Honeybees learn odour mixtures via a selection of key odorants

Abstract

Background: The honeybee has to detect, process and learn numerous complex odours from her natural environment on a daily basis. Most of these odours are floral scents, which are mixtures of dozens of different odorants. To date, it is still unclear how the bee brain unravels the complex information contained in scent mixtures.

Methodology/principal findings: This study investigates learning of complex odour mixtures in honeybees using a simple olfactory conditioning procedure, the Proboscis-Extension-Reflex (PER) paradigm. Restrained honeybees were trained to three scent mixtures composed of 14 floral odorants each, and then tested with the individual odorants of each mixture. Bees did not respond to all odorants of a mixture equally: They responded well to a selection of key odorants, which were unique for each of the three scent mixtures. Bees showed less or very little response to the other odorants of the mixtures. The bees' response to mixtures composed of only the key odorants was as good as to the original mixtures of 14 odorants. A mixture composed of the other, non-key-odorants elicited a significantly lower response. Neither an odorant's volatility or molecular structure, nor learning efficiencies for individual odorants affected whether an odorant became a key odorant for a particular mixture. Odorant concentration had a positive effect, with odorants at high concentration likely to become key odorants.

Conclusions/significance: Our study suggests that the brain processes complex scent mixtures by predominantly learning information from selected key odorants. Our observations on key odorant learning lend significant support to previous work on olfactory learning and mixture processing in honeybees.

Figure 1. Acquisition Curves for 32 Floral Odorants.

The ordinate represents the percentage of proboscis extensions (PER) to the training odorant. The abscissa indicates the training trials spaced over two days, three trials on day one and a fourth trial on day two. The numbers in brackets indicate the numbers of bees trained for each odorant. Odorants are listed alphabetically, for physico-chemical characteristics of odorants see Table 1.

Figure 2. Key Odorant Signatures for Complex Scents.

The ordinate represents the percentage of proboscis extensions (PER) to the training mixture (black bars), to the individual test odorants of which the mixture was composed (white bars), to a mixture of the key odorants (first grey bar), and to a mixture of non-key-odorants (second grey bar). The numbers in brackets indicate the numbers of bees trained and tested in each experiment. Different letters above bars (a or b) indicate significant differences between PER to the training mixture and to the individual odorants/key odorant mixture/non-key-odorant mixture (McNemar test [2×2 Table], Bonferroni corrected threshold p<0.0036). (A) Bees were trained to mixture 1, and responded well to nine key odorants; (B) bees were trained to mixture 2, and responded well to three key odorants; (C) bees were trained to mixture 3, and responded well to eight key odorants. For composition of the training mixture, key odorant mixture, and non-key-odorant mixture see Table 2. Odorants are listed alphabetically by their abbreviations; for corresponding odorant names, see Table 1.

Figure 3. Effect of Odorant Uniqueness on Key Odorant Signatures.

The ordinate represents the percentage of proboscis extensions (PER) to the training mixture (black bars), to the individual test odorants that the mixture was composed of (white bars), and to a control odorant that was not part of the training mixture (grey bars). Each mixture was composed of two odorants with the same functional group and one unique odorant with a different functional group, indicated by *. The control odorant shared the chemical characteristic of the unique odorant. The numbers in brackets indicate the numbers of bees trained and tested in each experiment. Different letters above bars (a or b) indicate significant differences between PER to the training mixture and to the individual odorants (McNemar test [2×2 Table], Bonferroni corrected threshold p<0.0125). Bees responded to the individual odorants of a mixture as well as to the training mixture, but responded significantly less to the control odorant. (Left) Bees were trained to mixture 4; (Centre) bees were trained to mixture 5; (Right) bees were trained to mixture 6. For mixture compositions see Table 6. Odorants are listed alphabetically by their abbreviations; for corresponding odorant names, see Table 1.

Figure 4. Effect of Odorant Concentration on Key Odorant Signatures.

The ordinate represents the percentage of proboscis extensions (PER) to the training mixture (black bars), and to different concentrations of the individual test odorants that the mixture was composed of (grey and white bars). Training mixtures were composed of the same three odorants, but with one odorant at higher concentration than the other two. Grey bars indicate response to the odorant that was present at the high concentration in the respective training mixture. (A) Bees were trained to mixture 7, which contained LI at 1∶10; (B) bees were trained to mixture 8, which contained MY at 1∶10; (C) bees were trained to mixture 9, which contained PIB at 1∶10; (D) bees were trained to control mixture 10, which contained all odorants at 1∶100; (E) bees were trained to control mixture 11, which contained all odorants at 1∶10. The numbers in brackets indicate the numbers of bees trained and tested in each experiment. Different letters above bars indicate significant differences between PER to the training mixture and to the individual odorants (McNemar test [2×2 Table], Bonferroni corrected threshold p<0.0056). For mixture compositions see Table 6. Odorants are listed alphabetically by their abbreviations; for corresponding odorant names, see Table 1.