted CD133(+) cells were verified by flow cytometry. The cells were cultured in serum-free medium supplemented with EGF, bFGF, insulin and BSA, and grew into spheroids. Immunofluorescence, differentiation and tumor formation tests of the cells were performed to characterize the properties of cancer stem cells. RESULTS: The ovarian cancer stem cells were successfully isolated from primary human ovarian tumors, which formed typical spheroids in serum-free medium and had stronger ability of tumorigenesis. The results of related experiments verified that CD133 positive cells owned the properties of cancer stem cells. CONCLUSIONS: The ovarian cancer stem cells presenting the characteristics of stemness in vitro and in vivo, have been successfully isolated from primary human ovarian tumor tissues by MACS. The isolated ovarian cancer stem cells could be used in future researches of their biological functions.

Binary particle swarm optimization algorithm with mutation for multiple sequence alignment.

Multiple sequence alignment (MSA) is a fundamental and challenging problem in the analysis of biologic sequence. The MSA problem is hard to be solved directly, for it always results in exponential complexity with the scale of the problem. In this paper, we propose mutation-based binary particle swarm optimization (M-BPSO) for MSA solving. In the proposed M-BPSO algorithm, BPSO algorithm is conducted to provide alignments. Thereafter, mutation operator is performed to move out of local optima and speed up convergence. From simulation results of nucleic acid and amino acid sequences, it is shown that the proposed M-BPSO algorithm has superior performance when compared to other existing algorithms. Furthermore, this algorithm can be used quickly and efficiently for smaller and medium size sequences.

Metabolic flux estimation using particle swarm optimization with penalty function.

Metabolic flux estimation through 13C trace experiment is crucial for quantifying the intracellular metabolic fluxes. In fact, it corresponds to a constrained optimization problem that minimizes a weighted distance between measured and simulated results. In this paper, we propose particle swarm optimization (PSO) with penalty function to solve 13C-based metabolic flux estimation problem. The stoichiometric constraints are transformed to an unconstrained one, by penalizing the constraints and building a single objective function, which in turn is minimized using PSO algorithm for flux quantification. The proposed algorithm is applied to estimate the central metabolic fluxes of Corynebacterium glutamicum. From simulation results, it is shown that the proposed algorithm has superior performance and fast convergence ability when compared to other existing algorithms.

New descriptors of amino acids and their application to peptide QSAR study.

A new set of descriptors was derived from a matrix of three structural variables of the natural amino acid, including van der Waal's volume, net charge index and hydrophobic parameter of side residues. They were selected from many properties of amino acid residues, which have been validated being the key factors to influence the interaction between peptides and its protein receptor. They were then applied to structure characterization and QSAR analysis on bitter tasting di-peptide, agiotensin-converting enzyme inhibitor and bactericidal peptides by using multiple linear regression (MLR) method. The leave one out cross validation values (Q(2)) were 0.921, 0.943 and 0.773. The multiple correlation coefficients (R(2)) were 0.948, 0.970 and 0.926, the root mean square (RMS) error for estimated error were 0.165, 0.154 and 0.41, respectively for bitter tasting di-peptide, angiotensin-converting enzyme inhibitor and bactericidal peptides. Test sets of peptides were used to validate the quantitative model, and it was shown that all these QSAR models had good predictability for outside samples. The results showed that, in comparison with the conventional descriptors, the new set of descriptors is a useful structure characterization method for peptide QSAR analysis, which has multiple advantages, such as definite physical and chemical meaning, easy to get, and good structural characterization ability.

TWIST1 upregulates miR-214 to promote epithelial-to-mesenchymal transition and metastasis in lung adenocarcinoma.

Epithelial-to-mesenchymal transition (EMT) is essential for the progression of non-invasive tumor cells into malignancy and metastasis. We found that miR-214 was increased in lung adenocarcinoma (LAD) and positively associated with metastasis, which was mediated by EMT. However, the mechanism whereby the overexpression of microRNAs (miRNAs), such as miR-214, promote EMT in LAD remains unclear. In this study, we found that TWIST1, an independent prognostic factor for overall survival, was increased in LAD and correlated positively with LAD recurrence and progression. We also found that TWIST1 contributes to the EMT process and metastasis of LAD cells. Most importantly, a positive correlation was found between the expression of miR-214 and TWIST1 in clinical LAD tissue. Additionally, miR-214 expression was decreased and its target gene suppressor of fused homolog (SUFU) was increased in LAD cells in response to the impairment of TWIST1 expression by shRNA. Overall, this study provides the first evidence to show that the high expression of TWIST1 increases the expression of miR-214 to promote the EMT process and metastasis in LAD. These findings contribute to clarify the mechanisms whereby miRNAs regulate the EMT process and implicate a new TWIST1-miR-214 pathway in the control of migration and invasion of LAD.

Aberrant microRNAs expression in CD133⁺/CD326⁺ human lung adenocarcinoma initiating cells from A549.

Increasing evidence demonstrates that miRNAs are involved in the dysregulation of tumor initiating cells (TICs) in various tumors. Due to a lack of definitive markers, cell sorting is not an ideal separation method for lung adenocarcinoma initiating cells. In this study, we combined paclitaxel with serum-free medium cultivation (inverse-induction) to enrich TICs from A549 cells, marked by CD133/CD326, defined features of stemness. We next investigated aberrant microRNAs in this subpopulation compared to normal cells with miRNA microarray and found that 50 miRNAs exhibited a greater than 2-fold change in expression. As further validation, 10 miRNAs were chosen to perform quantitative RT-PCR on the A549 cell line and primary samples. The results suggest that aberrant expression of miRNAs such as miR-29ab, miR-183, miR-17-5p and miR-127-3P may play an important role in regulating the bio-behavior of TICs.