Learning by Association in Plants

Abstract

In complex and ever-changing environments, resources such as food are often scarce and unevenly distributed in space and time. Therefore, utilizing external cues to locate and remember high-quality sources allows more efficient foraging, thus increasing chances for survival. Associations between environmental cues and food are readily formed because of the tangible benefits they confer. While examples of the key role they play in shaping foraging behaviours are widespread in the animal world, the possibility that plants are also able to acquire learned associations to guide their foraging behaviour has never been demonstrated. Here we show that this type of learning occurs in the garden pea, Pisum sativum. By using a Y-maze task, we show that the position of a neutral cue, predicting the location of a light source, affected the direction of plant growth. This learned behaviour prevailed over innate phototropism. Notably, learning was successful only when it occurred during the subjective day, suggesting that behavioural performance is regulated by metabolic demands. Our results show that associative learning is an essential component of plant behaviour. We conclude that associative learning represents a universal adaptive mechanism shared by both animals and plants.

Figure 1. Training and testing protocol for associative learning in pea seedlings.

(A) During training seedlings were exposed to the fan [F] and light [L] on either the same arm (i) or on the opposite arm (ii) of the Y-maze. The fan served as the conditioned stimulus (CS), light as the unconditioned stimulus (US). During testing with exposure to the fan alone two categories of responses were distinguished. Correct response: Seedlings growing into the arm of the maze where the light was “predicted” by the fan to occur [green arrow; iii (corresponding to scenario i) and iv (corresponding to scenario ii)]; Incorrect response: Seedlings growing into the arm of the maze where the light was not “predicted” by the fan to occur (black arrow; iii and iv). (B) Seedlings received training for three consecutive days before testing. Each training day consisted of three 2-h training sessions separated by 1-h intervals. The 90-min CS preceded the 60-min US by 60 minutes so that there was a 30-min overlap. (i). During the 1-day testing session, seedlings were exposed to the fan alone for three 90-min sessions (ii). Seedlings of the control group were left undisturbed (no fan, no light; iii).

Figure 2. Associative learning in pea seedlings.

In the absence of the fan, all control seedlings (100%) directed their growth toward the arm of the maze where the light was last presented (white bars). In the presence of the fan, the majority of seedlings grew toward the arm of the maze that had been associated with light during training ([F + L]: same side; [F vs L]: opposite side), thus exhibiting the conditioned response (green bars). A smaller proportion of seedlings did not show learning, thus exhibiting the innate response (blue bars). The response of the experimental groups was significantly different from controls (Two-tailed Fisher’s Exact Test, P = 0.0027 for [F + L] and P = 0.0017 for [F vs L]). See Data file in Supplementary Information.

Figure 3. Circadian effects on behavioural performance of pea seedlings.

(A) Seedlings were kept in incubation chambers, where initially both light and temperature were used as Zeitgebers (temperature = dotted line; mean values across all days; light:dark cycles, yellow:grey shaded areas). During three training days, the seedlings were kept in darkness with the exception of the three training sessions, while the temperature cycle was maintained (note: the LD cycle was not maintained during training). The training (orange and blue rectangular areas, indicating the time of exposure to the fan and the blue light respectively) and testing sessions occurred during the former light phase in the Light group (i), and partly or entirely outside the former light phase in Light-Dark (ii) and Dark group (iii), respectively. (B) In the ‘Light’ group (i), the growth response of tested seedlings was significantly different from control seedlings (Two-tailed Fisher’s Exact Test, P = 0.002). All control seedlings grew to the arm of the maze where the blue light had been delivered on the last training day [white bar; (i)], while 61% of tested seedlings grew towards the arm where the fan predicted the blue light to occur [green bar; (i)]. A minority of tested plants (39%) did not form an association [blue bar; (i)]. Under phase-shifted conditions, the tested seedlings did not differ from controls [Two-tailed Fisher’s Exact Test, P = 0.769 for the Light-Dark group (ii); P = 0.653 for the Dark group (iii)]. Phase-shift disrupted the phototropic response of control seedlings [white bars; (ii, iii)], causing only 46% of individuals in the Light-Dark group and 70% in the Dark group to direct their growth towards the side of last light exposure [white bars; (ii, iii)].