Adaptive Multiresolution Techniques for Subcellular Protein Location Classification

Srinivasa, Gowri; Merryman, T.; Chebira, Amina; Kovačević, Jelena; S., Mintos, Alexia

doi:10.1109/icassp.2006.1661491

Cited by 5 publications

(8 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We now summarize our initial MR classification effort [12,13]. We started with a simple classification system consisting of Haralick texture feature computation followed by a maximum-likelihood classifier, and demonstrated that, by adding an MR block in front, we were able to raise the classification accuracy by roughly 10% (from 71.8% to 82.2%) as compared to the system with no MR.…”

Section: Introductionmentioning

confidence: 99%

A multiresolution approach to automated classification of protein subcellular location images

et al. 2007

View full text Add to dashboard Cite

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 date, 91.5%, was obtained by including a set of multiresolution features. This demonstrates the value of multiresolution approaches to this important problem.

show abstract

Section: Introductionmentioning

confidence: 99%

A multiresolution approach to automated classification of protein subcellular location images

et al. 2007

View full text Add to dashboard Cite

show abstract

“…There is no reason why our approach in [8] would not work if we viewed each of the subbands as an individual classification branch and applied a generic classifier to it. This would enable us to come up with individual classification decisions at each particular subband.…”

Section: Proposed Algorithmmentioning

confidence: 95%

“…As we just discussed, although in [8] we demonstrated the power of adaptive MR techniques, problems still remain, mostly due to the classifier we used (maximum likelihood). The algorithm adjusts the weights trying to maximize the overall classification accuracy; however, the previous best is not kept.…”

Section: Proposed Algorithmmentioning

confidence: 95%

“…Adaptive MR Maximum-Likelihood Classifier. Our first step was the algorithm developed in [8]; we summarize it here briefly. We started with a simple classification system consisting of Haralick texture feature computation followed by a maximum-likelihood classifier, and demonstrated that, by adding an MR block in front, we are able to raise the average classification accuracy by roughly 10% (see Table 1).…”

Section: Background and Previous Workmentioning

confidence: 99%

“…The average accuracy per class from[8]. If no multiresolution is used, the texture features outperform morphological, and together they achieve the accuracy of 69.4%, lower than texture features only.…”

mentioning

confidence: 94%

See 2 more Smart Citations

A Multiresolution Enhancement to Generic Classifiers of Subcellular Protein Location Images

Merryman

Williams

Srinivasa

et al.

3rd IEEE International Symposium on Biomedical Imaging: Macro to Nano, 2006.

Self Cite

View full text Add to dashboard Cite

We propose an algorithm for the classification of fluorescence microscopy images depicting the spatial distribution of proteins within the cell. The problem is at the forefront of the current trend in biology towards understanding the role and function of all proteins. The importance of protein subcellular location was pointed out by Murphy, whose group produced the first automated system for classification of images depicting these locations, based on diverse feature sets and combinations of classifiers. With the addition of the simplest multiresolution features, the same group obtained the highest reported accuracy of 91.5% for the denoised 2D HeLa data set. Here, we aim to improve upon that system by adding the true power of multiresolution-adaptivity. In the process, we build a system able to work with any feature sets and any classifiers, which we denote as a Generic Classification System (GCS). Our system consists of multiresolution (MR) decomposition in the front, followed by feature computation and classification in each subband, yielding local decisions. This is followed by the crucial step of combining all those local decisions into a global one, while at the same time ensuring that the resulting system does no worse than a no-decomposition one. On a nondenoised data set and a much smaller number of features (a combination of texture and Zernicke moment features) and a neural network classifier, we obtain a high accuracy of 89.8%, effectively proving that the space-frequency localized information in the subbands adds to the discriminative power of the system.

show abstract

Protein subcellular localization of fluorescence imagery using spatial and transform domain features

Tahir¹,

Khan²,

Majid³

2011

Bioinformatics

View full text Add to dashboard Cite

show abstract

Adaptive Multiresolution Techniques for Subcellular Protein Location Classification

Cited by 5 publications

References 6 publications

A multiresolution approach to automated classification of protein subcellular location images

A multiresolution approach to automated classification of protein subcellular location images

A Multiresolution Enhancement to Generic Classifiers of Subcellular Protein Location Images

Protein subcellular localization of fluorescence imagery using spatial and transform domain features

Contact Info

Product

Resources

About