Uniform Manifold Approximation And Projection Research Articles

Characterizing Healthy Dietary Practices in Japan: Insights from a 2024 Nationwide Survey and Cluster Analysis

The increasing burden of lifestyle-related diseases highlights the need to address unhealthy dietary habits. This study aims to explore the latest dietary patterns in Japan following the COVID-19 pandemic, focusing on trends in health-promoting food choices. A web-based survey was conducted among 27,154 Japanese adults, selected via quota sampling to mirror national demographics. The study evaluated dietary diversity, measured through the Dietary Variety Score (Outcome 1), and the prioritization of nutritional and health considerations in food selection, assessed via a Likert scale (Outcome 2). Uniform Manifold Approximation and Projection (UMAP) and Ordering Points To Identify the Clustering Structure (OPTICS) algorithms were used to delineate patterns in health-centric food selections. OPTICS clustering revealed four distinct clusters for each outcome. Cluster 3, with a diverse diet, comprised older, predominantly female individuals with higher well-being and lower social isolation compared to Cluster 4, which lacked distinct dietary patterns. Cluster 3 also engaged more in snacking, treat foods, home cooking, and frozen meals. Similarly, a divide emerged between those prioritizing dietary considerations (Cluster C) and those indifferent to such aspects (Cluster D). The findings underscore the need for holistic post-COVID-19 public health initiatives addressing socioeconomic and cultural barriers to healthier dietary practices.

Using single-cell RNA sequencing and bulk RNA sequencing data to reveal a correlation between smoking and neutrophil activation in esophageal carcinoma patients.

Cigarette smoking is considered as a major risk factor for esophageal carcinoma (ESCA) patients. Neutrophil activation plays a key role in cancer development and progression. However, the relationship between cigarette smoking and neutrophils in ESCA patients remained unclear. Single-cell RNA sequencing (scRNA-seq) and bulk RNA sequencing data were obtained from public databases. Uniform manifold approximation and projection (UMAP) was used to perform downscaling and clustering based on scRNA-seq data. The module genes associated with smoking in ESCA patients were filtered by weighted gene co-expression network analysis (WGCNA). Using the "AUCell" package, the enrichment of different cell subpopulations and gene collections were assessed. "CellChat" and "CellphoneDB" were used to infer the probability and significance of ligand-receptor interactions between different cell subpopulations. WGCNA was performed to screened module genes associated with smoking in ESCA patients from MEdarkquosie, MEturquoise, and MEgreenyellow. Next, eight cell clusters were identified, and using the AUCell score, we determined that neutrophil clusters were more active in the gene modules associated with smoking in ESCA patients. Two neutrophil subtypes, Neutrophils 1 and Neutrophils 2, exhibited greater enrichment in inflammatory response regulation, intercellular adhesion, and regulation of T cell activation. Furthermore, we found that neutrophils may pass through AMPT-(ITGA5 + ITGB1) and ICAM1-AREG in order to promote the development of ESCA, and that the expression levels of the receptor genes insulin-degrading enzyme and ITGB1 were significantly and positively correlated with cigarette smoking per day. Combining smoking-related gene modules and scRNA-seq, the current findings revealed the heterogeneity of neutrophils in ESCA and a tumor-promoting role of neutrophils in the tumor microenvironment of smoking ESCA patients.

Cardiometabolic and immune response to exercise training in patients with metabolic syndrome: retrospective analysis of two randomized clinical trials.

