Stroke Disease Detection and Prediction Using Robust Learning Approaches

Stroke is a medical disorder in which the blood arteries in the brain are ruptured, causing damage to the brain. When the supply of blood and other nutrients to the brain is interrupted, symptoms might develop. According to the World Health Organization (WHO), stroke is the greatest cause of death and disability globally. Early recognition of the various warning signs of a stroke can help reduce the severity of the stroke. Different machine learning (ML) models have been developed to predict the likelihood of a stroke occurring in the brain. This research uses a range of physiological parameters and machine learning algorithms, such as Logistic Regression (LR), Decision Tree (DT) Classification, Random Forest (RF) Classification, and Voting Classifier, to train four different models for reliable prediction. Random Forest was the best performing algorithm for this task with an accuracy of approximately 96 percent. The dataset used in the development of the method was the open-access Stroke Prediction dataset. The accuracy percentage of the models used in this investigation is significantly higher than that of previous studies, indicating that the models used in this investigation are more reliable. Numerous model comparisons have established their robustness, and the scheme can be deduced from the study analysis.

Explainability methods for differential gene analysis of single cell RNA-seq clustering models

Single-cell RNA sequencing (scRNA-seq) produces transcriptomic profiling for individual cells. Due to the lack of cell-class annotations, scRNA-seq is routinely analyzed with unsupervised clustering methods. Because these methods are typically limited to producing clustering predictions (that is, assignment of cells to clusters of similar cells), numerous model agnostic differential expression (DE) libraries have been proposed to identify the genes expressed differently in the detected clusters, as needed in the downstream analysis. In parallel, the advancements in neural networks (NN) brought several model-specific explainability methods to identify salient features based on gradients, eliminating the need for external models. We propose a comprehensive study to compare the performance of dedicated DE methods, with that of explainability methods typically used in machine learning, both model agnostic (such as SHAP, permutation importance) and model-specific (such as NN gradient-based methods). The DE analysis is performed on the results of 3 state-of-the-art clustering methods based on NNs. Our results on 36 simulated datasets indicate that all analyzed DE methods have limited agreement between them and with ground-truth genes. The gradients method outperforms the traditional DE methods, which encourages the development of NN-based clustering methods to provide an out-of-the-box DE capability. Employing DE methods on the input data preprocessed by clustering method outperforms the traditional approach of using the original count data, albeit still performing worse than gradient-based methods.

Sensing and Delineating Mixed-VOC Composition in the Air Using a Single Metal Oxide Sensor

Monitoring volatile organic compounds (VOCs) places a crucial role in environmental pollutants control and indoor air quality. In this study, a metal-oxide (MOx) sensor detector (used in a commercially available monitor) was employed to delineate the composition of air containing three common VOCs (ethanol, acetone, and hexane) under various concentrations. Experiments with a single component and double components were conducted to investigate how the solvents interact with the metal oxide sensor. The experimental results revealed that the affinity between VOC and sensor was in the following order: acetone > ethanol > n-hexane. A mathematical model was developed, based on the experimental findings and data analysis, to convert the output resistance value of the sensor into concentration values, which, in turn, can be used to calculate a VOC-based air quality index. Empirical equations were established based on inferences of vapour composition versus resistance trends, and on an approach of using original and diluted air samples to generate two sets of resistance data per sample. The calibration of numerous model parameters allowed matching simulated curves to measured data. Therefore, the predictive mathematical model enabled quantifying the total concentration of sensed VOCs, in addition to estimating the VOC composition. This first attempt to obtain semiquantitative data from a single MOx sensor, despite the remaining selectivity challenges, is aimed at expanding the capability of mobile air pollutants monitoring devices.

Sensing and Delineating Mixed-VOC Composition in Air Using a Single Metal-Oxide Sensor

Monitoring volatile organic compounds (VOCs) places a crucial role in environmental pollutants control and indoor air quality. In this study, a metal-oxide (MOx) sensor detector (uRAD A3 mobile air quality monitor) was employed to delineate the composition of air containing three common VOCs (ethanol, acetone and hexane) under various concentrations. Experiments with a single component and double components were conducted to investigate how the solvents interact with the metal oxide sensor. The experimental results revealed that the affinity between VOC and sensor was in the following order: acetone > ethanol > n-hexane. A mathematical model was developed, based on the experimental findings and data analysis, to convert the output resistance value of the sensor into concentration values, which in turn can be used to calculate a VOC-based air quality index. Empirical equations were established based on inferences of vapor composition versus resistance trends, and on an approach of using original and diluted air samples to generate two sets of resistance data per sample. The calibration of numerous model parameters allowed matching simulated curves to measured data. As such, the predictive mathematical model enabled quantifying not only the total concentration of sensed VOCs, but also estimating the VOC composition. This first attempt to obtain semi-quantitative data from a single MOx sensor is aimed at expanding the capability of mobile air pollutants monitoring devices.

