SMITER-A Python Library for the Simulation of LC-MS/MS Experiments

A supervised machine-learning approach for the efficient development of a multi method (LC-MS) for a large number of drugs and subsets thereof: focus on oral antitumor agents

OBJECTIVES

Accumulating evidence argues for a more widespread use of therapeutic drug monitoring (TDM) to support individualized medicine, especially for therapies where toxicity and efficacy are critical issues, such as in oncology. However, development of TDM assays struggles to keep pace with the rapid introduction of new drugs. Therefore, novel approaches for faster assay development are needed that also allow effortless inclusion of newly approved drugs as well as customization to smaller subsets if scientific or clinical situations require.

METHODS

We applied and evaluated two machine-learning approaches i.e., a regression-based approach and an artificial neural network (ANN) to retention time (RT) prediction for efficient development of a liquid chromatography mass spectrometry (LC-MS) method quantifying 73 oral antitumor drugs (OADs) and five active metabolites. Individual steps included training, evaluation, comparison, and application of the superior approach to RT prediction, followed by stipulation of the optimal gradient.

RESULTS

Both approaches showed excellent results for RT prediction (mean difference ± standard deviation: 2.08 % ± 9.44 % ANN; 1.78 % ± 1.93 % regression-based approach). Using the regression-based approach, the optimum gradient (4.91 % MeOH/min) was predicted with a total run time of 17.92 min. The associated method was fully validated following FDA and EMA guidelines. Exemplary modification and application of the regression-based approach to a subset of 14 uro-oncological agents resulted in a considerably shortened run time of 9.29 min.

CONCLUSIONS

Using a regression-based approach, a multi drug LC-MS assay for RT prediction was efficiently developed, which can be easily expanded to newly approved OADs and customized to smaller subsets if required.

Insight on physicochemical properties governing peptide MS1 response in HPLC-ESI-MS/MS: A deep learning approach

Accurate and absolute quantification of peptides in complex mixtures using quantitative mass spectrometry (MS)-based methods requires foreground knowledge and isotopically labeled standards, thereby increasing analytical expenses, time consumption, and labor, thus limiting the number of peptides that can be accurately quantified. This originates from differential ionization efficiency between peptides and thus, understanding the physicochemical properties that influence the ionization and response in MS analysis is essential for developing less restrictive label-free quantitative methods. Here, we used equimolar peptide pool repository data to develop a deep learning model capable of identifying amino acids influencing the MS1 response. By using an encoder-decoder with an attention mechanism and correlating attention weights with amino acid physicochemical properties, we obtain insight on properties governing the peptide-level MS1 response within the datasets. While the problem cannot be described by one single set of amino acids and properties, distinct patterns were reproducibly obtained. Properties are grouped in three main categories related to peptide hydrophobicity, charge, and structural propensities. Moreover, our model can predict MS1 intensity output under defined conditions based solely on peptide sequence input. Using a refined training dataset, the model predicted log-transformed peptide MS1 intensities with an average error of 9.7 ± 0.5% based on 5-fold cross validation, and outperformed random forest and ridge regression models on both log-transformed and real scale data. This work demonstrates how deep learning can facilitate identification of physicochemical properties influencing peptide MS1 responses, but also illustrates how sequence-based response prediction and label-free peptide-level quantification may impact future workflows within quantitative proteomics.

Toward an Integrated Machine Learning Model of a Proteomics Experiment

In recent years machine learning has made extensive progress in modeling many aspects of mass spectrometry data. We brought together proteomics data generators, repository managers, and machine learning experts in a workshop with the goals to evaluate and explore machine learning applications for realistic modeling of data from multidimensional mass spectrometry-based proteomics analysis of any sample or organism. Following this sample-to-data roadmap helped identify knowledge gaps and define needs. Being able to generate bespoke and realistic synthetic data has legitimate and important uses in system suitability, method development, and algorithm benchmarking, while also posing critical ethical questions. The interdisciplinary nature of the workshop informed discussions of what is currently possible and future opportunities and challenges. In the following perspective we summarize these discussions in the hope of conveying our excitement about the potential of machine learning in proteomics and to inspire future research.

Simulation of mass spectrometry-based proteomics data with Synthedia

Motivation

A large number of experimental and bioinformatic parameters must be set to identify and quantify peptides in mass spectrometry experiments and each of these will impact the results. An ability to simulate raw data with known contents would allow researchers to rapidly explore the effects of varying experimental parameters and systematically investigate downstream processing software. A range of data simulators are available for established data-dependent acquisition methodologies, but these do not extend to the rapidly developing field of data-independent acquisition (DIA) strategies.

Results

Here, we present Synthedia-a software package to simulate DIA liquid chromatography-mass spectrometry for bottom-up proteomics experiments. Synthedia can generate datasets with known peptide precursor ions and fragments and allows for the customization of a wide variety of chromatographic and mass spectrometry parameters.

Availability and implementation

Synthedia is freely available via the internet and can be used through a graphical website (https://synthedia.org/) or locally via the command line (https://github.com/mgleeming/synthedia/).

Supplementary information

Supplementary data are available at Bioinformatics Advances online.

Normalizing and Correcting Variable and Complex LC-MS Metabolomic Data with the R Package pseudoDrift

In biological research domains, liquid chromatography-mass spectroscopy (LC-MS) has prevailed as the preferred technique for generating high quality metabolomic data. However, even with advanced instrumentation and established data acquisition protocols, technical errors are still routinely encountered and can pose a significant challenge to unveiling biologically relevant information. In large-scale studies, signal drift and batch effects are how technical errors are most commonly manifested. We developed pseudoDrift, an R package with capabilities for data simulation and outlier detection, and a new training and testing approach that is implemented to capture and to optionally correct for technical errors in LC-MS metabolomic data. Using data simulation, we demonstrate here that our approach performs equally as well as existing methods and offers increased flexibility to the researcher. As part of our study, we generated a targeted LC-MS dataset that profiled 33 phenolic compounds from seedling stem tissue in 602 genetically diverse non-transgenic maize inbred lines. This dataset provides a unique opportunity to investigate the dynamics of specialized metabolism in plants.