Metabolic syndrome (MetS) is defined by the presence of central obesity plus ≥two metabolic/cardiovascular risk factors (RF), with inflammation being a major disease-driving mechanism. Structured endurance exercise training (ET) may positively affect these traits, as well as cardiorespiratory fitness (V̇O2peak). We explore individual ET-mediated improvements of MetS-associated RF in relation to improvements in V̇O2peak and inflammatory profile. MetS patients from two randomized controlled trials, ExMET (n = 24) and OptimEx (n = 34), had performed 4- or 3-months supervised ET programs according to the respective trial protocol. V̇O2peak, MetS-defining RFs (both RCTs), broad blood leukocyte profile, cytokines and plasma proteins (ExMET only) were assessed at baseline and follow-up. Intra-individual changes in RFs were analysed for both trials separately using non-parametric approaches. Associations between changes in each RF over the exercise period (n-fold of baseline values) were correlated using a non-parametrical approach (Spearman). RF clustering was explored by uniform manifold approximation and projection (UMAP) and changes in RF depending on other RF or exercise parameters were explored by recursive partitioning. Four months of ET reduced circulating leukocyte counts (63.5% of baseline, P = 8.0e-6), especially effector subtypes. ET response of MetS-associated RFs differed depending on patients' individual RF constellation, but was not associated with individual change in V̇O2peak. Blood pressure lowering depended on cumulative exercise duration (ExMET: ≥102 min per week; OptimEx-MetS: ≥38 min per session) and baseline triglyceride levels (ExMET: <150 mg/dl; OptimEx-MetS: <174.8 mg/dl). Neuropilin-1 plasma levels were inversely associated with fasting plasma triglycerides (R: -0.4, P = 0.004) and changes of both parameters during the ET phase were inversely correlated (R: -0.7, P = 0.0001). ET significantly lowered effector leukocyte blood counts. The improvement of MetS-associated cardiovascular RFs depended on individual basal RF profile and exercise duration but was not associated with exercise-mediated increase in V̇O2peak. Neuropilin-1 may be linked to exercise-mediated triglyceride lowering.

Data reduction for SVM training using density-based border identification.

Numerous classification and regression problems have extensively used Support Vector Machines (SVMs). However, the SVM approach is less practical for large datasets because of its processing cost. This is primarily due to the requirement of optimizing a quadratic programming problem to determine the decision boundary during training. As a result, methods for selecting data instances that have a better likelihood of being chosen as support vectors by the SVM algorithm have been developed to help minimize the bulk of training data. This paper presents a density-based method, called Density-based Border Identification (DBI), in addition to four different variations of the method, for the lessening of the SVM training data through the extraction of a layer of border instances. For higher-dimensional datasets, the extraction is performed on lower-dimensional embeddings obtained by Uniform Manifold Approximation and Projection (UMAP), and the resulting subset can be repetitively used for SVM training in higher dimensions. Experimental findings on different datasets, such as Banana, USPS, and Adult9a, have shown that the best-performing variations of the proposed method effectively reduced the size of the training data and achieved acceptable training and prediction speedups while maintaining an adequate classification accuracy compared to training on the original dataset. These results, as well as comparisons to a selection of related state-of-the-art methods from the literature, such as Border Point extraction based on Locality-Sensitive Hashing (BPLSH), Clustering-Based Convex Hull (CBCH), and Shell Extraction (SE), suggest that our proposed methods are effective and potentially useful.

Predicting possible recommendations related to causes and consequences in the HAZOP study worksheet using natural language processing and machine learning: BERT, clustering, and classification

A set of recommendations is one of the most valuable outputs of the hazard and operability (HAZOP) study. The HAZOP study team provides recommendations when deficiencies are detected in the chemical process plant. These deficiencies can cause chemical process accidents and operability issues. This study employed a data-driven approach using natural language processing (NLP) and machine learning (ML) to predict potential recommendations based on causes and consequences. The dataset had no label; thus, clustering was used to label it. Firstly, bidirectional encoder representations from transformers (BERT) converted recommendation sentences into vectors. Secondly, uniform manifold approximation and projection (UMAP) and hierarchical density-based spatial clustering of applications with noise (HDBSCAN) were utilized to determine recommendation categories and label the dataset. Then, BERT was used to convert causes and consequences into vectors. Finally, a multi-layer perceptron (MLP) classifier was employed to predict possible recommendations based on causes and consequences. The class imbalance problem was handled by random over-sampling. The prediction accuracy of possible recommendations based on causes and consequences equals 93.7% and 89.5%, respectively. As a result of predicting potential recommendations utilizing causes and consequences, major recommendations will not be overlooked during the HAZOP study. This can further expand NLP and ML applications in HAZOP study automation.

