SEARCH · Search PubMed

Results for “network analysis”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 793 records · Page 44Linked to original sources

PubMed2026

Integrated single-cell transcriptomics, Mendelian randomization, and machine learning identify CEBPZ as an immune-related biomarker in oral lichen planus.

BACKGROUND: Oral lichen planus (OLP) is a chronic, immune-mediated oral mucosal disease with complex pathophysiology and potential for malignant transformation. Understanding its molecular basis is critical for the development of precise diagnostic and therapeutic strategies. OBJECTIVES: We aimed to identify key immune-related biomarkers and characterize cellular dynamics in OLP, with a particular focus on the role of CEBPZ in disease pathogenesis. MATERIAL AND METHODS: We analyzed single-cell RNA sequencing (scRNA-seq) data from OLP lamina propria samples (GSE211630) to identify disease-specific T-cell subpopulations using high-dimensional weighted gene co-expression network analysis (hdWGCNA) for oxidative stress-related gene modules.-data-based Mendelian randomization (SMR) integrated FinnGen genome-wide association study (GWAS; 342,499 Europeans) data with Genotype-Tissue Expression (GTEx) expression quantitative trait loci (eQTL) data to identify causal genes. Machine learning (ML) models (least absolute shrinkage and selection operator (LASSO) and convolutional neural network (CNN)) were developed using bulk RNA-seq datasets (GSE52130 and GSE38616) for diagnostic purposes. RESULTS: We identified OLP-specific T-cell populations (clusters 0, 3, 5, 7, 13, and 15) with enhanced migration inhibition factor (MIF) pathway signaling toward B cells and monocytes. Two oxidative stress-associated modules contained hub genes, including CEBPZ. Summary-data-based Mendelian randomization analysis identified 231 OLP-associated genes, with CEBPZ uniquely intersecting LASSO-selected markers (odds ratio (OR) = 1.057, 95% confidence interval (95% CI) = 1.013-1.102, p = 0.010). Machine learning models achieved area under the curve (AUC) values ranging from 0.653 to 0.745, with the CNN model reaching a validation accuracy of 0.735. CEBPZ showed elevated expression in OLP T cells and correlated with enhanced MIF-(CD74+CXCR4) signaling. CONCLUSIONS: This integrative approach identifies CEBPZ as a pivotal biomarker linking genetic susceptibility, oxidative stress, and immune dysregulation in OLP. Our diagnostic models offer promising tools for OLP management.

CEBPZ↗

PubMed2000

Peer promotion programs and social networks in Ghana: methods for monitoring and evaluating AIDS prevention and reproductive health programs among adolescents and young adults.

This article summarizes the observations and lessons learned regarding the application of human immunodeficiency virus (HIV)/acquired immune deficiency syndrome (AIDS) prevention and reproductive health evaluation methodologies in the context of adolescent and young adult populations and discusses the use of peer network evaluation to understand the dynamics of peer promotion. To examine the interpersonal communication process of peer education, this study tested a new approach using multiple semistructured interviews and network analysis to collect data on 106 peer educators and 526 of their contacts. These evaluation activities were conducted at three sites in Ghana during April 1998, in both periurban and rural locations in both in-school and out-of-school settings. By evaluating the social networks of peer educators it was possible to gain a better understanding of the process of peer education in terms of (a) defining the composition of peer contacts, (b) identifying the social norms that play a critical role in youth decision making, and (c) observing the range of messages and services transmitted during peer education. The objective of this paper is to disseminate the experience of the Center for Education and Development of Population Activities (CEDPA) and Focus on Young Adult's cooperative development of evaluation methodologies for peer promotion and to highlight utilization of these methodologies in a case study in Ghana. The results will be discussed in terms of their possible implications for program managers, researchers, and international agencies.

Acquired Immunodeficiency Syndrome↗

PubMed2026

Temporal DIA-MS proteomics reveals coordinated metabolic reprogramming associated with oil accumulation in oil palm mesocarp.

