Semi-supervised Projected Clustering for Classifying GABAergic Interneurons

A systematic classification of neuron types is a critical topic of debate in neuroscience. In this study, we propose a semi-supervised projected clustering algorithm based on finite mixture models and the expectation-maximization (EM) algorithm, that is useful for classifying neuron types. Specifically, we analyzed cortical GABAergic interneurons from different animals and cortical layers. The new algorithm, called SeSProC, is a probabilistic approach for classifying known classes and for discovering possible new groups of interneurons. Basic morphological features containing information about axonal and dendritic arborization sizes and orientations are used to characterize the interneurons. SeSProC also identifies the relevance of each feature and group separately. This article aims to present the methodological approach, reporting results for known classes and possible new groups of interneurons.

[1]  Huan Liu,et al.  Subspace clustering for high dimensional data: a review , 2004, SKDD.

[2]  Javier DeFelipe,et al.  Cortical interneurons: from Cajal to 2001. , 2002, Progress in brain research.

[3]  Rafael Yuste,et al.  Dendritic size of pyramidal neurons differs among mouse cortical regions. , 2006, Cerebral cortex.

[4]  Geoffrey J. McLachlan,et al.  Mixture models : inference and applications to clustering , 1989 .

[5]  J. Rossier,et al.  Classification of fusiform neocortical interneurons based on unsupervised clustering. , 2000, Proceedings of the National Academy of Sciences of the United States of America.

[6]  Demian Battaglia,et al.  Classification of NPY-Expressing Neocortical Interneurons , 2009, The Journal of Neuroscience.

[7]  R. Yuste,et al.  Comparison Between Supervised and Unsupervised Classifications of Neuronal Cell Types: A Case Study , 2010, Developmental neurobiology.

[8]  G. Ascoli,et al.  NeuroMorpho.Org: A Central Resource for Neuronal Morphologies , 2007, The Journal of Neuroscience.

[9]  Rafael Yuste,et al.  Quantitative morphologic classification of layer 5 neurons from mouse primary visual cortex , 2003, The Journal of comparative neurology.

[10]  Paulo J. G. Lisboa,et al.  Robust analysis of MRS brain tumour data using t-GTM , 2006, Neurocomputing.

[11]  Marvin Minsky,et al.  Steps toward Artificial Intelligence , 1995, Proceedings of the IRE.

[12]  Concha Bielza,et al.  Semi-supervised projected model-based clustering , 2014, Data Mining and Knowledge Discovery.

[13]  G. Schwarz.  Estimating the Dimension of a Model , 1978 .

[14]  Hans-Peter Kriegel,et al.  Clustering high-dimensional data: A survey on subspace clustering, pattern-based clustering, and correlation clustering , 2009, TKDD.

[15]  Xiaojin Zhu,et al.  Introduction to Semi-Supervised Learning , 2009, Synthesis Lectures on Artificial Intelligence and Machine Learning.

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

[17]  R. Yuste,et al.  Neural Circuits Original Research Article Materials and Methods Preparation of Brain Slices , 2022 .

[18]  Anil K. Jain,et al.  Simultaneous feature selection and clustering using mixture models , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[20]  H. Jörntell,et al.  Frontiers in Neural Circuits Neural Circuits , 2022 .

[21]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[22]  L. Luo,et al.  Representation of the Glomerular Olfactory Map in the Drosophila Brain , 2002, Cell.

[23]  Alexander Zien,et al.  Semi-Supervised Learning , 2006 .