Incorporating Machine Learning in Computer-Aided Molecular Design for Fragrance Molecules

Abstract

The demand for new novel flavour and fragrance (F&F) molecules has boosted the need for a systematic approach to designing fragrance molecules. However, the F&F-related industry still relies heavily on experimental approaches or on existing databases without considering the consequences resulting from changes in concentration, which could omit potential fragrances. Computer-aided molecular design (CAMD) has great potential to identify novel molecular structures to be used as fragrances. Using CAMD for this purpose requires models to predict the olfaction properties of molecules. A rough set-based machine learning (RSML) approach is used to develop an interpretable predictive model for odour characteristics in this work. New rule-based models are generated from RSML based on the dilution and a number of different topological indices which identify the structure-odour relationship of fragrance molecules. The most prominent rules are selected and formulated as constraints in a CAMD optimisation model. The combination of several rules was able to increase the coverage of different classes of molecules. To model the performance indicators that vary over a range of properties, a disjunctive programming model is also incorporated into the CAMD framework. A case study demonstrates the utilisation of this methodology to design fragrance additives in dishwashing liquid. The results illustrate the capability of the novel RSML and CAMD framework to identify potential fragrance molecules that can be used in consumer products.