Automated recognition system to classify subcellular protein localizations in images of different cell lines acquired by different imaging systems

Yuh Show Tsai, I. Fang Chung, Jeremy C. Simpson, Mei I. Lee, Chia Cheng Hsiung, Tai Yu Chiu, Lung Sen Kao, Te Cheng Chiu, Chin Teng Lin, Wen Chieh Lin, Sheng-Fu Liang, Chung Chih Lin

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Systemic analysis of subcellular protein localization (location proteomics) provides clues for understanding gene functions and physiological condition of the cells. However, recognition of cell images of subcellular structures highly depends on experience and becomes the rate-limiting step when classifying subcellular protein localization. Several research groups have extracted specific numerical features for the recognition of subcellular protein localization, but these recognition systems are restricted to images of single particular cell line acquired by one specific imaging system and not applied to recognize a range of cell image sources. In this study, we establish a single system for automated subcellular structure recognition to identify cell images from various sources. Two different sources of cell images, 317 Vero (http://gfp-cdna.embl.de) and 875 CHO cell images of subcellular structures, were used to train and test the system. When the system was trained by a single source of images, the recognition rate is high and specific to the trained source. The system trained by the CHO cell images gave high average recognition accuracy for CHO cells of 96%, but this was reduced to 46% with Vero images. When we trained the system using a mixture of CHO and Vero cell images, an average accuracy of recognition reached 86.6% for both CHO and Vero cell images. The system can reject images with low confidence and identify the cell images correctly recognized to avoid manual reconfirmation. In summary, we have established a single system that can recognize subcellular protein localizations from two different sources for location-proteomic studies.

Original languageEnglish
Pages (from-to)305-314
Number of pages10
JournalMicroscopy Research and Technique
Volume71
Issue number4
DOIs
Publication statusPublished - 2008 Apr 1

Fingerprint

cultured cells
CHO Cells
Imaging systems
Cells
proteins
Proteins
Cell Line
cells
Vero Cells
Proteomics
Genes
Research
classifying
genes
confidence

All Science Journal Classification (ASJC) codes

  • Anatomy
  • Histology
  • Instrumentation
  • Medical Laboratory Technology

Cite this

Tsai, Yuh Show ; Chung, I. Fang ; Simpson, Jeremy C. ; Lee, Mei I. ; Hsiung, Chia Cheng ; Chiu, Tai Yu ; Kao, Lung Sen ; Chiu, Te Cheng ; Lin, Chin Teng ; Lin, Wen Chieh ; Liang, Sheng-Fu ; Lin, Chung Chih. / Automated recognition system to classify subcellular protein localizations in images of different cell lines acquired by different imaging systems. In: Microscopy Research and Technique. 2008 ; Vol. 71, No. 4. pp. 305-314.
@article{65e6da40108b4f07b0e6cf722576cdde,
title = "Automated recognition system to classify subcellular protein localizations in images of different cell lines acquired by different imaging systems",
abstract = "Systemic analysis of subcellular protein localization (location proteomics) provides clues for understanding gene functions and physiological condition of the cells. However, recognition of cell images of subcellular structures highly depends on experience and becomes the rate-limiting step when classifying subcellular protein localization. Several research groups have extracted specific numerical features for the recognition of subcellular protein localization, but these recognition systems are restricted to images of single particular cell line acquired by one specific imaging system and not applied to recognize a range of cell image sources. In this study, we establish a single system for automated subcellular structure recognition to identify cell images from various sources. Two different sources of cell images, 317 Vero (http://gfp-cdna.embl.de) and 875 CHO cell images of subcellular structures, were used to train and test the system. When the system was trained by a single source of images, the recognition rate is high and specific to the trained source. The system trained by the CHO cell images gave high average recognition accuracy for CHO cells of 96{\%}, but this was reduced to 46{\%} with Vero images. When we trained the system using a mixture of CHO and Vero cell images, an average accuracy of recognition reached 86.6{\%} for both CHO and Vero cell images. The system can reject images with low confidence and identify the cell images correctly recognized to avoid manual reconfirmation. In summary, we have established a single system that can recognize subcellular protein localizations from two different sources for location-proteomic studies.",
author = "Tsai, {Yuh Show} and Chung, {I. Fang} and Simpson, {Jeremy C.} and Lee, {Mei I.} and Hsiung, {Chia Cheng} and Chiu, {Tai Yu} and Kao, {Lung Sen} and Chiu, {Te Cheng} and Lin, {Chin Teng} and Lin, {Wen Chieh} and Sheng-Fu Liang and Lin, {Chung Chih}",
year = "2008",
month = "4",
day = "1",
doi = "10.1002/jemt.20555",
language = "English",
volume = "71",
pages = "305--314",
journal = "Microscopy Research and Technique",
issn = "1059-910X",
publisher = "Wiley-Liss Inc.",
number = "4",

