Machine Learning Models for Prediction of Xenobiotic Chemicals with High Propensity to Transfer into Human Milk

Abstract

Breast milk serves as a vital source of essential nutrients for infants. However, human milk contamination via the transfer of environmental chemicals from maternal exposome is a significant concern for infant health. The milk to plasma concentration (M/P) ratio is a critical metric that quantifies the extent to which these chemicals transfer from maternal plasma into breast milk, impacting infant exposure. Machine learning-based predictive toxicology models can be valuable in predicting chemicals with a high propensity to transfer into human milk. To this end, we build such classification- and regression-based models by employing multiple machine learning algorithms and leveraging the largest curated data set, to date, of 375 chemicals with known milk-to-plasma concentration (M/P) ratios. Our support vector machine (SVM)-based classifier outperforms other models in terms of different performance metrics, when evaluated on both (internal) test data and an external test data set. Specifically, the SVM-based classifier on (internal) test data achieved a classification accuracy of 77.33%, a specificity of 84%, a sensitivity of 64%, and an F-score of 65.31%. When evaluated on an external test data set, our SVM-based classifier is found to be generalizable with a sensitivity of 77.78%. While we were able to build highly predictive classification models, our best regression models for predicting the M/P ratio of chemicals could achieve only moderate R² values on the (internal) test data. As noted in the earlier literature, our study also highlights the challenges in developing accurate regression models for predicting the M/P ratio of xenobiotic chemicals. Overall, this study attests to the immense potential of predictive computational toxicology models in characterizing the myriad of chemicals in the human exposome.

Figure 1

Schematic diagram summarizing the workflow to build the classification- and regression-based machine learning models to predict xenobiotic chemicals with a high propensity to transfer from maternal plasma to human milk. This figure shows the key steps involved in data curation, feature generation, data preprocessing, feature selection, and the training and evaluation of classification- and regression-based machine learning models. The word clouds in this figure were generated using https://www.wordclouds.com.

Figure 2

Confusion matrix depicting the performance of the best classification models corresponding to five classification algorithms, namely, (a) SVM, (b) XGBoost, (c) LDA, (d) MLP, and (e) RF on the (internal) test data of 75 chemicals. Note: TP, TN, FP, and FN stand for true positive, true negative, false positive, and false negative.

Figure 3

ROC curve and precision–recall curve for evaluating the best models built using the five different classification algorithms. (a) ROC curve plotted with sensitivity on the y-axis and 1-specificity on the x-axis. (b) Precision–recall curve plotted with precision on the y-axis and recall (sensitivity) on the x-axis.