2024-03-19T13:20:59Zhttp://digital.csic.es/dspace-oai/requestoai:digital.csic.es:10261/1736072022-06-30T11:34:02Zcom_10261_54com_10261_1col_10261_307
DIGITAL.CSIC
author
Mihaljević, Bojan
author
Larrañaga, Pedro
author
Benavides-Piccione, Ruth
author
Hill, Sean
author
DeFelipe, Javier
author
Bielza, Concha
funder
Ministerio de Economía, Industria y Competitividad (España)
funder
European Commission
funder
Comunidad de Madrid
funder
Fundación BBVA
2018-12-23T04:16:39Z
2018-12-23T04:16:39Z
2018-12-17
BMC Bioinformatics 19(1): 511 (2018)
http://hdl.handle.net/10261/173607
10.1186/s12859-018-2470-1
1471-2105
http://dx.doi.org/10.13039/100007406http://dx.doi.org/10.13039/501100000780http://dx.doi.org/10.13039/100012818http://dx.doi.org/10.13039/501100010198
30558530
[Background] The challenge of classifying cortical interneurons is yet to be solved. Data-driven classification into established morphological types may provide insight and practical values. [Results] We trained models using 217 high-quality morphologies of rat somatosensory neocortex interneurons reconstructed by a single laboratory and pre-classified into eight types. We quantified 103 axonal and dendritic morphometrics, including novel ones that capture features such as arbor orientation, extent in layer one, and dendritic polarity. We trained a one-versus-rest classifier for each type, combining well-known supervised classification algorithms with feature selection and over- and under-sampling. We accurately classified the nest basket, Martinotti, and basket cell types with the Martinotti model outperforming 39 out of 42 leading neuroscientists. We had moderate accuracy for the double bouquet, small and large basket types, and limited accuracy for the chandelier and bitufted types. We characterized the types with interpretable models or with up to ten morphometrics. [Conclusion] Except for large basket, 50 high-quality reconstructions sufficed to learn an accurate model of a type. Improving these models may require quantifying complex arborization patterns and finding correlates of bouton-related features. Our study brings attention to practical aspects important for neuron classification and is readily reproducible, with all code and data available online.
en
openAccess
Feature selection
Martinotti
Morphometrics
Feature selection
Martinott
Morphometrics
Towards a supervised classification of neocortical interneuron morphologies
artículo
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
URL
https://digital.csic.es/bitstream/10261/173607/1/12859_2018_Article_2470.pdf
File
MD5
bc3c84eb41c69f2d8ced211fba5d71fd
2712529
application/pdf
12859_2018_Article_2470.pdf