IHGC-GAN: influence hypergraph convolutional generative adversarial network for risk prediction of late mild cognitive impairment based on imaging genetic data.

Predicting disease progression in the initial stage to implement early intervention and treatment can effectively prevent the further deterioration of the condition. Traditional methods for medical data analysis usually fail to perform well because of their incapability for mining the correlation pattern of pathogenies. Therefore, many calculation methods have been excavated from the field of deep learning. In this study, we propose a novel method of influence hypergraph convolutional generative adversarial network (IHGC-GAN) for disease risk prediction. First, a hypergraph is constructed with genes and brain regions as nodes. Then, an influence transmission model is built to portray the associations between nodes and the transmission rule of disease information. Third, an IHGC-GAN method is constructed based on this model. This method innovatively combines the graph convolutional network (GCN) and GAN. The GCN is used as the generator in GAN to spread and update the lesion information of nodes in the brain region-gene hypergraph. Finally, the prediction accuracy of the method is improved by the mutual competition and repeated iteration between generator and discriminator. This method can not only capture the evolutionary pattern from early mild cognitive impairment (EMCI) to late MCI (LMCI) but also extract the pathogenic factors and predict the deterioration risk from EMCI to LMCI. The results on the two datasets indicate that the IHGC-GAN method has better prediction performance than the advanced methods in a variety of indicators.

Feature aggregation graph convolutional network based on imaging genetic data for diagnosis and pathogeny identification of Alzheimer's disease.

The roles of brain regions activities and gene expressions in the development of Alzheimer's disease (AD) remain unclear. Existing imaging genetic studies usually has the problem of inefficiency and inadequate fusion of data. This study proposes a novel deep learning method to efficiently capture the development pattern of AD. First, we model the interaction between brain regions and genes as node-to-node feature aggregation in a brain region-gene network. Second, we propose a feature aggregation graph convolutional network (FAGCN) to transmit and update the node feature. Compared with the trivial graph convolutional procedure, we replace the input from the adjacency matrix with a weight matrix based on correlation analysis and consider common neighbor similarity to discover broader associations of nodes. Finally, we use a full-gradient saliency graph mechanism to score and extract the pathogenetic brain regions and risk genes. According to the results, FAGCN achieved the best performance among both traditional and cutting-edge methods and extracted AD-related brain regions and genes, providing theoretical and methodological support for the research of related diseases.

A novel generation adversarial network framework with characteristics aggregation and diffusion for brain disease classification and feature selection.

Imaging genetics provides unique insights into the pathological studies of complex brain diseases by integrating the characteristics of multi-level medical data. However, most current imaging genetics research performs incomplete data fusion. Also, there is a lack of effective deep learning methods to analyze neuroimaging and genetic data jointly. Therefore, this paper first constructs the brain region-gene networks to intuitively represent the association pattern of pathogenetic factors. Second, a novel feature information aggregation model is constructed to accurately describe the information aggregation process among brain region nodes and gene nodes. Finally, a deep learning method called feature information aggregation and diffusion generative adversarial network (FIAD-GAN) is proposed to efficiently classify samples and select features. We focus on improving the generator with the proposed convolution and deconvolution operations, with which the interpretability of the deep learning framework has been dramatically improved. The experimental results indicate that FIAD-GAN can not only achieve superior results in various disease classification tasks but also extract brain regions and genes closely related to AD. This work provides a novel method for intelligent clinical decisions. The relevant biomedical discoveries provide a reliable reference and technical basis for the clinical diagnosis, treatment and pathological analysis of disease.

Structure Mapping Generative Adversarial Network for Multi-View Information Mapping Pattern Mining.

Multi-view learning is dedicated to integrating information from different views and improving the generalization performance of models. However, in most current works, learning under different views has significant independency, overlooking common information mapping patterns that exist between these views. This paper proposes a Structure Mapping Generative adversarial network (SM-GAN) framework, which utilizes the consistency and complementarity of multi-view data from the innovative perspective of information mapping. Specifically, based on network-structured multi-view data, a structural information mapping model is proposed to capture hierarchical interaction patterns among views. Subsequently, three different types of graph convolutional operations are designed in SM-GAN based on the model. Compared with regular GAN, we add a structural information mapping module between the encoder and decoder wthin the generator, completing the structural information mapping from the micro-view to the macro-view. This paper conducted sufficient validation experiments using public imaging genetics data in Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. It is shown that SM-GAN outperforms baseline and advanced methods in multi-label classification and evolution prediction tasks.

