Use of random forest methodology to link aroma profiles to volatile compounds: application to enzymatic hydrolysis of Atlantic salmon (Salmo salar) by-products combined with Maillard reactions

Type Article
Date 2020-08
Language English
Author(s) Cardinal MireilleORCID1, Chaussy Marianne1, Donnay-Moreno Claire1, Cornet Josiane1, Rannou Cecile2, Fillonneau Catherine2, Prost Carole2, Baron RegisORCID1, Courcoux Philippe3, 4
Affiliation(s) 1 : Ifremer, laboratoire EM3B, rue de l’île d’Yeu, 44311 Nantes Cedex, France
2 : Oniris, UMR CNRS 6144 GEPEA, groupe Flaveur, Nantes, France
3 : Oniris, StatSC, rue de la Géraudière, 44322 Nantes, France
4 : INRA USC 1381, 44322 Nantes, France
Source Food Research International (0963-9969) (Elsevier BV), 2020-08 , Vol. 134 , P. 109254 (11p.)
DOI 10.1016/j.foodres.2020.109254
WOS© Times Cited 5
Keyword(s) Sensory characteristics, Volatile compounds, HS-SPME/GC-MS, Regression tree, Random forest, Hydrolysate, Maillard reactions
Abstract

To use salmon protein hydrolysates as food ingredients and to mask the fish odor, Maillard reactions were associated with enzymatic production of hydrolysates. The study explored an original approach based on regression trees (RT) and random forest (RF) methodologies to predict hydrolysate odor profiles from volatile compounds. An experimental design with four factors: enzyme/substrate ratio, quantity of xylose, hydrolysis and cooking times was used to create a range of enzymatic hydrolysates. Twenty samples were submitted to a trained panel for sensory descriptions of odor. Hydrolysate volatile compounds were extracted by means of Headspace Solid Phase MicroExtraction (HS-SPME) and analyzed using gas chromatography/mass spectrometry (GC-MS). The results showed that RT and RF methodologies can be useful tools for predicting an entire sensory profile from volatile compounds. Four main volatile compounds made it possible to separate hydrolysates into five groups according to their specific sensory profile. 2,5-dimethylpyrazine, 1-hydroxy-2-propanone and 3-hydroxy-2-pentanone were identified as the main predictors of the roasted odor, whereas methanethiol was associated with a mud odor. These results also suggest the appropriate process conditions for obtaining a typical roasted odor.

Full Text
File Pages Size Access
Author's final draft 40 865 KB Open access
11 931 KB Access on demand
Top of the page

How to cite 

Cardinal Mireille, Chaussy Marianne, Donnay-Moreno Claire, Cornet Josiane, Rannou Cecile, Fillonneau Catherine, Prost Carole, Baron Regis, Courcoux Philippe (2020). Use of random forest methodology to link aroma profiles to volatile compounds: application to enzymatic hydrolysis of Atlantic salmon (Salmo salar) by-products combined with Maillard reactions. Food Research International, 134, 109254 (11p.). Publisher's official version : https://doi.org/10.1016/j.foodres.2020.109254 , Open Access version : https://archimer.ifremer.fr/doc/00624/73590/