Network Analysis Research Articles

Stimulant medication and symptom interrelations in children, adolescents and adults with attention-deficit/hyperactivity disorder

AbstractStimulant medication is effective in alleviating overall symptom severity of attention-deficit/hyperactivity disorder (ADHD), yet interindividual variability in treatment response and tolerability still exists. While network analysis has identified differences in ADHD symptom relations, the impact of stimulant medication remains unexplored. Increased understanding of this association could provide valuable insights for optimizing treatment approaches for individuals with ADHD. In this study, we compared and characterized ADHD symptom networks (including 18 ADHD symptoms) between stimulant-treated (n = 348) and untreated (n = 70) individuals with ADHD and non-ADHD controls (NACs; n = 444). Moreover, we compared symptom networks between subgroups defined by their stimulant treatment trajectory (early-and-intense use, late-and-moderate use). Stimulant-treated individuals with ADHD showed stronger associations between symptoms, compared with untreated individuals with ADHD and NACs. We found no differences in symptom networks between the stimulant treatment trajectory subgroups. Prospective longitudinal studies are needed to disentangle whether the identified differences stem from treatment or pre-existing factors.

The effect of hybrid classes on extrinsically motivated students

Emerging from the Covid19 pandemic, many higher education institutions rapidly improvised teaching students in a hybrid mode that concurrently combined online and in-person instruction. The varied engagement results from students and staff prompted many institutions to reconsider this hybrid approach (Raes et al., 2020), with opinions of both students and teachers divided on the merits of returning to an in-person classroom. While some studies (Peng & Wei, 2021) noted success at the ‘juggling act’ of supporting both an in-person class and an online class simultaneously, more studies found the emerging technology, split focus, resourcing and unfamiliar instructions to be a disengaging classroom experience (Aagaard et al, 2023). A lack of clear and quantitative evidence has been noted as a key issue with many of the studies of hybrid learning (Raes et al, 2020). The improvised nature of many pandemic teaching responses and the many variables that may confound engagement results, prompts a more considered and deliberate re-examination of hybrid learning which takes into account the motivational needs of students. If a student is motivated to attend a hybrid classroom, their subsequent evaluations of the experience seem likely to be related to their initial motives, expectations and reasons for attending. The lens of Self Determination Theory (SDT) offers a range of insights into the type of motivation felt by students and enables the disambiguation of whether a student is motivated intrinsically or extrinsically (Ryan & Deci, 2017). Intrinsic motivation being characterised by an internal locus of control –arising spontaneously from within. Extrinsic motivation conversely is characterised by an external locus of control – motivation is controlled by outside factors and compulsions that a student feels they ought to follow. Deci and Ryan’s Intrinsic Motivation Inventory (IMI) offers us additional insights into three descriptive sub-types of intrinsic and extrinsic motivation – autonomy, relatedness and mastery. The idea that an unfulfilled need for personal relatedness in some students might relate to levels of student engagement online and in-person was hoped might explain some of variable engagement responses from students. This presentation tells the story of how hundreds of students responded to a synchronous concurrent hybrid classroom intervention across four weeks of an otherwise online subject. Utilising high-quality hybrid learning technology available at the time, the advanced Class.com interface and a well-adapted pedagogy the journey of students with differing motivational needs was explored using the lens of Deci and Ryan’s (2017) IMI. Through regression modelling, network analysis and a broad analysis of associated demographic factors it was found in particular that low ATAR students with extrinsic motivation were more disengaged by the hybrid classroom environment, in comparison to other motivational subgroups. Contrary to expectation, students with a motivational need for relatedness were not found to respond differently to hybrid learning compared with other motivational subgroups. Recommendations for future iterations of synchronous concurrent hybrid classrooms and research are offered.