}

Tsai, YS, Chung, IF, Simpson, JC, Lee, MI, Hsiung, CC, Chiu, TY, Kao, LS, Chiu, TC, Lin, CT, Lin, WC, Liang, S-F & Lin, CC 2008, 'Automated recognition system to classify subcellular protein localizations in images of different cell lines acquired by different imaging systems', Microscopy Research and Technique, vol. 71, no. 4, pp. 305-314. https://doi.org/10.1002/jemt.20555

Automated recognition system to classify subcellular protein localizations in images of different cell lines acquired by different imaging systems. / Tsai, Yuh Show; Chung, I. Fang; Simpson, Jeremy C.; Lee, Mei I.; Hsiung, Chia Cheng; Chiu, Tai Yu; Kao, Lung Sen; Chiu, Te Cheng; Lin, Chin Teng; Lin, Wen Chieh; Liang, Sheng-Fu; Lin, Chung Chih.

In: Microscopy Research and Technique, Vol. 71, No. 4, 01.04.2008, p. 305-314.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Automated recognition system to classify subcellular protein localizations in images of different cell lines acquired by different imaging systems

AU - Tsai, Yuh Show

AU - Chung, I. Fang

AU - Simpson, Jeremy C.

AU - Lee, Mei I.

AU - Hsiung, Chia Cheng

AU - Chiu, Tai Yu

AU - Kao, Lung Sen

AU - Chiu, Te Cheng

AU - Lin, Chin Teng

AU - Lin, Wen Chieh

AU - Liang, Sheng-Fu

AU - Lin, Chung Chih

PY - 2008/4/1

Y1 - 2008/4/1

N2 - Systemic analysis of subcellular protein localization (location proteomics) provides clues for understanding gene functions and physiological condition of the cells. However, recognition of cell images of subcellular structures highly depends on experience and becomes the rate-limiting step when classifying subcellular protein localization. Several research groups have extracted specific numerical features for the recognition of subcellular protein localization, but these recognition systems are restricted to images of single particular cell line acquired by one specific imaging system and not applied to recognize a range of cell image sources. In this study, we establish a single system for automated subcellular structure recognition to identify cell images from various sources. Two different sources of cell images, 317 Vero (http://gfp-cdna.embl.de) and 875 CHO cell images of subcellular structures, were used to train and test the system. When the system was trained by a single source of images, the recognition rate is high and specific to the trained source. The system trained by the CHO cell images gave high average recognition accuracy for CHO cells of 96%, but this was reduced to 46% with Vero images. When we trained the system using a mixture of CHO and Vero cell images, an average accuracy of recognition reached 86.6% for both CHO and Vero cell images. The system can reject images with low confidence and identify the cell images correctly recognized to avoid manual reconfirmation. In summary, we have established a single system that can recognize subcellular protein localizations from two different sources for location-proteomic studies.

AB - Systemic analysis of subcellular protein localization (location proteomics) provides clues for understanding gene functions and physiological condition of the cells. However, recognition of cell images of subcellular structures highly depends on experience and becomes the rate-limiting step when classifying subcellular protein localization. Several research groups have extracted specific numerical features for the recognition of subcellular protein localization, but these recognition systems are restricted to images of single particular cell line acquired by one specific imaging system and not applied to recognize a range of cell image sources. In this study, we establish a single system for automated subcellular structure recognition to identify cell images from various sources. Two different sources of cell images, 317 Vero (http://gfp-cdna.embl.de) and 875 CHO cell images of subcellular structures, were used to train and test the system. When the system was trained by a single source of images, the recognition rate is high and specific to the trained source. The system trained by the CHO cell images gave high average recognition accuracy for CHO cells of 96%, but this was reduced to 46% with Vero images. When we trained the system using a mixture of CHO and Vero cell images, an average accuracy of recognition reached 86.6% for both CHO and Vero cell images. The system can reject images with low confidence and identify the cell images correctly recognized to avoid manual reconfirmation. In summary, we have established a single system that can recognize subcellular protein localizations from two different sources for location-proteomic studies.

UR - http://www.scopus.com/inward/record.url?scp=42049114520&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=42049114520&partnerID=8YFLogxK

U2 - 10.1002/jemt.20555

DO - 10.1002/jemt.20555

M3 - Article

VL - 71

SP - 305

EP - 314

JO - Microscopy Research and Technique

JF - Microscopy Research and Technique

SN - 1059-910X

IS - 4

ER -