Comparison of Uniform Manifold Approximation and Projection (UMAP)-based and feature-based spike sorting on synthetic data.

<p><b>(A)</b> In a simulated dataset containing three different neurons, UMAP-based sorting forms three well-separated clusters with distinct shapes and colors, indicating strong accuracy and minimal overlap. <b>(B)</b> Applying wavelet sorting to the same dataset merge...

Volledige beschrijving

Bewaard in:
Bibliografische gegevens
Hoofdauteur: Daniel Suárez-Barrera (22676654) (author)
Andere auteurs: Lucas Bayones (22676657) (author), Norberto Encinas-Rodríguez (22676660) (author), Sergio Parra (22676663) (author), Viktor Monroy (22676666) (author), Sebastián Pujalte (22676669) (author), Bernardo Andrade-Ortega (22676672) (author), Héctor Díaz (22676675) (author), Manuel Alvarez (3468647) (author), Antonio Zainos (22676678) (author), Alessio Franci (143351) (author), Román Rossi-Pool (22676681) (author)
Gepubliceerd in: 2025
Onderwerpen:
Tags: Voeg label toe
Geen labels, Wees de eerste die dit record labelt!
_version_ 1849927641759481856
author Daniel Suárez-Barrera (22676654)
author2 Lucas Bayones (22676657)
Norberto Encinas-Rodríguez (22676660)
Sergio Parra (22676663)
Viktor Monroy (22676666)
Sebastián Pujalte (22676669)
Bernardo Andrade-Ortega (22676672)
Héctor Díaz (22676675)
Manuel Alvarez (3468647)
Antonio Zainos (22676678)
Alessio Franci (143351)
Román Rossi-Pool (22676681)
author2_role author
author
author
author
author
author
author
author
author
author
author
author_facet Daniel Suárez-Barrera (22676654)
Lucas Bayones (22676657)
Norberto Encinas-Rodríguez (22676660)
Sergio Parra (22676663)
Viktor Monroy (22676666)
Sebastián Pujalte (22676669)
Bernardo Andrade-Ortega (22676672)
Héctor Díaz (22676675)
Manuel Alvarez (3468647)
Antonio Zainos (22676678)
Alessio Franci (143351)
Román Rossi-Pool (22676681)
author_role author
dc.creator.none.fl_str_mv Daniel Suárez-Barrera (22676654)
Lucas Bayones (22676657)
Norberto Encinas-Rodríguez (22676660)
Sergio Parra (22676663)
Viktor Monroy (22676666)
Sebastián Pujalte (22676669)
Bernardo Andrade-Ortega (22676672)
Héctor Díaz (22676675)
Manuel Alvarez (3468647)
Antonio Zainos (22676678)
Alessio Franci (143351)
Román Rossi-Pool (22676681)
dc.date.none.fl_str_mv 2025-11-24T18:33:33Z
dc.identifier.none.fl_str_mv 10.1371/journal.pbio.3003527.g002
dc.relation.none.fl_str_mv https://figshare.com/articles/figure/Comparison_of_Uniform_Manifold_Approximation_and_Projection_UMAP_-based_and_feature-based_spike_sorting_on_synthetic_data_/30697580
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Cell Biology
Molecular Biology
Neuroscience
Physiology
Biotechnology
Developmental Biology
Science Policy
Space Science
Biological Sciences not elsewhere classified
Mathematical Sciences not elsewhere classified
Information Systems not elsewhere classified
spike sorting pipelines
spike sorting pipeline
seldom spiking neurons
recorded putative neurons
correctly sorted neurons
clustering algorithms responsible
spike sorting makes
reliable spike sorting
umap drastically increases
data analysis techniques
drastically improve
processed data
experimental data
universal practice
precise explorations
neural recordings
neural code
mathematically grounded
fundamentally motivated
extracellular electrophysiology
enables deeper
crucial step
computational cost
ad hoc
dc.title.none.fl_str_mv Comparison of Uniform Manifold Approximation and Projection (UMAP)-based and feature-based spike sorting on synthetic data.