Utilization of Generative Artificial Intelligence in Nursing Education: A Topic Modeling Analysis

The advent of artificial intelligence (AI) has prompted the introduction of novel digital technologies, including mobile learning and metaverse learning, into nursing students’ learning environments. This study used text network and topic modeling analyses to identify the research trends in generative AI in nursing education for students and patients in schools, hospitals, and community settings. Additionally, an ego network analysis using strengths, weaknesses, opportunities, and threats (SWOT) words was performed to develop a comprehensive understanding of factors that impact the integration of generative AI in nursing education. The literature was searched from five databases published until July 2024. After excluding studies whose abstracts were not available and removing duplicates, 139 articles were identified. The seven derived topics were labeled as usability in future scientific applications, application and integration of technology, simulation education, utility in image and text analysis, performance in exams, utility in assignments, and patient education. The ego network analysis focusing on the SWOT keywords revealed “healthcare”, “use”, and “risk” were common keywords. The limited emphasis on “threats”, “strengths”, and “weaknesses” compared to “opportunities” in the SWOT analysis indicated that these areas are relatively underexplored in nursing education. To integrate generative AI technology into education such as simulation training, teaching activities, and the development of personalized learning, it is necessary to identify relevant internal strengths and weaknesses of schools, hospitals, and communities that apply it, and plan practical application strategies aligned with clear institutional guidelines.

Network analysis of U.S. non-fatal opioid-involved overdose journeys, 2018–2023

Network analysis of U.S. non-fatal opioid-involved overdose journeys, 2018–2023

EPCO-37. LONGITUDINAL TUMOR-WIDE SAMPLING OF GLIOBLASTOMA REVEALS EARLY EVOLUTIONARY DIVERGENCE OF RECURRENCE AND CLUES TOWARDS IDENTIFYING THE BIOLOGICAL TUMOR CENTER

Abstract Therapy resistance in glioblastoma is in part attributed to intratumoral heterogeneity and treatment-resistant cell populations. Understanding heterogeneity requires more complete tumor sampling at diagnosis and at recurrence. We used a whole-tumor sampling approach to obtain 43 spatially mapped biopsies from 3 glioblastomas at diagnosis and recurrence, Pyclone and ClonEvol imputed clonal evolution from exome data, and weighted gene co-expression network analysis inferred gene expression programs from RNA sequencing. Across the cohort, tumor-wide clonal alterations representing evolutionarily early expansions included canonical changes (i.e. Chr7 gain, EGFR amplification) and a diverse set of copy number variations (Chr19/20 gain), driver mutations (i.e. PTEN, KDR), and fusions (LIMCH1::UCHL1, KANK::DOCK8). In 2/3 patients, the founding clone was the only subclone common to primary and recurrence samples and 37% of cancer drivers across the cohort appeared after evolutionary divergence of the primary and recurrent tumors. We identified thirty-two transcriptional programs, six of which were differentially expressed between timepoints. Programs enriched for mitochondrial activity, endothelium/pericytes and classical glioblastoma subtype signature were more highly expressed in primary samples. Programs enriched for mesenchymal-like state, oligodendrocytes and inhibitory interneurons were more highly expressed in recurrence samples. At diagnosis, 11/16 samples showed higher expression of the classical subtype program compared to mesenchymal-like, but at recurrence the mesenchymal program dominated in 18/18 samples. Expression of the programs correlated more strongly with position relative to the contrast-enhancing rather than T2 tumor centroid (p<0.001). These findings reveal novel diversity and complexity in the genetic roots of individual glioblastoma. Recurrences arose from subclones diverging early in evolution of the primary tumor and contained clonal drivers not detected in the primary. Expression data revealed transition from an intratumorally heterogeneous mixture of classical and mesenchymal signatures to tumor-wide mesenchymal at recurrence and suggests that the contrast enhancing centroid may serve as the biological center of the tumor.

From sequentiality to schematization: network-based analysis of covarying collexemes in Mandarin degree adverb constructions

Abstract This study investigates the semantic structures of degree adverb constructions (DAC) in Mandarin through a network-based approach. We first utilized covarying collexeme analysis to determine significant collexeme pairs strongly associated with the DAC. We then incorporated network-based quantitative methods to analyze the emerging schemas from these collexeme pairs. Our approach involved implementing network analyses at two levels. The collexeme-based network consisted of lexical nodes representing degree adverbs and modified heads, while the construction-based network featured collexeme pairs as nodes. The collexeme-based network reveals that degree adverbs develop distinct semantic preferences for attributes within specific semantic fields, primarily capturing subjective and evaluative aspects of human experience. The construction-based network highlights dynamic interactions among these significant collexeme pairs, showcasing semantically interconnected collexeme pairs forming cohesive constructional families. Furthermore, these semantic groupings underscore the crucial role of metaphorical extension in creating larger semantic clusters for higher-level linguistic generalization. The emergence of semantic coherences from both networks reflects the evolving nature of linguistic generalizations, transitioning from low-level pivot schemas in the collexeme-based network to higher-order generalizations in the construction-based network. This study contributes to the field of usage-based grammar by emphasizing the fundamental role of sequentiality and interconnectedness between linguistic units in linguistic generalization.

