A contemporary review of machine learning to predict adverse pregnancy outcomes from pharmaceuticals, including DDIs.

Those undergoing pregnancy are often excluded from clinical drug trials due to the risk that participation would pose. However, they often require pharmaceuticals to manage health conditions that, if gone untreated, could harm themselves or the fetus. This can mean that such individuals take one or more pharmaceuticals during pregnancy, many of which have unknown reproductive effects. Machine learning models have been used to successfully predict a number of reproductive toxicological outcomes for pharmaceuticals, including transplacental transfer, US Food and Drug Administration safety rating, and drug interactions. Models use quantitative chemical and structural features of active compounds to make predictions concerning the outcome of interest using computational algorithms. Results from these models can be a potential source of valuable information for pregnant people and their medical providers when making decisions regarding therapeutic drug use. This review summarizes current machine learning applications to make predictions about risk and toxicity of medication use during pregnancy. Our review of the recent literature revealed that machine learning quantitative structure-activity relationship models can be used successfully to predict the transplacental transfer and the US Food and Drug Administration pregnancy safety category of pharmaceuticals; such models have also been employed to predict drug interactions, though not specifically during pregnancy. This latter topic is a potential area for future research. In this review, no single algorithm or descriptor-calculation software emerged as the most widely used, and their performances depend on a variety of factors, including outcome of interest and combination of such algorithms and software.

Skyrocketing pollution: assessing the environmental fate of July 4th fireworks in New York City.

BACKGROUND: Pyrotechnic displays often lead to significant increases in poor air quality. The widespread environmental fate-involving air, water, and spatial-temporal analyses-of fireworks-produced pollutants has seldom been investigated. OBJECTIVE: This study examined the environmental fate of pollutants from the largest fireworks event in the U.S.: Macy's Fourth of July Fireworks show in New York City (NYC). METHODS: Real-time PM2.5 and gravimetric PM2.5 and PM10 were collected at locations along the East River of NYC. Airborne particles were assayed for trace elements (X-ray fluorescence) and organic and elemental carbon (OC/EC). River water samples were evaluated by ICP-MS for heavy-metal water contamination. Spatial-temporal analyses were created using PM2.5 concentrations reported by both EPA and PurpleAir monitoring networks for NYC and 5 other major metropolitan areas. RESULTS: The fireworks event resulted in large increases in PM2.5 mass concentrations at the river-adjacent sampling locations. While background control PM2.5 was 10-15 µg/m3, peak real-time PM2.5 levels exceeded 3000 µg/m3 at one site and 1000 µg/m3 at two other locations. The integrated gravimetric PM2.5 and PM10 concentrations during the fireworks event ranged from 162 to 240 µg/m3 and 252 to 589 µg/m3, respectively. Zn, Pb, Sb, and Cu more than doubled in river water samples taken after the event, while S, K, Ba, Cu, Mg, Fe, Sr, Ti, and Zn increased in airborne PM2.5 from the fireworks. Data from hyperlocal monitoring networks for NYC and other metropolitan areas yielded similar, but generally smaller, increases in PM2.5 levels. IMPACT: Fireworks shows have been associated with environmental contamination. This comprehensive analysis considers the fate of pollutants from the largest annual U.S. pyrotechnic show through air, water, and hyperlocal temporal characterization.