Processing and classification of chemical data inspired by insect olfaction

Abstract

The chemical sense of insects has evolved to encode and classify odorants. Thus, the neural circuits in their olfactory system are likely to implement an efficient method for coding, processing, and classifying chemical information. Here, we describe a computational method to process molecular representations and classify molecules. The three-step approach mimics neurocomputational principles observed in olfactory systems. In the first step, the original stimulus space is sampled by ''virtual receptors,'' which are chemotopically arranged by a self-organizing map. In the second step, the signals from the virtual receptors are decorrelated via correlation-based lateral inhibition. Finally, in the third step, olfactory scent perception is modeled by a machine learning classifier. We found that signal decorrelation during the second stage significantly increases the accuracy of odorant classification. Moreover, our results suggest that the proposed signal transform is capable of dimensionality reduction and is more robust against overdetermined representations than principal component scores. Our olfaction-inspired method was successfully applied to predicting bioactivities of pharmaceutically active compounds with high accuracy. It represents a way to efficiently connect chemical structure with biological activity space.bioinformatics ͉ chemical biology ͉ computational model ͉ decorrelation ͉ olfactory coding T he mechanisms that enable olfactory discrimination are remarkably similar across species and even phyla (1, 2), and several principles of organization have been observed in insects and vertebrates. One such principle is that each primary olfactory sensory neuron (OSN) specifically expresses one type of olfactory receptor (OR), as has been demonstrated, e.g., in mice (3, 4) and in Drosophila (5, 6), although exceptions to this rule exist (7,8). ORs represent the largest family of seventransmembrane G protein-coupled receptors (9-12). Several studies addressed structure-activity relationships (SARs) of . A general observation is that one odorant typically activates a number of different ORs, and each OR has rather broad ligand selectivity. Investigation of Drosophila OR neurons (20) also indicated that each receptor preferably responds to a specific combination of chemical features; that is, each receptor samples a specific region of ''chemical space. '' Another characteristic of olfactory systems is that OSNs expressing a specific OR make synaptic contacts with a defined subset of second-order neurons in downstream neural populations, namely the olfactory bulb of vertebrates (21) or the antennal lobe of insects (22,23). These connections are formed in spatially discrete areas, the glomeruli. It has long been speculated, and in part also shown, that glomeruli are chemotopically ordered, such that neighboring glomeruli receive input from OSNs that prefer ligands with similar chemical characteristics (5,(24)(25)(26)(27). There is some evidence that the spatial distance of glomeruli in the olfactory bulb is re...

Olfactory Information Processing in theDrosophilaAntennal Lobe: Anything Goes?

“…We recently found that interglomerular interactions increase when more odors are mixed (Silbering and Galizia, 2007). The lack of narrowing effects in the present study might therefore be related to the stimulation with monomolecular odors, which activate fewer glomeruli altogether and thus might require less interglomerular inhibition for efficient coding (Schmuker and Schneider, 2007). Alternatively, our finding might reflect a genuine difference between flies and bees, since response-narrowing occurs even with monomolecular odors in bees (Sachse and Galizia, 2003).…”

Pattern orthogonalization via channel decorrelation by adaptive networks

“…The adapted connectivity can then not be given explicitly in terms of the input correlations SS t . Rather than determining the adapted connectivity by a numerical optimization procedure we investigate the performance of the connectivity (27) and how it is affected by the rectifying nonlinearity.…”

Predicting voluntary movements from motor cortical activity with neuromorphic hardware

“…This so-called lateral inhibition reduces input correlation and thereby improves classification performance [33], [36]. In the association layer there are two excitatory association neuron (ANe) populations that receive input from the projection neurons via plastic synapses.…”

“…functional groups of neurons that exist in the insect olfactory system [36]. Each glomerulus consists of a population of 6 excitatory projection neurons (PN) and a population of 6 local inhibitory neurons (LN).…”

“…Its threelayer architecture comprising an input layer, a decorrelation layer, and an association layer, is inspired by the insect olfactory system [36] (Figure 3). Neurons in each layer are organized as small neuronal populations, for two reasons: First, single spike sources are too weak to generate activity in downstream neurons due to hardware-constrained bounds on the synaptic weights.…”