A Systematic Literature Review and Bibliometric Analysis of Blockchain Technology for Food Security

The United Arab Emirates (UAE) faces obstacles in guaranteeing food security because of its desert climate, restricted arable land, and significant reliance on food imports. Establishing a robust and transparent food supply chain is crucial. This study investigates the crucial functions of blockchain technology in protecting and improving food security in the UAE. Using bibliographic and co-citation network analyses, this study examines 143 research articles that provide a thorough review of the current status of blockchain technology in relation to food security. We examine the interrelationships among studies, highlighting significant themes and identifying three emerging food security patterns in the incorporation of blockchain into the food security domain. This study enhances the understanding of how blockchain technology can transform the food security dimensions of availability, accessibility, utilization, and stability in the UAE and worldwide.

NIMG-50. MULTIPARAMETRIC MRI DISTINGUISHES NEURONAL AND IMMUNE SIGNATURES IN INVASIVE HIGH-GRADE GLIOMA RIM THROUGH GRAPH NETWORK ANALYSIS

Abstract BACKGROUND Standard of care surgery for high grade glioma (HGG) employs Magnetic Resonance Imaging to identify the contrast enhancing (CE) core for resection, leaving a non-enhancing (NE) invasive rim of tumor which contributes to recurrence. Multi-parametric MRI (mpMRI) has recently been used to map regional biological heterogeneity of neuronal and immune signatures in HGG, and continues to offer a promising strategy for non-invasive surveillance of tumor progression. Here, we present a graph network analysis relating mpMRI to biological signatures in the NE tumor rim and show the utility of communities of imaging features for discriminating tumor phenotypes. METHODS 53 mpMRI features across 101 spatially-localized RNA-sequenced biopsy samples from 64 patients with IDH-wt HGG were represented as nodes within a Neo4j graph network. Modularity optimization was used to identify communities of densely connected nodes. Communities of nodes representing high proportions of NE samples (one-tailed test) were kept for further analysis. Gene set enrichment analysis (GSEA) on samples within selected imaging communities was analyzed for biological process enrichment using clusterProfiler. Single sample GSEA (ssGSEA) using ssGSEA2 was used to annotate neuronal and immune cell states across samples within selected communities. mpMRI feature selection within each community identified the most relevant imaging features for isolating samples classified into neuronal and immune cell states. RESULTS 11 imaging communities gathered a high proportion of NE samples. Three NE communities showed significant enrichment of neuronal signatures, while one showed significant enrichment of immune pathways. One neuronal-predominant community showed unique upregulation of 14 pathways related to neuronal migration/astrocyte projection. CONCLUSION Network imaging communities can identify clusters of NE glioma samples showing contrasting neuronal and immune signatures, including distinct upregulation of migration and projection pathways. Mapping these imaging feature communities to specific biological processes implicated in glioma progression may aid treatment planning and prognostication for glioma patients.

