Abstract
Metabolism of xenobiotics (Greek xenos: exogenous substances) plays an essential role in the prediction of biological activity and testing for the subsequent research and development of new drug candidates. Integration of various methods and techniques using different computational and experimental approaches is one of the keys to a successful metabolism prediction. While multiple structure-based and ligand-based approaches to metabolism prediction exist, the most important problem arises at the first stage of metabolism prediction: detection of the sites of metabolism (SOMs). In this paper, we describe the application of Quantitative Neighborhoods of Atoms (QNA) descriptors for prediction of the SOMs using potential function method, as well as several different machine learning techniques: naïve Bayes, random forest classifier, multilayer perceptron with back propagation and convolutional neural networks, and deep neural networks.
Highlights
The prediction of the sites of metabolism (SOMs) for the cytochrome P450 family enzymes plays a pivotal role in drug discovery, as it is possible to generate the chemical structures of metabolites
The collected modeling sets contained the structural formulae of the ligands of the main cytochrome P450 isoforms that metabolize small molecules: CYP1A2, CYP2C9, CYP2C19, CYP2D6, and CYP3A4
A new approach based on quantitative neighborhoods of atoms (QNA) descriptors using machine learning methods was presented
Summary
The prediction of the sites of metabolism (SOMs) for the cytochrome P450 family enzymes (in particular, CYP1A2, CYP2C9, CYP2C19, CYP2D6, and CYP3A4 isoforms) plays a pivotal role in drug discovery, as it is possible to generate the chemical structures of metabolites. Prediction of the biological activities of potential metabolites for the design of prodrugs. There are many experimental and computational approaches to SOM prediction [1,2,3,4,5]. When the three-dimensional structure of the target protein is unknown or has low resolution, the application of a structure-based computational approach might be practically impossible [3]. Another limitation of the structure-based design is a variety of ligand-enzyme conformations appearing in the computer-based models, which makes it very difficult to predict several SOMs in one molecule correctly
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
