AI-assisted Cytochrome P450 Inhibition and Induction Prediction

Human cytochrome P450 (CYP) enzymes are membrane-bound hemoproteins that are essential for cellular metabolism, homeostasis, and drug detoxification. During the drug discovery, adverse side effects from CYP inhibition and induction of drug-drug interactions (DDI) are important considerations. In vitro experiments are time-consuming and have limited ability to provide data on structure-activity relationships for CYP inhibition/induction. Therefore, it is necessary to develop computational models that can predict the inhibitory effects of compounds on a specific CYP450 isoform. Numerous computer analyses that predict CYP inhibition or induction have recently been reported. Currently, the computational modeling approaches for CYP metabolism are classified as ligand and structure-based methods, such as molecular dynamics simulation, machine learning, docking, and quantitative structure-activity relationships analysis. Based on the advanced AI-assisted platform, Creative Biolabs can accurately predict the ADMET properties and help customers accelerate the drug screening process and reduce R&D costs.

A representative example of known CYP structures.Fig.1 A representative example of known CYP structures. (Zhao, et al., 2022)

Cytochrome P450 (CYP) in Drug Discovery

A new drug should not only have good pharmacological effects and be sufficiently safe, but it should also minimize the danger of DDIs because these interactions might negatively impact the efficacy of co-administered drugs. Many xenobiotics are metabolized in phase I by cytochrome P450 enzymes. Most CYP-related DDIs are caused by CYP inhibition or induction. The pharmaceutical industry is keen to detect potential DDI early because it can lead to serious adverse events, which can lead to poor patient health and drug development failure. The six major CYP isoforms, CYP1A2, CYP2B6, CYP2C9, CYP2C19, CYP2D6, and CYP3A4, metabolize more than 95% of approved drugs. Food and Drug Administration (FDA) guidelines require the evaluation of drugs for CYP inhibition or induction. Currently, the risk of DDI associated with the metabolism of candidate drug CYP is assessed experimentally by human liver microsomes or hepatocytes. To avoid or attenuate potential DDIs, many pharmaceutical companies conduct screening studies on new candidate drugs.

Computational Prediction of Cytochrome P450 Inhibition and Induction

In silico approaches are low-cost and have the ability to evaluate large numbers of compounds, which facilitates applications early in the drug discovery process. As a result, these approaches can be used to increase success rates and decrease the number of experimental studies in drug screening. They can also be used to make predictions about the behaviors of designed compounds that haven't yet been synthesized. Models that predict the inhibition of four typical CYP isoforms (CYP1A2, 2C9, 2D6, and 3A4) have been developed using a variety of ligand- and structure-based techniques employing molecular descriptors, protein structures, and pharmacophore features. Another reason for DDIs is CYP induction, which is triggered by an increase in CYP gene expression because of the binding of activated nuclear receptors. AhR, CAR, and PXR, mainly controlled the transcriptional regulation of CYP genes in the CYP1A, CYP2B, and CYP3A subfamilies. For AhR, CAR, and PXR, many in silico techniques utilizing the ligand- and structure-based approaches have been reported.

Machine learning-driven identification of drugs inhibiting cytochrome P450 2C9.Fig.2 Machine learning-driven identification of drugs inhibiting cytochrome P450 2C9. (Goldwaser, et al., 2022)

As a reliable partner to the world's leading pharmaceutical companies and research institutions, Creative Biolabs brings together the market-leading in silico expertise to build our AI-assisted platform that can provide custom professional cytochrome P450 inhibition and induction prediction.

References

  1. Zhao, M.; et al. Cytochrome P450 enzymes and drug metabolism in humans. International journal of molecular sciences. 2021, 22(23): 12808.
  2. Goldwaser, E.; et al. Machine learning-driven identification of drugs inhibiting cytochrome P450 2C9. PLoS computational biology. 2022, 18(1): e1009820.
For Research Use Only
Let's Get Started
Contact Us

USA
UK
Germany
Follow us on
Copyright © 2024 Creative Biolabs. All Rights Reserved.