EPCO-18. DECIPHERING SPATIAL DIVERSITY OF GLIOBLASTOMA GENETIC ARCHITECTURE

Abstract Glioblastoma (GBM) is hallmarked by profound inter- and intratumoral heterogeneity. Current research has mapped key genetic drivers to distinct transcriptional profiles within GBM. Nevertheless, the intricate interactions between genetic alterations and spatial-transcriptional heterogeneity remain elusive. We utilized nestin-Tva C57BL/6 mice to induce de novo GBM via oncogene overexpression alongside shRNA-mediated silencing or deletion of tumor suppressors. We modeled critical driver mutations: PDGFB, NF1, and EGFR. Employing 10X Genomics platform for single-cell RNA sequencing, combined with spatially resolved transcriptomics and proteomics (Nanostring GeoMx), we integrated data using both horizontal (mutual nearest neighbors) and vertical (weighted nearest neighbors) approaches, analyzed through the SPATA2 software. Advanced computational techniques, including graph neural networks and single-cell deconvolution, were leveraged to unravel the genotypic and spatial variability within tumors and their microenvironments. Our findings uncover persistent cellular heterogeneity across diverse genetic contexts. However, specific genetic mutations precipitated distinct dominant transcriptional states: NF1 and EGFR mutations drove mesenchymal and astrocytic-like states, respectively, whereas PDGFB fostered a neural progenitor/cell-like state. These transcriptional shifts were closely linked to unique microenvironmental modifications, such as elevated neuronal signaling in PDGFB-driven GBMs and significant immune infiltration in NF1 and EGFR models. Through weighted co-expression network analysis (WGCNA) and gene set enrichment analysis (GSEA) paired with spatial-niche deconvolution, we identified a mesenchymal transition leading to an immunosuppressive microenvironment in NF1-loss driven GBMs and increased lymphocyte presence around blood vessels in EGFR-amplified GBMs. These patterns were consistent with human spatially resolved transcriptomic data, emphasizing the genetic complexity and heterogeneity of human GBMs. Our genetically engineered mouse models serve as a robust platform for dissecting GBM with defined genetic mutations. Leveraging sophisticated analytical techniques and computational modeling, this study underscores the profound interplay between genetic drivers and the tumor microenvironment, paving the way for targeted therapeutic strategies and precision medicine in GBM.

Study of red vine phenotypic plasticity across central-southern Italy sites: an integrated analysis of the transcriptome and weather indices through WGCNA

The grapevine (Vitis spp., family Vitaceae) is characterized by marked phenotypic plasticity. Its ability to withstand specific environmental conditions depends on the activation of highly coordinated responses resulting from interactions among genotypes (G) and environmental factors (E). In this study, the transcriptomes of commercially ripe berries of the Cabernet Sauvignon and Aglianico genotypes grown in open fields at three different sites in central-southern Italy (Campania, Molise and Sicily) were analyzed with RNA sequencing. These transcriptomic data were integrated with a comprehensive set of weather course indices through weighted gene co-expression network analysis (WGCNA). A total of 11,887 differentially expressed genes (DEGs) were retrieved, most of which were associated with the Aglianico genotype. The plants from the Sicilian site presented the greatest number of DEGs for both genotypes. Most of the weather course data (daily maximum air temperature, relative humidity, air pressure, dew point, and hours of sun radiation) were significantly correlated with the “lightcyan1” module, confirming WGCNA as a powerful method for identifying genes of high biological interest. Within this module, the gene encoding the ACA10 cation transporter was highly expressed in plants of both genotypes from Campania, where the lowest anthocyanin content was recorded. The transcriptome was also correlated with quality traits, such as total soluble solids and polyphenol content. This approach could lead to the identification of a transcriptomic profile that may specifically identify a genotype and its growing site and to the discovery of hub genes that might function as markers of wine quality.

Evaluation of pitolisant, sodium oxybate, solriamfetol, and modafinil for the management of narcolepsy: a retrospective analysis of the FAERS database

ObjectiveNarcolepsy, a rare neurological disorder believed to have an autoimmune etiology, necessitates lifelong management. This study aimed to provide evidence supporting the safety of pharmacological treatment for narcolepsy.MethodsFive-year data on pitolisant, sodium oxybate, solriamfetol, and modafinil were extracted from the FDA Adverse Event Reporting System (FAERS) self-reporting database for the period spanning from 2019 to 2023. Various statistical methods, including the reporting odds ratio (ROR), proportional reporting ratio (PRR), Bayesian confidence propagation neural network analysis (BCPNN), and multi-item gamma Poisson shrinker (MGPS), were employed to quantify the signals. Finally, a comparative analysis was conducted between demographic data, outcomes, and inherent associations among the medications and the signals.ResultsAfter data analysis, we obtained 50 signals (a cumulative count of 762 cases) for pitolisant, 640 signals (corresponding to 46,962 cases) for sodium oxybate, 40 signals (equivalent to 1,228 cases) for solriamfetol, and finally, 72 signals (representing 632 cases) for modafinil. The majority of these patients were female. Psychiatric and nervous system disorders were identified as the predominant adverse drug events (ADEs). For sodium oxybate, it is crucial to consider psychiatric disorders (such as suicidal ideation), respiratory disorders (including sleep apnea syndrome and respiratory depression), and signs of pregnancy and congenital familial diseases. For solriamfetol, noteworthy new ADEs include drug inefficacy, suicidal ideation, restless legs syndrome, and somnambulism. Furthermore, a relationship has been observed between modafinil use and restricted fetal growth, spontaneous abortion, cognitive disorders, and drug inefficacy and abuse.ConclusionThe majority of observed adverse reactions in this study were consistent with those listed in the product instructions. However, potential novel or notable ADE signals were identified through real-world pharmacovigilance analysis. It is anticipated that this paper will offer additional information regarding safe and rational medication for narcolepsy.

