DEEPCYPs: A deep learning platform for enhanced cytochrome P450 activity prediction

Abstract

Cytochrome P450 (CYP) is a superfamily of heme-containing oxidizing enzymes involved in the metabolism of a wide range of medicines, xenobiotics, and endogenous compounds. Five of the CYPs (1A2, 2C9, 2C19, 2D6, and 3A4) are responsible for metabolizing the vast majority of approved drugs. Adverse drug-drug interactions, many of which are mediated by CYPs, are one of the important causes for the premature termination of drug development and drug withdrawal from the market. In this work, we reported in silicon classification models to predict the inhibitory activity of molecules against these five CYP isoforms using our recently developed FP-GNN deep learning method. The evaluation results showed that, to the best of our knowledge, the multi-task FP-GNN model achieved the best predictive performance with the highest average AUC (0.905), F1 (0.779), BA (0.819), and MCC (0.647) values for the test sets, even compared to advanced machine learning, deep learning, and existing models. Y-scrambling testing confirmed that the results of the multi-task FP-GNN model were not attributed to chance correlation. Furthermore, the interpretability of the multi-task FP-GNN model enables the discovery of critical structural fragments associated with CYPs inhibition. Finally, an online webserver called DEEPCYPs and its local version software were created based on the optimal multi-task FP-GNN model to detect whether compounds bear potential inhibitory activity against CYPs, thereby promoting the prediction of drug-drug interactions in clinical practice and could be used to rule out inappropriate compounds in the early stages of drug discovery and/or identify new CYPs inhibitors.

Keywords: CYPs inhibitors; cytochrome P450; deep learning; multi-task FP-GNN; online webserver.

FIGURE 1

Model construction pipeline.

FIGURE 2

The data occupation distribution for the five isoforms in the CYPs modelling datasets.

FIGURE 3

The distribution of molecular chemical space of CYP1A2 (A), CYP2C9 (B), CYP2C19 (C), CYP2D6 (D), and CYP3A4 (E). LogP (X-axis) and molecular weight (MW, Y-axis) were used to define chemical space. RDKit software was used to calculate MW and LogP.

FIGURE 4

The Bemis Murcko scaffold analysis of CYP1A2 (orange), CYP2C19 (green), CYP2C9 (purple), CYP2D6 (yellow), and CYP3A4 (blue) inhibitors. The five CYPs isoforms (X-axis) and the fraction of scaffolds in the modeling datasets (scaffolds/compounds (%), Y-axis) were used to determine structural diversity.

FIGURE 5

The importance of molecular structures during the prediction process of the GNN module of the multi-task FP-GNN model on the CYPs dataset. The darker the color, the more important are for the structures. (A) Represents an active molecule on the five isoforms. (B) Represents an inactive molecule on the five isoforms.

FIGURE 6

(A) Represents the bioactivity prediction diagram of the DEEPCYPs. (B) Represents a case result display of the model applicability domain module of the DEEPCYPs. The chemical structure of thiabendazole is used as an example.