Covering chemical diversity of genetically-modified tomatoes using metabolomics for objective substantial equivalence assessment

Abstract

As metabolomics can provide a biochemical snapshot of an organism's phenotype it is a promising approach for charting the unintended effects of genetic modification. A critical obstacle for this application is the inherently limited metabolomic coverage of any single analytical platform. We propose using multiple analytical platforms for the direct acquisition of an interpretable data set of estimable chemical diversity. As an example, we report an application of our multi-platform approach that assesses the substantial equivalence of tomatoes over-expressing the taste-modifying protein miraculin. In combination, the chosen platforms detected compounds that represent 86% of the estimated chemical diversity of the metabolites listed in the LycoCyc database. Following a proof-of-safety approach, we show that % had an acceptable range of variation while simultaneously indicating a reproducible transformation-related metabolic signature. We conclude that multi-platform metabolomics is an approach that is both sensitive and robust and that it constitutes a good starting point for characterizing genetically modified organisms.

Figure 1. A multi-platform metabolomics approach for evaluating SE.

(a) The first task is to quantify the evidence for a safe molecular composition. This is done by testing the null-hypothesis (), which states that the genetically modified organism (GMO) deviates more from the control line than a panel of traditional cultivars, against the alternative hypothesis of SE (). (b) The second task is to look for discriminative features [e.g. metabolite (met) A, met B and met C] between the transgenic line and the control to obtain an understanding of the consequences of the incurred effects. (c) The proposed work-flow. Samples are analyzed on three analytical platforms. The resulting data sets are summarized to consensus, non-redundant data sets with the help of the MetMask metabolite identifier management tool . The achieved coverage is evaluated by comparing the chemical properties of the detected metabolites with a reference metabolome in the literature. A proof-of-safety approach is used to quantify the evidence for safe metabolite levels; multivariate discrimination analysis is used to characterize the unintended effects.

Figure 2. Tomatoes grown on hydroponic culture (HC) solution.

(a) Visible phenotypes of the transgenic lines (56B and 7C), the control line Moneymaker, and five reference cultivars. The scale-bar represents 5 cm. (b) Miraculin protein accumulation in the two transgenic lines harvested in green and red stages. The protein levels were determined by enzyme-linked immunosorbent assay (ELISA). The horizontal lines in the boxes correspond to distribution quartiles.

Figure 3. Evaluation of the achieved coverage.

PCA was performed on the predicted physicochemical properties of the detected metabolites and the metabolites in the LycoCyc database. (a) The loading plots show that PC1 is dominated by size-related- and PC2 by solubility-related properties. (b) The score plots show that the distribution of the detected metabolites occupies a similar space as the reference metabolites. The inset barplot shows the ratio of variance among the reference metabolites covered by each of the individual platforms and the summarized data set. No small volatile molecules such as hydrogen cyanide (HCN) and ethyl aldehyde (EtO) or large secondary metabolites represented by the cluster of CoA ligates (x-CoA) were detected. Abbreviations: Log vapor pressure (LgPVap), octanol: water partitioning coefficient (LgP), octanol:water solubility distribution coefficient at pH 7.4 (LgD-7), biological concentration factor at pH 7.4 (BCF-7), adsorption coefficient at pH 7.4 (KOC), molecular volume (MVol), molecular refractivity (MR), molecular weight (MW), free rotating bonds (Rot), boiling temperature (Tb), flash point (Tf), enthalpy of vaporization (HVap), polar surface area (PArea), number of H-bond donors/acceptors (HDon/HAcc), surface tension (SrfTen), density (D), index of refraction (IoR).

Figure 4. Evaluating SE of miraculin over-expressing tomatoes grown on HC solution.

(a) Score scatter plot of PCA of the annotated metabolite profiles. Separation of the two ripening stages can be seen on PC1 and of the different cultivars on PC2. (b) Contribution to variance of the different experimental factors. Each peak was scaled to a total sum of squares (SS) of 100. Peaks above the 95th F-distribution percentile indicate significance at . Factors with separated observed- and F-distribution percentiles indicate the overall significance of that factor. (c) The ratio of peaks considered to indicate safety at a significance level of compared to the Moneymaker line. For comparison purposes, the test was applied to the transgenic lines and the traditional cultivars. (d) Parallel coordinates plot of the predictive components from the OPLS-DA model. Each biological sample is drawn as a line that connects its positions on each of the components. Each dimension describes a unique aspect of the genotype-correlated variance among the metabolite profiles. All genotypes except 7C and Moneymaker are separated on at least one axis. Percentages indicate the ratio of total variance explained by the corresponding dimension. (e) Result from Sammon's MDS of distances computed using the six predictive OPLS-DA components shown in (d). (f) Confusion matrix for predicting the genotype using the OPLS-DA model during five-fold cross-validation.

Figure 5. Focused OPLS-DA models for discriminating the Moneymaker (MM)- from the transgenic lines.

Percentages on the axes indicate the ratio between the explained and the total variance. The predictive components (56B and 7C) are correlated to the genotype; the components (56B and 7C) are orthogonal. (a–b) Score plot for the OPLS-DA model between 56B and MM using data from the soil experiment and (b) 7C and MM (b). (c) Correlation loading plots show the well-described peaks. The correlation indicates an overlap between the metabolites that are used to isolate 56B and 7C. The two models associate 4% and 6% of the variance to the genetic modification of 56B and 7C, respectively. (d–f) OPLS-DA models using the metabolite profiles of tomatoes grown on HC solution. (g) Overlap between the metabolites used to discriminate 7C and Moneymaker using metabolite profiles from soil and HC experiments. Asparagine (Asp) levels are lower in 7C than MM and the proline (Pro) levels are higher. Metabolite abbreviations are shown in Data S5 in File S2.