Recurrent neural networks (RNNs) are useful for text generation since they can generate outputs in the context of previous ones. Baroque music and language are similar, as every word or note exists in context with others, and they both follow strict rules. The authors hypothesized that if we represent music in a text format, an RNN designed to generate language could train on it and create music structurally similar to Bach’s. They found that the music generated by our RNN shared a similar structure with Bach’s music in the input dataset, while Bachbot’s outputs are significantly different from this experiment’s outputs and thus are less similar to Bach’s repertoire compared to our algorithm.

Cilia are little hair-like protrusions on many cells in the human body, including those lining the trachea where they play a role in clearing our respiratory tract of mucous and other irritants. Genetic mutations that impair ciliary function have serious consequences on our well-being making it important to understand how ciliary function is regulated. By using a simple organism, such as the worm C. elegans that use cilia to move, the authors explore the effect of certain genetic mutations on the cilia of the worms by measuring their ability to move towards or away from certain odorants.

Although the United States maintains millions of square kilometers of nature reserves to protect the biodiversity of the specimens living there, little is known about how confining these species within designated protected lands influences the genetic variation required for a healthy population. In this study, the authors sequenced genetic barcodes of insects from a recently established nature reserve, the Southwestern Riverside County Multi-Species Reserve (SWRCMSR), and a non-protected area, the Mt. San Jacinto College (MSJC) Menifee campus, to compare the genetic variation between the two populations. Their results demonstrated that the midge fly population from the SWRCMSR had fewer unique DNA barcode sequence changes than the MSJC population, indicating that the comparatively younger nature reserve's population had likely not yet established its own unique genetic drift changes.

Auto-Regressive Integrated Moving Average (ARIMA) models are known for their influence and application on time series data. This statistical analysis model uses time series data to depict future trends or values: a key contributor to crime mapping algorithms. However, the models may not function to their true potential when analyzing data with many different patterns. In order to determine the potential of ARIMA models, our research will test the model on irregularities in the data. Our team hypothesizes that the ARIMA model will be able to adapt to the different irregularities in the data that do not correspond to a certain trend or pattern. Using crime theft data and an ARIMA model, we determined the results of the ARIMA model’s forecast and how the accuracy differed on different days with irregularities in crime.

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.

Major depressive disorder (MDD) is a prevalent mood disorder. The direct causes and biological mechanisms of depression still elude understanding, though genetic factors have been implicated. This study looked to identify the mechanism behind the aberrant response to the dexamethasone suppression test (DST) displayed by MDD patients, in which they display a lack of cortisol suppression. Analysis revealed several pro-inflammatory genes that were significant and differentially expressed between affected and non-affected groups in response to the DST. Looking at ways to decrease the inflammatory response could have implications for treatment and may explain why some people treated for depression still display symptoms or may lead researchers to different classes of drugs for treatment.

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.

The authors develop and test a machine learning algorithm for predicting diabetes diagnoses.

Recent declines in the brook trout population of the Lake Champlain Basin have made the genetic screening of this and other trout species of utmost importance. In this study, the authors collected and analyzed 21 DNA samples from Lake Champlain Basin trout populations and performed a phylogenetic analysis on these samples using the cytochrome b gene. The findings presented in this study may influence future habitat decisions in this region.

The authors develop a new method for training machine learning algorithms to differentiate between hate speech and cultural speech in online platforms.