Target-triggered assembly of plasmon resonance nanostructures for quantitative detection of lncRNA in liver cancer cells via surface enhanced Raman spectroscopy.

Long-stranded non-coding RNAs (lncRNA) have important roles in disease as transcriptional regulators, mRNA processing regulators and protein synthesis factors. However, traditional methods for detecting lncRNA are time-consuming and labor-intensive, and the functions of lncRNA are still being explored. Here, we present a surface enhanced Raman spectroscopy (SERS) based biosensor for the detection of lncRNA associated with liver cancer (LC) as well as in situ cellular imaging. Using the dual SERS probes, quantitative detection of lncRNA (DAPK1-215) can be achieved with an ultra-low detection limit of 952 aM by the target-triggered assembly of core-satellite nanostructures. And the reliability of this assay can be further improved with the R2 value of 0.9923 by an internal standard probe that enables the signal dynamic calibration. Meanwhile, the high expression of DAPK1-215 mainly distributed in the cytoplasm was observed in LC cells compared with the normal ones using the SERS imaging method. Moreover, results of cellular function assays showed that DAPK1-215 promoted the migration and invasion of LC by significantly reducing the expression of the structural domain of death associated protein kinase. The development of this biosensor based on SERS can provide a sensitive and specific method for exploring the expression of lncRNA that would be a potential biomarker for the screening of LC.

CE-GAN: Community Evolutionary Generative Adversarial Network for Alzheimer's Disease Risk Prediction.

In the studies of neurodegenerative diseases such as Alzheimer's Disease (AD), researchers often focus on the associations among multi-omics pathogeny based on imaging genetics data. However, current studies overlook the communities in brain networks, leading to inaccurate models of disease development. This paper explores the developmental patterns of AD from the perspective of community evolution. We first establish a mathematical model to describe functional degeneration in the brain as the community evolution driven by entropy information propagation. Next, we propose an interpretable Community Evolutionary Generative Adversarial Network (CE-GAN) to predict disease risk. In the generator of CE-GAN, community evolutionary convolutions are designed to capture the evolutionary patterns of AD. The experiments are conducted using functional magnetic resonance imaging (fMRI) data and single nucleotide polymorphism (SNP) data. CE-GAN achieves 91.67% accuracy and 91.83% area under curve (AUC) in AD risk prediction tasks, surpassing advanced methods on the same dataset. In addition, we validated the effectiveness of CE-GAN for pathogeny extraction. The source code of this work is available at https://github.com/fmri123456/CE-GAN.

Optical Nanobiosensor Based on Surface-Enhanced Raman Spectroscopy and Catalytic Hairpin Assembly for Early-Stage Lung Cancer Detection via Blood Circular RNA.

Lung cancer has become the leading cause of cancer-related deaths globally. However, early detection of lung cancer remains challenging, resulting in poor outcomes for the patients. Herein, we developed an optical biosensor integrating surface-enhanced Raman spectroscopy (SERS) with a catalyzed hairpin assembly (CHA) to detect circular RNA (circRNA) associated with tumor formation and progression (circSATB2). The signals of the Raman reporter were considerably enhanced by generating abundant SERS "hot spots" with a core-shell nanoprobe and 2D SERS substrate with calibration capabilities. This approach enabled the sensitive (limit of detection: 0.766 fM) and reliable quantitative detection of the target circRNA. Further, we used the developed biosensor to detect the circRNA in human serum samples, revealing that patients with lung cancer had higher circRNA concentrations than healthy subjects. Moreover, we characterized the unique circRNA concentration profiles of the early stages (IA and IB) and subtypes (IA1, IA2, and IA3) of lung cancer. These results demonstrate the potential of the proposed optical sensing nanoplatform as a liquid biopsy and prognostic tool for the early screening of lung cancer.

