RESUMEN
In developing countries, smart grids are nonexistent, and electricity theft significantly hampers power supply. This research introduces a lightweight deep-learning model using monthly customer readings as input data. By employing careful direct and indirect feature engineering techniques, including Principal Component Analysis (PCA), t-distributed Stochastic Neighbor Embedding (t-SNE), UMAP (Uniform Manifold Approximation and Projection), and resampling methods such as Random-Under-Sampler (RUS), Synthetic Minority Over-sampling Technique (SMOTE), and Random-Over-Sampler (ROS), an effective solution is proposed. Previous studies indicate that models achieve high precision, recall, and F1 score for the non-theft (0) class, but perform poorly, even achieving 0 %, for the theft (1) class. Through parameter tuning and employing Random-Over-Sampler (ROS), significant improvements in accuracy, precision (89 %), recall (94 %), and F1 score (91 %) for the theft (1) class are achieved. The results demonstrate that the proposed model outperforms existing methods, showcasing its efficacy in detecting electricity theft in non-smart grid environments.
RESUMEN
Measuring the chemical composition in soybeans is time-consuming and laborious, and even simple near-infrared sensors generally require the creation of calibration curves before application. In this study, a new screening method for soybeans without calibration curves was investigated by combining the excitation emission matrix (EEM) and dimensionality reduction analysis. The EEMs of 34 soybean samples were measured, and representative chemical contents including crude protein, crude oil and isoflavone contents were measured by chemical analysis. Two methods of dimensionality reduction: principal component analysis (PCA) and t-distributed Stochastic Neighbor Embedding (t-SNE) were applied on the EEM data to obtain two-dimensional plots, which were divided into two regions with large or small amount of each chemical components. To classify the large or small levels of each of the chemical composition, machine learning classification models were constructed on the two-dimensional plots after dimensionality reduction. As a result, the classification accuracy was higher in t-SNE than in the combinations of PC1 and PC2 from PCA. Furthermore, in t-SNE, the classification accuracy reached over 90% for all the chemical components. From these results, t-SNE dimensionality reduction on the soybean EEM has the potential for easy and accurate screening of soybeans especially based on isoflavone contents.
RESUMEN
This study explores burnout among nursing students in Bangalore, India, focusing on Exhaustion and Disengagement scores. A cross-sectional design was applied using the Oldenburg Burnout Inventory modified for nursing students, collecting data using a survey that was conducted between October and December 2023. The sample consisted of 237 female nursing students from the Bachelor of Science in Nursing program at Bangalore College of Nursing, South India. The study integrated the t-distributed Stochastic Neighbor Embedding (t-SNE) procedure for data simplification into three t-SNE components, used in a hierarchical clustering analysis, which identified distinct student profiles: "High-Intensity Study Group" and "Altruistic Aspirants". While burnout scores were generally high, students with high study hours ("High-Intensity Study Group") reported greater Exhaustion, with a mean score of 26.78 (SD = 5.26), compared to those in the "Altruistic Aspirants" group, who reported a mean score of 25.00 (SD = 4.48), demonstrating significant differences (p-value = 0.005). Conversely, those motivated by altruism ("Altruistic Aspirants") showed higher Disengagement, with a mean score of 19.78 (SD = 5.08), in contrast to "High-Intensity Study Group", which reported a lower mean of 17.84 (SD = 4.74) (p-value = 0.002). This segmentation suggests that burnout manifests differently depending on the students' academic load and intrinsic motivations. This study underscores the need for targeted interventions that address specific factors characterizing the clusters and provide information for designing future research and interventions. This study was not registered.
RESUMEN
The architecture of the brain is too complex to be intuitively surveyable without the use of compressed representations that project its variation into a compact, navigable space. The task is especially challenging with high-dimensional data, such as gene expression, where the joint complexity of anatomical and transcriptional patterns demands maximum compression. The established practice is to use standard principal component analysis (PCA), whose computational felicity is offset by limited expressivity, especially at great compression ratios. Employing whole-brain, voxel-wise Allen Brain Atlas transcription data, here we systematically compare compressed representations based on the most widely supported linear and non-linear methods-PCA, kernel PCA, non-negative matrix factorisation (NMF), t-stochastic neighbour embedding (t-SNE), uniform manifold approximation and projection (UMAP), and deep auto-encoding-quantifying reconstruction fidelity, anatomical coherence, and predictive utility across signalling, microstructural, and metabolic targets, drawn from large-scale open-source MRI and PET data. We show that deep auto-encoders yield superior representations across all metrics of performance and target domains, supporting their use as the reference standard for representing transcription patterns in the human brain.
