With the exacerbation of global warming, the shift to renewable energy is further necessitated. Biogenic solar panels, a cheaper and more sustainable alternative to environmentally harmful silicon panels, utilize genetically modified E. coli that produce the pigment lycopene as the panel’s electron source. However, the bacteria have to be coated in titanium dioxide that undergoes a photocatalytic effect when exposed to UV radiation, killing the bacteria over time. The project identified CRISPR genes in natural lycopene-producing microorganisms that are resistant to UV radiation and aluminum, a substitute semiconductor to titanium dioxide, discovering organisms that can increase the panel’s longevity.

Diagnosing Mild Cognitive Impairment (MCI) can lead to the treatment and prevention of Alzheimer’s Disease. Current cognitive assessments built to diagnose MCI can have problems with bias. The goal of this project was to build a cognitive assessment along with a Machine Learning model that can objectively diagnose MCI. The final cognitive test was made up of 11 unbiased subscores derived from 3 commonly used cognitive tests. The Machine Learning model using this test performed better at diagnosing MCI than all three original tests combined and separately. The test and model developed in this project can diagnose MCI efficiently and objectively, and give someone a fighting chance to survive Alzheimer’s Disease.

Correct and timely detection of Mycobacterium tuberculosis (MTB) resistance against existing tuberculosis (TB) drugs is essential for limiting TB amplification. In this study, Gradient Boosting was found to overperform other classification models with the highest accuracy mean 0f 0.852, and its overfitting error exposed the need for dimensionality reduction prior to model training. Gene 625 and 331 were the most significant features in this project, and this suggested the potential of machine learning (ML) to find new resistance makers. The results confirmed the application of ML in clinical settings for quicker and better prediction of drug resistance based on large genome sequencing data.

Acute lymphoblastic leukemia (A.L.L.) is the most common childhood cancer with fewer than 200,000 US cases per year. Studies have hinted that cancer treatments such as chemotherapy have contributed to long-term circadian rhythm disruptions. This study aimed to determine the potential long-term effects of ALL coupled with chemotherapy on sleep patterns. Sleep actigraphy data were analyzed and merged with chemotherapy drug data. Machine learning models were used to predict the number of awakenings and total sleep time based on the Circadian Quotient, yielding a 76% accuracy rate. Linear regression modeling presented a strong positive correlation between sleep onset and the number of awakenings, thus strengthening the possibility of chemotherapy hindering sleep quality.

Polysomnography is a test for diagnosing sleep-related hypermotor epilepsy (SHE) and rapid-eye-movement sleep behavior disorder (RBD). It is highly inefficient because often-infrequent seizure events are required to reach a diagnosis. This study used the FOOOF package to calculate electroencephalographic aperiodic components—historically ignored by clinicians—for 28 subjects during non-seizure sleep, and t-tests to detect significant differences between SHE and RBD. Both the exponent (p = 0.041) and offset (p = 0.038) of the aperiodic component were found to differentiate between the disorders. It follows that making use of aperiodic components in polysomnography may yield improvements in efficiency, accuracy, and patient affordability.