dc.type.none.fl_str_mv Image
Figure
info:eu-repo/semantics/publishedVersion
image
description <p><b>(A)</b> In a simulated dataset containing three different neurons, UMAP-based sorting forms three well-separated clusters with distinct shapes and colors, indicating strong accuracy and minimal overlap. <b>(B)</b> Applying wavelet sorting to the same dataset merges the spikes into just two clusters that exhibit noticeable overlap and weak separation, as illustrated in both 3D (top) and 2D (bottom) views. <b>(C)</b> Principal component analysis (PCA)-based sorting isolates only a single cluster with poor separation, underscoring PCA’s difficulty with complex spike distributions. <b>(D)</b> By contrast, UMAP spike sorting consistently surpasses both wavelet and PCA methods, particularly in higher-dimensional spaces, as measured by the F1 score. <b>(E)</b> UMAP-based sorting also proves robust against noise perturbations at various spike dilution levels (dark trace; firing rate [fr] at 100% vs. light blue trace; fr diluted at 40%). Even under increased noise and cluster dilution, it preserves high F1 scores. <b>(F)</b> Moreover, UMAP-based sorting (dark blue) remains accurate despite data loss, achieving high F1 scores even when a large fraction of spikes (x-axis) is removed from one cluster, whereas wavelet (green) and PCA (orange) methods experience a significant decline in performance. The synthetic data used to generate this figure are publicly available at [<a href="http://www.plosbiology.org/article/info:doi/10.1371/journal.pbio.3003527#pbio.3003527.ref037" target="_blank">37</a>], and the code for performing the analyses is available at [<a href="http://www.plosbiology.org/article/info:doi/10.1371/journal.pbio.3003527#pbio.3003527.ref049" target="_blank">49</a>].</p>
eu_rights_str_mv openAccess
id Manara_1ec51fdac1d5c6519914f623f3df47d4
identifier_str_mv 10.1371/journal.pbio.3003527.g002
network_acronym_str Manara
network_name_str ManaraRepo
oai_identifier_str oai:figshare.com:article/30697580
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Comparison of Uniform Manifold Approximation and Projection (UMAP)-based and feature-based spike sorting on synthetic data.Daniel Suárez-Barrera (22676654)Lucas Bayones (22676657)Norberto Encinas-Rodríguez (22676660)Sergio Parra (22676663)Viktor Monroy (22676666)Sebastián Pujalte (22676669)Bernardo Andrade-Ortega (22676672)Héctor Díaz (22676675)Manuel Alvarez (3468647)Antonio Zainos (22676678)Alessio Franci (143351)Román Rossi-Pool (22676681)Cell BiologyMolecular BiologyNeurosciencePhysiologyBiotechnologyDevelopmental BiologyScience PolicySpace ScienceBiological Sciences not elsewhere classifiedMathematical Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedspike sorting pipelinesspike sorting pipelineseldom spiking neuronsrecorded putative neuronscorrectly sorted neuronsclustering algorithms responsiblespike sorting makesreliable spike sortingumap drastically increasesdata analysis techniquesdrastically improveprocessed dataexperimental datauniversal practiceprecise explorationsneural recordingsneural codemathematically groundedfundamentally motivatedextracellular electrophysiologyenables deepercrucial stepcomputational costad hoc<p><b>(A)</b> In a simulated dataset containing three different neurons, UMAP-based sorting forms three well-separated clusters with distinct shapes and colors, indicating strong accuracy and minimal overlap. <b>(B)</b> Applying wavelet sorting to the same dataset merges the spikes into just two clusters that exhibit noticeable overlap and weak separation, as illustrated in both 3D (top) and 2D (bottom) views. <b>(C)</b> Principal component analysis (PCA)-based sorting isolates only a single cluster with poor separation, underscoring PCA’s difficulty with complex spike distributions. <b>(D)</b> By contrast, UMAP spike sorting consistently surpasses both wavelet and PCA