Multiomics dissection of Brassica napus L. lateral roots and endophytes interactions under phosphorus starvation

Many plants associate with endophytic microbes that improve root phosphorus (P) uptake. Understanding the interactions between roots and endophytes can enable efforts to improve P utilization. Here, we characterize the interactions between lateral roots of endophytes in a core collection of 50 rapeseed (Brassica napus L.) genotypes with differing sensitivities to low P conditions. With the correlation analysis result between bacterial abundance and plant physiological indices of rapeseeds, and inoculation experiments on plates and soil, we identify one Flavobacterium strain (C2) that significantly alleviates the P deficiency phenotype of rapeseeds. The underlying mechanisms are explored by performing the weighted gene coexpression network analysis (WGCNA), and conducting genome-wide association studies (GWAS) using Flavobacterium abundance as a quantitative trait. Under P-limited conditions, C2 regulates fatty acid and lipid metabolic pathways. For example, C2 improves metabolism of linoleic acid, which mediates root suberin biosynthesis, and enhances P uptake efficiency. In addition, C2 suppresses root jasmonic acid biosynthesis, which depends on α-linolenic acid metabolism, improving C2 colonization and activating P uptake. This study demonstrates that adjusting the endophyte composition can modulate P uptake in B. napus plants, providing a basis for developing agricultural microbial agents.

Immune Response and Transcriptome Analysis of the Head Kidney to Different Concentrations of Aeromonas veronii in Common Carp (Cyprinus carpio)

The common carp (Cyprinus carpio), a major economic freshwater fish, is suffering from a variety of bacterial infectious diseases because of its high-density, factory and intensive farming patterns. Aeromonas veronii is the causative agent of high mortality in common carp, causing severe economic losses in aquaculture. However, the regulatory mechanisms involved in the response of common carp to this bacterial infection remain poorly understood. In this study, we compared mortality, blood serum LZM (Lysozyme) and IgM (Immunoglobulin M) levels and transcriptome patterns of head kidney tissues after infection with different concentrations of Aeromonas veronii. We observed that mortality increased progressively with an increasing pathogen concentration. The concentrations of blood serum LZM and IgM significantly increased after infection. A total of 13 and 925 differentially expressed genes (DEGs) were identified after infection with low (T4) and high (T9) concentrations of bacterial suspension, respectively. KEGG and GO analyses of the DEGs highlighted multiple immune-related signaling pathways. Weighted gene co-expression network analysis (WGCNA) revealed that 136 and 83 hub genes were related to blood serum LZM and IgM, respectively. Finally, the gene expression in the head kidney was validated via RT–qPCR to be consistent with the transcriptome. These results provide insights into the mechanisms of the immune response to infection with different concentrations of Aeromonas veronii and offer useful information for further studies on immune defense mechanisms in common carp.

PRONA: An R-package for Patient Reported Outcomes Network Analysis

Abstract Summary Network analysis (NA) has recently emerged as a new paradigm by which to model the symptom patterns of patients with complex illnesses such as cancer. NA uses graph theory-based methods to capture the interplay between symptoms and identify which symptoms may be most impactful to patient quality of life and are therefore most critical to treat/prevent. Despite NA’s increasing popularity in research settings, its clinical applicability is hindered by the lack of a unified platform that consolidates all the software tools needed to perform NA, and by the lack of methods for capturing heterogeneity across patient cohorts. Addressing these limitations, we present PRONA, an R-package for Patient Reported Outcomes Network Analysis. PRONA not only consolidates previous NA tools into a unified, easy-to-use analysis pipeline, but also augments the traditional approach with functionality for performing unsupervised discovery of patient subgroups with distinct symptom patterns. Availability and Implementation PRONA is implemented in R. Source code, installation, and use instructions are available on GitHub at https://github.com/bbergsneider/PRONA. Supplementary information Supplementary information is available at Bioinformatics online.

