Here, seeking to better understand the control algorithms used in autonomous vehicles, the authors compared the Stanley and pure pursuit control algorithms along with a new version of each. Unexpectedly, they found that no control algorithm offered optimal performance, but rather resulted in tradeoffs between the various ideal results.

Every year, around 40% of undergraduate students in the United States discontinue their studies, resulting in a loss of valuable education for students and a loss of money for colleges. Even so, colleges across the nation struggle to discover the underlying causes of these high dropout rates. In this paper, the authors discuss the use of machine learning to find correlations between the built environment factors and the retention rates of colleges. They hypothesized that one way for colleges to improve their retention rates could be to improve the physical characteristics of their campus to be more pleasing. The authors used image classification techniques to look at images of colleges and correlate certain features like colors, cars, and people to higher or lower retention rates. With three possible options of high, medium, and low retention rates, the probability that their models reached the right conclusion if they simply chose randomly was 33%. After finding that this 33%, or 0.33 mark, always fell outside of the 99% confidence intervals built around their models’ accuracies, the authors concluded that their machine learning techniques can be used to find correlations between certain environmental factors and retention rates.

In this study, Imani et al. investigate whether a new proprietary herbal formulation, HF1, can inhibit expression of immune suppressor protein PD-L1. PD-L1 is a transmembrane protein that can be expressed by cancer cells to assist in their ability to avoid attacks from the immune system. Work from this study demonstrates that HF1 treatment can reduce expression of PD-L1 in cultured cancer cells, implicating HF1 as a potential new cancer therapy.

The independent effects of metastasis-promoting gene CD151 in the process of metastasis are not known. This study aimed to isolate CD151 to discover what its role in metastasis would be uninfluenced by potential interactions with other components and pathways in human cells. Results showed that CD151 significantly increased the adhesion of the cells and decreased their motility. Thus, it may be that CD151 is upregulated in cancer cells for the last step of metastasis, and it increases the chances of success of metastasis by aiding in implantation of the cancer cells. Targeting CD151 in chemotherapeutic modalities could therefore potentially slow or prevent metastasis.

While some believe that ride-hailing services offer reduced CO₂ emissions compared to individual driving, studies have found that driving without passengers on ride-hailing trips or "deadheading" prevents this. Here, with a mathematical model, the authors investigated if the use of electric vehicles as ride-hailing vehicles could offer reduced CO₂ emissions. They found that the improved vehicle efficiency and cleaner generation could in fact lower emissions compared to the use of personal gas vehicles.

The authors looked at the ability of machine learning algorithms to interpret language given their increasing use in moderating content on social media. Using an explainable model they were able to achieve 81% accuracy in detecting fake vs. real news based on language of posts alone.

Acquired immunodeficiency syndrome (AIDS) is a life-threatening condition caused by the human immunodeficiency virus (HIV). In this work, Takemaru et al explored the role of Coiled-Coil Domain-Containing 11 (CCDC11) in HIV-1 budding. Their results suggest that CCDC11 is critical for efficient HIV-1 budding, potentially indicating CCDC11 a viable target for antiviral therapeutics without major side effects.

As the world struggled to grapple with the emerging COVID-19 pandemic in 2020, many countries instated policies to help minimize the spread of the virus among residents. This inadvertently led to a decrease in travel, and in some cases, industrial output, two major sources of pollutants in today's world. Here, the authors investigate whether California's shelter-in-place policy was associated with a measurable decrease in water and air pollution in that state between June and July of 2020, compared to the preceeding five years. Their findings suggest that, by some metrics, air quality improved within certain areas while water quality was relatively unchanged. Overall, these findings suggest that changing human behavior can, indeed, help reduce the level of air pollutants that compromise air quality.

Emissions from oil and natural gas (O&G) wells such as nitrogen dioxide (NO₂), volatile organic compounds (VOCs), and ozone (O₃) can severely impact the health of communities located near wells. In this study, we used O&G activity and wind-carried emissions to quantify the extent to which O&G wells affect the air quality of nearby communities, revealing that NO₂, NO_x, and NO are correlated to O&G activity. We then developed a novel land use regression (LUR) model using machine learning based on O&G prevalence to predict emissions.

Environmental disasters such as the Deepwater Horizon oil spill can be devastating to ecosystems for long periods of time. Safer, cheaper, and more effective methods of oil clean-up are needed to clean up oil spills in the future. Here, the authors investigate the ability of natural ocean algae to process crude oil into less toxic chemicals. They identify Coccochloris elabens as a particularly promising algae for future bioremediation efforts.