Feature selection and nearest centroid classification for protein mass spectrometry

Abstract

Background: The use of mass spectrometry as a proteomics tool is poised to revolutionize early disease diagnosis and biomarker identification. Unfortunately, before standard supervised classification algorithms can be employed, the "curse of dimensionality" needs to be solved. Due to the sheer amount of information contained within the mass spectra, most standard machine learning techniques cannot be directly applied. Instead, feature selection techniques are used to first reduce the dimensionality of the input space and thus enable the subsequent use of classification algorithms. This paper examines feature selection techniques for proteomic mass spectrometry.

Statistical data processing in clinical proteomics

“…Wrapper [17] and filter [18] methods have also been used for biomarker selection, and vice versa: some intrinsic methods are used for pre-selection to provide input for other classification methods [19,20]. We would like to point out that statistical validation is of crucial importance in variable selection, as it is throughout the entire data analysis.…”

Computational Intelligence in Medicine and Biology: A Survey

“…Apart from basic research that has benefited a lot from the fusion of computational intelligence into biological research as previously shown, molecular medicine and especially molecular diagnostics is a rapidly evolving field that incorporates high throughput technologies of proteomics [216][217][218][219][220][221][222][223][224][225][226][227][228][229] and genomics (e.g., MALDI, SELDI, microarrays). The basic question that these high tech biotechnological systems combined with the state-ofthe-art CI techniques try to solve is the discovery of efficient biomarkers for crucial diseases, contributing this way to the desired early diagnosis or even prognosis.…”

Proteomic-Based Biomarker Discovery with Emphasis on Cerebrospinal Fluid and Multiple Sclerosis

“…This leads the way into the field of supervised learning methods. A wide variety of techniques exist, some of which have been used in proteomic-based research; support vector machines (SVMs) [58], nearest centroid method [59], decision trees [60][61][62][63], artificial neural networks [64], logistic regression [63], linear discriminant analysis [63] and combinations of methods [65]. These methods all have their advantages and disadvantages, some of them can be easily interpreted to obtain biological knowledge (decision trees) others are more difficult to interpret and work as a black box classifier.…”