CYPstrate: A Set of Machine Learning Models for the Accurate Classification of Cytochrome P450 Enzyme Substrates and Non-Substrates.

Malte Holmer,Christina De Bruyn Kops,Johannes Kirchmair,Conrad Stork

doi:10.3390/molecules26154678

Abstract

The interaction of small organic molecules such as drugs, agrochemicals, and cosmetics with cytochrome P450 enzymes (CYPs) can lead to substantial changes in the bioavailability of active substances and hence consequences with respect to pharmacological efficacy and toxicity. Therefore, efficient means of predicting the interactions of small organic molecules with CYPs are of high importance to a host of different industries. In this work, we present a new set of machine learning models for the classification of xenobiotics into substrates and non-substrates of nine human CYP isozymes: CYPs 1A2, 2A6, 2B6, 2C8, 2C9, 2C19, 2D6, 2E1, and 3A4. The models are trained on an extended, high-quality collection of known substrates and non-substrates and have been subjected to thorough validation. Our results show that the models yield competitive performance and are favorable for the detection of CYP substrates. In particular, a new consensus model reached high performance, with Matthews correlation coefficients (MCCs) between 0.45 (CYP2C8) and 0.85 (CYP3A4), although at the cost of coverage. The best models presented in this work are accessible free of charge via the “CYPstrate” module of the New E-Resource for Drug Discovery (NERDD).

Highlights

The cytochrome P450 (CYP) family of enzymes metabolizes a wide range of xenobiotics
We present a new set of machine learning models for the classification of substrates and non-substrates for the nine above-mentioned human CYP isozymes
For the purpose of model development, a core data set consisting of 1831 compounds, both substrates and non-substrates, of nine human CYPs (1A2, 2A6, 2B6, 2C8, 2C9, 2C19, 2D6, 2E1, and 3A4) was compiled from the works of Tian et al [15] and Hunt et al [13]

Summary

Introduction

The cytochrome P450 (CYP) family of enzymes metabolizes a wide range of xenobiotics. In particular CYPs 1A2, 2A6, 2B6, 2C8, 2C9, 2C19, 2D6, 3A4, and 2E1 are of relevance to the metabolism of drugs [1], natural products, agrochemicals, and cosmetics [2,3,4]. The ability to predict the metabolic fate of small organic molecules is of high importance to a host of different industries [5]. Cell-based, and analytical methods allow the determination of metabolism at an unprecedented level of detail, but they require significant resources, expertise, and time. In particular machine learning methods [6,7,8,9] have seen significant progress and are increasingly becoming recognized as an important pillar of xenobiotic metabolism prediction

Methods

Results

Conclusion