Highly accurate two-gene classifier for differentiating gastrointestinal stromal tumors and leiomyosarcomas

Abstract

Gastrointestinal stromal tumor (GIST) has emerged as a clinically distinct type of sarcoma with frequent overexpression and mutation of the c-Kit oncogene and a favorable response to imatinib mesylate [also known as STI571 (Gleevec)] therapy. However, a significant diagnostic challenge remains in the differentiation of GIST from leiomyosarcomas (LMSs). To improve on the diagnostic evaluation and to complement the immunohistochemical evaluation of these tumors, we performed a whole-genome gene expression study on 68 well characterized tumor samples. Using bioinformatic approaches, we devised a two-gene relative expression classifier that distinguishes between GIST and LMS with an accuracy of 99.3% on the microarray samples and an estimated accuracy of 97.8% on future cases. We validated this classifier by using RT-PCR on 20 samples in the microarray study and on an additional 19 independent samples, with 100% accuracy. Thus, our two-gene relative expression classifier is a highly accurate diagnostic method to distinguish between GIST and LMS and has the potential to be rapidly implemented in a clinical setting. The success of this classifier is likely due to two general traits, namely that the classifier is independent of data normalization and that it uses as simple an approach as possible to achieve this independence to avoid overfitting. We expect that the use of simple marker pairs that exhibit these traits will be of significant clinical use in a variety of contexts.cancer ͉ classification ͉ diagnostic ͉ machine learning ͉ molecular signature G astrointestinal stromal tumors (GISTs) and leiomyosarcomas (LMSs) are common mesenchymal tumors with remarkably similar phenotypic features (1, 2). Until recently, the differentiation between these two entities had not been thought to be clinically relevant. Chemotherapeutic agents, such as doxorubicin and ifosfamide used in the treatment of soft-tissue sarcomas have resulted in response rates of 0-10% in patients with advanced GIST (3-5). However, the use of the selective tyrosine kinase inhibitor imatinib mesylate [also known as STI571 (Gleevec; Novartis Pharmaceuticals Corp., East Hanover, NJ)] has resulted in response rates of Ͼ50% for patients with GIST (6, 7, **). Conversely, patients with advanced LMS expect response rates of 27-53% when treated with doxorubicin or newer regimens combining gemcitabine with docetaxel (8, 9) but do not benefit from imatinib therapy (10, 11, † †). Thus, there is clear clinical importance in distinguishing between these two entities to guide the most effective therapy. Currently, the best marker to differentiate GIST from LMS is Kit immunostaining, which is subjective and variable due to cellular heterogeneity that may result in false-negative diagnoses. Kitnegative GISTs and Kit-expressing LMS have been reported on the basis of tumor cell morphology and other markers such as CD34, desmin, and smooth muscle actin ( ‡ ‡). The occurrence of Kit-negative GIST in the literature is Ϸ4-10% (2, 12). We used whole human genome microarray d...

Mitotic Checkpoints and Chromosome Instability Are Strong Predictors of Clinical Outcome in Gastrointestinal Stromal Tumors

“…At the expression level, most studies were designed to facilitate diagnosis (40,41) or to predict KIT or PDGFRA mutation status (42)(43)(44). Yamaguchi and colleagues (17) carried out gene expression profiling on 32 GISTs and identified CD26 as a prognostic marker, but only in GISTs of gastric origin.…”

Distinct Angiogenic Mediators Are Required for Basic Fibroblast Growth Factor– and Vascular Endothelial Growth Factor–induced Angiogenesis: The Role of Cytoplasmic Tyrosine Kinase c-Abl in Tumor Angiogenesis

“…As shown in Figure 3A, c-Abl pY 245 was detected at five-and twofold higher levels after stimulation of cells with bFGF for 5 and 10 min, respectively, relative to the basal level, and these effects were significantly reduced by STI571. It is known that STI571 also has the ability to inhibit PDGF receptor (PDGFR) and c-kit kinase in addition to c-Abl (Hagerstrand et al, 2006;Price et al, 2007). To test the possibility that PDGFR and/or c-kit kinase may also participate in bFGF-induced angiogenesis, we exposed the cells to bFGF and then examined potential changes in the levels of activated forms of PDGFR and c-kit.…”

Antitumor Effects and Biomarkers of Activity of AZD0530, a Src Inhibitor, in Pancreatic Cancer

“…The classification is based on comparing the relative expression of gene pairs, which is relatively easy to interpret and facilitates translational work as shown by RT-PCR validation in this study (Fig. 5B) and others (35).…”