Chemoinformatics using dimensionality reduction and clustering for enzyme commission number prediction in organic synthesis

The outbreak of COVID-19 has increased the demand for new drug development. That has led to a growing interest in chemoinformatics, which is valuable information technology to predict chemical reactions. The use of enzymes as catalysts is gaining importance in terms of the environment and reaction efficiency. In order to predict the best enzyme to obtain the desired product, the target chemical equation is compared with typical chemical equations of enzymes classified by Enzyme Commission number (EC number) using clustering. The EC number of the chemical equation that is evaluated to have the highest similarity is predicted. © 2023, ICIC International. All rights reserved.

Unsupervised Clustering and Binary Classification Analysis for Predicting COVID Syndrome (LONG COVID) in US Adults

Objectives: This study investigated the risk factors of developing COVID Syndrome and identified potential disease profiles that may exist among those who have contracted COVID-19. Method(s): Data on 13,953 adults who had experienced COVID-19 at any time were analyzed from the 2022 US National Health and Wellness Survey. XGBoost binary classification with 10-fold cross-validation was used to predict long COVID among those who reported experiencing COVID-19 and to extract feature importance. Synthetic minority oversampling technique (SMOTE) was used to address class imbalance in the outcome variable. Variable selection was conducted based on SHAP values. Fifty variables including demographic characteristics, COVID-19 symptoms, comorbidities, and health characteristics were used in the final model. Parameters were tuned using AUC. Among the 2,665 respondents who were diagnosed with long COVID, k-medoids clustering with t-SNE dimensionality reduction was implemented to determine whether distinct symptom profiles exist. Average silhouette score was used to determine the optimal number of clusters. Result(s): The XGBoost binary classification for predicting long COVID among those with COVID-19 had an AUC of 0.9145, accuracy of 0.9072, sensitivity of 0.9630, specificity of 0.8328, and Brier score of 0.0928. The most important features in predicting long COVID were age, smoking habits, COVID-19 vaccination status, certain COVID-19 symptoms experienced, and certain comorbidities. Among those diagnosed with long COVID, the clustering analysis found nine unique clusters of symptoms. The cluster that experienced the most severe symptoms was older, female, lower income, lower vaccination rate, and had more comorbidities like asthma, chronic bronchitis, and allergies. Conclusion(s): In a broadly representative US adult population, XGBoost model identified a selection of risk factors for developing long COVID. K-medoids clustering identified clusters of patients that were at risk for developing severe symptoms.Copyright © 2023

Machine learning uncovers blood test patterns subphenotypes at hospital admission discerning increased 30-day ICU mortality rates in COVID-19 elderly patients

Introduction: Since March 2020, a number of SARS-CoV-2 patients have frequently required intensive care unit (ICU) admission, associated with moderate survival outcomes and an increasing economic burden. Elderly patients are among the most numerous, due to previous comorbidities and complications they develop during hospitalization [1]. For this reason, a reliable early risk stratification tool could help estimate an early prognosis and allow for an appropriate resources allocation in favour of the most vulnerable and critically ill patients. Method(s): This retrospective study includes data from two Spanish hospitals, HU12O (Madrid) and HCUV (Valencia), from 193 patients aged > 64 with COVID-19 between February and November 2020 who were admitted to the ICU. Variables include demographics, full-blood-count (FBC) tests and clinical outcomes. Machine learning applied a non-linear dimensionality reduction by t-distributed stochastic neighbor embedding (t-SNE) [2];then hierarchical clustering on the t-SNE output was performed. The number of clinically relevant subphenotypes was chosen by combining silhouette and elbow coefficients, and validated through exploratory analysis. Result(s): We identified five subphenotypes with heterogeneous interclustering age and FBC patterns (Fig. 1). Cluster 1 was the 'healthiest' phenotype, with 2% 30-day mortality and characterized by moderate leukocytes and eosinophils. Cluster 5, the severe phenotype, showed 44% 30-day mortality and was characterized by the highest leukocyte, neutrophil and platelet count and minimal monocytes and lymphocyte count. Clusters 2-4 displayed intermediate mortality rates (20-28%). Conclusion(s): The findings of this preliminary report of Eld-ICUCOV19 patients suggest the patient's FBC and age can display discriminative patterns associated with disparate 30-day ICU mortality rates.

