A Fragrance Prediction Model for Molecules Using Rough Set‐based Machine Learning. Issue 3 (2nd November 2022)

• Record Type: Journal Article
• Authors: Tiew, Shie Teck; Chew, Yick Eu; Lee, Ho Yan; Chong, Jia Wen; Tan, Raymond R.; Aviso, Kathleen B.; Chemmangattuvalappil, Nishanth G.
• Other Names: Asprion Norbert guestEditor.; Bardow André guestEditor.; Mairhofer Jonas guestEditor.; Schilling Johannes guestEditor.
• Is Part Of: Chemie Ingenieur Technik. Volume 95:Issue 3(2023)
• Page Start: 438
• Page End: 446
• Publication Date: 2022-11-02
• Subjects: Cheminformatics -- Fragrance prediction -- Molecular structural descriptors -- Rough set‐based machine learning; Chemical engineering -- Patents -- Periodicals; Chemical engineering -- Periodicals; Chemical industry -- Periodicals; Chemistry, Technical -- Periodicals; 660.05
• DOI: 10.1002/cite.202200093
• Languages: English
• ISSNs: 0009-286X

Abstract

Abstract: In this work, a novel machine learning based methodology was developed to predict fragrance from the molecular structure and the effect of the subjects attributes on odour perception. As fragrance is linked to the molecular structure and interactions, topological indices are used to develop a predictive model. Rough set‐based machine learning is used to generate rule‐based models that link the topology of fragrant molecules and dilution to their respective odour characteristics. The results show that the generated models are effective in determining the odour characteristic of molecules. Abstract : Fragrance is a desirable and often essential attribute in various consumer products. To predict fragrance attributes of molecules, a novel machine learning based methodology has been developed. Rough set‐based machine learning is used to link fragrance to molecular structure. The factors affect the perception of fragrance has also been analysed.