SFPQ promotes the proliferation, migration and invasion of hepatocellular carcinoma cells and is associated with poor prognosis.

Liver cancer is a prevalent type of tumor worldwide. CRISPR-Cas9 technology can be utilized to identify therapeutic targets for novel therapeutic approaches. In this study, our goal was to identify key genes related to the survival of hepatocellular carcinoma (HCC) cells by analyzing the DepMap database based on CRISPR-Cas9. We screened candidate genes associated with HCC cell survival and proliferation from DepMap and identified their expression levels in HCC from the TCGA database. To develop a prognostic risk model based on these candidate genes, we performed WGCNA, functional pathway enrichment analysis, protein interaction network construction, and LASSO analysis. Our findings show that 692 genes were critical for HCC cell proliferation and survival, and among them, 571 DEGs were identified in HCC tissues. WGCNA categorized these 584 genes into three modules, and the blue module consisting of 135 genes was positively linked to the tumor stage. Using the MCODE approach in Cytoscape, we identified ten hub genes in the PPI network, and through Cox univariate analysis and Lasso analysis, we developed a prognostic model consisting of three genes (SFPQ, SSRP1, and KPNB1). Furthermore, knocking down SFPQ inhibited HCC cell proliferation, migration, and invasion. In conclusion, we identified three core genes (SFPQ, SSRP1, and KPNB1) that are essential for the proliferation and survival of HCC cells. These genes were used to develop a prognostic risk model, and knockdown of SFPQ was found to inhibit the proliferation, migration, and invasion of HCC cells.

Community Graph Convolution Neural Network for Alzheimer's Disease Classification and Pathogenetic Factors Identification.

As a complex neural network system, the brain regions and genes collaborate to effectively store and transmit information. We abstract the collaboration correlations as the brain region gene community network (BG-CN) and present a new deep learning approach, such as the community graph convolutional neural network (Com-GCN), for investigating the transmission of information within and between communities. The results can be used for diagnosing and extracting causal factors for Alzheimer's disease (AD). First, an affinity aggregation model for BG-CN is developed to describe intercommunity and intracommunity information transmission. Second, we design the Com-GCN architecture with intercommunity convolution and intracommunity convolution operations based on the affinity aggregation model. Through sufficient experimental validation on the AD neuroimaging initiative (ADNI) dataset, the design of Com-GCN matches the physiological mechanism better and improves the interpretability and classification performance. Furthermore, Com-GCN can identify lesioned brain regions and disease-causing genes, which may assist precision medicine and drug design in AD and serve as a valuable reference for other neurological disorders.

Laser tweezer Raman spectroscopy combined with deep neural networks for identification of liver cancer cells.

Rapid identification of cancer cells is crucial for clinical treatment guidance. Laser tweezer Raman spectroscopy (LTRS) that provides biochemical characteristics of cells can be used to identify cell phenotypes through classification models in a non-invasive and label-free manner. However, traditional classification methods require extensive reference databases and clinical experience, which is challenging when sampling at inaccessible locations. Here, we describe a classification method combing LTRS with deep neural network (DNN) for differential and discriminative analysis of multiple liver cancer (LC) cells. By using LTRS, we obtained high-quality single-cell Raman spectra of normal hepatocytes (HL-7702) and liver cancer cell lines (SMMC-7721, Hep3B, HepG2, SK-Hep1 and Huh7). The tentative assignment of Raman peaks indicated that arginine content was elevated and phenylalanine, glutathione and glutamate content was decreased in liver cancer cells. Subsequently, we randomly selected 300 spectra from each cell line for DNN model analysis, achieving a mean accuracy of 99.2%, a mean sensitivity of 99.2% and a mean specificity of 99.8% for the identification and classification of multiple LC cells and hepatocyte cells. These results demonstrate the combination of LTRS and DNN is a promising method for rapid and accurate cancer cell identification at single cell level.

How Does Teachers' Psychological Capital Influence Workplace Well-Being? A Moderated Mediation Model of Ego-Resiliency and Work-Meaning Cognition.