Tensor-based insights into systems immunity and infectious disease.

Profiling immune responses across several dimensions, including time, patients, molecular features, and tissue sites, can deepen our understanding of immunity as an integrated system. These studies require new analytical approaches to realize their full potential. We highlight recent applications of tensor methods and discuss several future opportunities.

Detection of Depression-Related Tweets in Mexico Using Crosslingual Schemes and Knowledge Distillation.

Mental health problems are one of the various ills that afflict the world's population. Early diagnosis and medical care are public health problems addressed from various perspectives. Among the mental illnesses that most afflict the population is depression; its early diagnosis is vitally important, as it can trigger more severe illnesses, such as suicidal ideation. Due to the lack of homogeneity in current diagnostic tools, the community has focused on using AI tools for opportune diagnosis. Unfortunately, there is a lack of data that allows the use of IA tools for the Spanish language. Our work has a cross-lingual scheme to address this issue, allowing us to identify Spanish and English texts. The experiments demonstrated the methodology's effectiveness with an F1-score of 0.95. With this methodology, we propose a method to solve a classification problem for depression tweets (or short texts) by reusing English language databases with insufficient data to generate a classification model, such as in the Spanish language. We also validated the information obtained with public data to analyze the behavior of depression in Mexico during the COVID-19 pandemic. Our results show that the use of these methodologies can serve as support, not only in the diagnosis of depression, but also in the construction of different language databases that allow the creation of more efficient diagnostic tools.

An Empirical Study on Copy-Move Forgery Detection Techniques in Images

Image Forgery is a common practice that can be observed in many of the social networking platforms as memes, animations, fake news, trolls and others. Now days, people in social media platforms got vexed with these fake news because these land them in confusion state. The latest case study in this pandemic is associated with viral news about COVID-19 variants, lockdowns, and vaccinations, which created a lot of tensions among the public. Traditional image processing techniques like PCA, LBP, RBF, and others are popular techniques to identify the forgery images but most of them are unsuccessful while dealing with high dimensionality, noisy, blur images. The people using social network sites need an "Efficient Identification of Copy Move Forgery Detection Techniques” to recognize the fake news. The existing approaches find the overlapped regions to identify the tampered parts in the images but the deep learning mechanisms tries to identify the non-overlapping regions and location parameter optimizations. In this paper, the focus is on various approaches available in the current scenario to detect the forgery parts in the image. © 2022, Mathematical and Research Society. All rights reserved.

Causal Discovery in High-dimensional, Multicollinear Datasets.

As the cost of high-throughput genomic sequencing technology declines, its application in clinical research becomes increasingly popular. The collected datasets often contain tens or hundreds of thousands of biological features that need to be mined to extract meaningful information. One area of particular interest is discovering underlying causal mechanisms of disease outcomes. Over the past few decades, causal discovery algorithms have been developed and expanded to infer such relationships. However, these algorithms suffer from the curse of dimensionality and multicollinearity. A recently introduced, non-orthogonal, general empirical Bayes approach to matrix factorization has been demonstrated to successfully infer latent factors with interpretable structures from observed variables. We hypothesize that applying this strategy to causal discovery algorithms can solve both the high dimensionality and collinearity problems, inherent to most biomedical datasets. We evaluate this strategy on simulated data and apply it to two real-world datasets. In a breast cancer dataset, we identified important survival-associated latent factors and biologically meaningful enriched pathways within factors related to important clinical features. In a SARS-CoV-2 dataset, we were able to predict whether a patient (1) had Covid-19 and (2) would enter the ICU. Furthermore, we were able to associate factors with known Covid-19 related biological pathways.

