Browse Articles

Breast cancer is the most common cancer in women, with approximately 300,000 diagnosed with breast cancer in 2023. It ranks second in cancer-related deaths for women, after lung cancer with nearly 50,000 deaths. Scientists have identified important genetic mutations in genes like BRCA1 and BRCA2 that lead to the development of breast cancer, but previous studies were limited as they focused on specific populations. To overcome limitations, diverse populations and powerful statistical methods like genome-wide association studies and whole-genome sequencing are needed. Explainable artificial intelligence (XAI) can be used in oncology and breast cancer research to overcome these limitations of specificity as it can analyze datasets of diagnosed patients by providing interpretable explanations for identified patterns and predictions. This project aims to achieve technological and medicinal goals by using advanced algorithms to identify breast cancer subtypes for faster diagnoses. Multiple methods were utilized to develop an efficient algorithm. We hypothesized that an XAI approach would be best as it can assign scores to genes, specifically with a 90% success rate. To test that, we ran multiple trials utilizing XAI methods through the identification of class-specific and patient-specific key genes. We found that the study demonstrated a pipeline that combines multiple XAI techniques to identify potential biomarker genes for breast cancer with a 95% success rate.

This study examines the higher harmonics in an oscillating string by analyzing the sound produced by a guitar with a spectrum analyzer. The authors mathematically hypothesized that the higher harmonics in the series of the directly excited 2^nd harmonic contain the alternate frequencies of the fundamental series, the higher harmonics of the directly excited 3^rd harmonic series contain every third frequency of fundamental series, and so on. To test the hypotheses, they enforced artificial nodes to excite the 2^nd, 3^rd, and 4^th harmonics directly, and analyzed the resulting spectrum to verify the mathematical hypothesis. The data analysis corroborates both hypotheses.

Excess sucrose consumption has been associated with several health problems, including inflammation and potential negative effects on immune function. However, the exact relationship between sucrose intake and immunity remains unclear, especially during bacterial infections. This study examined how sucrose intake affected the survival of fruit flies following oral infection with the bacterial pathogen Serratia marcescens.

The authors studied the effect of potassium bromate, a common food additive, to cell viability.

Recent observations by the “Extremely Metal-Poor Representatives Explored by the Subaru Survey” (EMPRESS) collaboration found normal deuterium levels but unexpectedly low helium-4, challenging current cosmological theories. This study used simulations with the PRyMordial package to test whether dark matter particles interacting with neutrinos in the early universe could explain the discrepancy.

The authors use computational methods to compare tau acetylation to the better studied tau phosphorylation in Alzheimer's disease and then design and computationally test a new drug to prevent abnormal post-translational modifications of tau.

Understanding and predicting cognitive decline in Alzheimer's disease

Detecting cervical spondylosis using deep learning

This paper looks at the antibacterial and toxic effects of silver nanoparticles (AgNPs) on Escherichia coli bacteria and Drosophila melanogaster fruit flies. They modified the AgNPs size, concentration, and surface coating to determine the effects on each of the organisms. For both organisms, increased AgNP concentration demonstrated increased toxicity but particle size and surface coating had opposing effects.

The authors looked the ability of sound sensors to predict clogged pipes when the sound intensity data is run through a machine learning algorithm.