Oil palm (Elaeis guineensis Jacq.) is the most productive oil-bearing crop globally, yet the molecular basis of mesocarp development and lipid accumulation remains poorly understood. Ultra-deep data-independent acquisition mass spectrometry (DIA-MS) was applied to characterize proteome dynamics in two contrasting genotypes, seedless (KS) and thin-shelled (TS), across five developmental stages (P1-P5) spanning fruit development to mature oil accumulation. Phenotypic analysis revealed higher mesocarp proportion and oil content in KS during late maturation. A total of 137,615 peptides corresponding to 12,163 protein groups were identified, providing a temporal proteomic landscape of mesocarp development. Multivariate analysis indicated that developmental progression was the primary contributor to proteomic variation, whereas genotype-associated differences increased during lipid accumulation. Differentially abundant proteins were mainly associated with carbohydrate metabolism, photosynthesis, proteolysis, antioxidant responses, and lipid biosynthesis. Gene Ontology (GO), Kyoto Encyclopedia of Genes and Genomes (KEGG), and KOG analyses suggested extensive remodeling of metabolic networks, including developmental changes in photosynthesis-associated proteins and increased representation of lipid-associated pathways during maturation. Weighted protein co-expression network analysis identified 17 modules associated with developmental progression and lipid accumulation, highlighting candidate proteins involved in carbon metabolism, energy production, and cellular protection. Genes encoding selected hub protein candidates were further examined by RT-qPCR. Biochemical analyses supported these proteomic patterns, showing increased acetyl-CoA availability, enhanced antioxidant enzyme activities (SOD, CAT, APX, and GR), improved GSH/GSSG balance, and reduced oxidative damage in KS. Together, these findings provide a temporal proteomic and biochemical framework for understanding genotype-associated differences in oil accumulation and identify candidate metabolic networks for functional studies.

Carbon metabolism↗

PubMed2006

ErbB receptor tyrosine kinase network inhibition radiosensitizes carcinoma cells.

PURPOSE: The expression of epidermal growth factor receptor (EGFR)-CD533, a truncation mutant of the wild-type EGFR, radiosensitizes carcinoma and malignant glioma cell lines. This deletion mutant disrupts EGFR activation and downstream signaling through the formation of inhibitory dimerizations. In this study, the effects of EGFR-CD533 on other ErbB receptor tyrosine kinase (RTK) family members were quantified to better understand the mechanism of EGFR-CD533-mediated radiosensitization. METHODS AND MATERIALS: Breast carcinoma cell lines with different ErbB RTK expression profiles were transduced with EGFR or ErbB2 deletion mutants (EGFR-CD533 and ErbB2-CD572) using an adenoviral vector. ErbB RTK activation, mitogen activated protein kinase (MAPK) and phosphatidylinositol-3-kinase (PI3K)/p70S6K signaling, and clonogenic survival were determined for expression of each deletion mutant. RESULTS: EGFR-CD533 radiosensitizes carcinoma cells with either high EGFR expression (MDA-MB231) or low EGFR expression (T47D) through significant blockade of the ErbB RTK network. Analysis of clonogenic survival demonstrate significant enhancement of the alpha/beta ratios, as determined by the linear-quadratic model. Split-dose survival experiments confirm that EGFR-CD533 reduces the repair of cellular damage after ionizing radiation. CONCLUSION: Expression of EGFR-CD533 inhibits the ErbB RTK network and radiosensitizes carcinoma cells irrespective of the ErbB RTK expression patterns, and ErbB2-CD572 does not radiosensitize cells with low EGFR expression. These studies demonstrate that the mechanism of action for EGFR-CD533-mediated radiosensitization is inhibition of the ErbB RTK network, and is an advantage for radiosensitizing multiple malignant cell types.

Breast Neoplasms↗

PubMed2024

Identification of cuproptosis-realated key genes and pathways in Parkinson's disease via bioinformatics analysis.