A Novel Data Science Approach to Personas' Creation to Study Willingness to Receive Vaccination in the General Population

Vaccines have proved to be effective in reducing mortality of the COVID-19 pandemic. However, a part of the population is still reluctant to be vaccinated. Thus, the aim of this work was to apply a framework to create Personas, fictional representations of real people, to assess the characteristics of the population willing to be vaccinated in order to develop personalized eHealth-based interventions to increase compliance to vaccinations. Data was collected through an online survey at the beginning of 2021. Multiple dimensionality reduction methods were used as input for K-Medoids clustering with PAM algorithm to create Personas. The optimal number of Personas and dimensionality reduction method to be used were evaluated through the average silhouette graph and the percentage of statistically different attributes between Personas. From 1070 respondents, three Personas were identified. Persona 3 showed statistically significant lower trust in institutions, lower education and lower willingness of being vaccinated when compared to the other two Personas. The developed approach to create Personas was deemed able to identify the main characteristics of those more prone not willing to be vaccinated, suggesting that behavioral change techniques should focus on taking advantage of the closer social circle of those reluctant to vaccines. © 2022 IEEE.

Detection of Covid-19 Using CAD System Depending on Chest X-Ray and Machine Learning Techniques

SARS-COV-2 (severe acute respiratory syndrome coronavirus-2) has caused widespread mortality. Infected individuals had specific radiographic visual features and fever, dry cough, lethargy, dyspnea, and other symptoms. According to the study, the chest X-ray (CXR) is one of the essential non-invasive clinical adjuncts for detecting such visual reactions associated with SARS-COV-2. Manual diagnosis is hindered by a lack of radiologists' availability to interpret CXR images and by the faint appearance of illness radiographic responses. The paper describes an automatic COVID detection based on the deep learningbased system that applied transfer learning techniques to extract features from CXR images to distinguish. The system has three main components. The first part is extracting CXR features with MobileNetV2. The second part used the extracted features and applied Dimensionality reduction using LDA. The final part is a Classifier, which employed XGBoost to classify dataset images into Normal, Pneumonia, and Covid-19. The proposed system achieved both immediate and high results with an overall accuracy of 0.96%, precision of 0.95%, recall of 0.94%, and F1 score of 0.94%. [ FROM AUTHOR]

Metabolic Changes of VOCs in Human Caused by Wearing Masks: A Preliminary Study Based on Electronic Nose

Wearing masks has been generally recommended to reduce the spreading of COVID-19. However, little is known about its effects on metabolic VOC changes in human body. To explore how the duration of wearing masks influences VOC metabolism in the human body, the essay used a self-developed electronic nose to analyse exhaled breath samples from 10 healthy individuals in this study. Firstly, polytetrafluoroethylene sampling bags are used to collect breath samples after volunteers wearing masks for 1h, 2h, 3h, 4h, and 5h. Secondly, data pre-processing, including baseline calibration and normalization are carried out. Thirdly, the study used LDA for dimensionality reduction on the original data to extract 4 features. Fourthly, differences in the length of time of wearing masks are analysed. Then, 4 algorithms were applied for cluster analysis based on extracted features. Moreover, 3 supervised classification algorithms were used to recognize the duration of wearing masks. Finally, multi-dimensional linear regression is used to study the possibility of predicting the duration of wearing masks based on breath signals acquired through electronic noses. As a result, the first feature extracted by LDA significantly differs from each other in the duration of wearing masks (p<0.05). Cluster analysis results show that the optimal internal parameters Adjusted Rand Index, Adjusted Mutual Information, Homogeneity and V-measure reach 80.2%, 81.5%, 83.5% and 83.7% respectively. Using 5-fold cross-validation on the K nearest neighbour classification model, the best accuracy of recognizing durations of wearing a mask reaches 88%. R-square of multi-dimensional linear regression reaches 92.5%, which shows excellent fitting performance. It can be concluded that the VOC metabolism of the human may change with the duration of wearing masks. Further, "breath prints” obtained by electronic nose may have the potential to predict the effective time and even the quality of masks. © 2022 SPIE.

