Field
Value
Language
dc.contributor.author
Khater, Ismail M.
datacite.creator.affiliationIdentifier
https://ror.org/0213rcc28
en_US
datacite.creator.affiliation
Simon Fraser University
en_US
datacite.creator.nameIdentifier
https://orcid.org/0000-0001-7827-7745
en_US
dc.date.accessioned
2021-04-22T21:12:53Z
dc.date.available
2021-04-22T21:12:53Z
dc.date.issued
2019-06-19
dc.identifier.uri
https://www.frdr-dfdr.ca/repo/dataset/0a7b2b94-7cad-4c92-a7b1-53668d7c6f6f
dc.identifier.uri
https://doi.org/10.25314/e55f116a-a0a3-4504-a274-377803ea0ea0
dc.description
Caveolae are plasma membrane invaginations whose formation requires caveolin-1 (Cav1), the adaptor protein polymerase I, and the transcript release factor (PTRF or CAVIN1). Caveolae have an important role in cell functioning, signaling, and disease. In the absence of CAVIN1/PTRF, Cav1 forms non-caveolar membrane domains called scaffolds. In this work, we train machine learning models to automatically distinguish between caveolae and scaffolds from single molecule localization microscopy (SMLM) data. We apply machine and deep learning algorithms to discriminate biological structures from SMLM data. Our work is the first that is leveraging machine and deep learning approaches to automatically identifying biological structures from SMLM data. In particular, we develop and compare three binary classification methods to identify whether or not a given 3D cluster of Cav1 proteins is a caveolae. The first uses a random forest classifier applied to 28 hand-picked features, the second uses a convolutional neural net (CNN) applied to a projection of the point clouds onto three planes, and the third uses a PointNet model, a recent development that can directly take point clouds as its input. We validate our methods on a dataset of super-resolution microscopy images of PC3 prostate cancer cells labeled for Cav1. Specifically, we have images from two cell populations: 10 PC3 and 10 CAVIN1/PTRF-transfected PC3 cells (PC3-PTRF cells) that form caveolae. We obtained a balanced set of 1714 different cellular structures. Our results show that both the random forest on hand selected features and the deep learning approach achieve high accuracy in distinguishing the intrinsic features of the caveolae and non-caveolae biological structures. More specifically, both random forest and deep CNN classifiers achieve classification accuracy reaching 94% on our test set, while the PointNet model only reached 83% accuracy. We also discuss the pros and cons of the different approaches. Additional information about individual files is in the accompanying CSV file (item_metadata.csv). This dataset was originally deposited in the Simon Fraser University institutional repository.
en_US
dc.publisher
Federated Research Data Repository / dépôt fédéré de données de recherche
dc.rights
Rights remain with the creator; contact for details. Ismail M. Khater, ismail.khater@gmail.com.
en_US
dc.subject
Point clouds
en_US
dc.subject
Super-resolution
en_US
dc.subject
Nanoscopy
en_US
dc.subject
Single molecule localization microscopy (SMLM)
en_US
dc.subject
Cluster analysis
en_US
dc.subject
Machine learning
en_US
dc.subject
Biological structures
en_US
dc.subject
Molecular complexes
en_US
dc.title
Caveolae and scaffold detection from single molecule localization microscopy data
en_US
globus.shared_endpoint.name
f163c1b3-9c88-42f6-a7bb-5839ed6c4063
globus.shared_endpoint.path
/8/published/publication_355/
frdr.preservation.status
AIP generation and transfer successful
frdr.preservation.datetime
2021-05-18
datacite.publicationyear
2019
datacite.resourcetype
Dataset
en_US
datacite.relatedidentifier.IsCitedBy
https://doi.org/10.1038/s41598-018-27216-4
datacite.relatedidentifier.IsSupplementTo
https://doi.org/10.1038/s41598-019-46174-z
datacite.relatedidentifier.IsSupplementTo
https://doi.org/10.1101/495382
datacite.relatedidentifier.IsSupplementTo
https://doi.org/10.1101/526327
datacite.relatedidentifier.IsSupplementTo
https://doi.org/10.1093/bioinformatics/btz113
datacite.relatedidentifier.IsSupplementTo
https://doi.org/10.1371/journal.pone.0211659
datacite.fundingReference.funderName
en_US
datacite.fundingReference.awardNumber
en_US
datacite.fundingReference.awardTitle
en_US
frdr.crdc.code
RDF1020805
frdr.crdc.group_en
Computer and information sciences
en_US
frdr.crdc.class_en
Bioinformatics
en_US
frdr.crdc.field_en
Molecular and atomic computing
en_US
frdr.crdc.group_fr
Informatique et systèmes d'information
fr_CA
frdr.crdc.class_fr
Bioinformatique
fr_CA
frdr.crdc.field_fr
Calculs moléculaire et atomique par ordinateur
fr_CA
Appears in Collections: