Comparison of connectivity inference algorithms for classification of neuronal cultures using graph kernels
Abstract
Neurons derived from human induced pluripotent stem cells (iPSCs), provide new means to study aspects of severe neurological diseases in vitro. Network features extracted from electrophysiological recordings of iPSC-derived neurons could be useful to better understand and study disease phenotypes. However, up to this date, there is no fully-validated method to infer connectivity between neurons when using spike trains as input. In this study, we compare two types of human iPSC-
derived dopaminergic neurons: wild type cells and cells with a genetic mutation associated with Parkinson’s disease. Moreover, we use graph
kernels to train a classifier on the inferred functional networks and probe which connectivity inference parameters generate networks with more discriminative features. Show more
Permanent link
https://doi.org/10.3929/ethz-b-000466325Publication status
publishedPublisher
PharmMLEvent
Subject
Connectivity estimation; Classification; Graph kernelsOrganisational unit
03684 - Hierlemann, Andreas / Hierlemann, Andreas
Funding
694829 - Microtechnology and integrated microsystems to investigate neuronal networks across scales (EC)
Related publications and datasets
Notes
Workshop presentation held on September 14, 2020. Due to the Coronavirus (COVID-19) the conference was conducted virtually.More
Show all metadata
ETH Bibliography
yes
Altmetrics