Recent Dimensionality Reduction Techniques for High-Dimensional COVID-19 Data

We are going through the last years of the COVID-19 pandemic, where almost the entire research community has focused on the challenges that constantly arise. From the computational and mathematical perspective, we have to deal with a dataset with ultra-high volume and ultra-high dimensionality in several experimental studies. An indicative example is DNA sequencing technologies, which offer a more realistic picture of human diseases at the molecular biology level. However, these technologies produce data with high complexity and ultra-high dimensionality. On the other hand, dimensionality reduction techniques are the first choice to address this complexity, revealing the hidden data structure in the original multidimensional space. Also, such techniques can improve the efficiency of machine learning tasks such as classification and clustering. Towards this direction, we study the behavior of seven well-known and cutting-edge dimensionality reduction techniques tailored for RNA-sequencing data. Along with the study of the effect of these algorithms, we propose the extension of the Random projection and Geodesic distance t-Stochastic Neighbor Embedding (RGt-SNE) algorithm, a recent t-Stochastic Neighbor Embedding (t-SNE) improvement. We suggest a new distance criterion for the kernel matrix construction. Our results show the potential of the proposed algorithm and, at the same time, highlight the complexity of the COVID-19 data, which are not separable, creating a significant challenge that the Machine Learning field will have to face. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Genomic Data Science And COVID -19 Genome Analysis Using Bio Python

The last few years have been amazing for biology and healthcare and the best thing that happens in this field was the human genome project .it was an international research project with the goal of mapping and understanding the entire human genome .data science is the field in which we study data, understand the data to get valuable insight from that. Data science has already become an umbrella under which every industry and field comes. We can work in medical, marketing, Information technology, and every other field, even far before data science comes into the real world, we were using statistical and computational knowledge to get an outcome from our data. But today with the grace of the internet and social media our ability to decipher the information from that data is out of our range, where data science has come as a saviour. Because of the amount of genomic data being generated it become essential that the field of genomics or biology must be combined with modern technology and tools so that we can properly analyze such big data for precise and accurate prediction of disease and prevention mechanisms for that, which ultimately will result in improved human health. The data collected from a single week-long sequence today can create more data than whole genome research done a few years ago. "Bioinformatics", "computational genomics" and "genomic data science" are all very similar fields. To provide biological insights in these disciplines, we must be able to process and analyse huge genomics datasets, as well as validate the processed data's quality and transform it. Afterwards, depending on the nature of our issue, we must apply statistical or machine-learning models. The most likely scenario is to first perform some dimension reduction and clustering, then visualisation. In this paper, I will use python to pass my accountancies over genomic data science and genomic data analysis. Copyright © 2022 Wolters Kluwer Medknow Publications. All rights reserved.

Analysis of exhausted T cells, systemically enhanced cytokine levels ex vivo and Machine Learning Facilitated Search for Ageing-Related Biomarkers

Einleitung The aging of the immune system is an individual process with high variability: Two persons of the same biological age may differ substantially in the response of their immune system towards diseases and further conditions. The goal of ImmunLearning is to identify cytokines that reflect the immune system's status and to subsequently use these biomarkers to assess a person's 'immuno-fitness' at home or at points-of-care. These could be used, for example, for personalized treatment scheduling without the need for elaborate clinical tests. Methoden To serve our objective of promoting the measurement of biomarkers at home, we studied technologies for cytokine measurement from small whole blood samples with low-end technologies at home and at points of care. We identified a small number of cytokines for which such mature technologies exist. To investigate age-related biomarkers we assessed ex-vivo T-cell marker and serum cytokines levels in samples collected from 74 healthy donors. To take account of the impact of the COVID-19 pandemic, we adapted the sampling procedure and the analytics' workflow, to include recovering COVID-19 patients. To investigate the relationship between cytokine levels and biological age we applied exploratory analysis techniques, regression and machine methods. Our machine learning toolbox encompasses classification algorithms that assess the expected (not biological) age of individuals on the basis of biomarkers, especially cytokine levels;workflows for dimensionality reduction, clustering, visualization and inspection of the association between age strata and cytokine levels;a workflow for the study of correlations among biomarkers in subsamples of individuals with different health conditions. Ergebnisse Our present results indicate a large variance in the biomarker profiles and in the relationship between biomarkers and age strata, both among healthy subjects and among subjects recovered from COVID-19. The correlations among different cytokines indicate that immuno-fitness predictors can be built from a small number of carefully cytokines. Schlussfolgerung Studies on larger samples are needed, especially involving subjects with chronic diseases.

