CalciumGAN: A Generative Adversarial Network Model for Synthesising Realistic Calcium Imaging Data of Neuronal Populations

Calcium imaging has become a powerful and popular technique to monitor the activity of large populations of neurons in vivo. However, for ethical considerations and despite recent technical developments, recordings are still constrained to a limited number of trials and animals. This limits the amount of data available from individual experiments and hinders the development of analysis techniques and models for more realistic size of neuronal populations. The ability to artificially synthesize realistic neuronal calcium signals could greatly alleviate this problem by scaling up the number of trials. Here we propose a Generative Adversarial Network (GAN) model to generate realistic calcium signals as seen in neuronal somata with calcium imaging. To this end, we adapt the WaveGAN architecture and train it with the Wasserstein distance. We test the model on artificial data with known ground-truth and show that the distribution of the generated signals closely resembles the underlying data distribution. Then, we train the model on real calcium signals recorded from the primary visual cortex of behaving mice and confirm that the deconvolved spike trains match the statistics of the recorded data. Together, these results demonstrate that our model can successfully generate realistic calcium imaging data, thereby providing the means to augment existing datasets of neuronal activity for enhanced data exploration and modeling.

[1]  Liam Paninski,et al.  Fast online deconvolution of calcium imaging data , 2016, PLoS Comput. Biol..

[2]  Mark C. W. van Rossum,et al.  A Novel Spike Distance , 2001, Neural Computation.

[3]  Nathalie L Rochefort,et al.  Reward Association Enhances Stimulus-Specific Representations in Primary Visual Cortex , 2020, Current Biology.

[4]  Karel Svoboda,et al.  A comparison of neuronal population dynamics measured with calcium imaging and electrophysiology , 2019, bioRxiv.

[5]  Jakob H. Macke,et al.  Adversarial Training of Neural Encoding Models on Population Spike Trains , 2019, 2019 Conference on Cognitive Computational Neuroscience.

[6]  Jaakko Lehtinen,et al.  Progressive Growing of GANs for Improved Quality, Stability, and Variation , 2017, ICLR.

[7]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[8]  Vincent Dumoulin,et al.  Deconvolution and Checkerboard Artifacts , 2016 .

[9]  Sonja Grün,et al.  CuBIC: cumulant based inference of higher-order correlations in massively parallel spike trains , 2009, Journal of Computational Neuroscience.

[10]  David Lopez-Paz,et al.  Optimizing the Latent Space of Generative Networks , 2017, ICML.

[11]  Simon Osindero,et al.  Conditional Generative Adversarial Nets , 2014, ArXiv.

[12]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[13]  拓海 杉山,et al.  “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告 , 2017 .

[14]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[15]  Rodrigo Quian Quiroga,et al.  Past, present and future of spike sorting techniques , 2015, Brain Research Bulletin.

[16]  Geoffrey E. Hinton,et al.  Layer Normalization , 2016, ArXiv.

[17]  Chethan Pandarinath,et al.  Inferring single-trial neural population dynamics using sequential auto-encoders , 2017, Nature Methods.

[18]  Kenneth D Harris,et al.  Improving data quality in neuronal population recordings , 2016, Nature Neuroscience.

[19]  Nathalie L. Rochefort,et al.  The Impact of Visual Cues, Reward, and Motor Feedback on the Representation of Behaviorally Relevant Spatial Locations in Primary Visual Cortex , 2018, Cell reports.

[20]  Alexander S. Ecker,et al.  Generating Spike Trains with Specified Correlation Coefficients , 2009, Neural Computation.

[21]  Aaron C. Courville,et al.  Improved Training of Wasserstein GANs , 2017, NIPS.

[22]  Chris Donahue,et al.  Adversarial Audio Synthesis , 2018, ICLR.

[23]  Shreya Saxena,et al.  Towards the neural population doctrine , 2019, Current Opinion in Neurobiology.

[24]  Konrad P Kording,et al.  How advances in neural recording affect data analysis , 2011, Nature Neuroscience.

[25]  R. Kass,et al.  Multiple neural spike train data analysis: state-of-the-art and future challenges , 2004, Nature Neuroscience.

[26]  Léon Bottou,et al.  Wasserstein GAN , 2017, ArXiv.

[27]  Stefano Panzeri,et al.  Synthesizing realistic neural population activity patterns using Generative Adversarial Networks , 2018, ICLR.