Allergenicity prediction of novel and modified proteins: Not a mission impossible! Development of a Random Forest allergenicity prediction model.

Alternative and sustainable protein sources (e.g., algae, duckweed, insects) are required to produce (future) foods. However, introduction of new food sources to the market requires a thorough risk assessment of nutritional, microbial and toxicological risks and potential allergic responses. Yet, the risk assessment of allergenic potential of novel proteins is challenging. Currently, guidance for genetically modified proteins relies on a weight-of-evidence approach. Current Codex (2009) and EFSA (2010; 2017) guidance indicates that sequence identity to known allergens is acceptable for predicting the cross-reactive potential of novel proteins and resistance to pepsin digestion and glycosylation status is used for evaluating de novo allergenicity potential. Other physicochemical and biochemical protein properties, however, are not used in the current weight-of-evidence approach. In this study, we have used the Random Forest algorithm for developing an in silico model that yields a prediction of the allergenic potential of a protein based on its physicochemical and biochemical properties. The final model contains twenty-nine variables, which were all calculated using the protein sequence by means of the ProtParam software and the PSIPred Protein Sequence Analysis program. Proteins were assigned as allergenic when present in the COMPARE database. Results show a robust model performance with a sensitivity, specificity and accuracy each greater than ≥85%. As the model only requires the protein sequence for calculations, it can be easily incorporated into the existing risk assessment approach. In conclusion, the model developed in this study improves the predictability of the allergenicity of new or modified food proteins, as demonstrated for insect proteins.

Plasma anandamide and other N-acylethanolamines are correlated with their corresponding free fatty acid levels under both fasting and non-fasting conditions in women.

N-acylethanolamines (NAEs), such as anandamide (AEA), are a group of endogenous lipids derived from a fatty acid linked to ethanolamine and have a wide range of biological activities, including regulation of metabolism and food intake. We hypothesized that i) NAE plasma levels are associated with levels of total free fatty acids (FFAs) and their precursor fatty acid in fasting and non-fasting conditions and ii) moderate alcohol consumption alters non-fasting NAE levels. In a fasting and non-fasting study we sampled blood for measurements of specific NAEs and FFAs. In the fasting study blood was drawn after an overnight fast in 22 postmenopausal women. In the non-fasting study blood was sampled before and frequently after a standardized lunch with beer or alcohol-free beer in 19 premenopausal women. Fasting AEA levels correlated with total FFAs (r = 0.84; p < 0.001) and arachidonic acid levels (r = 0.42; p < 0.05). Similar results were observed for other NAEs with both total FFAs and their corresponding fatty acid precursors. In addition, AEA (r = 0.66; p < 0.01) and OEA levels (r = 0.49; p <0.02) positively related with BMI. Changes over time in non-fasting AEA levels were correlated with changes in total FFA levels, both after a lunch with beer (r = 0.80; 95% confidence interval: 0.54-0.92) and alcohol-free beer (r = 0.73; 0.41-0.89). Comparable correlations were found for other NAEs, without differences in correlations of each NAE between beer and alcohol free beer with lunch. In conclusion, i) in fasting and non-fasting states circulating anandamide and other N-acylethanolamines were associated with free fatty acid levels and ii) moderate alcohol consumption does not affect non-fasting NAE levels. This suggests that similar physiological stimuli cause the release of plasma N-acylethanolamines and free fatty acids in blood. The trials are registered at ClinicalTrials.gov numbers: NCT00524550 and NCT00652405.