SINGLE-CELL IMMUNE PROFILING AND REPERTOIRE ANALYSIS OF CONVALESCENT PATIENTS WITH INFLAMMATORY BOWEL DISEASE AND SARS-COV-2 ANTIBODY RESPONSE

Background: Inflammatory bowel disease (IBD) is a chronic inflammatory disorder of the gastrointestinal tract characterized by immune dysregulation and decreased T cell receptor (TCR) repertoire diversity. Patients with immune-mediated disorders such as IBD have attenuated convalescent antibody responses after COVID-19 infection. We sought to understand the immune configuration associated with high versus low convalescent SARS-CoV- 2 antibodies in patients with IBD using single-cell immunophenotyping. Methods: We performed a study of 9 patients with IBD who were SARS-CoV-2 convalescent (recovered from COVID-19 and converted RNA positive to negative) and 9 matched SARS-CoV-2 naïve controls (no prior COVID-19, confirmed RNA negative). We measured plasma SARS-CoV- 2 antibody (N protein IgG, S1RBD IgG, S1RBD IgA) levels from patients with IBD two months after recovering from COVID-19 (RNA negative). We selected three patients with the highest SARS-CoV-2 antibodies and three matched (for age, sex, IBD subtype and disease activity, medications, COVID-19 severity) patients with the lowest antibodies and performed their peripheral blood mononuclear cell (PBMC) single-cell transcriptomics with paired TCR and BCR sequencing using 10X Genomics. Normalization, dimensionality reduction, and clustering were performed using Seurat. TCR and BCR immune repertoire analyses were performed using Immunarch. Results: SARS-CoV-2 convalescent patients with IBD had detectable but variable SARS-CoV-2 antibody levels (range 0-469 U/mL), whereas SARSCoV- 2 naïve IBD patients had no detectable antibodies. The mean SARS-CoV-2 antibody concentration among the three IBD patients with the highest and three patients with the lowest groups differed by more than 10-fold (206.0 vs 17.5 U/mL, P<0.001). PBMC singlecell immunophenotyping revealed decreased naïve CD4+ T cell and increased CD14+ monocyte and memory CD4+ T cell proportions in IBD patients in the low versus high SARSCoV- 2 antibody group. There were higher numbers of HLA-DQA1+ B cells and CD8 T cells and lower GPR183+ B cells and CD8 T cells in the high SARS-CoV-2 antibody group. There was a trend towards decreased TCR and BCR repertoire diversity in the low SARS-COV-2 antibody group. Finally, we identified immunoglobulin gene signatures (IGHV1-69D/IGLV3- 25, IGHV3-48, IGHV3-7/IGKV41/IGLV1-47, IGHV3-7/IGKV4-1, IGHV3-7/IGKV4-44) that were enriched only in the high SARS-CoV-2 antibody group. Conclusions: Single-cell immunophenotyping of PBMC from convalescent patients with IBD reveal differences in CD4+ T cell, CD14+ monocyte, and HLA-DQA1+ and GPR183+ B and CD8 T cell immunophenotypes, immune repertoire diversity, and immunoglobulin gene signatures in patients with high versus low SARS-CoV-2 antibody levels.(Figure Presented)Figure 1. SARS-COV-2 Antibodies in Convalescent Patients with IBD and Single-Cell Immunophenotypes. A) SARS-COV-2 antibody levels in COVID-19 convalescent versus SARS-CoV-2 naïve patients with IBD B) T-SNE plot of PBMC immunophenotypes in all convalescent patients with IBD C) Differences in proportion of single-cell PBMC immunophenotypes in high versus low SARS-COV-2 antibody patients D) Differences in HLA-DQA1 and GPR183 immunophenotypes in high versus low SARS-COV-2 antibody patients.