Unravelling the complexity of suicidality: a network analysis of theory-driven and culturally relevant suicide risk factors in a country with high suicide rates

Purpose This study aimed to explore whether individual theory-based constructs are sufficient in explaining suicidality in a culture marked by high suicide rates and whether, if any, culturally relevant factors need to be considered additionally. Methods The study used a community sample of 1873 Lithuanian adults (age M = 43.61 SD = 16.96, 69.1% female). A survey using online and pen-and-paper formats was conducted, measuring suicidality, the main constructs from two predominant theories of suicide (thwarted belongingness, perceived burdensomeness, acquired capability for suicide, and defeat and entrapment), and culturally relevant factors (gender role expectations, attitudes towards help-seeking, perfectionism, negative social comparisons, alcohol use, child-parent relationships and childhood experiences). Network analysis method was used in the analysis. Results From the key factors identified in the two theories perceived burdensomeness had stronger links with self-perceived risk for suicide compared to thwarted belongingness and entrapment. Acquired capability to suicide had no direct links with other factors in the network apart from a weak link with history of suicidal behavior. In the network some of the culturally relevant variables (reasons for alcohol use, experience of sexual abuse, emotional neglect, and cultural norms representing restricted emotionality and attitudes towards psychological help) had direct relationships with suicidality, not only via key theory based factors. Conclusions The results suggest the need to consider cultural context when applying universal suicide theories.

An integrated empirical and computational study to decipher help-seeking behaviors and vocal stigma

BackgroundProfessional voice users often experience stigma associated with voice disorders and are reluctant to seek medical help. This study deployed empirical and computational tools to (1) quantify the experience of vocal stigma and help-seeking behaviors in performers; and (2) predict their modulations with peer influences in social networks.MethodsExperience of vocal stigma and information-motivation-behavioral (IMB) skills were prospectively profiled using online surveys from a total of 403 Canadians (200 singers and actors and 203 controls). Data were used to formulate an agent-based network model of social interactions on vocal stigma (self-stigma and social-stigma) and help-seeking behaviors. Network analysis was performed to evaluate the effect of social network structure on the flow of IMB among virtual agents.ResultsLarger social networks are more likely to contribute to an increase in vocal stigma. For small social networks, total stigma is reduced with higher total IMB but not much so for large networks. For agents with high social-stigma and risk for voice disorder, their vocal stigma is resistant to large changes in IMB ( > 2 standard deviations). Agents with extreme IMB and stigma values are likely to polarize their networks faster in larger social groups.ConclusionsWe integrated empirical surveys and computational techniques to contextualize vocal stigma and IMB beyond theory and to quantify the interaction among stigma, health-seeking behavior and influence of social interactions. This work establishes an effective, predictable experimental platform to provide scientific evidence in developing interventions to reduce health stigma in voice disorders and other medical conditions.

AI and Database Management for Organizational Transformation With Insights From Twitter Data

This paper explores the role of AI and database management in organizational transformation using insights from Twitter data. By analyzing 30,000 English-language tweets with methods such as word analysis, topic modeling, network analysis, sentiment analysis, and emotion analysis, the study reveals a strong correlation between AI and digital transformation. The findings show positive sentiment and optimism about AI's potential. This research highlights the importance of social influence, perceived trust, and awareness in AI adoption, offering valuable insights for researchers and practitioners. Despite relying on Twitter data, the study provides practical guidance for leveraging AI in digital transformation efforts.