INTRODUCTION: Parkinson's disease (PD) is the second most common worldwide age-related neurodegenerative disorder without effective treatments. Cuproptosis is a newly proposed conception of cell death extensively studied in oncological diseases. Currently, whether cuproptosis contributes to PD remains largely unclear. METHODS: The dataset GSE22491 was studied as the training dataset, and GSE100054 was the validation dataset. According to the expression levels of cuproptosis-related genes (CRGs) and differentially expressed genes (DEGs) between PD patients and normal samples, we obtained the differentially expressed CRGs. The protein-protein interaction (PPI) network was achieved through the Search Tool for the Retrieval of Interacting Genes. Meanwhile, the disease-associated module genes were screened from the weighted gene co-expression network analysis (WGCNA). Afterward, the intersection genes of WGCNA and PPI were obtained and enriched using the Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG). Subsequently, the key genes were identified from the datasets. The receiver operating characteristic curves were plotted and a PPI network was constructed, and the PD-related miRNAs and key genes-related miRNAs were intersected and enriched. Finally, the 2 hub genes were verified via qRT-PCR in the cell model of the PD and the control group. RESULTS: 525 DEGs in the dataset GSE22491 were identified, including 128 upregulated genes and 397 downregulated genes. Based on the PPI network, 41 genes were obtained. Additionally, the dataset was integrated into 34 modules by WGCNA. 36 intersection genes found from WGCNA and PPI were significantly abundant in 7 pathways. The expression levels of the genes were validated, and 2 key genes were obtained, namely peptidase inhibitor 3 (PI3) and neuroserpin family I member 1 (SERPINI1). PD-related miRNAs and key genes-related miRNAs were intersected into 29 miRNAs including hsa-miR-30c-2-3p. At last, the qRT-PCR results of 2 hub genes showed that the expressions of mRNA were up-regulated in PD. CONCLUSION: Taken together, this study demonstrates the coordination of cuproptosis in PD. The key genes and miRNAs offer novel perspectives in the pathogenesis and molecular targeting treatment for PD.

Humans↗

PubMed2026

Molecular-networking-based characterization of cytotoxic metabolites produced by the cyanobacterium Nostoc edaphicum CCNP1411.

Cyanobacteria of the genus Nostoc, known for their large genomes and rich repertoire of biosynthetic gene clusters, represent a prolific source of structurally diverse secondary metabolites with diverse biological activities, including cytotoxic effects. However, the identification of bioactive compounds is often hindered by low metabolite abundance and difficulties in isolating sufficient quantities for individual testing. In this study, we investigated the cytotoxic potential of chromatographic fractions obtained from Nostoc edaphicum CCNP1411 using a combination of bioassay-guided fractionation and LC-MS/MS-based feature-based molecular networking (FBMN). Cytotoxic activity was evaluated using the MTT assay across a panel of epithelial and neuronal cancer cell lines, as well as normal human dermal fibroblasts. The most active fractions, eluted with 80-90% MeOH, exhibited broad cytotoxic effects across all tested cancer cell lines. Molecular networking analysis revealed that these fractions were dominated by lipid derivatives, including lysophospholipids, monoacylglycerols, and free fatty acids, whereas previously described peptide metabolites were distributed across all fractions and were unlikely to be the main agents responsible for the observed activity. Targeted testing of selected commercially available lipid compounds confirmed their cytotoxic effects, with lysophospholipids showing the highest potency in selected cell lines. However, dose-response analysis indicated that most compounds exhibited limited potency at lower concentrations, as reflected by relatively high IC₅₀ values. Overall, our results demonstrate that lipid constituents, previously overlooked as bioactive metabolites produced by N. edaphicum CCNP1411, contribute significantly to the cytotoxic activity of the tested fractions. The application of molecular networking enabled the prioritization of bioactive metabolites and highlights its utility in linking chemical composition with biological effects in complex cyanobacterial extracts.

Bioactivity-guided fractionation↗

PubMed2026

Unveiling microbial risks in Chinese household dust: a comprehensive analysis from absolute abundance to virulence unit.