Text Clustering of COVID-19 Vaccine Tweets

The advent of the novel coronavirus disease (COVID-19) in late December 2019 led to the dramatic loss of human life worldwide and presented an unprecedented challenge to public health, education, social life, world economics, and the world of work. Equal access to safe and effective vaccines is very vital to ending the coronavirus pandemic. This research paper aims to perform text clustering on COVID-19 vaccine tweets. It investigates the optimal number of clusters prevalent in the COVID-19 vaccine corpus using deep learning techniques and machine learning algorithms. The study also investigates how using word embeddings can improve the accuracy of the proposed models by evaluating unsupervised learning methods. Machine learning clustering algorithms such as k-means and HDBSCAN, deep learning-based clustering techniques, and UMAP a dimensionality reduction algorithm were employed to perform text clustering. The results of this research showed the optimal clusters obtained by using deep learning clustering techniques and machine-learning algorithms for text clustering. HDBSCAN clustering algorithm showed better clustering results based on features learned while k-means performed better clustering based on various evaluation metrics. © 2022 IEEE.

Dynamic mode decomposition in adaptive mesh refinement and coarsening simulations.

Dynamic mode decomposition (DMD) is a powerful data-driven method used to extract spatio-temporal coherent structures that dictate a given dynamical system. The method consists of stacking collected temporal snapshots into a matrix and mapping the nonlinear dynamics using a linear operator. The classical procedure considers that snapshots possess the same dimensionality for all the observable data. However, this often does not occur in numerical simulations with adaptive mesh refinement/coarsening schemes (AMR/C). This paper proposes a strategy to enable DMD to extract features from observations with different mesh topologies and dimensions, such as those found in AMR/C simulations. For this purpose, the adaptive snapshots are projected onto the same reference function space, enabling the use of snapshot-based methods such as DMD. The present strategy is applied to challenging AMR/C simulations: a continuous diffusion-reaction epidemiological model for COVID-19, a density-driven gravity current simulation, and a bubble rising problem. We also evaluate the DMD efficiency to reconstruct the dynamics and some relevant quantities of interest. In particular, for the SEIRD model and the bubble rising problem, we evaluate DMD's ability to extrapolate in time (short-time future estimates).

Deep extracted features to support Content-Based Image Retrieval systems in the diagnosis of Covid-19 and Interstitial diseases