Multiscale modelling for fatigue crack propagation of notched laminates using the UMAP clustering algorithm

In this study, a novel multiscale fatigue-damage model was developed based on the parametric finite-volume direct-averaging micromechanics theory (FVDAM), the uniform manifold approximation and projection (UMAP) algorithm, and the extended finite element method (XFEM) to accurately portray the progressive propagation of fatigue cracks in notched laminates. The UMAP clustering technique was integrated with fatigue damage evolution for the first time, enabling the construction of a reduced-order unit cell with fatigue information. Compared with the conventional FVDAM unit cell, the data was reduced to 0.4% of its original size, significantly accelerating fatigue damage calculations. The reduced-order unit cell was then incorporated into XFEM, functions as the fatigue damage criterion, transmitting fatigue damage information to meso- and macro-scales, and enables fatigue crack simulation in notched laminates. To further accelerate the calculation, a cycle-jump scheme was integrated, resulting in computational time being 10 times shorter compared to cycle-by-cycle simulation while maintaining accuracy. To validate the effectiveness of the proposed model, experiments of notched [±60]7s glass-fibre/epoxy laminates under three different fatigue loads were conducted. The simulation results of all three loads were within a scatter band of factor two, which was a good accuracy in fatigue, showing the effectiveness of the proposed model.

Abstract 6117: Characterizing cancer patterns in Okinawan vs. mainland Japanese Americans: The Multiethnic Cohort

Abstract Differences in chronic disease rates have been documented in Japan between Okinawa and mainland Japan. Limited data exist on whether these differences are also present in Okinawans and mainland Japanese who have migrated to the US. We used genotyped genome-wide association study data from the Multiethnic Cohort Study (MEC) to identify Japanese Americans of Okinawan or mainland ancestral similarity, and to investigate these two groups for differences in baseline chronic disease risk factors and for incidence of the four most common cancers during follow-up after blood draw. Cancer cases were identified via linkage to state cancer registries. Principal component analysis followed by uniform manifold approximation and projection (UMAP) was run using 15,678 single nucleotide polymorphisms among the 24,484 MEC Japanese Americans with blood samples. The Okinawan cluster was confirmed by labeling male MEC participants with Okinawan surnames on UMAP plots. Hazard ratios (HR), 95% confidence intervals (CI), and two-sided p-values were reported for Cox proportional hazards models, comparing cancer incidence between Okinawan and mainland Japanese individuals. The Okinawan cluster included 3,649 individuals (15% of the MEC Japanese Americans) and the mainland Japanese cluster included 19,611 individuals (80% of the MEC Japanese Americans). Small clusters of part-Okinawan and/or part-mainland Japanese (5% of the MEC Japanese Americans) were not included in the analysis. Ninety-six percent of Okinawan Americans and 94% of mainland Japanese Americans in MEC were born in the US. Okinawans were more likely to have a higher body mass index and daily alcohol intake, and less likely to be a current or former smoker, compared to mainland Japanese (all p-values&amp;lt;0.05). Post-menopausal Okinawan women were significantly more likely to be diagnosed with breast cancer (age-adjusted HR=1.39, 95% CI=1.10-1.75) compared to post-menopausal mainland Japanese women. This association was not modified by adjusting for additional known breast cancer risk factors (HR=1.36, 95% CI=1.07-1.73). Okinawans were also less likely to be diagnosed with lung cancer (HR=0.75, 95% CI=0.58-0.98); however, this association was no longer significant when adjusting for known risk factors, including smoking history (HR=0.82, 95% CI=0.62-1.07). There were no significant differences in risk of colorectal or prostate cancer between Okinawan and mainland Japanese individuals. Our results in this US-based sample are consistent with recent trends of higher breast cancer and lower lung cancer age-adjusted incidence rates reported from Japan for the Okinawan prefecture compared to mainland prefectures. Investigating reasons for the observed breast cancer risk difference may identify new risk factors for this disease in the Okinawan and other populations. Citation Format: Samantha A. Streicher, Song-Yi Park, Charleston W. Chiang, Xin Sheng, David Bogumil, David V. Conti, Christopher A. Haiman, Lynne R. Wilkens, Loic Le Marchand. Characterizing cancer patterns in Okinawan vs. mainland Japanese Americans: The Multiethnic Cohort [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 6117.

