Mechanistic modeling in neuroscience aims to explain observed phenomena in terms of underlying causes. However, determining which model parameters agree with complex and stochastic neural data presents a significant challenge. We address this challenge with a machine learning tool which uses deep neural density estimators—trained using model simulations—to carry out Bayesian inference and retrieve the full space of parameters compatible with raw data or selected data features. Our method is scalable in parameters and data features and can rapidly analyze new data after initial training. We demonstrate the power and flexibility of our approach on receptive fields, ion channels, and Hodgkin–Huxley models. We also characterize the space of circuit configurations giving rise to rhythmic activity in the crustacean stomatogastric ganglion, and use these results to derive hypotheses for underlying compensation mechanisms. Our approach will help close the gap between data-driven and theory-driven models of neural dynamics.
We thank Mahmood S Hoseini and Michael Stryker for sharing their data for Figure 2, and Philipp Berens, Sean Bittner, Jan Boelts, John Cunningham, Richard Gao, Scott Linderman, Eve Marder, Iain Murray, George Papamakarios, Astrid Prinz, Auguste Schulz and Srinivas Turaga for discussions and/or comments on the manuscript. This work was supported by the German Research Foundation (DFG) through SFB 1233 ‘Robust Vision’, (276693517), SFB 1089 ‘Synaptic Microcircuits’, SPP 2041 ‘Computational Connectomics’ and Germany's Excellence Strategy – EXC-Number 2064/1 – Project number 390727645 and the German Federal Ministry of Education and Research (BMBF, project ‘ADIMEM’, FKZ 01IS18052 A-D) to JHM, a Sir Henry Dale Fellowship by the Wellcome Trust and the Royal Society (WT100000; WFP and TPV), a Wellcome Trust Senior Research Fellowship (214316/Z/18/Z; TPV), a ERC Consolidator Grant (SYNAPSEEK; WPF and CC), and a UK Research and Innovation, Biotechnology and Biological Sciences Research Council (CC, UKRI-BBSRC BB/N019512/1). We gratefully acknowledge the Leibniz Supercomputing Centre for funding this project by providing computing time on its Linux-Cluster.
Gonçalves PJ, Lueckmann J-M, Deistler M, et al. Training deep neural density estimators to identify mechanistic models of neural dynamics. eLife. 2020;9. doi:10.7554/eLife.56261
Gonçalves, P. J., Lueckmann, J.-M., Deistler, M., Nonnenmacher, M., Öcal, K., Bassetto, G., … Macke, J. H. (2020). Training deep neural density estimators to identify mechanistic models of neural dynamics. ELife, 9. https://doi.org/10.7554/eLife.56261
Gonçalves, Pedro J., Jan-Matthis Lueckmann, Michael Deistler, Marcel Nonnenmacher, Kaan Öcal, Giacomo Bassetto, Chaitanya Chintaluri, et al. “Training Deep Neural Density Estimators to Identify Mechanistic Models of Neural Dynamics.” ELife 9 (2020). https://doi.org/10.7554/eLife.56261.
P. J. Gonçalves et al., “Training deep neural density estimators to identify mechanistic models of neural dynamics,” eLife, vol. 9, 2020.
Gonçalves PJ, Lueckmann J-M, Deistler M, Nonnenmacher M, Öcal K, Bassetto G, Chintaluri C, Podlaski WF, Haddad SA, Vogels TP, Greenberg DS, Macke JH. 2020. Training deep neural density estimators to identify mechanistic models of neural dynamics. eLife. 9.
Gonçalves, Pedro J., et al. “Training Deep Neural Density Estimators to Identify Mechanistic Models of Neural Dynamics.” ELife, vol. 9, e56261, eLife Sciences Publications, 2020, doi:10.7554/eLife.56261.
All files available under the following license(s):
Creative Commons Attribution 4.0 International Public License (CC-BY 4.0):
2020_eLife_Gonçalves.pdf 17.36 MB