Browse Articles

Current drug discovery processes can cost billions of dollars and usually take five to ten years. People have been researching and implementing various computational approaches to search for molecules and compounds from the chemical space, which can be on the order of 1060 molecules. One solution involves deep generative models, which are artificial intelligence models that learn from nonlinear data by modeling the probability distribution of chemical structures and creating similar data points from the trends it identifies. Aiming for faster runtime and greater robustness when analyzing high-dimensional data, we designed and implemented a Hybrid Quantum-Classical Generative Adversarial Network (QGAN) to synthesize molecules.

As cancer continues to take millions of lives worldwide, the need to create effective therapeutics for the disease persists. The kinesin Eg5 assembly motor protein is a promising target for cancer therapeutics as inhibition of this protein leads to cell cycle arrest. Monastrol, a small dihydropyrimidine-based molecule capable of inhibiting the kinesin Eg5 function, has attracted the attention of medicinal chemists with its potency, affinity, and specificity to the highly targeted loop5/α2/α3 allosteric binding pocket. In this work, we employed high-throughput virtual screening (HTVS) to identify potential small molecule Eg5 inhibitors from a designed set of novel dihydropyrimidine analogs structurally similar to monastrol.

Nolt and Elwonger examine how different types of music impact our emotional and physical states. They found that music can influence a subject's emotional state, with sad music inspiring sadness and exciting music bringing excitement. They were not able to find a clear relationship between heart rate and music type. Music's effect on emotional state can be useful when designing novel therapies for emotional and mental disorders.

The authors assessed the correlation between the stock, commodity, and consumer markets with the housing market.

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.

Identifying treatments that can stimulate hair growth use could help those struggling with undesirable hair loss. Here, the authors show that Fibroblast Growth Factors can stimulate the division of cells isolated from the mouse hair follicle. Their results suggest that this family of growth factors might be helpful in stimulating hair growth in living animals as well.

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

In this study, the authors hypothesized that closed-circuit television images could be stored with improved resolution by using enhanced deep residual (EDSR) networks.

The authors studied the ability of deep learning models to predict droughts in the midwestern United States.

The authors investigated alcohol content of foods during preparation and when ready to serve to determine how much alcohol remained in the food.