Fast real-time monitoring of meat freshness based on fluorescent sensing array and deep learning: From development to deployment

A fluorescent sensor array (FSA) combined with deep learning (DL) techniques was developed for meat freshness real-time monitoring from development to deployment. The array was made up of copper metal nanoclusters (CuNCs) and fluorescent dyes, having a good ability in the quantitative and qualitative detection of ammonia, dimethylamine, and trimethylamine gases with a low limit of detection (as low as 131.56 ppb) in range of 5 ∼ 1000 ppm and visually monitoring the freshness of various meats stored at 4 °C. Moreover, SqueezeNet was applied to automatically identify the fresh level of meat based on FSA images with high accuracy (98.17 %) and further deployed in various production environments such as personal computers, mobile devices, and websites by using open neural network exchange (ONNX) technique. The entire meat freshness recognition process only takes 5 ∼ 7 s. Furthermore, gradient-weighted class activation mapping (Grad-CAM) and uniform manifold approximation and projection (UMAP) explanatory algorithms were used to improve the interpretability and transparency of SqueezeNet. Thus, this study shows a new idea for FSA assisted with DL in meat freshness intelligent monitoring from development to deployment.

Comparison of Data Visualization, Outlier Detection and Data Dimensionality Reduction Methods

With the deepening of the digital age of information, people's daily data is getting larger and larger, and it is more and more difficult to quantify and process. At this time, the data processing means becomes particularly important. This paper compares and analyzes some methods from data visualization to data dimensionality reduction to outlier detection. In this paper, two different types of datasets, ModelNet40, and red wine quality, are used to introduce the visualization method of the Farthest Point Sampling (FPS). This method can have a clear visual effect on the data dimension and scale, and allow users to observe the structure, type, and scale of the data. In data dimensionality reduction, the study uses Principal Component Analysis (PCA), T-Distributed Stochastic Neighbor Embedding (t-SNE), Triplets Manifold Approximation and Projection (TriMAP), Uniform Manifold Approximation and Projection (UMAP), Pairwise Controlled Manifold Approximation Projection (PaCMAP), and Autoencoder to compare their dimensionality reduction effects. Through these methods, this paper finds that different methods have different effects on different datasets. Therefore, in data dimensionality reduction, it can get twice the result with half the effort by choosing the appropriate method. Finally, this paper also detects outliers. Outliers in datasets will make it difficult for people to process data and make subsequent results inaccurate, so it is necessary to identify outliers. This paper involves methods such as isolation forest and Density-Based Spatial Clustering of Applications with Noise (DBSCAN). Through this paper, the methods of different datasets are analyzed and summarized.

Antidepressant fluoxetine alleviates colitis by reshaping intestinal microenvironment

BackgroundThe impact of antidepressants on Inflammatory bowel diseases (IBD) has been extensively studied. However, the biological effects and molecular mechanisms of antidepressants in alleviating colitis remain unclear.MethodsWe systematically assessed how antidepressants (fluoxetine, fluvoxamine and venlafaxine) affected IBD and chose fluoxetine, the most effective one, for mechanism studies. We treated the C56BL/6 mice of the IBD model with fluoxetine and their controls. We initially assessed the severity of intestinal inflammation in mice by body weight loss, disease Activity Index scores and the length of the colon. The H&E staining and immunohistochemical staining of MUC2 of colon sections were performed to observe the pathological changes. RT-qPCR and western blot were conducted to assess the expression level of the barrier and inflammation-associated genes. Then, single-cell RNA sequencing was performed on mouse intestinal mucosa. Seurat was used to visualize the data. Uniform Manifold Approximation and Projection (UMAP) was used to perform the dimensionality reduction. Cell Chat package was used to perform cell–cell communication analysis. Monocle was used to conduct developmental pseudotime analysis. Last, RT-qPCR, western blot and immunofluorescence staining were conducted to test the phenomenon discovered by single-cell RNA sequencing in vitro.ResultsWe found that fluoxetine treatment significantly alleviated colon inflammation. Notably, single-cell RNA sequencing analysis revealed that fluoxetine affected the distribution of different cell clusters, cell–cell communication and KEGG pathway enrichment. Under the treatment of fluoxetine, enterocytes, Goblet cells and stem cells became the dominating cells. The pseudotime analysis showed that there was a trend for M1 macrophages to differentiate into M2 macrophages. Lastly, we tested this phenomenon in vitro, which exhibited anti-inflammatory effects on enterocytes.ConclusionsFluoxetine exhibited anti-inflammatory effects on intestinal mucosa via remodeling of the intestinal cells and macrophages, which reveals that fluoxetine is a promising therapeutic drug for the treatment of IBD and psychiatric comorbidities.