BACKGROUND: People spend the majority of their lives indoors, yet the risk and virulence potential of household microbiota remain largely unexplored, particularly in developing countries. RESULTS: Here, we conducted a nationwide survey on both dust samples and health information across 118 Chinese households. The microbiota composition and its functional units were analyzed using absolute 16S rRNA/ITS sequencing, metagenomics, and metaproteomics. Cross-domain network analysis of the core microbial communities revealed robust co-occurrence patterns in household dust. The mean absolute abundance of potentially pathogenic bacteria and fungi in households was 2.39 × 105 and 2.83 × 106 DNA copies/g dust. The potentially pathogenic community was primarily influenced by latitude, relative humidity, and average temperature. Although total absolute abundance was substantially lower in urban areas, the relative abundance of potentially pathogenic bacteria was markedly higher compared to rural environments. While urban-rural differences existed, the underlying statistical drivers were the environmental variables. The absolute abundance of potential pathogens was significantly associated with the prevalence of rhinitis, wheeze, and dermatitis in 266 participants. Children were identified as the highest-risk group from inhalation exposure of average daily dose. A total of 170 bacterial, 223 fungal virulence factors (VFs), and 370 antibiotic resistance genes (ARGs) were detected in dust and dust extracellular vesicle (EV)-associated DNA. EV-associated cargoes contributed 47.13% to the bacterial VF profiles, 11.90% to fungal VF profiles, and 44.45% to ARG profiles. Metaproteomic analysis confirmed the presence of VF profiles in dust EVs, which was further verified by curated proteomics data from 35 household pathogens. CONCLUSIONS: This study provides a comprehensive, quantitative framework linking indoor microbial exposure to health risks, highlighting EVs as a non-negligible, novel, extracellular mechanistic pathway for health impact in household environments. Video Abstract.

Child↗

PubMed2004

Minimal sharing of Y-chromosome STR haplotypes among five endogamous population groups from western and southwestern India.

We attempt to address the issue of genetic variation and the pattern of male gene flow among and between five Indian population groups of two different geographic and linguistic affiliations using Y-chromosome markers. We studied 221 males at three Y-chromosome biallelic loci and 184 males for the five Y-chromosome STRs. We observed 111 Y-chromosome STR haplotypes. An analysis of molecular variance (AMOVA) based on Y-chromosome STRs showed that the variation observed between the population groups belonging to two major regions (western and southwestern India) was 0.17%, which was significantly lower than the level of genetic variance among the five populations (0.59%) considered as a single group. Combined haplotype analysis of the five STRs and the biallelic locus 92R7 revealed minimal sharing of haplotypes among these five ethnic groups, irrespective of the similar origin of the linguistic and geographic affiliations; this minimal sharing indicates restricted male gene flow. As a consequence, most of the haplotypes were population specific. Network analysis showed that the haplotypes, which were shared between the populations, seem to have originated from different mutational pathways at different loci. Biallelic markers showed that all five ethnic groups have a similar ancestral origin despite their geographic and linguistic diversity.

Chromosomes, Human, Y↗

PubMed2024

Polycystic ovarian syndrome (PCOS) and recurrent spontaneous abortion (RSA) are associated with the PI3K-AKT pathway activation.