Previous studies found that teachers' psychological capital positively affects their workplace well-being. However, the underlying internal mechanism behind this relationship remains ambiguous. The current study aimed to investigate the effects of ego-resiliency and work-meaning cognition on this relationship among Chinese teachers. The questionnaire, including the psychology capital scale (PCS), workplace well-being subscale (WWBS), Psychological Empowerment Scale (PESS), and Ego-Resiliency Scale (ERS), was used to collect data points from 1388 primary and secondary school teachers. The results reveal that: (1) teachers' psychological capital positively predicts workplace well-being; (2) work-meaning cognition mediates the relationship between teachers' psychological capital and workplace well-being; (3) the influence of work-meaning cognition on the relationship between teachers' psychological capital and workplace well-being is moderated by ego-resiliency. These findings explore the factors that affect well-being and point to potential ways to enhance teachers' workplace well-being.

Pathogeny Detection for Mild Cognitive Impairment via Weighted Evolutionary Random Forest With Brain Imaging and Genetic Data.

Medical imaging technology and gene sequencing technology have long been widely used to analyze the pathogenesis and make precise diagnoses of mild cognitive impairment (MCI). However, few studies involve the fusion of radiomics data with genomics data to make full use of the complementarity between different omics to detect pathogenic factors of MCI. This paper performs multimodal fusion analysis based on functional magnetic resonance imaging (fMRI) data and single nucleotide polymorphism (SNP) data of MCI patients. In specific, first, using correlation analysis methods on sequence information of regions of interests (ROIs) and digitalized gene sequences, the fusion features of samples are constructed. Then, introducing weighted evolution strategy into ensemble learning, a novel weighted evolutionary random forest (WERF) model is built to eliminate the inefficient features. Consequently, with the help of WERF, an overall multimodal data analysis framework is established to effectively identify MCI patients and extract pathogenic factors. Based on the data of MCI patients from the ADNI database and compared with some existing popular methods, the superiority in performance of the framework is verified. Our study has great potential to be an effective tool for pathogenic factors detection of MCI.

Hypergraph Structural Information Aggregation Generative Adversarial Networks for Diagnosis and Pathogenetic Factors Identification of Alzheimer's Disease With Imaging Genetic Data.

Alzheimer's disease (AD) is a neurodegenerative disease with profound pathogenetic causes. Imaging genetic data analysis can provide comprehensive insights into its causes. To fully utilize the multi-level information in the data, this article proposes a hypergraph structural information aggregation model, and constructs a novel deep learning method named hypergraph structural information aggregation generative adversarial networks (HSIA-GANs) for the automatic sample classification and accurate feature extraction. Specifically, HSIA-GAN is composed of generator and discriminator. The generator has three main functions. First, vertex graph and edge graph are constructed based on the input hypergraph to present the low-order relations. Second, the low-order structural information of hypergraph is extracted by the designed vertex convolution layers and edge convolution layers. Finally, the synthetic hypergraph is generated as the input of the discriminator. The discriminator can extract the high-order structural information directly from hypergraph through vertex-edge convolution, fuse the high and low-order structural information, and finalize the results through the full connection (FC) layers. Based on the data acquired from AD neuroimaging initiative, HSIA-GAN shows significant advantages in three classification tasks, and extracts discriminant features conducive to better disease classification.

Identification of UBE2I as a Novel Biomarker in ccRCC Based on a Large-Scale CRISPR-Cas9 Screening Database and Immunohistochemistry.