Asunto(s)
Encéfalo , Imagen por Resonancia Magnética , Transcripción Genética , Humanos , Encéfalo/diagnóstico por imagen , Encéfalo/metabolismo , Transcripción Genética/fisiología , Tomografía de Emisión de Positrones , Procesamiento de Imagen Asistido por Computador/métodos , Análisis de Componente Principal , Compresión de Datos/métodos , Atlas como AsuntoRESUMEN
Dendrobium, a highly effective traditional Chinese medicinal herb, exhibits significant variations in efficacy and price among different varieties. Therefore, achieving an efficient classification of Dendrobium is crucial. However, most of the existing identification methods for Dendrobium make it difficult to simultaneously achieve both non-destructiveness and high efficiency, making it challenging to truly meet the needs of industrial production. In this study, we combined Laser-Induced Breakdown Spectroscopy (LIBS) with multivariate models to classify 10 varieties of Dendrobium. LIBS spectral data for each Dendrobium variety were collected from three circular medicinal blocks. During the data analysis phase, multivariate models to classify different Dendrobium varieties first preprocess the LIBS spectral data using Gaussian filtering and stacked correlation coefficient feature selection. Subsequently, the constructed fusion model is utilized for classification. The results demonstrate that the classification accuracy of 10 Dendrobium varieties reached 100%. Compared to Support Vector Machine (SVM), Random Forest (RF), and K-Nearest Neighbors (KNN), our method improved classification accuracy by 14%, 20%, and 20%, respectively. Additionally, it outperforms three models (SVM, RF, and KNN) with added Principal Component Analysis (PCA) by 10%, 10%, and 17%. This fully validates the excellent performance of our classification method. Finally, visualization analysis of the entire research process based on t-distributed Stochastic Neighbor Embedding (t-SNE) technology further enhances the interpretability of the model. This study, by combining LIBS and machine learning technologies, achieves efficient classification of Dendrobium, providing a feasible solution for the identification of Dendrobium and even traditional Chinese medicinal herbs.
RESUMEN
Background: Several pelvic area cancers exhibit high incidence rates, and their surgical treatment can result in adverse effects such as urinary and fecal incontinence, significantly impacting patients' quality of life. Post-surgery incontinence is a significant concern, with prevalence rates ranging from 25 to 45% for urinary incontinence and 9-68% for fecal incontinence. Cancer survivors are increasingly turning to YouTube as a platform to connect with others, yet caution is warranted as misinformation is prevalent. Objective: This study aims to evaluate the information quality in YouTube videos about post-surgical incontinence after pelvic area cancer surgery. Methods: A YouTube search for "Incontinence after cancer surgery" yielded 108 videos, which were subsequently analyzed. To evaluate these videos, several quality assessment tools were utilized, including DISCERN, GQS, JAMA, PEMAT, and MQ-VET. Statistical analyses, such as descriptive statistics and intercorrelation tests, were employed to assess various video attributes, including characteristics, popularity, educational value, quality, and reliability. Also, artificial intelligence techniques like PCA, t-SNE, and UMAP were used for data analysis. HeatMap and Hierarchical Clustering Dendrogram techniques validated the Machine Learning results. Results: The quality scales presented a high level of correlation one with each other (p < 0.01) and the Artificial Intelligence-based techniques presented clear clustering representations of the dataset samples, which were reinforced by the Heat Map and Hierarchical Clustering Dendrogram. Conclusions: YouTube videos on "Incontinence after Cancer Surgery" present a "High" quality across multiple scales. The use of AI tools, like PCA, t-SNE, and UMAP, is highlighted for clustering large health datasets, improving data visualization, pattern recognition, and complex healthcare analysis.
