Spatial segmentation and feature selection for desi imaging mass spectrometry data with spatially-aware sparse clustering

Bemis, Kyle D.; Eberlin, Lívia S.; Ferreira, Christina R.; Cooks, R. Graham; Vitek, Olga

doi:10.1186/1471-2105-13-s18-a8

Cited by 4 publications

(4 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For localized quantification of analytes in tissue, a successful outcome generally depends on appropriate deposition of internal standard. Various approaches exist in the imaging mass spectrometry field. − These include normalization to a matrix compound that was homogeneously deposited with MALDI and DESI, addition of internal standard to the spray solvent with nano-DESI, and normalizing to the total ion count. − Another method that has been used is a tissue extraction coefficient (TEC), to account for various ion suppression factors in a tissue sample. , We consider a selection of these approaches here for compatibility with DAPNe. One potential advantage of DAPNe over other techniques is that the diameter of the spot can be measured (by visualizing the wetted area under a microscope directly after extraction), and this allows for another normalization (the spot area) to be used.…”

mentioning

confidence: 99%

Application of Various Normalization Methods for Microscale Analysis of Tissues Using Direct Analyte Probed Nanoextraction

et al. 2018

View full text Add to dashboard Cite

Direct analyte probed nanoextraction (DAPNe) is a method of extracting material from a microscale region of a sample and provides the opportunity for detailed mass spectrometry analysis of extracted analytes from a small area. The technique has been shown to provide enhanced sensitivity compared with bulk analysis by selectively removing analytes from their matrix and has been applied for selective analysis of single cells and even single organelles. However, the quantitative capabilities of the technique are yet to be fully evaluated. In this study, various normalization techniques were investigated in order to improve the quantitative capabilities of the technique. Two methods of internal standard incorporation were applied to test substrates, which were designed to replicate biological sample matrices. Additionally, normalization to the extraction spot area and matrix compounds were investigated for suitability in situations when an internal standard is not available. The variability observed can be significantly reduced by using a sprayed internal standard and, in some cases, by normalizing to the extracted area.

show abstract

mentioning

confidence: 99%

Application of Various Normalization Methods for Microscale Analysis of Tissues Using Direct Analyte Probed Nanoextraction

et al. 2018

View full text Add to dashboard Cite

show abstract

“…Bemis et al [12] presented statistic-based signal processing and feature selection methods for desorption electrospray ionization (DESI) imaging mass spectrometry experiments. Their method performs a better spatial segmentation and improves the mapping between morphological and functional structures.…”

Section: Student Presentationsmentioning

confidence: 99%

Highlights from the Eighth International Society for Computational Biology (ISCB) Student Council Symposium 2012

et al. 2012

View full text Add to dashboard Cite

show abstract

“…Thus far, many information-processing algorithms have been proposed and considerably benefited people [7][8]. Among these algorithms, clustering methods, which are one of popular techniques, are being widely used in data mining, object classification, pattern recognition, machine learning, image analysis, information retrieval and bioinformatics [9][10][11][12][13][14][15]. There are two types of clus-tering approaches: the supervised algorithm and the unsupervised algorithm [16].…”

Section: Introductionmentioning

confidence: 99%

K-means based Clustering Method with a Fixed Number of Cluster Members

Moon²

2014

Journal of Korea Multimedia Society

View full text Add to dashboard Cite

Clustering methods are very useful in many fields such as data mining, classification, and object recognition. Both the supervised and unsupervised grouping approaches can classify a series of sample data with a predefined or automatically assigned cluster number. However, there is no constraint on the number of elements for each cluster. Numbers of cluster members for each cluster obtained from clustering schemes are usually random. Thus, some clusters possess a large number of elements whereas others only have a few members. In some areas such as logistics management, a fixed number of members are preferred for each cluster or logistic center. Consequently, it is necessary to design a clustering method that can automatically adjust the number of group elements. In this paper, a k-means based clustering method with a fixed number of cluster members is proposed. In the proposed method, first, the data samples are clustered using the k-means algorithm. Then, the number of group elements is adjusted by employing a greedy strategy. Experimental results demonstrate that the proposed clustering scheme can classify data samples efficiently for a fixed number of cluster members.

show abstract

Spatial segmentation and feature selection for desi imaging mass spectrometry data with spatially-aware sparse clustering

Cited by 4 publications

References 1 publication

Application of Various Normalization Methods for Microscale Analysis of Tissues Using Direct Analyte Probed Nanoextraction

Application of Various Normalization Methods for Microscale Analysis of Tissues Using Direct Analyte Probed Nanoextraction

Highlights from the Eighth International Society for Computational Biology (ISCB) Student Council Symposium 2012

K-means based Clustering Method with a Fixed Number of Cluster Members

Contact Info

Product

Resources

About