Purpose Coronavirus disease 2019 (Covid-19) may cause dyspnoea, whereas Interstitial Lung Diseases (ILD) may lead to the loss of breathing ability. In both cases, chest X-Ray is typically one of the initial studies to identify the diseases as they are simple and widely available scans, especially in under-development countries. However, the assessment of such images is subject to a high intraobserver variability because it depends on the reader's expertise, which may expose patients to unnecessary investigations and delay the diagnosis. Content-based Image Retrieval (CBIR) tools can bridge such a variability gap by recovering similar past cases to a given reference image from an annotated database and acting as a differential diagnosis CAD-IA system [1]. The main CBIR components are the feature extraction and the query formulation. The former represents the compared images into a space where a distance function can be applied, and the latter relies on the k-Nearest Neighbor (kNN) method to fetch the most similar cases by their distances to the query reference. In this study, we examine the quality of Covid-19 and ILD deep features extracted by a modified VGG-19 Convolutional Neural Network (CNN) [2] following the perspective of the Voronoi frontiers induced by kNN, which is at the core of the CBIR query formulation component. Methods We curated a dataset of annotated chest X-Rays from our PACS/HIS systems following a retrospective study approved by the institutional board. A set of 185 Covid-19 and 307 ILD cases from different patients was selected, being Covid-19 cases confirmed by RT-PCR tests and ILD images included after the analysis of two thoracic radiologists. We also added 381 images of ''Healthy'' lungs (without Covid-19 or ILD) to enrich the dataset. The resulting set includes 873 X-Rays (mean age 60.49 ± 15.21, and 52.58% females). We cast the DICOM images into PNG files by using the Hounsfield conversion and a 256 Gy-scale window. The files were scaled to 224 × 224 images and fed into a modified VGG-19 version we implemented [2]. Our version includes the stack of convolutional layers and five new layers after the block5-pool, namely: GlobalAveragePooling2D, BatchNormalization, a dense layer with 128 units and ReLU, a dropout layer with ratio 0.6, and a final dense layer with three neurons for classification. The Adam function was used to minimize cross-entropy, whereas batch size and epochs were set to 36 and 100, respectively. All layers start with ImageNet weights that were frozen until block4-pool so that only the remaining layers were updated. We fed the CNN with images and labels (i.e., {Covid-19, ILD, Healthy}) so that our feature extraction procedure was oriented towards those classes rather than autoencoders. The flattened outputs of the last max-pooling layer were collected as feature vectors of dimensionality d = 512. We clean and preprocess those vectors before applying the kNN-based search mechanism. First, we scaled the dimensions into the [0,1] interval. Then, we perform a reduction by using the Principal Component Analysis (PCA). The number of reduced dimensions was determined by the intrinsic dimensionality of the features, estimated by the mean (l) and standard deviation (r) of the pairwise distance distribution as the value μ2/2.σ2. Finally, the reduced vectors were also scaled into the [0,1] interval. The experiments were performed in a 3854 core 1.5 GHz GPU NVidia TitanX 12 GB RAM, and an Intel(R) Xeon(R) CPU 2.00 GHz, 96 GB RAM. The code was implemented under Tensorflow (v.2.1.0) and R (v4.1.2). Results We used two Principal Components to reduce the vectors according to the estimated intrinsic dimensionality. Figure 1 shows the Voronoi frontiers induced by kNN with a smooth separation between the three classes, which creates a search space in which CBIR searches are expected to be accurate. We quantify such behavior through a kNNbased classification on the two experimental settings (i.e., 10-folds and Holdout) by using the scaled features with and without dimensionality reductio . able 1 summarizes the results with the following findings: • The accuracy measures increased with the neighborhood (k = 1 vs. k = 5) in all experimental cases, • Covid-19 cases were more difficult to label than ILD according to F1 and RC, • The kNN hit-ratio (TP) for Covid-19 was comparable to the very first diagnosis stored into the PACS/HIS systems by readers on duty regarding the Holdout cases (readers' mean ∗ 63% vs. KNN ∼ 59%), • Searches over the reduced data were ∼ 4 9 faster, and • While dimensionality reduction was just as suitable as nonreduced data in the 10-folds evaluation, it expressively enhanced the kNN performance for the Holdout test (e.g., 0.68 vs. 0.82, k = 1 and F1). This result shows the side-effects of searching high-dimensional spaces with kNN (the ''curse of dimensionality''), which requires pre-processing the vectors or defining other query criteria to browse the data. Conclusion This study has discussed feature extraction for Covid-19 and ILD images from the perspective of kNN queries, the query formulation component within CBIR systems. Although we used cross-validation and one external batch to mitigate overfitting, a practical limitation was the size of the CNN training set. Still, our approach showed promising results in the extraction of suitable features for CBIR environments.

