Automated Sample Preparation and Data Collection Workflow for High-Throughput In Vitro Metabolomics

Abstract

Regulatory bodies have started to recognise the value of in vitro screening and metabolomics as two types of new approach methodologies (NAMs) for chemical risk assessments, yet few high-throughput in vitro toxicometabolomics studies have been reported. A significant challenge is to implement automated sample preparation of the low biomass samples typically used for in vitro screening. Building on previous work, we have developed, characterised and demonstrated an automated sample preparation and analysis workflow for in vitro metabolomics of HepaRG cells in 96-well microplates using a Biomek i7 Hybrid Workstation (Beckman Coulter) and Orbitrap Elite (Thermo Scientific) high-resolution nanoelectrospray direct infusion mass spectrometry (nESI-DIMS), across polar metabolites and lipids. The experimental conditions evaluated included the day of metabolite extraction, order of extraction of samples in 96-well microplates, position of the 96-well microplate on the instrument's deck and well location within a microplate. By using the median relative standard deviation (mRSD (%)) of spectral features, we have demonstrated good repeatability of the workflow (final mRSD < 30%) with a low percentage of features outside the threshold applied for statistical analysis. To improve the quality of the automated workflow further, small method modifications were made and then applied to a large cohort study (4860 sample infusions across three nESI-DIMS assays), which confirmed very high repeatability of the whole workflow from cell culturing to metabolite measurements, whilst providing a significant improvement in sample throughput. It is envisioned that the automated in vitro metabolomics workflow will help to advance the application of metabolomics (as a part of NAMs) in chemical safety, primarily as an approach for high throughput screening and prioritisation.

Keywords: automation; direct infusion mass spectrometry; high-throughput screening; in vitro metabolomics; sample preparation.

Figure 1

Results presented for all three nESI-DIMS assays (polar positive, polar negative and lipid positive) with 96-well microplates, labelled as “test plates” or “TP”, indicating the order of their extraction (1–3) and position on the instrument’s deck (a-b) following normalisation (termed “After PQN”), and filtering of variable features (termed “After RSD filter”). For each 96-well microplate, median relative standard deviation (mRSD (%)) of spectral feature intensities was calculated before and after the RSD filtering (i.e., removal) of spectral features for which the feature RSDs exceeded 30% in intrastudy QC samples.

Figure 2

Percentage of metabolic features which were found “not repeatable” across studied experimental conditions measured for polar metabolites (both ionisation modes) and lipids (positive ionisation mode only). The order of extraction of 96-well microplates contributed most significantly to observed differences in feature intensities between the microplates, which triggered a modification of the proposed workflow.

Figure 3

mRSD (%) of spectral feature intensities using control samples at 24 h from the high-throughput metabolomics study (a) before and (b) after RSD filtering for HepaRG control samples: n = 3 biological control replicates (here defined as replicates prepared across multiple weeks of cell culture), each measured as n = 9 technical replicates (here defined as replicates wells of cells cultured within the same test 96-well microplate).

Figure 4

Assessment of (a) sensitivity and (b) workflow repeatability from the high-throughput metabolomics study by employing biological feature count and the intensity of putatively annotated features of the internal standards across 3 nESI-DIMS assays. Sensitivity and repeatability in intrastudy QC samples were determined on the whole dataset (ca. 1620 samples), whilst repeatability in biological samples employed a subset dataset comprising of control (unexposed) samples at 24 h (bottom right bar chart).

Figure 5

An overview of the experimental design for assessing the automated sample preparation workflow for in vitro metabolomics. Extraction blanks and intrastudy QC samples were prepared on day 1 of the experiment, whilst biological control samples were prepared on days 2 and 3. Conditions tested included the location of a 96-well microplate (containing frozen cells for extraction) on the instrument’s deck (indicated as “a” or “b”), day and order of metabolite extraction as well as the location of samples within a microplate (edge vs. centre).