Abstract P06: Characterization of the Immune Tumor Microenvironment in a Diverse Cohort of Patients with Multiple Myeloma

Abstract Multiple myeloma (MM) is the most common blood cancer in African American (AA) individuals. AAs have an increased risk of developing Monoclonal Gammopathy of Undetermined Significance (MGUS) and MM compared to non-Hispanic White (NHW) individuals. While several studies have shown a pivotal role for the immune tumor microenvironment (iTME) in MM pathogenesis, the composition of the iTME in AAs with MM is under investigated. Viably frozen whole bone marrow (BM) aspirates from 128 individuals (53 AA and 75 NHW) with either MM (n=65), MGUS (n=28), smoldering MM (SMM, n=13), or healthy controls (n=22) were evaluated by single cell RNA-sequencing (scRNA-seq) or mass cytometry (CyTOF). We characterized 34 (14 AA and 20 NHW) by scRNA-seq and 94 (39 AA and 55 NHW) by CyTOF. CyTOF samples were stained with Maxpar Direct Immune Profiling Assay Kit (Fluidigm), acquired on a Helios mass cytometer and analyzed in Cytobank. Data were analyzed by logistic equivalent regression model with p&amp;lt;0.05 for significance. ScRNA-seq samples were processed as in Yao, 2022. Data were normalized using scvi-tools and clustered by Uniform manifold approximation and projection (UMAP). Differentially expressed markers between clusters were identified using Model-based Analysis of Single-cell Transcriptomics (MAST) in Seurat R package at FDR &amp;lt; 0.05 and log2 fold change &amp;gt; 0.55. ScRNA-seq of the CD45+ non-tumor lymphocytes revealed 17 immune populations (HSC, erythroblast, MDSC, GMP, CD1c+ DC, CD4+ and CD8+ T cell, CD14+ M1 macrophage, CD16+monocyte, monocyte, pDC, naïve B, pre-B, pro-B, memory B, NK/MAIT). CD3E/D+cells were clustered into naïve/central memory (CCR7+, LEF1+, SELL+), memory (GZMK+), effector (GZMB+, GZMH+, FGFBP2+), g/d (TRDC+), MAIT (SLC4A10+, KLRB1+) and IFN CD8+ T cells (IFIT1+, IFIT2+,IFIT3+). Disease progression was associated with increases in median CD4+ and CD8+ GZMK+ T cells, memory B cells and a reduction in all monocyte clusters. Within the diseased cohort in comparison to NHW patients, AA patients had increased CD3+ T cells (CD4 and CD8+) (AA 57.5% vs. NHW 44.3%) and a reduction in overall monocytes (AA 10.5% vs. 26.5%). These results were validated by CyTOF, which confirmed an increase in CD3+ T cells (AA 53.7% vs. NHW 35.7%, p&amp;lt;0.001) including increases in CD8+ (AA 7.0% vs. NHW 3.2%, p&amp;lt;0.05) and CD4+ terminal effector T cells (AA 5.7% vs. NHW 2.7%, p&amp;lt;0.05) and a reduction in monocytes (AA 18.3% vs. NHW 26.6%) among AAs. After adjusting for age and sex, AAs retained an increase in T cells (OR 1.59 (95%CI 1.2-2.01, p=0.00023)) and a reduction in monocytes (OR 0.88 (95%CI 0.78-1, p=0.045)). Despite the increase in CD8+ T cells in AA patients, we identified reduced GZMK+ T cells and reductions in exhaustion markers (TIGIT, LAG3, TOX) in CD8+ T cells in comparison to NHWs. Nevertheless, the distribution of the immune populations was similar between healthy AA and NHW individuals. Our multiomics approach to characterize the iTME identified significant differences among AA compared to NHW patients with MM. Citation Format: Suganti Shivaram, Hongwei Tang, Huihuang Yan, Shulan Tian, Guyu Qin, Emilie Anderson, Neeraj Sharma, Abiola Bolarinwa, Cinthya Zepeda-Mendoza, Stacey Lehman, Felicia Gomez, Amit Mitra, Surendra Dasari, Taxiarchis Kourelis, Shaji Kumar, Linda Baughn. Characterization of the Immune Tumor Microenvironment in a Diverse Cohort of Patients with Multiple Myeloma [abstract]. In: Proceedings of the Blood Cancer Discovery Symposium; 2024 Mar 4-6; Boston, MA. Philadelphia (PA): AACR; Blood Cancer Discov 2024;5(2_Suppl):Abstract nr P06.

