Consistent cross-modal identification of cortical neurons with coupled autoencoders

Consistent identification of neurons in different experimental modalities is a key problem in neuroscience. Although methods to perform multimodal measurements in the same set of single neurons have become available, parsing complex relationships across different modalities to uncover neuronal identity is a growing challenge. Here we present an optimization framework to learn coordinated representations of multimodal data and apply it to a large multimodal dataset profiling mouse cortical interneurons. Our approach reveals strong alignment between transcriptomic and electrophysiological characterizations, enables accurate cross-modal data prediction, and identifies cell types that are consistent across modalities. Aligning multimodal data for cell type research is a challenging problem in neuroscience. Coupled autoencoders, a deep neural network-based methodology, can be used to effectively address this task.

[1]  M. Hawrylycz,et al.  New light on cortical neuropeptides and synaptic network plasticity , 2020, Current Opinion in Neurobiology.

[2]  Allan R. Jones,et al.  Shared and distinct transcriptomic cell types across neocortical areas , 2018, Nature.

[3]  Z Josh Huang,et al.  The diversity of GABAergic neurons and neural communication elements , 2019, Nature Reviews Neuroscience.

[4]  P. Somogyi,et al.  Salient features of synaptic organisation in the cerebral cortex 1 Published on the World Wide Web on 3 March 1998. 1 , 1998, Brain Research Reviews.

[5]  Anton Arkhipov,et al.  Consistent cross-modal identification of cortical neurons with coupled autoencoders , 2020 .

[6]  Satrajit S. Ghosh,et al.  A multimodal cell census and atlas of the mammalian primary motor cortex , 2020, Nature.

[7]  Hongkui Zeng,et al.  Neuronal cell-type classification: challenges, opportunities and the path forward , 2017, Nature Reviews Neuroscience.

[8]  Philipp Berens,et al.  Neuronal Diversity In The Retina , 2017 .

[9]  Brian R. Lee,et al.  Classification of electrophysiological and morphological neuron types in the mouse visual cortex , 2019, Nature Neuroscience.

[10]  Ruifan Li,et al.  Cross-modal Retrieval with Correspondence Autoencoder , 2014, ACM Multimedia.

[11]  S. Linnarsson,et al.  Cell types in the mouse cortex and hippocampus revealed by single-cell RNA-seq , 2015, Science.

[12]  Philipp Berens,et al.  Sparse reduced-rank regression for exploratory visualization of multimodal data sets , 2018, bioRxiv.

[13]  Paul J. Hoffman,et al.  Comprehensive Integration of Single-Cell Data , 2018, Cell.

[14]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[15]  Brian R. Lee,et al.  Integrated Morphoelectric and Transcriptomic Classification of Cortical GABAergic Cells , 2020, Cell.

[16]  Trygve E Bakken,et al.  Single-nucleus and single-cell transcriptomes compared in matched cortical cell types , 2018, PloS one.

[17]  D. Freedman,et al.  On the histogram as a density estimator:L2 theory , 1981 .

[18]  R. Tremblay,et al.  GABAergic Interneurons in the Neocortex: From Cellular Properties to Circuits , 2016, Neuron.

[19]  Trygve E Bakken,et al.  Single-cell transcriptomic evidence for dense intracortical neuropeptide networks , 2019, bioRxiv.

[20]  Louis-Philippe Morency,et al.  Multimodal Machine Learning: A Survey and Taxonomy , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Kenneth D Harris,et al.  Classes and continua of hippocampal CA1 inhibitory neurons revealed by single-cell transcriptomics , 2017, bioRxiv.

[22]  X. Zhuang,et al.  Spatially resolved, highly multiplexed RNA profiling in single cells , 2015, Science.

[23]  Saumil S. Patel,et al.  Layer 4 of mouse neocortex differs in cell types and circuit organization between sensory areas , 2019, Nature Communications.

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

[25]  E. P. Gardner,et al.  Petilla terminology: nomenclature of features of GABAergic interneurons of the cerebral cortex , 2008, Nature Reviews Neuroscience.

[26]  Jeff A. Bilmes,et al.  Deep Canonical Correlation Analysis , 2013, ICML.

[27]  Ming Yang,et al.  A Survey of Multi-View Representation Learning , 2019, IEEE Transactions on Knowledge and Data Engineering.

[28]  P. Kharchenko,et al.  Bayesian approach to single-cell differential expression analysis , 2014, Nature Methods.

[29]  Hongkui Zeng,et al.  A coupled autoencoder approach for multi-modal analysis of cell types , 2019, NeurIPS.

[30]  Jeff A. Bilmes,et al.  On Deep Multi-View Representation Learning , 2015, ICML.

[31]  Z. J. Huang,et al.  Transcriptional Architecture of Synaptic Communication Delineates GABAergic Neuron Identity , 2017, Cell.

[32]  Andreas S Tolias,et al.  Multimodal profiling of single-cell morphology, electrophysiology, and gene expression using Patch-seq , 2017, Nature Protocols.

[33]  Philipp Berens,et al.  Phenotypic variation of transcriptomic cell types in mouse motor cortex , 2020, Nature.

[34]  Concha Bielza,et al.  New insights into the classification and nomenclature of cortical GABAergic interneurons , 2013, Nature Reviews Neuroscience.

[35]  Spyros Darmanis,et al.  Single-cell RNAseq reveals cell adhesion molecule profiles in electrophysiologically defined neurons , 2016, Proceedings of the National Academy of Sciences.