scholarly journals Gene Expression Profiles for Predicting Metastasis in Breast Cancer: A Cross-Study Comparison of Classification Methods

2012 ◽  
Vol 2012 ◽  
pp. 1-11 ◽  
Author(s):  
Mark Burton ◽  
Mads Thomassen ◽  
Qihua Tan ◽  
Torben A. Kruse
Keyword(s):  
Breast Cancer ◽  
Gene Expression ◽  
Cancer Patients ◽  
Expression Profiles ◽  
External Validation ◽  
Gene Expression Profiles ◽  
Microarray Gene Expression Data ◽  
Classification Methods ◽  
Breast Cancer Patients ◽  
Microarray Gene Expression

Machine learning has increasingly been used with microarray gene expression data and for the development of classifiers using a variety of methods. However, method comparisons in cross-study datasets are very scarce. This study compares the performance of seven classification methods and the effect of voting for predicting metastasis outcome in breast cancer patients, in three situations: within the same dataset or across datasets on similar or dissimilar microarray platforms. Combining classification results from seven classifiers into one voting decision performed significantly better during internal validation as well as external validation in similar microarray platforms than the underlying classification methods. When validating between different microarray platforms, random forest, another voting-based method, proved to be the best performing method. We conclude that voting based classifiers provided an advantage with respect to classifying metastasis outcome in breast cancer patients.

Genomic Prediction of Locoregional Recurrence After Mastectomy in Breast Cancer

2006 ◽  
Vol 24 (28) ◽  
pp. 4594-4602 ◽  
Author(s):  
Skye H. Cheng ◽  
Cheng-Fang Horng ◽  
Mike West ◽  
Erich Huang ◽  
Jennifer Pittman ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Gene Expression ◽  
Cancer Patients ◽  
Expression Profiles ◽  
Eligible Patient ◽  
Gene Expression Profiles ◽  
Breast Cancer Patients ◽  
Predictive Index ◽  
Validation Data ◽  
Data Set

Purpose This study aims to explore gene expression profiles that are associated with locoregional (LR) recurrence in breast cancer after mastectomy. Patients and Methods A total of 94 breast cancer patients who underwent mastectomy between 1990 and 2001 and had DNA microarray study on the primary tumor tissues were chosen for this study. Eligible patient should have no evidence of LR recurrence without postmastectomy radiotherapy (PMRT) after a minimum of 3-year follow-up (n = 67) and any LR recurrence (n = 27). They were randomly split into training and validation sets. Statistical classification tree analysis and proportional hazards models were developed to identify and validate gene expression profiles that relate to LR recurrence. Results Our study demonstrates two sets of gene expression profiles (one with 258 genes and the other 34 genes) to be of predictive value with respect to LR recurrence. The overall accuracy of the prediction tree model in validation sets is estimated 75% to 78%. Of patients in validation data set, the 3-year LR control rate with predictive index more than 0.8 derived from 34-gene prediction models is 91%, and predictive index 0.8 or less is 40% (P = .008). Multivariate analysis of all patients reveals that estrogen receptor and genomic predictive index are independent prognostic factors that affect LR control. Conclusion Using gene expression profiles to develop prediction tree models effectively identifies breast cancer patients who are at higher risk for LR recurrence. This gene expression–based predictive index can be used to select patients for PMRT.

scholarly journals Comparison of gene expression profiles predicting progression in breast cancer patients treated with tamoxifen

2008 ◽  
Vol 113 (2) ◽  
pp. 275-283 ◽  
Author(s):  
Marleen Kok ◽  
Sabine C. Linn ◽  
Ryan K. Van Laar ◽  
Maurice P. H. M. Jansen ◽  
Teun M. van den Berg ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Gene Expression ◽  
Cancer Patients ◽  
Expression Profiles ◽  
Gene Expression Profiles ◽  
Breast Cancer Patients

Gene expression profiles of circulating tumor cells in metastatic breast cancer patients.