Machine Learning Analysis of Seismograms Reveals a Continuous Plumbing System Evolution Beneath the Klyuchevskoy Volcano in Kamchatka, Russia

AbstractVolcanoes produce a variety of seismic signals and, therefore, continuous seismograms provide crucial information for monitoring the state of a volcano. According to their source mechanism and signal properties, seismo‐volcanic signals can be categorized into distinct classes, which works particularly well for short transients. Applying classification approaches to long‐duration continuous signals containing volcanic tremors, characterized by varying signal characteristics, proves challenging due to the complex nature of these signals. That makes it difficult to attribute them to a single volcanic process and questions the feasibility of classification. In the present study, we consider the whole seismic time series as valuable information about the plumbing system (the combination of plumbing structure and activity distribution). The considered data are year‐long seismograms recorded at individual stations near the Klyuchevskoy Volcanic Group (Kamchatka, Russia). With a scattering network and a Uniform Manifold Approximation and Projection (UMAP), we transform the continuous data into a two‐dimensional representation (a seismogram atlas), which helps us to identify sudden and continuous changes in the signal properties. We observe an ever‐changing seismic wavefield that we relate to a continuously evolving plumbing system. Through additional data, we can relate signal variations to various state changes of the volcano including transitions from deep to shallow activity, deep reactivation, weak signals during quiet times, and eruptive activity. The atlases serve as a visual tool for analyzing extensive seismic time series, allowing us to associate specific atlas areas, indicative of similar signal characteristics, with distinct volcanic activities and variations in the volcanic plumbing system.

Nonlinear dimensionality reduction with q-Gaussian distribution

In recent years, the dimensionality reduction has become more important as the number of dimensions of data used in various tasks such as regression and classification has increased. As popular nonlinear dimensionality reduction methods, t-distributed stochastic neighbor embedding (t-SNE) and uniform manifold approximation and projection (UMAP) have been proposed. However, the former outputs only one low-dimensional space determined by the t-distribution and the latter is difficult to control the distribution of distance between each pair of samples in low-dimensional space. To tackle these issues, we propose novel t-SNE and UMAP extended by q-Gaussian distribution, called q-Gaussian-distributed stochastic neighbor embedding (q-SNE) and q-Gaussian-distributed uniform manifold approximation and projection (q-UMAP). The q-Gaussian distribution is a probability distribution derived by maximizing the tsallis entropy by escort distribution with mean and variance, and a generalized version of Gaussian distribution with a hyperparameter q. Since the shape of the q-Gaussian distribution can be tuned smoothly by the hyperparameter q, q-SNE and q-UMAP can in- tuitively derive different embedding spaces. To show the quality of the proposed method, we compared the visualization of the low-dimensional embedding space and the classification accuracy by k-NN in the low-dimensional space. Empirical results on MNIST, COIL-20, OliverttiFaces and FashionMNIST demonstrate that the q-SNE and q-UMAP can derive better embedding spaces than t-SNE and UMAP.

Identification of hypoxia-immune-related signatures for predicting immune efficacy in triple-negative breast cancer

Abstract Objectives The therapeutic effect against triple-negative breast cancer (TNBC) varies among individuals. Finding signatures to predict immune efficacy is particularly urgent. Considering the connection between the microenvironment and hypoxia, hypoxia-related signatures could be more effective. Therefore, in this study, we aimed sought to construct a hypoxia-immune-related prediction model for breast cancer and identify therapeutic targets. Methods Immune and hypoxia status in the TNBC microenvironment were investigated using single-sample Gene Set Enrichment Analysis (ssGSEA) and Uniform Manifold Approximation and Projection (UMAP). The least absolute shrinkage and selection operator (LASSO) and multivariate Cox regression analysis were employed to build a prognostic model based on hypoxia-immune-related differentially expressed genes. The Cancer Genome Atlas (TCGA) cohort, real-time quantitative polymerase chain reaction (qRT-PCR), and immunofluorescence staining were utilized to analyze the expression differences. Tumor immune dysfunction and exclusion indexes were used to indicate the effect of immunotherapy. Results We identified 11 signatures related to hypoxia and immunity. Among these genes, C-X-C motif chemokine ligand (CXCL) 9, 10, and 11 were up-regulated in TNBC tissues compared to normal tissues. Furthermore, CXCL9, 10, 11, and 13 were found to enhance the effect of immunotherapy. Conclusions These findings suggest the value of the hypoxia-immune-related prognostic model for estimating the risk in patients with TNBC, and CXCL9, 10, 11, and 13 are potential targets to overcome immune resistance in TNBC.

