Prediction model for milk transfer of drugs by primarily evaluating the area under the curve using QSAR/QSPR

Abstract

Purpose Information on milk transferability of drugs is important for patients who wish to breastfeed. The purpose of this study is to develop a prediction model for milk-to-plasma drug concentration ratio based on area under the curve (M/PAUC). The quantitative structure–activity/property relationship (QSAR/QSPR) approach was used to predict compounds involved in active transport during milk transfer. Methods We collected M/P ratio data from literature, which were curated and divided into M/PAUC ≥ 1 and M/PAUC < 1. Using the ADMET Predictor® and ADMET Modeler™, we constructed two types of binary classification models: an artificial neural network (ANN) and a support vector machine (SVM). Results M/P ratios of 403 compounds were collected, M/PAUC data were obtained for 173 compounds, while 230 compounds only had M/Pnon-AUC values reported. The models were constructed using 129 of the 173 compounds, excluding colostrum data. The sensitivity of the ANN model was 0.969 for the training set and 0.833 for the test set, while the sensitivity of the SVM model was 0.971 for the training set and 0.667 for the test set. The contribution of the charge-based descriptor was high in both models. Conclusions We built a M/PAUC prediction model using QSAR/QSPR. These predictive models can play an auxiliary role in evaluating the milk transferability of drugs.

Assessment of Infant Exposure to Antidepressants through Breastfeeding: A Literature Review of Currently Available Approaches

“…According to a similar retrospective study by Singal et al, in utero exposure to SSRIs or SNRIs was associated with an increase in neurodevelopmental deficits in a cohort of kindergarten children in Canada [80]. These children, whose mothers had filled ≥ 2 antidepressant prescriptions during pregnancy, were found to have increased odds of being developmentally vulnerable, defined as scoring in the bottom 10th percentile of the Educational Developmental Instrument, or EDI [78]. Additionally, children in the exposed group had a significantly higher risk of language and/or cognitive vulnerability [80].…”

“…The resulting model showed satisfactory correlation (R 2 = 0.791) between predicted and observed logarithmic M/P ratios and could, in theory, be used to predict the distribution coefficient between human breast milk and plasma of many different compounds [77]. Maeshima et al developed a similar QSAR/QSPR model by using a binary classification model to predict M/P AUC ratios [78]. These models incorporated descriptors calculated specifically from the molecular structure of compounds and were found to perform at an acceptable range.…”