AIMS: We aimed to elucidate the mechanism leading to polycystic ovarian syndrome (PCOS) and recurrent spontaneous abortion (RSA). BACKGROUND: PCOS is an endocrine disorder. Patients with RSA also have a high incidence rate of PCOS, implying that PCOS and RSA may share the same pathological mechanism. OBJECTIVE: The single-cell RNA-seq datasets of PCOS (GSE168404 and GSE193123) and RSA GSE113790 and GSE178535) were downloaded from the Gene Expression Omnibus (GEO) database. METHODS: Datasets of PSCO and RSA patients were retrieved from the Gene Expression Omnibus (GEO) database. The "WGCNA" package was used to determine the module eigengenes associated with the PCOS and RSA phenotypes and the gene functions were analyzed using the "DAVID" database. The GSEA analysis was performed in "clusterProfiler" package, and key genes in the activated pathways were identified using the Kyoto Encyclopedia of Genes and Genomes (KEGG) analysis. Real-time quantitative PCR (RT-qPCR) was conducted to determine the mRNA level. Cell viability and apoptosis were measured by cell counting kit-8 (CCK-8) and flow cytometry, respectively. RESULTS: The modules related to PCOS and RSA were sectioned by weighted gene co-expression network analysis (WGCNA) and positive correlation modules of PCOS and RSA were all enriched in angiogenesis and Wnt pathways. The GSEA further revealed that these biological processes of angiogenesis, Wnt and regulation of cell cycle were significantly positively correlated with the PCOS and RSA phenotypes. The intersection of the positive correlation modules of PCOS and RSA contained 80 key genes, which were mainly enriched in kinase-related signal pathways and were significant high-expressed in the disease samples. Subsequently, visualization of these genes including PDGFC, GHR, PRLR and ITGA3 showed that these genes were associated with the PI3K-AKT signal pathway. Moreover, the experimental results showed that PRLR had a higher expression in KGN cells, and that knocking PRLR down suppressed cell viability and promoted apoptosis of KGN cells. CONCLUSION: This study revealed the common pathological mechanisms between PCOS and RSA and explored the role of the PI3K-AKT signaling pathway in the two diseases, providing a new direction for the clinical treatment of PCOS and RSA.

Humans↗

PubMed1996

Interpretation of captopril transplant renography using a feed forward neural network.

UNLABELLED: Severe renal artery stenosis (RAS) is a relatively uncommon complication after renal transplantation but is a curable cause of hypertension, which demands reliable early diagnosis to reduce morbidity, mortality and graft loss. Captopril renography has been used for a number of years as a method of detecting RAS but controversy still exists as to the diagnostic accuracy of this test and as to the most appropriate interpretation criteria with which to establish a positive result. METHODS: This report presents the results of using artificial neural networks to impartially assess these interpretation criteria. Data comprised 31 99mTc-MAG3 captopril renography investigations undertaken on hypertensive renal transplant patients with a suspected diagnosis of RAS. Each renogram study was correlated with an arteriogram as the "gold standard". Training of the network was performed using the round-robin technique. RESULTS: An accuracy of 95% could be achieved by considering perfusion index, time-to-peak activity, accumulation index and excretion index for both pre- and post-challenge studies. This varied as the parameters were either included or excluded. CONCLUSION: Artificial neural network analysis is a useful technique to evaluate the most appropriate criteria for interpreting captopril transplant renography investigations.

Antihypertensive Agents↗

PubMed2005

Kinase substrate protein microarray analysis of human colon cancer and hepatic metastasis.

BACKGROUND: Liver metastases represent the major determinant of survival in patients with colorectal cancer (CRC). In cases with unresectable liver disease, more effective agents are needed, since chemotherapy achieves median survival of only 15 months. Protein kinases coordinate complex functions that are often disregulated in cancer and are therefore considered important targets for molecular therapeutics. In this study, we investigated the phosphoproteomic status of different protein kinases in primary CRC and in liver metastases. METHODS: The status of 29 key endpoints was evaluated using reverse phase protein array on laser capture microdissected neoplastic cells from five primary CRCs without metastases, three patient-matched primary CRCs and synchronous liver metastases and five CRC metachronous liver metastases. RESULTS: Unsupervised hierarchical two-way clustering analysis showed an entirely different phosphoproteomic profile in primary CRCs compared to liver metastases. This difference was observed also in primary and metastatic patient-matched lesions. CONCLUSIONS: Our findings of different signaling pathways between primary and metastatic CRC suggest a possible microenvironment effect, and emphasize the need to perform molecular network analysis of metastatic tissue when molecular targeting is considered.

