Classification of the aroma quality of pyrazine derivatives using Random Forest Tree technique

Khaled Saadi (1) , Mourad Korichi (1) , Vincent Gerbaud (2) , Thierry Talou (3) , Pascal Floquet (2)

1 Université Kasdi Merbah Ouargla
2 LGC - Laboratoire de Génie Chimique
3 CAI - Chimie Agro-Industrielle

We present an alternative classification of the odor molecules based on 0D, 1D, 2D, and 3D molecular descriptors by using the Random Forest Tree (RFT). Ninety eight molecules of pyrazine derivatives are classified among three classes of aroma notes: Green, Nutty, and Bell-Pepper. The classification model uses 180, 40, 45, and 50 trees in the forest respectively for the 0D, 1D, 2D, and 3D descriptors. The use of descriptors 0D, 1D, 2D, and 3D correctly classify 72.1%, 70.6%, 82.4%, and 85.3% of the molecules during the learning phase. For the test phase, the classification rate is 80%, 86.7%, 93.3%, and 90%. This shows that RFT is able to develop the molecular Structure–Odor relationship.

Mots clés: Random forest tree; Pyrazine

Mots clés: Odour; Molecular descriptors; QSAR

Domaines: Ingénierie des aliments; Génie des procédés

Khaled Saadi, Mourad Korichi, Vincent Gerbaud, Thierry Talou, Pascal Floquet. Classification of the aroma quality of pyrazine derivatives using Random Forest Tree technique. 13. Weurman Flavour Research Symposium, Sep 2011, Saragosse, Spain. 742 p., ⟨10.1016/B978-0-12-398549-1.00092-1⟩. ⟨hal-02741604⟩