RESUMEN
INTRODUCTION: Ginger (Zingiber officinale Rosc.) varies widely due to varying concentrations of phytochemicals and geographical origin. Rapid non-invasive quality and traceability assessment techniques ensure a sustainable value chain. OBJECTIVE: The objective of this study is the development of suitable machine learning models to estimate the concentration of 6-gingerol and check traceability based on the spectral fingerprints of dried ginger samples collected from Northeast India and the Indian market using near-infrared spectrometry. METHODS: Samples from the market and Northeast India underwent High Performance Liquid Chromatographic analysis for 6-gingerol content estimation. Near infrared (NIR) Spectrometer acquired spectral data. Quality prediction utilized partial least square regression (PLSR), while fingerprint-based traceability identification employed principal component analysis and t-distributed stochastic neighbor embedding (t-SNE). Model performance was assessed using RMSE and R2 values across selective wavelengths and spectral fingerprints. RESULTS: The standard normal variate pretreated spectral data over the wavelength region of 1,100-1,250 nm and 1,325-1,550 nm showed the optimal calibration model with root mean square error of calibration and R2 C (coefficient of determination for calibration) values of 0.87 and 0.897 respectively. A lower value (0.24) of root mean square error of prediction and a higher value (0.973) of R2 P (coefficient of determination for prediction) indicated the effectiveness of the developed model. t-SNE performed better clustering of samples based on geographical location, which was independent of gingerol content. CONCLUSION: The developed NIR spectroscopic model for Indian ginger samples predicts the 6-gingerol content and provides geographical traceability-based identification to ensure a sustainable value chain, which can promote efficiency, cost-effectiveness, consumer confidence, sustainable sourcing, traceability, and data-driven decision-making.
RESUMEN
Labelling medical images is an arduous and costly task that necessitates clinical expertise and large numbers of qualified images. Insufficient samples can lead to underfitting during training and poor performance of supervised learning models. In this study, we aim to develop a SimCLR-based semi-supervised learning framework to classify colorectal neoplasia based on the NICE classification. First, the proposed framework was trained under self-supervised learning using a large unlabelled dataset; subsequently, it was fine-tuned on a limited labelled dataset based on the NICE classification. The model was evaluated on an independent dataset and compared with models based on supervised transfer learning and endoscopists using accuracy, Matthew's correlation coefficient (MCC), and Cohen's kappa. Finally, Grad-CAM and t-SNE were applied to visualize the models' interpretations. A ResNet-backboned SimCLR model (accuracy of 0.908, MCC of 0.862, and Cohen's kappa of 0.896) outperformed supervised transfer learning-based models (means: 0.803, 0.698, and 0.742) and junior endoscopists (0.816, 0.724, and 0.863), while performing only slightly worse than senior endoscopists (0.916, 0.875, and 0.944). Moreover, t-SNE showed a better clustering of ternary samples through self-supervised learning in SimCLR than through supervised transfer learning. Compared with traditional supervised learning, semi-supervised learning enables deep learning models to achieve improved performance with limited labelled endoscopic images.
RESUMEN
Using multi-color flow cytometry analysis, we studied the immunophenotypical differences between leukemic cells from patients with AML/MDS and hematopoietic stem and progenitor cells (HSPCs) from patients in complete remission (CR) following their successful treatment. The panel of markers included CD34, CD38, CD45RA, CD123 as representatives for a hierarchical hematopoietic stem and progenitor cell (HSPC) classification as well as programmed death ligand 1 (PD-L1). Rather than restricting the evaluation on a 2- or 3-dimensional analysis, we applied a t-distributed stochastic neighbor embedding (t-SNE) approach to obtain deeper insight and segregation between leukemic cells and normal HPSCs. For that purpose, we created a t-SNE map, which resulted in the visualization of 27 cell clusters based on their similarity concerning the composition and intensity of antigen expression. Two of these clusters were "leukemia-related" containing a great proportion of CD34+/CD38- hematopoietic stem cells (HSCs) or CD34+ cells with a strong co-expression of CD45RA/CD123, respectively. CD34+ cells within the latter cluster were also highly positive for PD-L1 reflecting their immunosuppressive capacity. Beyond this proof of principle study, the inclusion of additional markers will be helpful to refine the differentiation between normal HSPCs and leukemic cells, particularly in the context of minimal disease detection and antigen-targeted therapeutic interventions. Furthermore, we suggest a protocol for the assignment of new cell ensembles in quantitative terms, via a numerical value, the Pearson coefficient, based on a similarity comparison of the t-SNE pattern with a reference.
