Relationship among subjective responses, flavor, and chemical composition across more than 800 commercial cannabis varieties

DE LA FUENTE, ALETHIA; ZAMBERLAN, FEDERICO; SÁNCHEZ FERRÁN, ANDRÉS; CARRILLO, FACUNDO; TAGLIAZUCCHI, ENZO; PALLAVICINI, CARLA

Journal of Cannabis Research

BMC

Año: 2020 vol. 2

Background: Widespread commercialization of cannabis has led to the introduction of brand names based onusers? subjective experience of psychological effects and flavors, but this process has occurred in the absence ofagreed standards. The objective of this work was to leverage information extracted from large databases toevaluate the consistency and validity of these subjective reports, and to determine their correlation with thereported cultivars and with estimates of their chemical composition (delta-9-THC, CBD, terpenes).Methods: We analyzed a large publicly available dataset extracted from Leafly.com where users freely reportedtheir experiences with cannabis cultivars, including different subjective effects and flavour associations. This analysiswas complemented with information on the chemical composition of a subset of the cultivars extracted fromPsilabs.org. The structure of this dataset was investigated using network analysis applied to the pairwise similaritiesbetween reported subjective effects and/or chemical compositions. Random forest classifiers were used to evaluatewhether reports of flavours and subjective effects could identify the labelled species cultivar. We applied NaturalLanguage Processing (NLP) tools to free narratives written by the users to validate the subjective effect and flavourtags. Finally, we explored the relationship between terpenoid content, cannabinoid composition and subjectivereports in a subset of the cultivars.Results: Machine learning classifiers distinguished between species tags given by ?Cannabis sativa? and ?Cannabisindica? based on the reported flavours: = 0.828 ± 0.002 (p < 0.001); and effects: = 0.9965 ± 0.0002 (p