Multiple approaches to data‐mining of proteomic data based on statistical and pattern classification methods

Tatay, Jacob W.; Feng, Xin; Sobczak, Nancy; Jiang, Hao; Chen, Chin-Fu; Kirova, Roumyana; Struble, Craig A.; Wang, Nan Jiang; Tonellato, Peter J.

doi:10.1002/pmic.200300512

Cited by 16 publications

(9 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Identification of disease specific proteins could yield mechanistic information as well as potential diagnostic markers or drug targets. The importance in recognizing these points is highlighted in recent comparative analyses of profile spectra [25][26][27][28][29][30][31], whereby varied biostatisticians all reported an accuracy >90% in classifying the same profile spectra from either tumor or non-tumor samples. However, in identifying which ions were most significant in determining the classifications there was little to no agreement.…”

Section: Introductionmentioning

confidence: 99%

Processing MALDI mass spectra to improve mass spectral direct tissue analysis

Norris¹,

Cornett

Mobley

et al. 2007

International Journal of Mass Spectrometry

194

188

View full text Add to dashboard Cite

Profiling and imaging biological specimens using MALDI mass spectrometry has significant potential to contribute to our understanding and diagnosis of disease. The technique is efficient and high-throughput providing a wealth of data about the biological state of the sample from a very simple and direct experiment. However, in order for these techniques to be put to use for clinical purposes, the approaches used to process and analyze the data must improve. This study examines some of the existing tools to baseline subtract, normalize, align, and remove spectral noise for MALDI data, comparing the advantages of each. A preferred workflow is presented that can be easily implemented for data in ASCII format. The advantages of using such an approach are discussed for both molecular profiling and imaging mass spectrometry.

show abstract

Section: Introductionmentioning

confidence: 99%

Processing MALDI mass spectra to improve mass spectral direct tissue analysis

Norris¹,

Cornett

Mobley

et al. 2007

International Journal of Mass Spectrometry

194

188

View full text Add to dashboard Cite

show abstract

“…Distinguishing protein ions as disease-specific requires isolating those abundance changes symptomatic of disease from those changes influenced by experimental conditions. From this perspective, various studies have explored techniques for pre-processing spectra as a means of minimizing overall variance (7)(8)(9)(10)(11) prior to statistical analysis, but these procedures vary and do not completely eliminate inconsistent classification results (7,(11)(12)(13)(14)(15). Nevertheless, the existing body of work is strong evidence that biomarker discovery by tissue profiling is possible and may one day benefit the clinical diagnosis and treatment of disease.…”

mentioning

confidence: 99%

A Novel Histology-directed Strategy for MALDI-MS Tissue Profiling That Improves Throughput and Cellular Specificity in Human Breast Cancer

Cornett

Mobley

Dias

et al. 2006

Molecular & Cellular Proteomics

175

149

View full text Add to dashboard Cite

We describe a novel tissue profiling strategy that improves the cellular specificity and analysis throughput of protein profiles obtained by direct MALDI analysis. The new approach integrates the cellular specificity of histology, the accuracy and reproducibility of robotic liquid dispensing, and the speed and objectivity of automated spectra acquisition. Traditional methodologies for preparing and analyzing tissue samples rely heavily on manual procedures, which for various reasons discussed, restrict cellular specificity and sample throughput. Here, a robotic spotter deposits micron-sized droplets of matrix precisely onto foci of normal mammary epithelium, ductal carcinoma in situ, invasive mammary cancer, and peritumoral stroma selected by a pathologist from high resolution histological images of sectioned human breast cancer samples. The location of each matrix spot was then determined and uploaded into the instrument to facilitate automated profile acquisition by MALDI-TOF. In the example shown, the different lesions were clearly differentiated using mass profiling. Further, the workflow permits a visual projection of any information produced from the profile analyses directly on the histological image for a unique combination of proteomic and histological assessment of sample regions. The higher performance characteristics offered by the new workflow promises to be a significant advancement toward the next generation of tissue profiling studies. Molecular & Cellular Proteomics 5: 1975-1983, 2006.

show abstract

“…A well‐designed data pre‐processing and multivariate analysis step must be performed for the recognition of the proteins evaluated as significant in the classification, otherwise from the same data set different results can be obtained. For example, in many recent comparative studies concerning the same tumor/non‐tumor protein patterns,26–32 a prediction ability >90% was always obtained, but there was no agreement about the proteins involved in the discrimination.…”

Section: Resultsmentioning

confidence: 96%

Serum protein profiling in patients with inflammatory bowel diseases using selective solid‐phase bulk extraction, matrix‐assisted laser desorption/ionization time‐of‐flight mass spectrometry and chemometric data analysis

Nanni

Parisi

Roda

et al. 2007

Rapid Comm Mass Spectrometry

View full text Add to dashboard Cite

The identification of new biomarkers or a disease-related protein fingerprint for inflammatory bowel diseases (IBDs) represents a major task in the diagnosis, prognosis and pharmacological therapy. To address these issues, a simple and rapid analytical proteomic method for serum protein profiling based on selective beads-based solid-phase bulk extraction, matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) and chemometric data analysis was developed. Serum proteins from healthy subjects (22) and patients with Crohn's disease (15) and ulcerative colitis (26) were selectively extracted according to reversed-phase (C18), strong anion-exchange (SAX) and metal ion affinity (IDA-Cu(II)) principles. This approach allowed enrichment of serum proteins/peptides due to the high interaction surface between analytes and the solid phase and high recovery due to the elution step performed directly on the MALDI-target plate. The MALDI-TOF MS serum protein profiles were acquired and, after a data pre-processing step, analyzed by linear discriminant analysis (LDA), a chemometric classification technique, in order to classify serum samples among healthy subjects and patients with inflammatory bowel diseases (IBDs). Since the high number of variables in the MALDI spectra (more than 16000 m/z values) prevents the use of LDA, the variables were reduced to 10-20 by features selection, thus allowing the evaluation of a pattern of m/z values with high discriminant power. Serum protein profiles obtained by reversed-phase extraction and the selection of 20 m/z values gave the best overall prediction ability (96.9%). The recognition of these m/z values may allow the identification of protein biomarkers involved in IBDs.

show abstract

Multiple approaches to data‐mining of proteomic data based on statistical and pattern classification methods

Cited by 16 publications

References 7 publications

Processing MALDI mass spectra to improve mass spectral direct tissue analysis

Processing MALDI mass spectra to improve mass spectral direct tissue analysis

A Novel Histology-directed Strategy for MALDI-MS Tissue Profiling That Improves Throughput and Cellular Specificity in Human Breast Cancer

Serum protein profiling in patients with inflammatory bowel diseases using selective solid‐phase bulk extraction, matrix‐assisted laser desorption/ionization time‐of‐flight mass spectrometry and chemometric data analysis

Contact Info

Product

Resources

About