RESUMEN
Objective: Chondrocyte death is the hallmark of cartilage degeneration during osteoarthritis (OA). However, the specific pathogenesis of cell death in OA chondrocytes has not been elucidated. This study aims to validate the role of CDKN1A, a key programmed cell death (PCD)-related gene, in chondrogenic differentiation using a combination of single-cell and bulk sequencing approaches. Design: OA-related RNA-seq data (GSE114007, GSE55235, GSE152805) were downloaded from Gene Expression Omnibus database. PCD-related genes were obtained from GeneCards database. RNA-seq was performed to annotate the cell types in OA and control samples. Differentially expressed genes (DEGs) among those cell types (scRNA-DEGs) were screened. A nomogram of OA was constructed based on the featured genes, and potential drugs targeting the featured genes were predicted. The presence of key genes was confirmed using Real-Time Quantitative Polymerase Chain Reaction (RT-qPCR), Western blot (WB), and immunohistochemistry (IHC). Micromass culture and Alcian blue staining were used to determine the effect of CDKN1A on chondrogenesis. Results: Six cell types, namely HomC, HTC, RepC, preFC, FC, and RegC, were annotated in scRNA-seq data. Five featured genes (JUN, CDKN1A, HMGB2, DDIT3, and DDIT4) were screened by multiple biological information analysis methods. TAXOTERE had the highest ability to dock with DDIT3. Functional analysis indicated that CDKN1A was enriched in processes related to collagen catabolism and acts as a positive regulator of autophagy. Additionally, CDKN1A was found to be associated with several KEGG pathways, including those involved in acute myeloid leukemia and autoimmune thyroid disease. CDKN1A was confirmed down-regulated in the joint tissues of OA mouse model and OA model cell. Inhibiting the expression of CDKN1A can significantly suppress the differentiation of OA chondrocytes. Conclusion: Our findings highlight the critical role of CDKN1A in promoting cartilage formation in both in vivo and in vitro and suggest its potential as a therapeutic target for OA treatment.
RESUMEN
Classifying big data in hyperspectral imaging (HSI) can be challenging when minor (low-concentrated) compounds are present in actual samples, as for chemical additives and adulterants in food matrix. Herein, we propose a new strategy to classify HSI data for the identification of adulterants in food material for the first time. This strategy is based on the selection of essential spectral pixels of full HSI data followed by the feature space construction using uniform manifold approximation and projection as well as the data clustering utilizing hierarchical clustering analysis on the reduced data (named ESPs-UMAP-HCA). We apply our approach to analyze two real NIR datasets and four new Raman datasets. Compared with non-ESPs UMAP-HCA and t-distributed stochastic neighbor embedding combined with ESPs and HCA (ESPs-t-SNE-HCA), the developed strategy provides well-separated clusters for major and minor compounds in food matrix. Finally, the adulterants as minor compounds are accurately identified, which is confirmed by the fact that the extracted spectra of them perfectly match with their pure spectra. In addition, their locations are found in the contribution map even though they are present in a few pixels. What's more, the proposed strategy does not need any a priori knowledge of the data structure and the class memberships and therefore reduced the studied difficulty and confirmation bias in the analysis of big HSI datasets. Overall, the proposed ESPs-UMAP-HCA method could be a potential approach for food adulteration detection.
Asunto(s)
Alimentos , Imágenes Hiperespectrales , Análisis por ConglomeradosRESUMEN
Water distribution networks (WDNs) experience significant water loss due to leaks, necessitating advanced water leak detection methods. However, machine learning-based acoustic method heavily relies on signal information and is limited by data scarcity and the limited diversity of available data. To address this challenge and enhance water leak detection in WDNs, this study proposes an LSTM-GAN approach. Acoustic signals are collected from WDNs to train the LSTM-GAN model, which generates synthetic leak signals to enhance the dataset. The validity of the generative method is evaluated through t-SNE and acoustic characteristics analysis. LSTM-based water leak detection models are established and compared using the original and the generated datasets to confirm the efficacy of generated samples in improving water leak detection performances. The capability of LSTM-GAN has been evaluated through different perspectives, including sensitivity analysis and model comparison. The results validate the quality and consistency of the generated acoustic signals under leak conditions. Besides, the optimal number of generated samples should be determined according to the requirements and characteristics of the leak detection task. Furthermore, the comparison between the proposed method and other acoustic generative methods demonstrates the superiority of LSTM-GAN-generated signals in enhancing the performance of leak detection models. The proposed generative method offers an innovative approach to facilitate machine learning-based leak detection models with limited data, thereby enhancing robustness.
