Department of Obstetrics, Gynecology and Reproductive Sciences, Program on Reproductive Health and the Environment, University of California, San Francisco, 490 Illinois Street, San Francisco, CA, 94143, USA.
California Environmental Protection Agency, Office of Environmental Health Hazard Assessment, 1001 I St, Sacramento, CA, 95814, USA.
J Expo Sci Environ Epidemiol. 2022 Nov;32(6):808-819. doi: 10.1038/s41370-022-00481-2. Epub 2022 Oct 7.
Despite their large numbers and widespread use, very little is known about the extent to which per- and polyfluoroalkyl substances (PFAS) can cross the placenta and expose the developing fetus.
The aim of our study is to develop a computational approach that can be used to evaluate the of extend to which small molecules, and in particular PFAS, can cross to cross the placenta and partition to cord blood.
We collected experimental values of the concentration ratio between cord and maternal blood (R) for 260 chemical compounds and calculated their physicochemical descriptors using the cheminformatics package Mordred. We used the compiled database to, train and test an artificial neural network (ANN). And then applied the best performing model to predict R for a large dataset of PFAS chemicals (n = 7982). We, finally, examined the calculated physicochemical descriptors of the chemicals to identify which properties correlated significantly with R.
We determined that 7855 compounds were within the applicability domain and 127 compounds are outside the applicability domain of our model. Our predictions of R for PFAS suggested that 3623 compounds had a log R > 0 indicating preferable partitioning to cord blood. Some examples of these compounds were bisphenol AF, 2,2-bis(4-aminophenyl)hexafluoropropane, and nonafluoro-tert-butyl 3-methylbutyrate.
These observations have important public health implications as many PFAS have been shown to interfere with fetal development. In addition, as these compounds are highly persistent and many of them can readily cross the placenta, they are expected to remain in the population for a long time as they are being passed from parent to offspring.
Understanding the behavior of chemicals in the human body during pregnancy is critical in preventing harmful exposures during critical periods of development. Many chemicals can cross the placenta and expose the fetus, however, the mechanism by which this transport occurs is not well understood. In our study, we developed a machine learning model that describes the transplacental transfer of chemicals as a function of their physicochemical properties. The model was then used to make predictions for a set of 7982 per- and polyfluorinated alkyl substances that are listed on EPA's CompTox Chemicals Dashboard. The model can be applied to make predictions for other chemical categories of interest, such as plasticizers and pesticides. Accurate predictions of R can help scientists and regulators to prioritize chemicals that have the potential to cause harm by exposing the fetus.
尽管全氟和多氟烷基物质（PFAS）数量众多且用途广泛，但人们对其能够穿过胎盘并暴露于发育中的胎儿的程度知之甚少。
我们研究的目的是开发一种计算方法，用于评估小分子（特别是 PFAS）穿过胎盘并分配到脐带血的程度。
我们收集了 260 种化合物的脐带血与母血浓度比（R）的实验值，并使用化学信息学软件包 Mordred 计算了它们的物理化学描述符。我们利用编译的数据库，训练和测试了一个人工神经网络（ANN）。然后，我们将表现最佳的模型应用于预测大量 PFAS 化学物质（n=7982）的 R 值。最后，我们检查了化学物质的计算物理化学描述符，以确定哪些特性与 R 显著相关。
我们确定 7855 种化合物在模型的适用范围内，127 种化合物在模型的适用范围之外。我们对 PFAS 的 R 值的预测表明，3623 种化合物的 log R>0，表明它们更倾向于分配到脐带血中。这些化合物的一些例子是双酚 AF、2,2-双（4-氨基苯基）六氟丙烷和全氟叔丁基 3-甲基丁酸酯。
这些观察结果具有重要的公共卫生意义，因为许多 PFAS 已被证明会干扰胎儿发育。此外，由于这些化合物具有高度持久性，并且其中许多化合物很容易穿过胎盘，因此它们作为从父母传递给后代的物质，预计将在很长一段时间内在人群中存在。
了解怀孕期间化学物质在人体中的行为对于防止在发育关键期发生有害暴露至关重要。许多化学物质可以穿过胎盘并暴露胎儿，但这种转运的机制尚不清楚。在我们的研究中，我们开发了一个机器学习模型，将化学物质的胎盘转运描述为其物理化学性质的函数。然后，我们使用该模型对 EPA 的 CompTox Chemicals Dashboard 上列出的 7982 种全氟和多氟烷基物质进行了预测。该模型可用于对其他感兴趣的化学物质类别（如增塑剂和杀虫剂）进行预测。准确预测 R 可以帮助科学家和监管机构优先考虑那些有可能通过暴露胎儿而造成危害的化学物质。