Background: The genome-wide CRISPR-cas9 dropout screening has emerged as an outstanding approach for characterization of driver genes of tumor growth. The present study aims to investigate core genes related to clear cell renal cell carcinoma (ccRCC) cell viability by analyzing the CRISPR-cas9 screening database DepMap, which may provide a novel target in ccRCC therapy. Methods: Candidate genes related to ccRCC cell viability by CRISPR-cas9 screening from DepMap and genes differentially expressed between ccRCC tissues and normal tissues from TCGA were overlapped. Weighted gene coexpression network analysis, pathway enrichment analysis, and protein-protein interaction network analysis were applied for the overlapped genes. The least absolute shrinkage and selection operator (LASSO) regression was used to construct a signature to predict the overall survival (OS) of ccRCC patients and validated in the International Cancer Genome Consortium (ICGC) and E-MTAB-1980 database. Core protein expression was determined using immunohistochemistry in 40 cases of ccRCC patients. Results: A total of 485 essential genes in the DepMap database were identified and overlapped with differentially expressed genes in the TCGA database, which were enriched in the cell cycle pathway. A total of four genes, including UBE2I, NCAPG, NUP93, and TOP2A, were included in the gene signature based on LASSO regression. The high-risk score of ccRCC patients showed worse OS compared with these low-risk patients in the ICGC and E-MTAB-1980 validation cohort. UBE2I was screened out as a key gene. The immunohistochemistry indicated UBE2I protein was highly expressed in ccRCC tissues, and a high-level nuclear translocation of UBE2I occurs in ccRCC. Based on the area under the curve (AUC) values, nuclear UBE2I had the best diagnostic power (AUC = 1). Meanwhile, the knockdown of UBE2I can inhibit the proliferation of ccRCC cells. Conclusion: UBE2I, identified by CRISPR-cas9 screening, was a core gene-regulating ccRCC cell viability, which accumulated in the nucleus and acted as a potential novel promising diagnostic biomarker for ccRCC patients. Blocking the nuclear translocation of UBE2I may have potential therapeutic value with ccRCC patients.

Elevated expression of LIF predicts a poor prognosis and promotes cell migration and invasion of clear cell renal cell carcinoma.

Background: Renal cell carcinoma (RCC) is the seventh most common cancer in humans, of which clear cell renal cell carcinoma (ccRCC) accounts for the majority. Recently, although there have been significant breakthroughs in the treatment of ccRCC, the prognosis of targeted therapy is still poor. Leukemia inhibitory factor (LIF) is a pleiotropic protein, which is overexpressed in many cancers and plays a carcinogenic role. In this study, we explored the expression and potential role of LIF in ccRCC. Methods: The expression levels and prognostic effects of the LIF gene in ccRCC were detected using TCGA, GEO, ICGC, and ArrayExpress databases. The function of LIF in ccRCC was investigated using a series of cell function approaches. LIF-related genes were identified by weighted gene correlation network analysis (WGCNA). GO and KEGG analyses were performed subsequently. Cox univariate and LASSO analyses were used to develop risk signatures based on LIF-related genes, and the prognostic model was validated in the ICGC and E-MTAB-1980 databases. Then, a nomogram model was constructed for survival prediction and validation of ccRCC patients. To further explore the drug sensitivity between LIF-related genes, we also conducted a drug sensitivity analysis based on the GDSC database. Results: The mRNA and protein expression levels of LIF were significantly increased in ccRCC patients. In addition, a high expression of LIF has a poor prognostic effect in ccRCC patients. LIF knockdown can inhibit the migration and invasion of ccRCC cells. By using WGCNA, 97 LIF-related genes in ccRCC were identified. Next, a prognostic risk prediction model including eight LIF-related genes (TOB2, MEPCE, LIF, RGS2, RND3, KLF6, RRP12, and SOCS3) was developed and validated. Survival analysis and ROC curve analysis indicated that the eight LIF-related-gene predictive model had good performance in evaluating patients' prognosis in different subgroups of ccRCC. Conclusion: Our study revealed that LIF plays a carcinogenic role in ccRCC. In addition, we firstly integrated multiple LIF-related genes to set up a risk-predictive model. The model could accurately predict the prognosis of ccRCC, which offers clinical implications for risk stratification, drug screening, and therapeutic decision.

Low FNDC5/Irisin expression is associated with aggressive phenotypes in gastric cancer.

