New algorithms for multi-class cancer diagnosis using tumor gene expression signatures

Bagirov, Adil M.; Ferguson, Brent; Ivkovic, Sasha; Saunders, Geoff; Yearwood, John

doi:10.1093/bioinformatics/btg238

Cited by 45 publications

(19 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Use of protein markers and marker fragments in combination is likely to confer higher specificity than using any single one. [12][13][14][15] Singular value decomposition (SVD) was applied to the data of the 2 forms of ApoA1 and 4 forms of transthyretin to allow for visualization at reduced dimension. 16 The groups of ovarian cancer samples, controls and the breast, colon and prostate cancer samples each formed overlapping but distinguishable clusters with moderately good separation from one another in the 2-dimensional space spanned by the first and third components of the SVD analysis (Fig.…”

Section: Resultsmentioning

confidence: 99%

Classification of cancer types by measuring variants of host response proteins using SELDI serum assays

Fung¹,

Yip²,

Lomas³

et al. 2005

Intl Journal of Cancer

168

160

View full text Add to dashboard Cite

Protein expression profiling has been increasingly used to discover and characterize biomarkers that can be used for diagnostic, prognostic or therapeutic purposes. Most proteomic studies published to date have identified relatively abundant host response proteins as candidate biomarkers, which are often dismissed because of an apparent lack of specificity. We demonstrate that 2 host response proteins previously identified as candidate markers for early stage ovarian cancer, transthyretin and inter-alpha trypsin inhibitor heavy chain 4 (ITIH4), are posttranslationally modified. These modifications include proteolytic truncation, cysteinylation and glutathionylation. Assays using Surface Enhanced Laser Desorption/Ionization Time of Flight Mass Spectrometry (SELDI-TOF-MS) may provide a means to confer specificity to these proteins because of their ability to detect and quantitate multiple posttranslationally modified forms of these proteins in a single assay. Quantitative measurements of these modifications using chromatographic and antibody-based ProteinChip1 array assays reveal that these posttranslational modifications occur to different extents in different cancers and that multivariate analysis permits the derivation of algorithms to improve the classification of these cancers. We have termed this process host response protein amplification cascade (HRPAC), since the process of synthesis, posttranslational modification and metabolism of host response proteins amplifies the signal of potentially low-abundant biologically active disease markers such as enzymes. ' 2005 Wiley-Liss, Inc.

show abstract

Section: Resultsmentioning

confidence: 99%

Classification of cancer types by measuring variants of host response proteins using SELDI serum assays

Fung¹,

Yip²,

Lomas³

et al. 2005

Intl Journal of Cancer

168

160

View full text Add to dashboard Cite

show abstract

“…Using a recursive feature selection procedure and support vector machine (SVM) classification algorithm, Ramaswamy et al4 obtained their best result with 42 tumors correctly predicted among the 54 test samples, corresponding to an accuracy of 78%. Using a feature selection algorithm based on overlaps of gene expression values between different classes in conjunction with the Covering Classification Algorithm (CCA), a modification of the k-NN method, Bagirov et al17 achieved prediction accuracy of around 80%. Based on the concept of gene interaction, Antonov et al18 proposed a Maximal Margin Linear Programming (MAMA) procedure that combines linear programming and SVM and they got around 85.2% classification accuracy on an OVA set up.…”

Section: Resultsmentioning

confidence: 99%

Comparison of Two Output-Coding Strategies for Multi-Class Tumor Classification Using Gene Expression Data and Latent Variable Model as Binary Classifier

et al. 2010

View full text Add to dashboard Cite

Multi-class cancer classification based on microarray data is described. A generalized output-coding scheme based on One Versus One (OVO) combined with Latent Variable Model (LVM) is used. Results from the proposed One Versus One (OVO) outputcoding strategy is compared with the results obtained from the generalized One Versus All (OVA) method and their efficiencies of using them for multi-class tumor classification have been studied. This comparative study was done using two microarray gene expression data: Global Cancer Map (GCM) dataset and brain cancer (BC) dataset. Primary feature selection was based on fold change and penalized t-statistics. Evaluation was conducted with varying feature numbers. The OVO coding strategy worked quite well with the BC data, while both OVO and OVA results seemed to be similar for the GCM data. The selection of output coding methods for combining binary classifiers for multi-class tumor classification depends on the number of tumor types considered, the discrepancies between the tumor samples used for training as well as the heterogeneity of expression within the cancer subtypes used as training data.

show abstract

“…To solve this optimization problem, different optimization functions are proposed and solutions are provided. Bagirov et al designed the optimization function to find the cluster centroids by minimizing the sum of the deviations of all tissue samples [15]:…”

Section: Optimization Functionmentioning

confidence: 99%

Pattern recognition methods in microarray based oncology study

Lu¹,

Zhang

2009

Front. Electr. Electron. Eng. China

View full text Add to dashboard Cite

With the development of microarray technology, more and more microarray-based oncology studies have been carried out. Huge amounts of data and the complexity of cancer mechanisms make data analysis methods a much more important part of these studies. In this article, we will mainly focus on the pattern recognition methods used in oncology studies. According to the availability of sample information, the unsupervised methods and supervised methods are reviewed separately. Finally, some possible future directions are proposed.

show abstract

New algorithms for multi-class cancer diagnosis using tumor gene expression signatures

Abstract: Available on request from the authors.

Cited by 45 publications

References 18 publications

Classification of cancer types by measuring variants of host response proteins using SELDI serum assays

Classification of cancer types by measuring variants of host response proteins using SELDI serum assays

Comparison of Two Output-Coding Strategies for Multi-Class Tumor Classification Using Gene Expression Data and Latent Variable Model as Binary Classifier

Pattern recognition methods in microarray based oncology study

Contact Info

Product

Resources

About