Classification and Regression Tree Approach for Prediction of Potential Hazards of Urban Airborne Bacteria during Asian Dust Events

Abstract

Despite progress in monitoring and modeling Asian dust (AD) events, real-time public hazard prediction based on biological evidence during AD events remains a challenge. Herein, both a classification and regression tree (CART) and multiple linear regression (MLR) were applied to assess the applicability of prediction for potential urban airborne bacterial hazards during AD events using metagenomic analysis and real-time qPCR. In the present work, Bacillus cereus was screened as a potential pathogenic candidate and positively correlated with PM10 concentration (p < 0.05). Additionally, detection of the bceT gene with qPCR, which codes for an enterotoxin in B. cereus, was significantly increased during AD events (p < 0.05). The CART approach more successfully predicted potential airborne bacterial hazards with a relatively high coefficient of determination (R2) and small bias, with the smallest root mean square error (RMSE) and mean absolute error (MAE) compared to the MLR approach. Regression tree analyses from the CART model showed that the PM10 concentration, from 78.4 µg/m3 to 92.2 µg/m3, is an important atmospheric parameter that significantly affects the potential airborne bacterial hazard during AD events. The results show that the CART approach may be useful to effectively derive a predictive understanding of potential airborne bacterial hazards during AD events and thus has a possible for improving decision-making tools for environmental policies associated with air pollution and public health.

The capacity of wastewater treatment plants drives bacterial community structure and its assembly

“…Sequences were processed using MOTHUR software version 1.39.5 17 according to the standard operating procedure (http://www.mothur.org/wiki/MiSeq_SOP) 18,19 with minor modifications 20 . Briefly, sequences longer than 466 bp were discarded, and those that remained were screened with start and end positions of 10,364 and 25,316, respectively, after being aligned to the SILVA database Release 132 21 .…”

Metagenomic Profiles of Antibiotic Resistance Genes in Activated Sludge, Dewatered Sludge and Bioaerosols

“…Dewatered sludges were also collected from the belt-press inside the dewatering system unit on the same day. Bioaerosols samples were collected beside the belt-press on sterilized 0.2 µm track-etched polycarbonate filters (Whatman, GE, Freiburg, Germany) using two high-volume air samplers (Model TE 5200, Tisch Environmental, Inc., Cleves, OH, USA) at a flow rate of 1.5 m 3 min −1 for 24 h. The polycarbonate filters were autoclaved prior to sampling, and the filter holders were washed with 70% ethanol at the sampling time to avoid potential contamination [26]. The temperature and relative humidity inside the dewatering facility were 22 • C and 19%, respectively.…”

“…For the sludge and dewatered sludge samples, DNA was extracted from the cell pellet formed after centrifuging 1.5 mL of each sample at 14,000× g for 2 min. For the bioaerosol samples, gDNA was extracted from the filter pieces by a method described in previous studies [26,27]. The quality of the extracted DNA was checked using a Qubit Fluorometer (Thermo, Wilmington, DE, USA) for the subsequent shotgun metagenome sequencing.…”

Predicting the decision making chemicals used for bacterial growth

“…Precise and high-throughput growth assays were performed to acquire sufficient experimental records of bacterial growth for data analysis. To obtain an alternative view of bacterial growth and ultimately extract insight from the growth data, decision tree learning 43,44 , which is one of the multifaceted disciplines in data science 45 , was introduced. This approach could lead to meaningful decisions as to where to mark the boundaries among the ranges of attributed chemicals to split the different branches of a growth parameter tree.…”