An Evaluation Protocol for Subtype-Specific Breast Cancer Event Prediction
نویسندگان
چکیده
In recent years increasing evidence appeared that breast cancer may not constitute a single disease at the molecular level, but comprises a heterogeneous set of subtypes. This suggests that instead of building a single monolithic predictor, better predictors might be constructed that solely target samples of a designated subtype, which are believed to represent more homogeneous sets of samples. An unavoidable drawback of developing subtype-specific predictors, however, is that a stratification by subtype drastically reduces the number of samples available for their construction. As numerous studies have indicated sample size to be an important factor in predictor construction, it is therefore questionable whether the potential benefit of subtyping can outweigh the drawback of a severe loss in sample size. Factors like unequal class distributions and differences in the number of samples per subtype, further complicate comparisons. We present a novel experimental protocol that facilitates a comprehensive comparison between subtype-specific predictors and predictors that do not take subtype information into account. Emphasis lies on careful control of sample size as well as class and subtype distributions. The methodology is applied to a large breast cancer compendium involving over 1500 arrays, using a state-of-the-art subtyping scheme. We show that the resulting subtype-specific predictors outperform those that do not take subtype information into account, especially when taking sample size considerations into account.
منابع مشابه
Supporting Information S2 - An Evaluation Protocol for Subtype-Specific Breast Cancer Event Prediction
Supporting Information S2 An Evaluation Protocol for Subtype-Specific Breast Cancer Event Prediction Herman MJ Sontrop, Wim FJ Verhaegh, Marcel JT Reinders, Perry D Moerland3,4,∗ 1 Molecular Diagnostics Department, Philips Research, High Tech Campus 11, 5656 AE Eindhoven, The Netherlands 2 Delft Bioinformatics Lab, Delft University of Technology, Mekelweg 4, 2628 CD Delft, The Netherlands 3 Bio...
متن کاملاپیژنتیک سرطان پستان: مقاله مروری
Stable molecular changes during cell division without any change in the sequence of DNA molecules is known as epigenetic. Molecular mechanisms involved in this process, including histone modifications, methylation of DNA, protein complex and RNA antisense. Cancer genome changes happen through a combination of DNA hypermethylation, long-term epigenetic silencing with heterozygosis loss and genom...
متن کاملEvaluation of Local Recurrence of Breast Cancer after Mastectomy and Breast Preservation Therapy
Abstract Introduction: Breast cancer is the most common cancer among women. Even though mastectomy is known as a highly effective method to treat breast cancer, the percentage of patients with local recurrence is still high. Objective: To determine the incidence of local recurrence after mastectomy and breast preservation surgery. Materials and Methods: Patients with breast cancer that under...
متن کاملMutation Screening of BRCA Genes in 10 Iranian Males with Breast Cancer
Male breast cancer is a rare disease with an increasing trend. Due to limited information especially about the genetic basis of the disease in Iran and the lower age of its onset, the disease requires more attention. The aim of this study was to screen the male patients with breast cancer for BRCA mutations as well as tissue markers of estrogen receptor (ER), progesterone receptor (PR), human e...
متن کاملFuture of Triple Negative Breast Cancer: Can Immunotherapy Treat This Deadly Subtype of Breast Cancer?
Triple negative breast cancer (TNBC): challenges and solutions via the immune cells TNBC is one of the most complicated types of breast cancer to treat. It is generally diagnosed based on the absence of three receptors: estrogen, progesterone, and human epidermal growth factor receptor 2 (HER2) and is thus defined as a triple negative. TNBC is often more aggressive with lower survival rates...
متن کامل