methods, particularly in higher-dimensional spaces, as measured by the F1 score. <b>(E)</b> UMAP-based sorting also proves robust against noise perturbations at various spike dilution levels (dark trace; firing rate [fr] at 100% vs. light blue trace; fr diluted at 40%). Even under increased noise and cluster dilution, it preserves high F1 scores. <b>(F)</b> Moreover, UMAP-based sorting (dark blue) remains accurate despite data loss, achieving high F1 scores even when a large fraction of spikes (x-axis) is removed from one cluster, whereas wavelet (green) and PCA (orange) methods experience a significant decline in performance. The synthetic data used to generate this figure are publicly available at [<a href="http://www.plosbiology.org/article/info:doi/10.1371/journal.pbio.3003527#pbio.3003527.ref037" target="_blank">37</a>], and the code for performing the analyses is available at [<a href="http://www.plosbiology.org/article/info:doi/10.1371/journal.pbio.3003527#pbio.3003527.ref049" target="_blank">49</a>].</p>2025-11-24T18:33:33ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pbio.3003527.g002https://figshare.com/articles/figure/Comparison_of_Uniform_Manifold_Approximation_and_Projection_UMAP_-based_and_feature-based_spike_sorting_on_synthetic_data_/30697580CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/306975802025-11-24T18:33:33Z
spellingShingle Comparison of Uniform Manifold Approximation and Projection (UMAP)-based and feature-based spike sorting on synthetic data.
Daniel Suárez-Barrera (22676654)
Cell Biology
Molecular Biology
Neuroscience
Physiology
Biotechnology
Developmental Biology
Science Policy
Space Science
Biological Sciences not elsewhere classified
Mathematical Sciences not elsewhere classified
Information Systems not elsewhere classified
spike sorting pipelines
spike sorting pipeline
seldom spiking neurons
recorded putative neurons
correctly sorted neurons
clustering algorithms responsible
spike sorting makes
reliable spike sorting
umap drastically increases
data analysis techniques
drastically improve
processed data
experimental data
universal practice
precise explorations
neural recordings
neural code
mathematically grounded
fundamentally motivated
extracellular electrophysiology
enables deeper
crucial step
computational cost
ad hoc
status_str publishedVersion
title Comparison of Uniform Manifold Approximation and Projection (UMAP)-based and feature-based spike sorting on synthetic data.
title_full Comparison of Uniform Manifold Approximation and Projection (UMAP)-based and feature-based spike sorting on synthetic data.
title_fullStr Comparison of Uniform Manifold Approximation and Projection (UMAP)-based and feature-based spike sorting on synthetic data.
title_full_unstemmed Comparison of Uniform Manifold Approximation and Projection (UMAP)-based and feature-based spike sorting on synthetic data.
title_short Comparison of Uniform Manifold Approximation and Projection (UMAP)-based and feature-based spike sorting on synthetic data.
title_sort Comparison of Uniform Manifold Approximation and Projection (UMAP)-based and feature-based spike sorting on synthetic data.
topic Cell Biology
Molecular Biology
Neuroscience
Physiology
Biotechnology
Developmental Biology
Science Policy
Space Science
Biological Sciences not elsewhere classified
Mathematical Sciences not elsewhere classified
Information Systems not elsewhere classified
spike sorting pipelines
spike sorting pipeline
seldom spiking neurons
recorded putative neurons
correctly sorted neurons
clustering algorithms responsible
spike sorting makes
reliable spike sorting
umap drastically increases
data analysis techniques
drastically improve
processed data
experimental data
universal practice
precise explorations
neural recordings
neural code
mathematically grounded
fundamentally motivated
extracellular electrophysiology
enables deeper
crucial step
computational cost
ad hoc