A novel method to analyse DART TOFMS spectra based on Convolutional Neural Networks: A case study on methanol extracts of wool fibres from endangered camelids

Monitoring the illegal trade of wool fibres wild vicuña (Vicugna vicugna) and guanaco (Lama guanicoe) is highly desirable. The high market value fleece from these camelid species poses a threat to their populations. A previous study showed that direct analysis in real time time-of-flight mass spectrometry (DART-TOFMS) effectively identifies species. Producing high-resolution data short period makes DART-TOFMS reliable identification tool, even though can still be improved. present proposes novel analysing pipeline based on Convolutional Neural Networks (CNN), applicable any kind DART-TOF MS data. We tested our proposed method keratin four vicugna: n = 19; Vicugna pacos: 20; Lama guanicoe: 20, glama: 20). Analyses selecting 512 ions with highest relative intensity provides best resolution yields 100% accuracy for identification.