Cluster Analysis↗

PubMed1997

Neural network modeling accurately predicts the functional outcome of stroke survivors with moderate disabilities.

OBJECTIVE: To predict the place of discharge or discharge Functional Independence Measure (FIM) score for stroke survivors with moderate disability using neural network modeling. Our previous work demonstrated that the FIM predicts the level of recovery for stroke survivors with either severe or mild disabilities. DESIGN: Neural network analysis. SETTING: Tertiary care rehabilitation program. PATIENTS: One hundred forty-seven consecutive stroke survivors admitted for rehabilitation with admission FIM scores between 37 and 96 were used as the training and internal test set. Seventeen other randomly selected stroke survivors were used as the external test set. INTERVENTION: A neural network model was developed using a small set of clinical variables and the admission FIM score. MAIN OUTCOME MEASURE: Neural network model predicting place of discharge or discharge FIM score. RESULTS: A working and accurate model was developed to predict the discharge FIM score. The model was able to predict the 17 external test cases with an accuracy = 88%, sensitivity = 83%, specificity = 91%, positive predictive value = 83%, and negative predictive value = 91%. CONCLUSION: Neural network modeling is useful in the prediction of functional recovery and helps in discharge planning and allocation of rehabilitation resources.

Aged↗

PubMed2026

Integrative transcriptomic, spatial and functional-genomic analysis identifies a UFMylation-related vascular-stromal program and prioritizes WWTR1 in glioblastoma.

Glioblastoma (GBM) contains spatially organized stress-adaptive and vascular niches. Because transcript abundance does not measure UFM1 conjugation, we asked whether a UFMylation-related transcriptional axis identifies a reproducible tissue program and alters candidate prioritization. In 518 unique primary TCGA-GBM tumors profiled on the Affymetrix HT Human Genome U133A array, weighted gene co-expression network analysis of 8,000 variable genes yielded 12 modules. The 278-gene green module ranked first across nine prespecified traits (mean |r|=0.637). Direct overlap comprised 1/3 measurable UFMylation-core, 5/19 ER-stress/UPR, and 2/15 proteostasis genes; after excluding overlapping genes, correlations with the green eigengene remained significant (r = 0.373, 0.831, 0.639, and 0.699 for UFMylation-core, ER-stress/UPR, proteostasis, and composite scores, respectively). The green score was associated with overall survival per standard-deviation increase (HR 1.17, 95% CI 1.07-1.28), although clinical adjustment attenuated the estimate. In a 10-sample single-cell dataset, sample-level scores were higher in pericytes and endothelial cells than in malignant cells. Donor-aware IvyGAP analysis supported regional organization, whereas one Visium section showed stronger concordance with ER-stress/UPR and mesenchymal scores than with the UFMylation-core score. CellChat indicated pathway-selective rather than global remodeling of inferred vascular communication. Layer ablation moved WWTR1 from rank 48 using WGCNA alone to rank 4 overall and rank 1 among non-common-essential genes after cross-platform integration. These findings define an ER-stress/mesenchymal-weighted, UFMylation-related vascular-stromal transcriptional association and nominate WWTR1 for experimental testing.

Humans↗

PubMed2026

Epigenetic alterations of AKT1 orchestrate a metabolic reprogramming in advanced lipedema: translational insights from an integrated multi-omics study.

