Comparing Machine Learning Models for Aromatase (P450 19A1)

Abstract

Aromatase, or cytochrome P450 19A1, catalyzes the aromatization of androgens to estrogens within the body. Changes in the activity of this enzyme can produce hormonal imbalances that can be detrimental to sexual and skeletal development. Inhibition of this enzyme can occur with drugs and natural products as well as environmental chemicals. Therefore, predicting potential endocrine disruption via exogenous chemicals requires that aromatase inhibition be considered in addition to androgen and estrogen pathway interference. Bayesian machine learning methods can be used for prospective prediction from the molecular structure without the need for experimental data. Herein, the generation and evaluation of multiple machine learning models utilizing different sources of aromatase inhibition data are described. These models are applied to two test sets for external validation with molecules relevant to drug discovery from the public domain. In addition, the performance of multiple machine learning algorithms was evaluated by comparing internal five-fold cross-validation statistics of the training data. These methods to predict aromatase inhibition from molecular structure, when used in concert with estrogen and androgen machine learning models, allow for a more holistic assessment of endocrine-disrupting potential of chemicals with limited empirical data and enable the reduction of the use of hazardous substances.

Figure 1:

Machine learning algorithm comparisons across multiple metrics for the training datasets described in Table 2. The radius of a given point reflects the value of the metric at each corner of the radar plot. The ToxCast assay corresponds to “NVS_ADME_hCYP19A1”, and the Tox21 assay to “TOX21_Aromatase_Inhibition”. Abbreviations: Combo = ToxCast and Tox21 assays combined, BFHC = burst-flag hit-call, HC = hit-call, Kappa = Cohen’s Kappa, MCC = Matthews Correlation Coefficient, AC = Assay Central® (Bayesian), rf = random forest, knn = k-Nearest Neighbors, svc = support vector classification, bnb = Naïve Bayesian, ada = AdaBoosted decision trees, DL = deep learning architecture.

Figure 2:

Machine learning algorithm comparisons across multiple five-fold cross-validation metrics using either rank normalized scores (left) or ΔRNS (right). Box and whisker plots show individual points for those values that fall outside of the 5–95 percentile. Abbreviations: AC = Assay Central® (Bayesian), rf = Random Forest, knn = k-Nearest Neighbors, svc = Support Vector Classification, bnb = Naïve Bayesian, ada = AdaBoosted Decision Trees, DL = Deep Learning Architecture.