Premium
Discrimination of fibroblast subtypes by multivariate analysis of gene expression
Author(s) -
Spanakis Emmanuel,
BroutyBoyé Danièle
Publication year - 1997
Publication title -
international journal of cancer
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 2.475
H-Index - 234
eISSN - 1097-0215
pISSN - 0020-7136
DOI - 10.1002/(sici)1097-0215(19970502)71:3<402::aid-ijc17>3.0.co;2-h
Subject(s) - myofibroblast , biology , stroma , stromal cell , pathology , fibroblast , cell type , fibrosis , gene expression , gene , cell , cancer research , immunohistochemistry , cell culture , genetics , immunology , medicine
Fibroblasts and myofibroblasts from normal, fibrotic or tumoral breast tissues present multiple quantitative differences in gene expression even when grown in isolation. We were therefore prompted to investigate whether one could recognize various subtypes by their constitutive‐gene expression profile. Quantitative autoradiographic data for 34 constitutively expressed transcripts were submitted to multivariate analysis of variance, followed by discriminant analysis and single linkage cluster analysis. Models assuming up to 8 putative fibroblast subtypes (among fibroblasts or myofibroblasts from breast skin, normal mammary stroma, tumor‐adjacent “normal” stroma, post‐radiation fibrosis lesions and benign or malignant tumors) and an epithelial‐cell group used as an internal control resulted in 100% correct classification. Myofibroblasts from various origins clustered close to, although distinctly apart from, their corresponding α‐smooth‐muscle‐actin‐negative counterparts. Malignant tumor fibroblasts were phenotypically more distant from normal cells compared with other pathological types. Our results support the hypothesis of co‐adaptive transformation of stromal and epithelial tissues during breast tumoral development and suggest that different types of fibroblasts give rise to different types of myofibroblasts. Discriminant analysis of quantitative molecular variation may be considered for the development of a powerful artificial‐inteligence method for cell typing and should be particularly useful when no reliable discrete molecular markers are available. Int. J. Cancer 71:402‐409, 1997. © 1997 Wiley‐Liss Inc.