BACKGROUND: lipedema is a chronic, progressive adipose disorder predominantly affecting women, characterized by painful, symmetrical subcutaneous fat accumulation, and typically resistant to lifestyle interventions. The pathophysiology of advanced-stage lipedema remains poorly defined, and no validated biomarkers or targeted therapies are currently available. METHODS: in this observational study, we applied a comprehensive multi-omics approach to dissect the molecular and metabolic alterations underlying late-stage lipedema. RESULTS: Genome-wide DNA methylation profiling identified over 5,000 differentially methylated CpG sites affecting genes involved in receptor tyrosine kinase signaling, phospho-metabolism, and immune pathways. Transcriptomic analysis revealed profound downregulation of mitochondrial functions, including oxidative phosphorylation, the TCA cycle, and fatty acid β-oxidation, alongside disruption of the sirtuin pathway and extracellular matrix remodeling. Integrative analysis pinpointed AKT1 as a central regulatory node: its promoter region was hypomethylated, correlating with increased gene expression and protein phosphorylation. Metabolomic profiling confirmed AKT1-linked metabolic dysregulation, including altered levels of L-arginine, NADP+, ATP, guanosine, glycerol, and glutamate, indicating impaired redox balance and energy metabolism. Trans-omic network analysis positioned AKT1 at the intersection of multiple dysregulated pathways, suggesting its key role in advanced-stage lipedema. CONCLUSIONS: the consistent enhancing of AKT pathway signaling across omic layers highlights its potential not only as a biomarker for disease stratification but also as a putative druggable target for therapeutic intervention. These findings offer new mechanistic insights into lipedema pathophysiology and provide a rationale for future personalized treatment strategies guided by AKT1-centric molecular profiling.

Proto-Oncogene Proteins c-akt↗

PubMed1993

Artificial neural networks as adjuncts for assessing medical students' problem solving performances on computer-based simulations.

Artificial neural networks were trained by supervised learning to recognize the test selection patterns associated with students' successful solutions to seven immunology computer-based simulations. New test selection patterns evaluated by the trained neural network were correctly classified as successful or unsuccessful solutions to the problem > 90% of the time. The examination of the neural networks output weights after each test selection revealed a progressive and selective increase for the relevant problem suggesting that a successful solution is represented by the neural network as the accumulation of relevant tests. Unsuccessful problem solutions were classified by the neural network software into two patterns of students performance. The first pattern was characterized by low neural network output weights for all seven problems reflecting extensive searching and lack of recognition of relevant information. In the second pattern, the output weights from the neural network were biased toward one of the remaining six incorrect problems suggesting that the student misrepresented the current problem as an instance of a previous problem. Finally, neural network analysis could detect cases where the students switched hypotheses during the problem solving exercises.

California↗

PubMed2003

Neural network for photoplethysmographic respiratory rate monitoring.

The reflection mode photoplethysmographic (PPG) signal was studied with the aim of determining respiratory rate. The PPG signal includes respiratory synchronous components, seen as frequency modulation of the heart rate (respiratory sinus arrhythmia), amplitude modulation of the cardiac pulse and respiratory-induced intensity variations (RIIVs) in the PPG baseline. PPG signals were recorded from the foreheads of 15 healthy subjects. From these signals, the systolic wave-form, diastolic waveform, respiratory sinus arrhythmia, pulse amplitude and RIIVs were extracted. Using basic algorithms, the rates of false positive and false negative detection of breaths were calculated separately for each of the five components. Furthermore, a neural network was assessed in a combined pattern recognition approach. The error rates (sum of false positive and false negative breath detections) for the basic algorithms ranged from 9.7% (pulse amplitude) to 14.5% (systolic waveform). The corresponding values for the neural network analysis were 9.5-9.6%. These results suggest the use of a combined PPG system for simultaneous monitoring of respiratory rate and arterial oxygen saturation (pulse oximetry).

Adult↗

PubMedDate not supplied

Development of neural network simulator for structure--activity correlation of molecules (NECO). Prediction of endo/exo substitution of norbornane derivatives and of carcinogenic activity of PAHs from 13C-NMR shifts.

A perceptron type neural network simulator for structure--activity correlation of molecules has been developed with two different learning methods, i.e., back-propagation and reconstruction methods. First by use of the back-propagation method the exo/endo branching of norbornane and norbornene derivatives was correctly predicted from the set of 13C NMR chemical shifts for various ring carbon atoms. Then the obtained correlation was analyzed by the reconstruction learning method. It was shown in this case that the NMR shifts for two carbon atoms out of seven have strong correlation with the exo/endo branching. Further, structure--activity correlation between the 13C NMR chemical shifts and carcinogenicity of 11 polycyclic aromatic hydrocarbons was also analyzed using the reconstruction method. It was demonstrated that neural network analysis is suitable for the elucidation of complicated structure--activity problems where many factors are nonlinearly entangled.

