The purpose of the study was to determine whether graph-based machine learning techniques, which have increased prevalence in the last few years, can accurately classify data into one of many clusters, while requiring less labeled training data and parameter tuning as opposed to traditional machine learning algorithms. The results determined that the accuracy of graph-based and traditional classification algorithms depends directly upon the number of features of each dataset, the number of classes in each dataset, and the amount of labeled training data used.

The Human Immunodeficiency Virus (HIV) infects approximately 40 million people globally, and one million people die every year from Acquired Immune Deficiency Syndrome (AIDS)-related illnesses. This study examined the interactions between the HIV-1 envelope glycoprotein gp120 and the human lymphocyte receptor integrin α4β7, the putative first long-range receptor for the envelope glycoprotein of the virus in mucosal tissues. Presented data support the claim that the V1 loop is involved in the binding between α4β7 and the HIV-1 envelope glycoprotein through molecular dockings.

The authors test the antiproliferative and apoptosis-inducing properties of an extract created from a traditional Indian medicinal plant of the Amaranthus genus.

Recognizing the need for a method to filter microplastics from polluted water the authors sought to use nonpolar solvents, palm oil and palm kernel oil, to filter microplastics out of model seawater. By relying on the separation of polar and nonpolar solvents followed by freezing the nonpolar solvent, they reported that microplastics could be extracted with percentages ranging from 96.2% to 94.2%. They also provided an estimation to use this method as part of container ships to clean the Pacific Ocean of microplastics.

Human cytomegalovirus (HCMV) causes serious infections in immunocompromised patients and therapies to inhibit latent HCMV are not developed. Using CRISPR/Cas9, the authors were able to delete an important promoter region in HCMV.

In this article, the authors use datasets of professional and youth soccer players' movements to map and statistically compare them. Analysis compared movements that led to goals or no-goals and differences between pros and youth.

In a 10-year period in the early 2000’s, hospital-based (nosocomial) infections increased by 123%, and this number is increasing as time goes on. The purpose of this experiment was to use hyaluronic acid, silver nanoparticles, and a bacteriophage cocktail to create a hydrogel that promotes wound healing by increasing cell proliferation while simultaneously disrupting biofilm formation and breaking down Staphylococcus aureus and Pseudomonas aeruginosa, which are two strains of bacteria that attribute to nosocomial infections and are increasing in antibiotic resistance.

Previously established data indicate that cemeteries have contributed to groundwater and soil pollution, as embalming fluids can impact the microbiomes that exist in decomposing remains. In this study, Caputo et al hypothesized that microbial variation would be high between cemeteries from different eras due to dissimilarities between embalming techniques employed, and furthermore, that specific microbes would act as an indication for certain contaminants. Overall, they found that there is a variation in the microbiomes of the different eras’ cemeteries according to the concentrations of the phyla and their more specific taxa.

Here, based on the identification of androgapholide as a potential therapeutic treatment against cancer, Alzheimer's disease, diabetes, and multiple sclerosis, due to its ability to inhibit a signaling pathway in immune system function, the authors sought ways to optimize the natural product human systems by manipulating its chemical structure. Through the semisynthesis of a natural product along with computational studies, the authors developed an understanding of the kinetic mechanisms of andrographolide and semisynthetic analogs in the context of Michael additions.

With advancements in machine learning a large data scale, high throughput virtual screening has become a more attractive method for screening drug candidates. This study compared the accuracy of molecular descriptors from two cheminformatics Mordred and PaDEL, software libraries, in characterizing the chemo-structural composition of 53 compounds from the non-nucleoside reverse transcriptase inhibitors (NNRTI) class. The classification model built with the filtered set of descriptors from Mordred was superior to the model using PaDEL descriptors. This approach can accelerate the identification of hit compounds and improve the efficiency of the drug discovery pipeline.