Machine Learning Methods for Endocrine Disrupting Potential Identification Based on Single-Cell Data

Abstract

Humans are continuously exposed to a variety of toxicants and chemicals which is exacerbated during and after environmental catastrophes such as floods, earthquakes, and hurricanes. The hazardous chemical mixtures generated during these events threaten the health and safety of humans and other living organisms. This necessitates the development of rapid decision-making tools to facilitate mitigating the adverse effects of exposure on the key modulators of the endocrine system, such as the estrogen receptor alpha (ERα), for example. The mechanistic stages of the estrogenic transcriptional activity can be measured with high content/high throughput microscopy-based biosensor assays at the single-cell level, which generates millions of object-based minable data points. By combining computational modeling and experimental analysis, we built a highly accurate data-driven classification framework to assess the endocrine disrupting potential of environmental compounds. The effects of these compounds on the ERα pathway are predicted as being receptor agonists or antagonists using the principal component analysis (PCA) projections of high throughput, high content image analysis descriptors. The framework also combines rigorous preprocessing steps and nonlinear machine learning algorithms, such as the Support Vector Machines and Random Forest classifiers, to develop highly accurate mathematical representations of the separation between ERα agonists and antagonists. The results show that Support Vector Machines classify the unseen chemicals correctly with more than 96% accuracy using the proposed framework, where the preprocessing and the PCA steps play a key role in suppressing experimental noise and unraveling hidden patterns in the dataset.

Keywords: Classification analysis; Endocrine disrupting chemicals; Estrogen receptor activity; High throughput microscopy; Machine learning; Predictive modeling.

Fig 1.

The estrogenic activity classification flowchart with single-cell level high throughput imaging data.

Fig 2.

Scree plot of explained variance and principal components for datasets with visible nuclear spots. The purple bar indicates the “elbow” of the scree plot which is the optimal number of PCs to retain in the analysis.

Fig 3.

The Train-test split of the active benchmark chemicals.

Fig 4.

Euclidean distance complete linkage hierarchical clustering for datasets with visible nuclear spots.

Fig 5.

3D PCA plot for the array positive M50 scenario. Green points specify the overlap in the agonist region by AZD, ZK, ICI compounds.

Fig 6.

Heatmaps of grid search results for the nonlinear classifiers of array positive M50 scenario: a) SVM, b) RF. The hyperparameter combination with the highest accuracy (indicated with red) is selected to train the final model.

Fig 7.

Confusion matrices for nonlinear classifiers for the testing set of array positive M50 scenario: a) SVM, b) RF.

Fig 8.

Testing accuracies with 15 unseen chemicals over 6 different data preparation techniques for the 2-class SVM and RF classifiers.