Survival Analysis of COVID-19 Patients With Symptoms Information by Machine Learning Algorithms

In this study, a survival analysis of the time to death caused by coronavirus disease 2019 is presented. The analysis of a dataset from the East Asian region with a focus on data from the Philippines revealed that the hazard of time to death was associated with the symptoms and background variables of patients. Machine learning algorithms, i.e., dimensionality reduction and boosting, were used along with conventional Cox regression. Machine learning algorithms solved the diverging problem observed when using traditional Cox regression and improved performance by maximizing the concordance index (C-index). Logistic principal component analysis for dimensionality reduction was significantly efficient in addressing the collinearity problem. In addition, to address the nonlinear pattern, a higher C-index was achieved using extreme gradient boosting (XGBoost). The results of the analysis showed that the symptoms were statistically significant for the hazard rate. Among the symptoms, respiratory and pneumonia symptoms resulted in the highest hazard level, which can help in the preliminary identification of high-risk patients. Among various background variables, the influence of age, chronic disease, and their interaction were identified as significant. The use of XGBoost revealed that the hazards were minimized during middle age and increased for younger and older people without any chronic diseases, with only the elderly having a higher risk of chronic disease. These results imply that patients with respiratory and pneumonia symptoms or older patients should be given medical attention.

An Empirical Study on Copy-Move Forgery Detection Techniques in Images

Image Forgery is a common practice that can be observed in many of the social networking platforms as memes, animations, fake news, trolls and others. Now days, people in social media platforms got vexed with these fake news because these land them in confusion state. The latest case study in this pandemic is associated with viral news about COVID-19 variants, lockdowns, and vaccinations, which created a lot of tensions among the public. Traditional image processing techniques like PCA, LBP, RBF, and others are popular techniques to identify the forgery images but most of them are unsuccessful while dealing with high dimensionality, noisy, blur images. The people using social network sites need an “Efficient Identification of Copy Move Forgery Detection Techniques” to recognize the fake news. The existing approaches find the overlapped regions to identify the tampered parts in the images but the deep learning mechanisms tries to identify the non-overlapping regions and location parameter optimizations. In this paper, the focus is on various approaches available in the current scenario to detect the forgery parts in the image. © 2022, Mathematical and Research Society. All rights reserved.

DIMENSIONALITY REDUCTION for STEPWISE ANALYSIS of IMMUNE RESPONSE DYNAMICS in COVID19

Background: COVID-19 is highly heterogeneous in clinical severity and outcome. Considerable advances have uncovered biomolecular traits associated with fatal outcome. However, novel analytical tools are needed to rapidly and accurately delineate patient subgroups with various immunovirological profiles, analyze diverging disease trajectories and prioritize in-depth molecular studies. Methods: To find how immunovirological features are interrelated, we profiled 12 plasma analytes (SARS-CoV-2 vRNA, SARS-CoV-2-specifc antibodies, cytokine and tissue injury markers) in 500 acute longitudinal plasma samples collected from 214 hospitalized COVID-19 patients. We analyzed them simultaneously using PHATE algorithm (potential of heat diffusion for affinity-based transition embedding, Moon et al, Nature Biotech 2019), which can reduce multiple input variables to two salient features for visualization. We performed whole blood transcriptomic analyses to identify molecular signatures associated with survival vs death in a patient cluster identified as being at extreme mortality risk. Results: PHATE analysis of samples collected 11 days after symptom onset (DSO11) revealed four distinct k-means clusters of patients, which aligned with disease severity and outcome. Two groups were highly enriched in critical patients requiring mechanical ventilation: a high-fatality critical cluster 1 accounted for 59% of fatal outcomes (16/27) by DSO60, while critical cluster 2 had good prognosis. Clusters 3 and 4 consisted almost entirely of non-critical survivors delineated respectively by low and high antibody responses. Averaged trajectories between DSO3 to DSO30 diverged between clusters. All patients of the high-fatality cluster had detectable plasma vRNA, which lingered unlike the critical survivor cluster. Their antibody response had a 4-day delay, while their cytokine profile diverged from the other clusters by DSO8, remaining distinct until DSO22. Transcriptome profiles differed between deceased and survivors of the high-fatality cluster 1, with differential expression of GO terms associated with metabolic processes, protein regulation, cell signaling and immune pathways. Conclusion: This unbiased approach gives an integrated view of dysregulated immune response components in fatal COVID-19, which may be explained through differences in molecular pathways. This approach allows to efficiently target detailed investigations on very high-risk patient subgroups who may most likely benefit from new therapeutic interventions.