Predicting odorant chemical class from odorant descriptor values with an assembly of multi-layer perceptrons

Chemical descriptors are a way to define information concerning the physical, chemical and biological properties of a chemical compound. Machine learning methods such as the Artificial Neural Network (ANN) can be used to learn and predict such compounds by training on the compounds chemical descriptors. The motivation of our work is to predict odorant molecules for the development of an artificial biosensor. In this work, we demonstrate using a set of 32 optimized odorant descriptors how an assembly of MultiLayer Perceptrons (MLPs) can be successfully trained to differentiate among eight different chemical classes of odorant. In this communication, we demonstrate how it is possible to predict all 15/15 vectors from an unseen validation set with a high average prediction accuracy of 88.5% for the validation vectors. Furthermore, an introduction of a 10% noise injection level to the training set, increased the learning rate significantly as well as improve the average prediction accuracy of the MLPs to 92% for the validating vectors. Thus, this work indicates the promise of using odorant descriptor values to accurately predict chemical class and so move us forward to the realisation of an artificial odorant biosensor.