Background: FNDC5 belongs to the family of proteins called fibronectin type III domain-containing which carry out a variety of functions. The expression of FNDC5 is associated with the occurrence and development of tumors. However, the role of FNDC5 in gastric cancer remains relatively unknown. Methods: In the research, the expression of FNDC5 and its value for the prognosis of gastric cancer patients were observed with the TCGA database and GEO datasets of gastric cancer patients. The role of FNDC5 in the regulation of gastric cancer cells proliferation, invasion, and migration was determined. WGCNA and Enrichment analysis was performed on genes co-expressed with FNDC5 to identify potential FNDC5-related signaling pathways. Meanwhile, the LASSO Cox regression analysis based on FNDC5-related genes develops a risk score to predict the survival of gastric cancer patients. Results: The expression of FNDC5 was decreased in gastric cancer tissues compared to normal gastric tissues. However, survival analysis indicated that lower FNDC5 mRNA levels were associated with better overall survival and disease-free survival in gastric cancer patients. Meanwhile, a significant negative correlation was found between FNDC5 and the abundance of CD4+ memory T cells in gastric cancer. In vitro overexpression of FNDC5 inhibits the migration and invasion of gastric cancer cells, without affecting proliferation. Finally, A two-gene risk score module based on FNDC5 co-expressed gene was built to predict the overall clinical ending of patients. Conclusion: FNDC5 is low expressed in gastric cancer and low FNDC5 predicts a better prognosis. The better prognosis of low FNDC5 expression may be attributed to the increased number of CD4+ memory activated T-cell infiltration in tumors, but the exact mechanism of the effect needs to be further explored. Overexpressing FNDC5 inhibits the invasion and migration of gastric cancer but does not affect proliferation. At last, we constructed a clinical risk score model composed of two FNDC5-related genes, and this model may help lay the foundation for further in-depth research on the individualized treatment of gastric cancer patients.

The Expression and Prognostic Value of SUMO1-Activating Enzyme Subunit 1 and Its Potential Mechanism in Triple-Negative Breast Cancer.

Background: Triple-negative breast cancer (TNBC) is the most invasive and metastatic subtype of breast cancer. SUMO1-activating enzyme subunit 1 (SAE1), an E1-activating enzyme, is indispensable for protein SUMOylation. SAE1 has been found to be a relevant biomarker for progression and prognosis in several tumor types. However, the role of SAE1 in TNBC remains to be elucidated. Methods: In the research, the mRNA expression of SAE1 was analyzed via the cancer genome atlas (TCGA) and gene expression omnibus (GEO) database. Cistrome DB Toolkit was used to predict which transcription factors (TFs) are most likely to increase SAE1 expression in TNBC. The correlation between the expression of SAE1 and the methylation of SAE1 or quantity of tumor-infiltrating immune cells was further invested. Single-cell analysis, using CancerSEA, was performed to query which functional states are associated with SAE1 in different cancers in breast cancer at the single-cell level. Next, weighted gene coexpression network (WGCNA) was applied to reveal the highly correlated genes and coexpression networks of SAE1 in TNBC patients, and a prognostic model containing SAE1 and correlated genes was constructed. Finally, we also examined SAE1 protein expression of 207 TNBC tissues using immunohistochemical (IHC) staining. Results: The mRNA and protein expression of SAE1 were increased in TNBC tissues compared with adjacent normal tissues, and the protein expression of SAE1 was significantly associated with overall survival (OS) and disease-free survival (DFS). Correlation analyses revealed that SAE1 expression was positively correlated with forkhead box M1 (FOXM1) TFs and negatively correlated with SAE1 methylation site (cg14042711) level. WGCNA indicated that the genes coexpressed with SAE1 belonged to the green module containing 1,176 genes. Through pathway enrichment analysis of the module, 1,176 genes were found enriched in cell cycle and DNA repair. Single-cell analysis indicated that SAE1 and its coexpression genes were associated with cell cycle, DNA damage, DNA repair, and cell proliferation. Using the LASSO COX regression, a prognostic model including SAE1 and polo-like kinase 1 (PLK1) was built to accurately predict the likelihood of DFS in TNBC patients. Conclusion: In conclusion, we comprehensively analyzed the mRNA and protein expression, prognosis, and interaction genes of SAE1 in TNBC and constructed a prognostic model including SAE1 and PLK1. These results might be important for better understanding of the role of SAE1 in TNBC. In addition, DNA methyltransferase and TFs inhibitor treatments targeting SAE1 might improve the survival of TNBC patients.