Search

The World Health Organization (WHO) highlights that cardiovascular diseases (CVDs) are one of the leading causes of death globally, with an estimated rise to over 23.6 million deaths by 2030. This alarming trend can be attributed to our unhealthy lifestyles and lack of attention towards early CVD diagnosis. Traditional cardiac auscultation, where a highly qualified cardiologist listens to the heart sounds, is a crucial diagnostic method, but not always feasible or affordable. Therefore, developing accessible and user-friendly CVD recognition solutions can encourage individuals to integrate regular heart screenings into their routine. Although many automatic CVD screening methods have been proposed, most of them rely on complex prepocessing steps and heart cycle segmentation processes. In this work, we introduce a simple and efficient approach for recognizing normal and abnormal PCG signals using Physionet data. We employ data selection techniques such as kernel density estimation (KDE) for signal duration extraction, signal-to-noise Ratio (SNR), and GMM clustering to improve the performance of 17 pretrained Keras CNN models. Our results indicate that using KDE to select the appropriate signal duration and fine-tuning the VGG19 model results in excellent classification performance with an overall accuracy of 0.97, sensitivity of 0.946, precision of 0.944, and specificity of 0.946.

Biclustering is a non-supervised data mining technique used to analyze gene expression data, it consists to classify subgroups of genes that have similar behavior under subgroups of conditions. The classified genes can have independent behavior under other subgroups of conditions. Discovering such co-expressed genes, called biclusters , can be helpful to find specific biological features such as gene interactions under different circumstances. Compared to clustering, biclustering has two main characteristics: bi-dimensionality which means grouping both genes and conditions simultaneously and overlapping which means allowing genes to be in more than one bicluster at the same time. Biclustering algorithms, which continue to be developed at a constant pace, give as output a large number of overlapping biclusters. Visualizing groups of biclusters is still a non-trivial task due to their overlapping. In this paper, we present the most interesting techniques to visualize groups of biclusters and evaluate them., (© 2021 Haithem Aouabed et al., published by De Gruyter, Berlin/Boston.)

Assessment of heart sounds which are generated by the beating heart and the resultant blood flow through it provides a valuable tool for cardiovascular disease (CVD) diagnostics. The cardiac auscultation using the classical stethoscope phonological cardiogram is known as the most famous exam method to detect heart anomalies. This exam requires a qualified cardiologist, who relies on the cardiac cycle vibration sound (heart muscle contractions and valves closure) to detect abnormalities in the heart during the pumping action. Phonocardiogram (PCG) signal represents the recording of sounds and murmurs resulting from the heart auscultation, typically with a stethoscope, as a part of medical diagnosis. For the sake of helping physicians in a clinical environment, a range of artificial intelligence methods was proposed to automatically analyze PCG signal to help in the preliminary diagnosis of different heart diseases. The aim of this research paper is providing an accurate CVD recognition model based on unsupervised and supervised machine learning methods relayed on convolutional neural network (CNN). The proposed approach is evaluated on heart sound signals from the well-known, publicly available PASCAL and PhysioNet datasets. Experimental results show that the heart cycle segmentation and segment selection processes have a direct impact on the validation accuracy, sensitivity (TPR), precision (PPV), and specificity (TNR). Based on PASCAL dataset, we obtained encouraging classification results with overall accuracy 0.87, overall precision 0.81, and overall sensitivity 0.83. Concerning Micro classification results, we obtained Micro accuracy 0.91, Micro sensitivity 0.83, Micro precision 0.84, and Micro specificity 0.92. Using PhysioNet dataset, we achieved very good results: 0.97 accuracy, 0.946 sensitivity, 0.944 precision, and 0.946 specificity.

One of the main methods to analyze gene expression data is biclustering, a nonsupervised technique, which consists of selection subgroups of genes that co-expressed under subgroups of experimental conditions. A large number of biclustering algorithms have been developed to classify gene expression data. These algorithms can give as output a large number of overlapped biclusters, whose visualization still requires deeper studies. We present VisBicluster, a web-based interactive visualization tool for displaying biclustering results. The developed visualization technique consists of laying out the generated biclusters in a two-dimensional matrix where each bicluster is represented as a column and each overlap between a set of biclusters is represented as a row. A search interface for the user is developed to query the matrix of bicluster intersection and visualize the results matching the queries. Our tool supports many interactive features such as sorting, zooming, and details-on-demand. We proved the usefulness of VisBicluster with biclustering results from real and synthetic datasets. Besides, we performed a user study with 14 participants to illustrate the clarity and simplicity of overlap representation with our tool.

Cutaneous leishmaniosis (CL) is treated with pentavalent antimony (SbV) as a first-line drug, while amphotericin B and paromomycin are potential alternatives in antimonial- resistant isolates. However, the mechanisms of drug resistance remain unclear. The present study analyses the gene expression of RNA polymerase II (RNAP II) and J-binding protein 1 (JBP1), and J-binding protein 2 (JBP2) in Leishmania major after exposure to drugs in vitro. L. major (MRHO/IR/75/ER) promastigotes were exposed to various concentrations of glucantime, paromomycin and amphotericin B for 72 hours. The RNA was then extracted and used for cDNA synthesis. The expressions of JBP1, JBP2 and RNAP II were analysed using SYBR Green real-time PCR. No change in JBP2 or RNAP II expression was associated with amphotericin B, but JBP1 expression decreased with increasing drug concentration. Paromomycin had no effect on JBP2 expression, but a 13.5-fold increase in JBP1 was observed at 100 μg/ml, and a decrease in RNAP II expression at 25 and 50 μg/ml. Exposure to glucantime resulted in 1.4-fold lower JBP1 expression at 5 μg/ml, and 333.33- to 500-fold lower RNAP II at concentrations of 5 to 15 μg/ml. As Base J synthesis requires both JBP1 and JBP2, RNAP II (encoding RNA polymerase II) could reduce expression. However, RNAP II was not expressed in all groups, indicating that the genes associated with drug resistance may be regulated in other ways.

In this paper we present a method for finding infrequent simple motifs in a finite set of sequences. The method uses a lattice structure and minimal forbidden patterns. It is based on a method for solving the Simple Motif Problem and has the potential to discover new patents in biological macromolecules. Indeed, the extracted motifs can help biologists to learn about the biological functions of these macromolecules and, consequently, can help them to understand the mechanisms of the biological processes in which these sequences are involved.