Identification of diverse synchrony patterns in dissociated cortical culture using Bayesian non-negative matrix factorization

Synchrony in a neuronal network is not just a spontaneous event but rather a representation of inner information. In this point of view, the variety of synchrony patterns is considered to be related to inner capacity of the network. However, evaluating and comparing the variety of synchrony patterns, especially between different samples or different times, is difficult. In this paper, we proposed to identify the variety of synchrony based on Bayesian model selection. Hypothesizing that globally synchronized activity consists of partial synchrony, we attempted to identify reproducible-spatial pattern bases in spontaneous bursting activities of dissociated cortical cultures using Bayesian non-negative matrix factorization. Neuronal activity was recorded with high-density CMOS electrode arrays. Bayesian treatment provides evidence for selection of the number of bases based on marginal likelihood. We compared model evidence of the activity in juvenile and matured cultures. Our results suggested that the variety of synchrony patterns diversify through maturation.