Object type recognition for automated analysis of protein subcellular location

Ting Zhao, Meel Velliste, Michael Boland, Robert F. Murphy

Research output: Contribution to journalArticle

Abstract

The new field of location proteomics seeks to provide a comprehensive, objective characterization of the subcellular locations of all proteins expressed in a given cell type. Previous work has demonstrated that automated classifiers can recognize the patterns of all major subcellular organelles and structures in fluorescence microscope images with high accuracy. However, since some proteins may be present in more than one organelle, this paper addresses a more difficult task: recognizing a pattern that is a mixture of two or more fundamental patterns. The approach utilizes an object-based image model, in which each image of a location pattern is represented by a set of objects of distinct, learned types. Using a two-stage approach in which object types are learned and then cell-level features are calculated based on the object types, the basic location patterns were well recognized. Given the object types, a multinomial mixture model was built to recognize mixture patterns. Under appropriate conditions, synthetic mixture patterns can be decomposed with over 80% accuracy, which, for the first time, shows that the problem of computationally decomposing subcellular patterns into fundamental organelle patterns can be solved.

Original languageEnglish (US)
Pages (from-to)1351-1359
Number of pages9
JournalIEEE Transactions on Image Processing
Volume14
Issue number9
DOIs
StatePublished - Sep 2005
Externally publishedYes

Fingerprint

Proteins
Protein
Microscopes
Classifiers
Fluorescence
Object
Multinomial Model
Image Model
Proteomics
Cell
Mixture Model
Microscope
High Accuracy
Classifier
Distinct

Keywords

  • Fluorescence microscopy
  • Image modeling
  • Location proteomics
  • Mixed-pattern decomposition
  • Object type recognition
  • Protein subcellular location

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Graphics and Computer-Aided Design
  • Software
  • Theoretical Computer Science
  • Computational Theory and Mathematics
  • Computer Vision and Pattern Recognition

Cite this

Object type recognition for automated analysis of protein subcellular location. / Zhao, Ting; Velliste, Meel; Boland, Michael; Murphy, Robert F.

In: IEEE Transactions on Image Processing, Vol. 14, No. 9, 09.2005, p. 1351-1359.

Research output: Contribution to journalArticle

Zhao, Ting ; Velliste, Meel ; Boland, Michael ; Murphy, Robert F. / Object type recognition for automated analysis of protein subcellular location. In: IEEE Transactions on Image Processing. 2005 ; Vol. 14, No. 9. pp. 1351-1359.
@article{df30b708efa74f499f57d763cc0ce5fb,
title = "Object type recognition for automated analysis of protein subcellular location",
abstract = "The new field of location proteomics seeks to provide a comprehensive, objective characterization of the subcellular locations of all proteins expressed in a given cell type. Previous work has demonstrated that automated classifiers can recognize the patterns of all major subcellular organelles and structures in fluorescence microscope images with high accuracy. However, since some proteins may be present in more than one organelle, this paper addresses a more difficult task: recognizing a pattern that is a mixture of two or more fundamental patterns. The approach utilizes an object-based image model, in which each image of a location pattern is represented by a set of objects of distinct, learned types. Using a two-stage approach in which object types are learned and then cell-level features are calculated based on the object types, the basic location patterns were well recognized. Given the object types, a multinomial mixture model was built to recognize mixture patterns. Under appropriate conditions, synthetic mixture patterns can be decomposed with over 80{\%} accuracy, which, for the first time, shows that the problem of computationally decomposing subcellular patterns into fundamental organelle patterns can be solved.",
keywords = "Fluorescence microscopy, Image modeling, Location proteomics, Mixed-pattern decomposition, Object type recognition, Protein subcellular location",
author = "Ting Zhao and Meel Velliste and Michael Boland and Murphy, {Robert F.}",
year = "2005",
month = "9",
doi = "10.1109/TIP.2005.852456",
language = "English (US)",
volume = "14",
pages = "1351--1359",
journal = "IEEE Transactions on Image Processing",
issn = "1057-7149",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "9",

}

TY - JOUR

T1 - Object type recognition for automated analysis of protein subcellular location

AU - Zhao, Ting

AU - Velliste, Meel

AU - Boland, Michael

AU - Murphy, Robert F.

PY - 2005/9

Y1 - 2005/9

N2 - The new field of location proteomics seeks to provide a comprehensive, objective characterization of the subcellular locations of all proteins expressed in a given cell type. Previous work has demonstrated that automated classifiers can recognize the patterns of all major subcellular organelles and structures in fluorescence microscope images with high accuracy. However, since some proteins may be present in more than one organelle, this paper addresses a more difficult task: recognizing a pattern that is a mixture of two or more fundamental patterns. The approach utilizes an object-based image model, in which each image of a location pattern is represented by a set of objects of distinct, learned types. Using a two-stage approach in which object types are learned and then cell-level features are calculated based on the object types, the basic location patterns were well recognized. Given the object types, a multinomial mixture model was built to recognize mixture patterns. Under appropriate conditions, synthetic mixture patterns can be decomposed with over 80% accuracy, which, for the first time, shows that the problem of computationally decomposing subcellular patterns into fundamental organelle patterns can be solved.

AB - The new field of location proteomics seeks to provide a comprehensive, objective characterization of the subcellular locations of all proteins expressed in a given cell type. Previous work has demonstrated that automated classifiers can recognize the patterns of all major subcellular organelles and structures in fluorescence microscope images with high accuracy. However, since some proteins may be present in more than one organelle, this paper addresses a more difficult task: recognizing a pattern that is a mixture of two or more fundamental patterns. The approach utilizes an object-based image model, in which each image of a location pattern is represented by a set of objects of distinct, learned types. Using a two-stage approach in which object types are learned and then cell-level features are calculated based on the object types, the basic location patterns were well recognized. Given the object types, a multinomial mixture model was built to recognize mixture patterns. Under appropriate conditions, synthetic mixture patterns can be decomposed with over 80% accuracy, which, for the first time, shows that the problem of computationally decomposing subcellular patterns into fundamental organelle patterns can be solved.

KW - Fluorescence microscopy

KW - Image modeling

KW - Location proteomics

KW - Mixed-pattern decomposition

KW - Object type recognition

KW - Protein subcellular location

UR - http://www.scopus.com/inward/record.url?scp=26444451080&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=26444451080&partnerID=8YFLogxK

U2 - 10.1109/TIP.2005.852456

DO - 10.1109/TIP.2005.852456

M3 - Article

C2 - 16190470

AN - SCOPUS:26444451080

VL - 14

SP - 1351

EP - 1359

JO - IEEE Transactions on Image Processing

JF - IEEE Transactions on Image Processing

SN - 1057-7149

IS - 9

ER -