Exploring the ceRNA network involving AGAP2-AS1 as a novel biomarker for preeclampsia

Preeclampsia (PE) is an important research subject in obstetrics. Nevertheless, the underlying mechanisms of PE remain elusive. PE-related expression datasets (GSE96983, GSE96984 and GSE24129) were downloaded from the Gene Expression Omnibus (GEO) database. Firstly, the differentially expressed messenger RNAs (DE-mRNAs), DE-microRNA (DE-miRNAs) and DE-long non-coding RNA (DE-lncRNAs) between PE and control cohorts were identified, and the ceRNA network was constructed. Then candidate hub genes were obtained through five algorithms by the protein-protein intersection (PPI) network of the mRNAs. Further, five hub genes were identified by receiver operating characteristic (ROC) curve and gene expression profiles: DAXX, EFNB1, NCOR2, RBBP4 and SOCS1. The function of 5 hub genes was analyzed and the interaction between drugs and hub genes was predicted. A total of 5 small molecule drugs were predicted, namely benzbromarone, 9,10-phenanthrenequinone, chembl312032, insulin and aldesleukin. AGAP2-AS1 was mainly located in exosome and cytoplasm. Agap2-as1-related regulatory subnetworks were extracted from ceRNA networks which included 41 mRNAs, 2 miRNAs and 1 lncRNA, including the regulated relationship pairs AGAP2-AS1-hsa-miR-497-5p-SRPRB, and AGAP2-AS1-hsa-miR-195-5p-RPL36. In summary, we constructed a competitive endogenous RNA (ceRNA) network to identify five potential biomarkers (DAXX, EFNB1, NCOR2, SOCS1 and RBBP4) of PE. The in-depth analysis of the AGAP2-AS1 regulatory network will help to uncover more important molecules closely related to PE and provide a scientific Reference.

Improving Rainfall Prediction Accuracy in the USA Using Advanced Machine Learning Techniques

The key aim of this research project is to design and evaluate advanced machine learning models for increasing accuracy in rainfall forecasting over the USA. We intended to investigate nonlinear relationships typical of the atmospheric variables using state-of-the-art ML methods for more accurate rainfall predictions. For this research project on rainfall forecasting in the USA, we utilized an extensive dataset that comprises historical rainfall data collected from the National Oceanic and Atmospheric Administration (NOAA) and other meteorological agencies. The main dataset we use in this paper consists of daily rainfall measurements across various geographical locations of the USA, thus capturing the wide-ranging historical data necessary for both training and validation of the model. Besides measuring rainfall, we included meteorological data from sources such as NOAA's Global Historical Climatology Network and NASA's Modern-Era Retrospective Analysis for Research and Applications. These datasets further provided key variables that are known to affect rain, including temperature, humidity, wind speed, and atmospheric pressure. The performance metrics used in this research work for the models considered include accuracy, precision, recall, and F1 score. The above table shows that the Random Forest Classifier outperformed the other models, achieving perfect accuracy. That indicated that it rightly classified all the instances in the test set. The Logistic Regression and Support Vector Machine models gave a quite good performance by giving above average accuracy but had lower precision and recall for the rainfall prediction. Accurate rainfall forecasting has direct consequences on agriculture, greatly empowering farmers and agricultural planners to make more effective decisions regarding planting, harvesting, and crop management. The forecasts of rainfall are also of critical importance in disaster management regarding planning for flood emergencies. Moreover, precise forecasting of rainfall, particularly in sustainable water resources management, presents the most important data in planning for and conserving these resources.

Studies on Submersible Short-Circuit Blowing Based on Orthogonal Experiments, Back Propagation Neural Network Prediction, and Pearson Correlation Analysis

Short-circuit blowing is a crucial technical approach for ensuring the rapid surfacing of submersibles. In order to investigate the law, L18(37) orthogonal experiments based on a proportional short-circuit blowing model test bench were conducted. Subsequently, a Back Propagation Neural Network (BPNN) and Pearson correlation analysis were employed to train the experimental data; further examination of the correlation between individual factors and blowing served as an enhancement to the orthogonal experiments. It has been proved that both multi-factor combinations and personal factors, including blowing duration, sea tank back pressure, gas blowing pressure from the cylinder group, and sea valve flowing area, exert significant influence with Pearson correlation coefficients of 0.6535, 0.8105, 0.5569, and 0.5373, respectively. Notably, the F-ratio for blowing duration exceeds the critical value of 3.24. The statistical evaluation metrics for the BPNN ranged from 10−1 to 10−12, with relative errors below 3%, and achieving a prediction accuracy rate of 100%. Based on these findings, a robust predictive methodology for submersible short-circuit blowing has been established along with recommendations for engineering design and operational strategies that highlight its advantages as well as its initial condition settings.