Development of a Predictive Multiple Reaction Monitoring (MRM) Model for High-Throughput ADME Analyses Using Learning-to-Rank (LTR) Techniques
Development of a Predictive Multiple Reaction Monitoring (MRM) Model for High-Throughput ADME Analyses Using Learning-to-Rank (LTR) Techniques
November 28, 2023.
Ramon Adalia, Shivani Patel, Anthony Paiva, Tierni Kaufman, Ismael Zamora, Xianmei Cai, Gemma Sanjuan, Wilson Z. Shou*
Abstract
Multiple Reaction Monitoring (MRM) is an important MS/MS technique commonly used in drug discovery and development, allowing for the selective and sensitive quantification of compounds in complex matrices. However, compound optimization can be resource intensive and requires experimental determination of product ions for each compound. In this study, we developed a Learning-to-Rank (LTR) model to predict the product ions directly from compound structures, eliminating the requirement for MRM optimization experiments. Experimentally determined MRM conditions for 5757 compounds were used to develop the model. Using the MassChemSite software, theoretical fragments and their mass-to-charge ratios were generated, which were then matched to the experimental product ions to create a data set. Each possible fragment was ranked based on its intensity in the experimental data. Different LTR models were built on a training split. Hyperparameter selection was performed using 5-fold cross validation. The models were evaluated using the Normalized Discounted Cumulative Gain at top k (NDCG@k) and the Coverage at top k (Coverage@k) metrics. Finally, the model was applied to predict MRM conditions for a prospective set of 235 compounds in high-throughput Caco-2 permeability and metabolic stability assays, and quantification results were compared to those obtained with experimentally acquired MRM conditions. The LTR model achieved a NDCG@5 of 0.732 and Coverage@5 of 0.841 on the validation split, and its predictions led to 97% of biologically equivalent results in the Caco-2 permeability and metabolic stability assays.
Tutorial_Lip_MSI_09
You must be logged in to access this content. Not yet registered? Create a new account
MARS: A Multipurpose Software for Untargeted LC–MS-Based Metabolomics and Exposomics
MARS: A Multipurpose Software for Untargeted LC–MS-Based Metabolomics and Exposomics
January 18, 2024.
Laura Goracci*, Paolo Tiberi, Stefano Di Bona, Stefano Bonciarelli, Giovanna Ilaria Passeri, Marta Piroddi, Simone Moretti, Claudia Volpi, Ismael Zamora and Gabriele Cruciani
Abstract
Untargeted metabolomics is a growing field, in which recent advances in high-resolution mass spectrometry coupled with liquid chromatography (LC-MS) have facilitated untargeted approaches as a result of improvements in sensitivity, mass accuracy, and resolving power. However, a very large amount of data are generated. Consequently, using computational tools is now mandatory for the in-depth analysis of untargeted metabolomics data. This article describes MetAbolomics ReSearch (MARS), an all-in-one vendor-agnostic graphical user interface-based software applying LC-MS analysis to untargeted metabolomics. All of the analytical steps are described (from instrument data conversion and processing to statistical analysis, annotation/identification, quantification, and preliminary biological interpretation), and tools developed to improve annotation accuracy (e.g., multiple adducts and in-source fragmentation detection, trends across samples, and the MS/MS validator) are highlighted. In addition, MARS allows in-house building of reference databases, to bypass the limits of freely available MS/MS spectra collections. Focusing on the flexibility of the software and its user-friendliness, which are two important features in multipurpose software, MARS could provide new perspectives in untargeted metabolomics data analysis.
MassChemSite for In-Depth Forced Degradation Analysis of PARP Inhibitors Olaparib, Rucaparib, and Niraparib
MassChemSite for In-Depth Forced Degradation Analysis of PARP Inhibitors Olaparib, Rucaparib, and Niraparib
February 2023
Abstract
Drugs must satisfy several protocols and tests before being approved for the market. Among them, forced degradation studies aim to evaluate drug stability under stressful conditions in order to predict the formation of harmful degradation products (DPs). Recent advances in LC-MS instrumentation have facilitated the structure elucidation of degradants, although a comprehensive data analysis still represents a bottle-neck due to the massive amount of data that can be easily generated. MassChemSite has been recently described as a promising informatics solution for LC-MS/MS and UV data analysis of forced degradation experiments and for the automated structural identification of DPs. Here, we applied MassChemSite to investigate the forced degradation of three poly(ADP-ribose) polymerase inhibitors (olaparib, rucaparib, and niraparib) under basic, acidic, neutral, and oxidative stress conditions. Samples were analyzed by UHPLC with online DAD coupled to high-resolution mass spectrometry. The kinetic evolution of the reactions and the influence of solvent on the degradation process were also assessed. Our investigation confirmed the formation of three DPs of olaparib and the wide degradation of the drug under the basic condition. Intriguingly, base-catalyzed hydrolysis of olaparib was greater when the content of aprotic-dipolar solvent in the mixture decreased. For the other two compounds, whose stability has been much less studied previously, six new degradants of rucaparib were identified under oxidative degradation, while niraparib emerged as stable under all stress conditions tested.