Comparison of species classification models of mass spectrometry data: Kernel Discriminant Analysis vs Random Forest; A case study of Afrormosia (Pericopsis elata (Harms) Meeuwen)

Abstract

Rationale:The genus Pericopsis includes four species of which only Pericopsis elata (Harms) Meeuwen is of commercial interest. Enforcement officers might have difficulties discerning this CITES-listed species (Appendix II) from some other tropical African timber species. Therefore, we tested several methods to separate and identify these species rapidly in order to enable customs to uncover illegal trade. In this study, two classification methods using DART TOFMS data to discern between several species are presented. Methods:Metabolome profiles were collected using DART TOFMS analysis of heartwood specimens of all four Pericopsis species, Haplormosia monophylla (Harms) Harms, Dalbergia melanoxylon Guill. & Perr. Harms, and Milicia excelsa (Welw.) C.C.Berg. In total, 95 specimens were analysed and the spectra evaluated. The species were chosen based on their importance in CITES, belonging to the same genus, and wood morphological resemblance. Kernel Discriminant Analysis (KDA) and Random Forest classification were used to discern the species. Results:DART TOFMS spectra obtained from wood slivers and post-processing analysis using KDA and Random Forest classification separated Pericopsis elata from the other Pericopsis taxa and its lookalike timbers Haplormosia monophylla, Milicia excelsa, and Dalbergia melanoxylon. Only 50 ions were needed to achieve the highest accuracy. Conclusions:DART TOFMS spectra of the taxa were reproducible and the results of the chemometric analysis provided comparable accuracy. Haplormosia monophylla was visually distinguished based on the heatmap and was excluded from further analysis. Both classification methods, KDA and Random Forest, were capable of distinguishing Pericopsis elata from the other Pericopsis taxa, Milicia excelsa, and Dalbergia melanoxylon, timbers commonly traded.

Volatile compounds profiling by using proton transfer reaction‐time of flight‐mass spectrometry (PTR‐ToF‐MS). The case study of dark chocolates organoleptic differences

“…Thus, direct analysis in real time has been recently used to classify tree species. 38 Extractive electrospray ionization and secondary electrospray ionization have demonstrated some potentialities. 39,40 Ambient mass spectrometry techniques and their applications were reviewed.…”

“…It is out of the scope of this article to be exhaustive, but it is worthwhile citing ambient mass spectrometry techniques that found applications in VOC profiling. Thus, direct analysis in real time has been recently used to classify tree species . Extractive electrospray ionization and secondary electrospray ionization have demonstrated some potentialities .…”

Chemical differentiation of Bolivian Cedrela species as a tool to trace illegal timber trade

“…Chemical analysis tools, such as mass spectrometry (Fidelis et al, 2012), near-infrared spectroscopy (Braga et al, 2011;Bergo et al, 2016), and stable isotopes (Kagawa and Leavitt, 2010;Förstel et al, 2011;Vlam et al, 2018), can be used to discriminate species and verify the geographical origin of traded timber. For example, previous studies used a specific mass spectrometer to discriminate species that cannot be identified based on wood anatomy in the Americas (Espinoza et al, 2015), Africa (Deklerck et al, 2017), andAsia (McClure et al, 2015). In this study, we focus on chemical characterization by Direct Analysis in Real Time (DART) coupled with Time-of-Flight Mass Spectrometry (TOFMS).…”

Identification of rhinoceros keratin using direct analysis in real time time‐of‐flight mass spectrometry and multivariate statistical analysis

“…Here we evaluate the use of DART‐TOFMS for determining the taxonomic source of keratin tissue. DART‐TOFMS has been successful in the identification of solid wood samples to determine species source . This ambient ionization technique allows for exact mass measurements of ions from a solid matrix without the need to modify or derivatize the sample.…”

“…DART-TOFMS has been successful in the identification of solid wood samples to determine species source. [21][22][23] This ambient ionization technique allows for exact mass measurements of ions from a solid matrix without the need to modify or derivatize the sample. Sample preparation is simple, requiring only a sliver of sample for analysis, which results in minimal destruction to the original item.…”