2007
DOI: 10.1186/1471-2105-8-210
|View full text |Cite
|
Sign up to set email alerts
|

Abstract: Background: Fluorescence microscopy is widely used to determine the subcellular location of proteins. Efforts to determine location on a proteome-wide basis create a need for automated methods to analyze the resulting images. Over the past ten years, the feasibility of using machine learning methods to recognize all major subcellular location patterns has been convincingly demonstrated, using diverse feature sets and classifiers. On a well-studied data set of 2D HeLa single-cell images, the best performance to… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

1
90
1

Year Published

2007
2007
2023
2023

Publication Types

Select...
4
2
1
1

Relationship

1
7

Authors

Journals

citations
Cited by 105 publications
(92 citation statements)
references
References 19 publications
1
90
1
Order By: Relevance
“…Some of the relevant biological applications of PREs at the cellular and subcellular levels include classification of cells and nuclei based on their morphological, textural, and appearance features (24,25), and interpreting and analyzing localization of proteins, antibodies, and subcellular structures within the cell (26)(27)(28)(29). For instance, Hill et al (30) assessed the impact of imperfect segmentation on the quality of highcontent screening data using a support vector machine (SVM)-based PRE to identify accurately delineated nuclei.…”
Section: Introductionmentioning
confidence: 99%
“…Some of the relevant biological applications of PREs at the cellular and subcellular levels include classification of cells and nuclei based on their morphological, textural, and appearance features (24,25), and interpreting and analyzing localization of proteins, antibodies, and subcellular structures within the cell (26)(27)(28)(29). For instance, Hill et al (30) assessed the impact of imperfect segmentation on the quality of highcontent screening data using a support vector machine (SVM)-based PRE to identify accurately delineated nuclei.…”
Section: Introductionmentioning
confidence: 99%
“…In [47] the authors use frames for image interpolation and resolution enhancement. In [48], the authors use frames to significantly improve the classification accuracy of protein subcellular location images, to close to 96% as well as the high-throughput tagging of Drosophila embryo developmental stages [112]. In theoretical neuroscience, another advantage of frames…”
Section: From Biology To Teleportationmentioning
confidence: 99%
“…Frame-like ideas, that is, building redundancy into a signal expansion, can be found in pyramid coding [33], resilience to noise [18,19,60,64,65,93,98,133], denoising [53,77,88,110,177], robust transmission [20,21,22,25,41,92,105,139,157,165], CDMA systems [131,161,168,169], multiantenna code design [100,104], segmentation [69,124,162], classification [48,124,162], prediction of epileptic seizures [16,17], restoration and enhancement [113], motion estimation [128], signal reconstruction [6], coding theory [101,143], operator theory [2], quantum theory and computing [80,151,153], and many others.…”
Section: Introductionmentioning
confidence: 99%
“…MRA for classification has been described previously via projections [8], or application of wavelet transforms to the feature sets [11]. A similar approach is described in [2]. In this article, we explicitly present the detail and approximation constructions (reconstructions at different scales) and utilize the LSTM algorithm on the resulting feature sets, taking as input all representation sequences for training.…”
Section: Introductionmentioning
confidence: 99%