Behavioural analysis of single-cell aneural ciliate, Stentor roeselii, using machine learning approaches

Abstract

There is still a significant gap between our understanding of neural circuits and the behaviours they compute - i.e. the computations performed by these neural networks (Carandini 2012). Learning, behaviour, and memory formation, what used to only be associated with animals with neural systems, have been observed in many unicellular aneural species, namely Physarum, Paramecium, and Stentor (Tang & Marshall 2018). As these are fully functioning organisms, yet being unicellular, there is a much better chance to elucidate the detailed mechanisms underlying these learning processes in these organisms without the complications of highly interconnected neural circuits. An intriguing learning behaviour observed in Stentor roeselii (Jennings 1902) when stimulated with carmine has left scientists puzzled for more than a century. So far, none of the existing learning paradigm can fully encapsulate this particular series of five characteristic avoidant reactions. Although we were able to observe all responses described in literature and in a previous study (Dexter et al. 2019, manuscript in preparation), they do not conform to any particular learning model. We then investigated whether models based on machine learning approaches, including decision tree, random forest, and feed-forward neural networks could infer and predict the behavior of S. roeselii. Our results showed that an artificial neural network with multiple computational neurons is inefficient at modelling the single-celled ciliates avoidant reactions. This has highlighted the complexity of behaviours in aneural organisms. Additionally, this report will also discuss the significance of elucidating molecular details underlying learning and decision-making processes in these unicellular organisms, which could offer valuable insights that are applicable to higher animals.