PT - JOURNAL ARTICLE
AU - Ketan Mehta
AU - Rebecca F. Goldin
AU - David Marchette
AU - Joshua T. Vogelstein
AU - Carey E. Priebe
AU - Giorgio A. Ascoli
TI - Neuronal Classification from Network Connectivity via Adjacency Spectral Embedding
AID - 10.1101/2020.06.18.160259
DP - 2020 Jan 01
TA - bioRxiv
PG - 2020.06.18.160259
4099 - http://biorxiv.org/content/early/2020/06/20/2020.06.18.160259.short
4100 - http://biorxiv.org/content/early/2020/06/20/2020.06.18.160259.full
AB - This work presents a novel strategy for classifying neurons, represented by nodes of a directed graph, based on their circuitry (edge connectivity). We assume a stochastic block model (SBM) where neurons belong together if they connect to neurons of other groups according to the same probability distributions. Following adjacency spectral embedding (ASE) of the SBM graph, we derive the number of classes and assign each neuron to a class with a Gaussian mixture model-based expectation-maximization (EM) clustering algorithm. To improve accuracy, we introduce a simple variation using random hierarchical agglomerative clustering to initialize the EM algorithm and picking the best solution over multiple EM restarts. We test this procedure on a large (n ~ 212 − 215 neurons), sparse, biologically inspired connectome with eight neuron classes. The simulation results demonstrate that the proposed approach is broadly stable to the choice of dimensional embedding and scales extremely well as the number of neurons in the network increases. Clustering accuracy is robust to variations in model parameters and highly tolerant to simulated experimental noise, achieving perfect classifications with up to 40% of swapped edges. Thus, this approach may be useful to analyze and interpret large-scale brain connectomics data in terms of underlying cellular components.Competing Interest StatementThe authors have declared no competing interest.