Targeted Feature Extraction in MALDI Mass Spectrometry Imaging to Discriminate Proteomic Profiles of Breast and Ovarian Cancer. Issue 1 (19th December 2018)

• Record Type: Journal Article
• Authors: Cordero Hernandez, Yovany; Boskamp, Tobias; Casadonte, Rita; Hauberg‐Lotte, Lena; Oetjen, Janina; Lachmund, Delf; Peter, Annette; Trede, Dennis; Kriegsmann, Katharina; Kriegsmann, Mark; Kriegsmann, Jörg; Maass, Peter
• Other Names: Longuespée Rémi guestEditor.; Casadonte Rita guestEditor.; Schwamborn Kristina guestEditor.; Kriegsmann Mark guestEditor.
• Is Part Of: Proteomics. Volume 13:Issue 1(2019)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2018-12-19
• Subjects: biomarker proteins -- feature extraction -- matrix‐assisted laser desorption/ionization mass spectrometry imaging -- tissue classification -- tumor typing; Proteomics -- Periodicals; 572.605
• DOI: 10.1002/prca.201700168
• Languages: English
• ISSNs: 1862-8346

Abstract

Abstract : Purpose: To develop a mass spectrometry imaging (MSI) based workflow for extracting m/z values related to putative protein biomarkers and using these for reliable tumor classification. Experimental design: Given a list of putative breast and ovarian cancer biomarker proteins, a set of related m/z values are extracted from heterogeneous MSI datasets derived from formalin‐fixed paraffin‐embedded tissue material. Based on these features, a linear discriminant analysis classification model is trained to discriminate the two tumor types. Results: It is shown that the discriminative power of classification models based on the extracted features is increased compared to the automatic training approach, especially when classifiers are applied to spectral data acquired under different conditions (instrument, preparation, laboratory). Conclusions and clinical relevance: Robust classification models not confounded by technical variation between MSI measurements are obtained. This supports the assumption that the classification of the respective tumor types is based on biological rather than technical differences, and that the selected features are related to the proteomic profiles of the tumor types under consideration.