Antibiotic Potential and Biophysical Characterization of Amphipathic β-Stranded [XZ]n Peptides With Alternating Cationic and Hydrophobic Residues

Cationic membrane-active peptides are considered to be promising candidates for antibiotic treatment. Many natural and artificial sequences show an antimicrobial activity when they are able to take on an amphipathic fold upon membrane binding, which in turn perturbs the integrity of the lipid bilayer. Most known structures are α-helices and β-hairpins, but also cyclic knots and other irregular conformations are known. Linear β-stranded antimicrobial peptides are not so common in nature, but numerous model sequences have been designed. Interestingly, many of them tend to be highly membranolytic, but also have a significant tendency to self-assemble into β-sheets by hydrogen-bonding. In this minireview we examine the literature on such amphipathic peptides consisting of simple repetitive sequences of alternating cationic and hydrophobic residues, and discuss their advantages and disadvantages. Their interactions with lipids have been characterized with a number of biophysical techniques—especially circular dichroism, fluorescence, and infrared—in order to determine their secondary structure, membrane binding, aggregation tendency, and ability to permeabilize vesicles. Their activities against bacteria, biofilms, erythrocytes, and human cells have also been studied using biological assays. In line with the main scope of this Special Issue, we attempt to correlate the biophysical results with the biological data, and in particular we discuss which properties (length, charge, aggregation tendency, etc.) of these simple model peptides are most relevant for their biological function. The overview presented here offers ideas for future experiments, and also suggests a few design rules for promising β-stranded peptides to develop efficient antimicrobial agents.

The Arctic Surface Climate in CMIP6: Status and Developments since CMIP5

Here we evaluate the sea ice, surface air temperature, and sea level pressure from 34 of the models used in phase 6 of the Coupled Model Intercomparison Project (CMIP6) for their biases, trends, and variability, and compare them to the CMIP5 ensemble and ERA5 for the period 1979 to 2004. The principal purpose of this assessment is to provide an overview of the ability of the CMIP6 ensemble to represent the Arctic climate, and to see how this has changed since the last phase of CMIP. Overall, we find a distinct improvement in the representation of the sea ice volume and extent, the latter mostly linked to improvements in the seasonal cycle in the Barents Sea. However, numerous model biases have persisted into CMIP6 including too-cold conditions in the winter (4-K cold bias) and a negative trend in the day-to-day variability over ice in winter. We find that under the low-emission scenario, SSP126, the Arctic climate is projected to stabilize by 2060 with an annual mean sea ice extent of around 2.5 million km2 and an annual mean temperature 4.7 K warmer than the early-twentieth-century average, compared to 1.7 K of warming globally.

On the History and Applications of Congenic Strains in Cryptococcus Research

Congenic strains have been utilized in numerous model organisms to determine the genetic underpinning of various phenotypic traits. Congenic strains are usually derived after 10 backcrosses to a recipient parent, at which point they are 99.95% genetically identical to the parental strain. In recent decades, congenic pairs have provided an invaluable tool for genetics and molecular biology research in the Cryptococcus neoformans species complex. Here, we summarize the history of Cryptococcus congenic pairs and their application in Cryptococcus research on topics including the impact of the mating type locus on unisexual reproduction, virulence, tissue tropism, uniparental mitochondrial inheritance, and the genetic underpinning of other various traits. We also discuss the limitations of these approaches and other biological questions, which could be explored by employing congenic pairs.

Swimming Through Parameter Subspaces of a Simple Anguilliform Swimmer

Synopsis Computational scientists have investigated swimming performance across a multitude of different systems for decades. Most models depend on numerous model input parameters and performance is sensitive to those parameters. In this article, parameter subspaces are qualitatively identified in which there exists enhanced swimming performance for an idealized, simple swimming model that resembles a Caenorhabditis elegans, an organism that exhibits an anguilliform mode of locomotion. The computational model uses the immersed boundary method to solve the fluid-interaction system. The 1D swimmer propagates itself forward by dynamically changing its preferred body curvature. Observations indicate that the swimmer’s performance appears more sensitive to fluid scale and stroke frequency, rather than variations in the velocity and acceleration of either its upstroke or downstroke as a whole. Pareto-like optimal fronts were also identified within the data for the cost of transport and swimming speed. While this methodology allows one to locate robust parameter subspaces for desired performance in a straight-forward manner, it comes at the cost of simulating orders of magnitude more simulations than traditional fluid–structure interaction studies.

Improving the accuracy of model-based quantitative nuclear magnetic resonance

Low spectral resolution and extensive peak overlap are the common challenges that preclude quantitative analysis of nuclear magnetic resonance (NMR) data with the established peak integration method. While numerous model-based approaches overcome these obstacles and enable quantification, they intrinsically rely on rigid assumptions about functional forms for peaks, which are often insufficient to account for all unforeseen imperfections in experimental data. Indeed, even in spectra with well-separated peaks whose integration is possible, model-based methods often achieve suboptimal results, which in turn raises the question of their validity for more challenging datasets. We address this problem with a simple model adjustment procedure, which draws its inspiration directly from the peak integration approach that is almost invariant to lineshape deviations. Specifically, we assume that the number of mixture components along with their ideal spectral responses are known; we then aim to recover all useful signals left in the residual after model fitting and use it to adjust the intensity estimates of modelled peaks. We propose an alternative objective function, which we found particularly effective for correcting imperfect phasing of the data – a critical step in the processing pipeline. Application of our method to the analysis of experimental data shows the accuracy improvement of 20 %–40 % compared to the simple least-squares model fitting.

A massively parallel barcoded sequencing pipeline enables generation of the first ORFeome and interactome map for rice

Systematic mappings of protein interactome networks have provided invaluable functional information for numerous model organisms. Here we developPCR-mediatedLinkage of barcodedAdaptersTo nucleic acidElements forsequencing (PLATE-seq) that serves as a general tool to rapidly sequence thousands of DNA elements. We validate its utility by generating the ORFeome forOryza sativacovering 2,300 genes and constructing a high-quality protein–protein interactome map consisting of 322 interactions between 289 proteins, expanding the known interactions in rice by roughly 50%. Our work paves the way for high-throughput profiling of protein–protein interactions in a wide range of organisms.