Asunto(s)
Acústica , Agua , Abastecimiento de AguaRESUMEN
BCL9 is a key protein in Wnt signaling pathway. It acts as a transcriptional co-activator to ß-catenin, and dysregulation in this pathway leads to tumor growth. Inhibiting such a protein-protein interaction is considered as a therapeutic challenge. The interaction between ß-catenin and BCL9 is facilitated by a 23-residue helical domain from BCL9 and a hydrophobic groove of ß-catenin. To prevent this interaction, a peptide that mimics the alpha-helical domain of BCL9 can be designed. Stapling is considered a successful strategy in the pursuit of designing such peptides in which amino acids side are stitched together using chemical moieties. Among the various types of cross-linkers, triazole is the most rapid and effective one synthesized via click reaction. However, the underlying interactions behind maintaining the secondary structure of stapled peptides remain less explored. In the current work, we employed the molecular dynamics simulation to study the conformational behavior of the experimentally synthesized single and double triazole stapled BCL9 peptide. Upon the addition of a triazole staple, there is a significant reduction in the conformational space of BCL9. The helical character of the stapled peptide increases with an increase in separation between the triazole cross-linkers. Also, we encompassed the Replica Exchange with Solute Tempering (REST2) simulation to validate the high-temperature response of the stapled peptide. From REST2, the PCA and t-SNE show the reduction in distinct cluster formation on the addition of triazole staple. Our study infers further development of these triazole-stapled BCL9 peptides into effective inhibitors to target the interaction between ß-catenin and BCL9.
Asunto(s)
Triazoles , beta Catenina , beta Catenina/química , beta Catenina/metabolismo , Triazoles/farmacología , Proteínas de Neoplasias/química , Proteínas de Neoplasias/metabolismo , Factores de Transcripción/metabolismo , Péptidos/química , Estructura Secundaria de ProteínaRESUMEN
In this study, we explored the potential of novel inhibitors for FYN kinase, a critical target in cancer and neurodegenerative disorders, by integrating advanced cheminformatics, machine learning, and molecular simulation techniques. Our approach involved analyzing key interactions for FYN inhibition using established multi-kinase inhibitors such as Staurosporine, Dasatinib, and Saracatinib. We utilized ECFP4 circular fingerprints and the t-SNE machine learning algorithm to compare molecular similarities between FDA-approved drugs and known clinical trial inhibitors. This led to the identification of potential inhibitors, including Afatinib, Copanlisib, and Vandetanib. Using the DrugSpaceX platform, we generated a vast library of 72,196 analogues from these leads, which after careful refinement, resulted in 6008 promising candidates. Subsequent clustering identified 48 analogues with significant similarity to known inhibitors. Notably, two candidates derived from Vandetanib, DE27123047 and DE27123035, exhibited strong docking affinities and stable binding in molecular dynamics simulations. These candidates showed high potential as effective FYN kinase inhibitors, as evidenced by MMGBSA calculations and MCE-18 scores exceeding 50. Additionally, our exploration into their molecular architecture revealed potential modification sites on the quinazolin-4-amine scaffold, suggesting opportunities for strategic alterations to enhance activity and optimize ADME properties. Our research is a pioneering effort in drug discovery, unveiling novel candidates for FYN inhibition and demonstrating the efficacy of a multi-layered computational strategy. The molecular insights gained provide a pathway for strategic refinements and future experimental validations, setting a new direction in targeted drug development against diseases involving FYN kinase.