Statistical method scDEED for detecting dubious 2D single-cell embeddings and optimizing t-SNE and UMAP hyperparameters

Two-dimensional (2D) embedding methods are crucial for single-cell data visualization. Popular methods such as t-distributed stochastic neighbor embedding (t-SNE) and uniform manifold approximation and projection (UMAP) are commonly used for visualizing cell clusters; however, it is well known that t-SNE and UMAP’s 2D embeddings might not reliably inform the similarities among cell clusters. Motivated by this challenge, we present a statistical method, scDEED, for detecting dubious cell embeddings output by a 2D-embedding method. By calculating a reliability score for every cell embedding based on the similarity between the cell’s 2D-embedding neighbors and pre-embedding neighbors, scDEED identifies the cell embeddings with low reliability scores as dubious and those with high reliability scores as trustworthy. Moreover, by minimizing the number of dubious cell embeddings, scDEED provides intuitive guidance for optimizing the hyperparameters of an embedding method. We show the effectiveness of scDEED on multiple datasets for detecting dubious cell embeddings and optimizing the hyperparameters of t-SNE and UMAP.

Machine Learning Deciphered Molecular Mechanistics with Accurate Kinetic and Thermodynamic Prediction.

Time-lagged independent component analysis (tICA) and the Markov state model (MSM) have been extensively employed for extracting conformational dynamics and kinetic community networks from unbiased trajectory ensembles. However, these techniques may not be the optimal choice for elucidating transition mechanisms within low-dimensional representations, especially for intricate biosystems. Unraveling the association mechanism in such complex systems always necessitates permutations of several essential independent components or collective variables, a process that is inherently obscure and may require empirical knowledge for selection. To address these challenges, we have implemented an integrated unsupervised dimension reduction model: uniform manifold approximation and projection (UMAP) with hierarchy density-based spatial clustering of applications with noise (HDBSCAN). This approach effectively generates low-dimensional configurational embeddings. The hierarchical application of this architecture, in conjunction with MSM, reveals global kinetic connectivity while identifying local conformational states. Consequently, our methodology establishes a multiscale mechanistic elucidation framework. Leveraging the benefits of the uniform sample distribution and a denoising approach, our model demonstrates robustness in preserving global and local data structures compared to traditional dimension reduction methods in the field of MD analysis area. The interpretability of hyperparameter selection and compatibility with downstream tasks are cross-validated across various simulation data sets, utilizing both computational evaluation metrics and experimental kinetic observables. Furthermore, the predicted Mcl1-BH3 association kinetics (0.76 s-1) is in close agreement with surface plasmon resonance experiments (0.12 s-1), affirming the plausibility of the identified pathway composed of representative conformations. We anticipate that the devised workflow will serve as a foundational framework for studying recognition patterns in complex biological systems. Its contributions extend to the exploration of protein functional dynamics and rational drug design, offering a potent avenue for advancing research in these domains.

Comparison of dimensionality reduction techniques for the visualisation of chemical space in organometallic catalysis

We have used a Ligand Knowledge Base for bidentate P,P-donor ligands of potential interest to homogeneous catalysis to compare three dimensionality reduction techniques, namely Principal Component Analysis (PCA), Uniform Manifold Approximation and Projection (UMAP) and t-distributed Stochastic Neighbor Embedding (t-SNE). While our previous work on Ligand Knowledge Bases has focused on PCA, here we compare this approach with more recently-published approaches and assess the information retention, visualization, clustering and interpretability which can be achieved for each approach. We find that potential advantages of t-SNE are not realized with a database of the current size (275 entries), and that there is a degree of complementarity between PCA and UMAP. The statistics underlying PCA rely on linear relationships, making interpretation of the resulting plots comparatively straightforward. Since much of chemistry relies on linear structure-property relationships and low-dimensional visualization, the explainability and information retention achieved is attractive. UMAP proved more challenging to interpret, but achieved clear clustering which was often chemically meaningful, and it would be a useful approach for ensuring that distinct subsets of compounds are sampled in a machine-learning context. This analysis also highlighted that the tunability of catalysis achieved through ligand exchange maps well onto some areas of chemical space where closely related ligands cluster, while others represent outliers; these arise from different combinations of steric and electronic effects which chemists will find intuitive.

