Using artificial neural networks to classify unknown volatile chemicals from the firings of insect olfactory sensory neurons

Abstract

The olfactory system detects volatile chemical compounds, known as odour molecules or odorants. Such odorants have a diverse chemical structure which in turn interact with the receptors of the olfactory system. The insect olfactory system provides a unique opportunity to directly measure the firing rates that are generated by the individual olfactory sensory neurons (OSNs) which have been stimulated by odorants in order to use this data to inform their classification. In this work, we demonstrate that it is possible to use the firing rates from an array of OSNs of the vinegar fly, Drosophila melanogaster, to train an Artificial Neural Network (ANN), as a series of a Multi-Layer Perceptrons (MLPs), to differentiate between eight distinct chemical classes. We demonstrate that the MLPs when trained on 108 odorants, for both clean and 10% noise injected data, can reliably identify 87% of an unseen validation set of chemicals using noise injection. In addition, the noise injected MLPs provide a more accurate level of identification. This demonstrates that a 10% noise injected series of MLPs provides a robust method for classifying chemicals from the firing rates of OSNs and paves the way to a future realisation of an artificial olfactory biosensor.

Application of artificial neural networks on mosquito Olfactory Receptor Neurons for an olfactory biosensor

“…Furthermore, the effectiveness of implementing bootstrapping is seen when comparing previous works which did not utilize bootstrapping [17,19]. By effectively removing the outliers, bootstrapping of the odorant data has given a more representative approximation of the network performance.…”

“…However, an Artificial Neural Network (ANN) is employed for the analysis in this work. In our previous work, we have investigated odorant classification using ANNs on the firing rates of the Drosophila Melanogaster olfactory receptors [17,18] and on chemical descriptor values [19].…”

“…We employed an array of single-output MLPs in parallel as depicted in Fig. 2, called the Hybrid network system [17,19,25], which allowed the system to capture more of the complex relationships present in the data. This hybrid system consisted of nine MLPs, where each MLP corresponded to a unique chemical class of the odorant data.…”

Artificial Neural Network prediction of specific VOCs and blended VOCs for various concentrations from the olfactory receptor firing rates of Drosophila melanogaster

“…The Artificial Neural Network (ANN) architecture employed in this work was a feed forward Multi-Layer Perceptron (MLP) with binary sigmoidal activation functions [6][7][8][9]. Thorough rigorous initial experiments, we determined that a double hidden layer MLP with 75 neurons in the first hidden layer, 5 neurons in the second hidden layer and a single neuron in the output layer provided optimum network output.…”

“…In our previous work, we have successfully employed the ANN architecture of Multi-Layer Perceptrons (MLPs) for analyzing D. melanogaster odorant receptors (DmOr) [6,7] and Anopheles gambiae mosquito odorant receptors (AgOr) [8] firing rate responses, and chemical descriptor values [9], to classify odorants into their chemical classes, e.g. Alcohol, Ester or Terpene.…”