Predicting crop root concentration factors of organic contaminants with machine learning models.

Accurate prediction of uptake and accumulation of organic contaminants by crops from soils is essential to assessing human exposure via the food chain. However, traditional empirical or mechanistic models frequently show variable performance due to complex interactions among contaminants, soils, and plants. Thus, in this study different machine learning algorithms were compared and applied to predict root concentration factors (RCFs) based on a dataset comprising 57 chemicals and 11 crops, followed by comparison with a traditional linear regression model as the benchmark. The RCF patterns and predictions were investigated by unsupervised t-distributed stochastic neighbor embedding and four supervised machine learning models including Random Forest, Gradient Boosting Regression Tree, Fully Connected Neural Network, and Supporting Vector Regression based on 15 property descriptors. The Fully Connected Neural Network demonstrated superior prediction performance for RCFs (R2 =0.79, mean absolute error [MAE] = 0.22) over other machine learning models (R2 =0.68-0.76, MAE = 0.23-0.26). All four machine learning models performed better than the traditional linear regression model (R2 =0.62, MAE = 0.29). Four key property descriptors were identified in predicting RCFs. Specifically, increasing root lipid content and decreasing soil organic matter content increased RCFs, while increasing excess molar refractivity and molecular volume of contaminants decreased RCFs. These results show that machine learning models can improve prediction accuracy by learning nonlinear relationships between RCFs and properties of contaminants, soils, and plants.

TCDD administered on activated carbon eliminates bioavailability and subsequent shifts to a key murine gut commensal.

Activated carbon (AC) is an increasingly attractive remediation alternative for the sequestration of dioxins at contaminated sites globally. However, the potential for AC to reduce the bioavailability of dioxins in mammals and the residing gut microbiota has received less attention. This question was partially answered in a recent study examining 2,3,7,8-tetrachlorodibenzo-p-dioxin (TCDD)-induced hallmark toxic responses in mice administered with TCDD sequestered by AC or freely available in corn oil by oral gavage. Results from that study support the use of AC to significantly reduce the bioavailability of TCDD to the host. Herein, we examined the bioavailability of TCDD sequestered to AC on a key murine gut commensal and the influence of AC on the community structure of the gut microbiota. The analysis included qPCR to quantify the expression of segmented filamentous bacteria (SFB) in the mouse ileum, which has responded to TCDD-induced host toxicity in previous studies and community structure via sequencing the 16S ribosomal RNA (rRNA) gene. The expression of SFB 16S rRNA gene and functional genes significantly increased with TCDD administered with corn oil vehicle. Such a response was absent when TCDD was sequestered by AC. In addition, AC appeared to have a minimal influence on murine gut community structure and diversity, affecting only the relative abundance of Lactobacillaceae and two other groups. Results of this study further support the remedial use of AC for eliminating bioavailability of TCDD to host and subsequent influence on the gut microbiome.