A Natural Language Processing Approach Towards Harmonized Communication of Uncertainties Identified During the European Medicine Authorization Process.

Within the European Union, the European Medicines Agency's (EMA's) European Public Assessment Report (EPAR) is an important source of information for healthcare professionals and patients that allows them to understand important risks and uncertainties associated with the use of a medicine. However, the EPAR sections describing such important uncertainties can differ substantially in wording, length, and detail, thereby potentially limiting understanding. In this study, we therefore present a natural language processing approach to cluster sentences extracted from the sections on uncertainties in EPARs of centrally authorized medicines, as a steppingstone to harmonization of text describing uncertainties. We used a BERT language model together with dimensionality reduction (Uniform Manifold Approximation and Projection (UMAP)) and clustering (Density-Based Spatial Clustering of Applications with Noise (DBSCAN)) to identify semantic similarities between sentences. Clusters were labeled according to an overarching topic by reviewing the semantically similar sentences. Each cluster was also characterized according to medicine-related characteristics, such as efficacy or side effects. In total, 1,648 medicines were included in this study. For 573 of these medicines (authorized July 27, 2010 to December 31, 2022), we identified an EPAR that described a complete regulatory dossier and contained sections on uncertainties. Of these, 553 EPARs could be attributed to unique active substance-indication combinations. In these 553 EPARs, we identified 13,105 sentences in sections on uncertainties, leading to 26 clusters of which 2 were labeled as noise. The clusters and associated topics provided in this article can be used by regulators and medicine developers as a steppingstone toward a unified way of communicating uncertainties identified during the EMA process to the broader public.

Is Unsupervised Dimensionality Reduction Sufficient to Decode the Complexities of Electrochemical Impedance Spectra?

AbstractAs electrochemical research undergoes rapid technological progression, the acquisition of substantial amounts of electrochemical impedance spectra (EIS) becomes increasingly feasible. Yet, this advancement introduces intricate challenges in data processing, automation, and interpretation. This paper delves into the sufficiency of unsupervised machine learning (ML) and in particular dimensionality reduction methods in decoding EIS complexities, examining its strengths, limitations, and potential pathways for optimization. As we navigated the intricacies of non‐linear dimensionality reduction, spotlighting t‐distributed stochastic neighbor embedding (t‐SNE) and uniform manifold approximation and projection (UMAP) algorithms, a pattern emerged: these techniques excel at categorizing divergent impedance spectra but show limitations when faced with analogous circuit configurations, especially those substituting a capacitor with a constant phase element. This observation not only underscores a limitation but also accentuates that unsupervised ML approaches, alone, may not fully unravel the nuances of EIS spectra. In the concluding section of our manuscript, we discuss the implications of this finding from a practical standpoint, particularly for electrochemists seeking to apply these methods in their work.

A 3D lung lesion variational autoencoder

In this study, we develop a 3D beta variational autoencoder (beta-VAE) to advance lung cancer imaging analysis, countering the constraints of conventional radiomics methods. The autoencoder extracts information from public lung computed tomography (CT) datasets without additional labels. It reconstructs 3D lung nodule images with high quality (structural similarity: 0.774, peak signal-to-noise ratio: 26.1, and mean-squared error: 0.0008). The model effectively encodes lesion sizes in its latent embeddings, with a significant correlation with lesion size found after applying uniform manifold approximation and projection (UMAP) for dimensionality reduction. Additionally, the beta-VAE can synthesize new lesions of varying sizes by manipulating the latent features. The model can predict multiple clinical endpoints, including pathological N stage or KRAS mutation status, on the Stanford radiogenomics lung cancer dataset. Comparisons with other methods show that the beta-VAE performs equally well in these tasks, suggesting its potential as a pretrained model for predicting patient outcomes in medical imaging.