RESUMEN
The hippocampus is known to play an important role in memory by processing spatiotemporal information of episodic experiences. By recording synchronized multiple-unit firing events (ripple firings with 300 Hz-10 kHz) of hippocampal CA1 neurons in freely moving rats, we previously found an episode-dependent diversity in the waveform of ripple firings. In the present study, we hypothesized that changes in the diversity would depend on the type of episode experienced. If this hypothesis holds, we can identify the ripple waveforms associated with each episode. Thus, we first attempted to classify the ripple firings measured from rats into five categories: those experiencing any of the four episodes and those before experiencing any of the four episodes. In this paper, we construct a convolutional neural network (CNN) to classify the current stocks of ripple firings into these five categories and demonstrate that the CNN can successfully classify the ripple firings. We subsequently indicate partial ripple waveforms that the CNN focuses on for classification by applying gradient-weighted class activation mapping (Grad-CAM) to the CNN. The method of t-distributed stochastic neighbor embedding (t-SNE) maps ripple waveforms into a two-dimensional feature space. Analyzing the distribution of partial waveforms extracted by Grad-CAM in a t-SNE feature space suggests that the partial waveforms may be representative of each category.
RESUMEN
In the era of targeted therapeutics, protein kinases like WEE1 have become pivotal drug targets, especially for cancer therapy. Utilizing a multi-faceted approach, our study adds fresh insights to this endeavour. We employed the t-SNE algorithm, combined with ECFP4 fingerprints, to analyse the molecular similarity between FDA-approved drugs and known clinical trial inhibitors. Our t-SNE analysis identified the closest clusters to known inhibitors and selected 11 FDA-approved drugs for further study. Using the DrugSpaceX platform, we generated analogues for these 11 FDA-approved drugs. These analogues were refined according to Lipinski's Rule of Five and Synthetic Accessibility scores, yielding 68,640 analogues for additional scrutiny. Among these, derivatives of Palbociclib and Ribociclib stood out as the most promising WEE1 inhibitors, based on docking scores and interaction patterns. Molecular dynamics simulations validated the stability of these protein-ligand interactions, particularly for DE50607359, a top-ranked Palbociclib analogue, which also met most pharmacokinetic parameters within acceptable limits. Our study uncovers new candidates for WEE1 inhibition not previously reported. With our multi-layered computational strategy, we provide a solid foundation for future experimental validation and targeted drug development in cancer therapeutics.Communicated by Ramaswamy H. Sarma.
Employed the t-SNE algorithm and ECFP4 fingerprints to discern molecular similarities between FDA-approved drugs and known clinical trial inhibitors, identifying 11 key drugs.Leveraged the DrugSpaceX platform to generate analogues for these selected FDA-approved drugs, yielding a massive collection of 68,640 refined analogues based on Lipinski's Rule of Five and Synthetic Accessibility scores.Derivatives of Palbociclib and Ribociclib emerged as the most promising WEE1 inhibitors, supported by their docking scores and interaction patterns.Validated protein-ligand interactions through molecular dynamics simulations, spotlighting DE50607359, a superior Palbociclib analogue, meeting critical pharmacokinetic parameters.
RESUMEN
Characterizing the connectomic and morphological diversity of thalamic neurons is key for better understanding how the thalamus relays sensory inputs to the cortex. The recent public release of complete single-neuron morphological reconstructions enables the analysis of previously inaccessible connectivity patterns from individual neurons. Here we focus on the Ventral Posteromedial (VPM) nucleus and characterize the full diversity of 257 VPM neurons, obtained by combining data from the MouseLight and Braintell projects. Neurons were clustered according to their most dominantly targeted cortical area and further subdivided by their jointly targeted areas. We obtained a 2D embedding of morphological diversity using the dissimilarity between all pairs of axonal trees. The curved shape of the embedding allowed us to characterize neurons by a 1-dimensional coordinate. The coordinate values were aligned both with the progression of soma position along the dorsal-ventral and lateral-medial axes and with that of axonal terminals along the posterior-anterior and medial-lateral axes, as well as with an increase in the number of branching points, distance from soma and branching width. Taken together, we have developed a novel workflow for linking three challenging aspects of connectomics, namely the topography, higher order connectivity patterns and morphological diversity, with VPM as a test-case. The workflow is linked to a unified access portal that contains the morphologies and integrated with 2D cortical flatmap and subcortical visualization tools. The workflow and resulting processed data have been made available in Python, and can thus be used for modeling and experimentally validating new hypotheses on thalamocortical connectivity.