Animals↗

PubMed2025

Construction of a prognostic model for gastric cancer based on immune infiltration and microenvironment, and exploration of MEF2C gene function.

BACKGROUND: Advanced gastric cancer (GC) exhibits a high recurrence rate and a dismal prognosis. Myocyte enhancer factor 2c (MEF2C) was found to contribute to the development of various types of cancer. Therefore, our aim is to develop a prognostic model that predicts the prognosis of GC patients and initially explore the role of MEF2C in immunotherapy for GC. METHODS: Transcriptome sequence data of GC was obtained from The Cancer Genome Atlas (TCGA), the Gene Expression Omnibus (GEO) and PRJEB25780 cohort for subsequent immune infiltration analysis, immune microenvironment analysis, consensus clustering analysis and feature selection for definition and classification of gene M and N. Principal component analysis (PCA) modeling was performed based on gene M and N for the calculation of immune checkpoint inhibitor (ICI) Score. Then, a Nomogram was constructed and evaluated for predicting the prognosis of GC patients, based on univariate and multivariate Cox regression. Functional enrichment analysis was performed to initially investigate the potential biological mechanisms. Through Genomics of Drug Sensitivity in Cancer (GDSC) dataset, the estimated IC50 values of several chemotherapeutic drugs were calculated. Tumor-related transcription factors (TFs) were retrieved from the Cistrome Cancer database and utilized our model to screen these TFs, and weighted correlation network analysis (WGCNA) was performed to identify transcription factors strongly associated with immunotherapy in GC. Finally, 10 patients with advanced GC were enrolled from Sun Yat-sen University Cancer Center, including paired tumor tissues, paracancerous tissues and peritoneal metastases, for preparing sequencing library, in order to perform external validation. RESULTS: Lower ICI Score was correlated with improved prognosis in both the training and validation cohorts. First, lower mutant-allele tumor heterogeneity (MATH) was associated with lower ICI Score, and those GC patients with lower MATH and lower ICI Score had the best prognosis. Second, regardless of the T or N staging, the low ICI Score group had significantly higher overall survival (OS) compared to the high ICI Score group. For its mechanisms, consistently, for Camptothecin, Doxorubicin, Mitomycin, Docetaxel, Cisplatin, Vinblastine, Sorafenib and Paclitaxel, all of the IC50 values were significantly lower in the low ICI Score group compared to the high ICI Score group. As a result, based on univariate and multivariate Cox regression, ICI Score was considered to be an independent prognostic factor for GC. And our Nomogram showed good agreement between predicted and actual probabilities. Based on CIBERSORT deconvolution analysis, there was difference of immune cell composition found between high and low ICI Score groups, probably affecting the efficacy of immunotherapy. Then, MEF2C, a tumor-related transcription factor, was screened out by WGCNA analysis. Higher MEF2C expression is significantly correlated with a worse OS. Moreover, its higher expression is also negatively correlated with tumor mutation burden (TMB) and microsatellite instability (MSI), but positively correlated with several immunosuppressive molecules, indicating MEF2C may exert its influence on tumor development by upregulating immunosuppressive molecules. Finally, based on transcriptome sequencing data on 10 paired tumor tissues from Sun Yat-sen University Cancer Center, MEF2C expression was significantly lower in paracancerous tissues compared to tumor tissues and peritoneal metastases, and it was also lower in tumor tissues compared to peritoneal metastases, indicating a potential positive association between MEF2C expression and tumor invasiveness. CONCLUSIONS: Our prognostic model can effectively predict outcomes and facilitate stratification GC patients, offering valuable insights for clinical decision-making. The identified transcription factor MEF2C can serve as a biomarker for assessing the efficacy of immunotherapy for GC.

Humans↗