Browse Articles

The authors looked at the impact of vitamin A (retinol) on growth of S. epidermidis (most abundant bacterium on the skin) and E. coli (found in the gut microbiome, but not on the skin).

This study explored how green spaces, climate, traffic, and air quality (GCTA) collectively influence asthma-related emergency department visits in the U.S using machine learning models and explainable AI.

The authors develop a machine learning method to reduce misclassification of objects in safety-critical applications such as medical diagnosis.

The authors studied the chemoreception of moon jellyfish in response to food, and developed an AI tool to identify track and quantify the pulsation of swimming jellyfish.

The authors looked at different ways to build computational resources that would analyze shooting form for basketball players.

Cutibacterium acnes is a bacterium believed to play an important role in the pathogenesis of common skin diseases such as acne vulgaris. Currently, acne is known to be associated with strains from the type IA1 and IC clades of C. acnes, while those from the type IA2, IB, II, and III phylogroups are associated with skin health. This is the first study to explore the sequence space of individual gene products of different C. acnes phylogroups. Our analysis compared the sequence space topology of virulence factors to proteins with unknown functions and housekeeping proteins. We hypothesized that sequence space features of virulence factors are different from housekeeping protein features, which potentially provides an avenue to deduce unknown proteins’ functions. This proposition should be confirmed based on further experimental outcomes. A notable similarity in the sequence spaces’ topological features of previously known as housekeeping proteins encoded by recA and guaA genes to ‘putative virulence’ genes camp2 and tly was observed. Our research suggests further investigation of recA and guaA’s potential virulence properties to better understand acne pathogenesis and develop more targeted acne treatments.

Vibrato, defined as a rapid and subtle oscillation in pitch, is a technique that is commonly used by musicians to add expression and colour to notes. However, on stringed instruments, there are certain notes (open string notes) on which it is impossible to perform the technique. Without vibrato, they can sound angular and unpleasant, especially when juxtaposed against other notes played with vibrato. String players therefore use an alternative to achieve the same vibrato effect on the open string — a technique referred to as “open string vibrato”. While the technique is widely used, it is unknown how much of a physical effect it has on the sound waves produced, if any at all. The purpose of this study is to analyse open string vibrato using a statistical approach to provide evidence to characterize the physical effect of the technique, and then compare it to normal vibrato. We hypothesised that it would have a noticeable and measurable effect on the sound waves produced because of the technique’s widespread usage. To test this, notes, with and without either open string vibrato or normal vibrato, were recorded on the violin. We analyzed the audio recordings using a computational and statistical approach. The results of the study partially agreed with our hypothesis: while the technique has an observable physical effect on the sound waves, the effect is weaker than expected. We concluded that open string vibrato does work, but has quite a subtle effect, and thus should only be used when there is no other option.

The authors looked at the ability of Spirulina platensis to reduce contaminants in wastewater in order to develop a more accessible treatment option. They found that S platensis did reduce the concentration of pollutants present within simulated agricultural wastewater.

Here, recognizing that brain aneurysms pose a severe threat, often misdiagnosed and leading to high mortality, particularly in younger individuals, the authors explored a novel computer-aided engineering approach. They used magnetic resonance angiography images and computational fluid dynamics, to improve aneurysm detection and risk assessment, aiming for more personalized treatment.

Pediatric cancers pose unique challenges due to their rarity and distinct biological factors, emphasizing the need for accurate survival prediction to guide treatment. This study integrated generative AI and machine learning, including synthetic data, to analyze 9,184 pediatric cancer patients, identifying age at diagnosis, cancer types, and anatomical sites as significant survival predictors. The findings highlight the potential of AI-driven approaches to improve survival prediction and inform personalized treatment strategies, with broader implications for innovative healthcare applications.