2012 ◽  
Vol 30 (15_suppl) ◽  
pp. 10504-10504
Author(s):  
Bianca Mostert ◽  
Anieta M Sieuwerts ◽  
Jaco Kraan ◽  
Joan Bolt-de Vries ◽  
Dieter Peeters ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Gene Expression ◽  
Metastatic Breast Cancer ◽  
Cancer Patients ◽  
Prognostic Value ◽  
Expression Profiles ◽  
Gene Expression Profiles ◽  
Metastatic Breast ◽  
Breast Cancer Patients ◽  
Gene Profile

10504 Background: A circulating tumor cell (CTC) count is an established prognostic factor in metastatic breast cancer. Besides enumeration, CTC characterization promises to further improve outcome prediction and treatment guidance. We have previously shown the feasibility of measuring the expression of a panel of 96 clinically relevant genes in CTCs in a leukocyte background, and in the current study, we determined the prognostic value of CTC gene expression profiling in metastatic breast cancer. Methods: CTCs were isolated and enumerated from blood of 130 metastatic breast cancer patients prior to start of first-line systemic, endocrine or chemotherapeutic, therapy. Of these, 103 were evaluable for mRNA gene expression levels measured by quantitative RT-PCR in relation to time to treatment switch (TTS). Separate prognostic CTC gene profiles were generated by leave-one-out cross validation for all patients and for patients with ≥5 CTCs per 7.5 mL blood, and cut-offs were chosen to ensure optimal prediction of patients who might benefit from an early therapy switch. Results: In the total cohort, of whom 56% received chemotherapeutic and 44% endocrine therapy, baseline CTC count (≥5 versus <5 CTCs/7.5 mL blood) predicted for TTS (Hazard Ratio (HR) 2.92 [95% Confidence Interval (CI) 1.71 – 4.95] P <0.0001). A 16-gene CTC profile for all patients and a separate 9-gene CTC profile applicable for patients with ≥5 CTCs were identified, which distinguished those patients with TTS or death within 9 months from those with a more favorable outcome. Test performance for both profiles was favorable; the 16-gene profile had 90% sensitivity, 38% specificity, 50% positive predictive value (PPV) and 85% negative predictive value (NPV), and the 9-gene profile performed slightly better at 92% sensitivity, 52% specificity, 66% PPV and 87% NPV. In multivariate Cox regression analysis, the 16-gene profile was the only factor independently associated with TTS (HR 3.15 [95%CI 1.35 – 7.33] P 0.008). Conclusions: Two CTC gene expression profiles were discovered, which provide prognostic value in metastatic breast cancer patients. This study further underscores the potential of molecular characterization of CTCs.

scholarly journals Differences in gene-expression profiles in breast cancer between African and European-ancestry women

2020 ◽  
Vol 41 (7) ◽  
pp. 887-893 ◽  
Author(s):  
Jie Ping ◽  
Xingyi Guo ◽  
Fei Ye ◽  
Jirong Long ◽  
Loren Lipworth ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Gene Expression ◽  
Cancer Patients ◽  
Expression Profiles ◽  
Breast Cancer Mortality ◽  
Tumor Biology ◽  
Gene Expression Profiles ◽  
Gene Signature ◽  
European Ancestry ◽  
Breast Cancer Patients

Abstract African American (AA) women have an excess breast cancer mortality than European American (EA) women. To investigate the contribution of tumor biology to this survival health disparity, we compared gene expression profiles in breast tumors using RNA sequencing data derived from 260 AA and 155 EA women who were prospectively enrolled in the Southern Community Cohort Study (SCCS) and developed breast cancer during follow-up. We identified 59 genes (54 protein-coding genes and 5 long intergenic non-coding RNAs) that were expressed differently between EA and AA at a stringent false discovery rate (FDR) &lt; 0.01. A gene signature was derived with these 59 genes and externally validated using the publicly available Cancer Genome Atlas (TCGA) data from180 AA and 838 EA breast cancer patients. Applying C-statistics, we found that this 59-gene signature has a high discriminative ability in distinguishing AA and EA breast cancer patients in the TCGA dataset (C-index = 0.81). These findings may provide new insight into tumor biological differences and the causes of the survival disparity between AA and EA breast cancer patients.

scholarly journals Identification of genes and pathways related to lymphovascular invasion in breast cancer patients: A bioinformatics analysis of gene expression profiles

Tumor Biology ◽  
2017 ◽  
Vol 39 (6) ◽  
pp. 101042831770557 ◽  
Author(s):  
Sukhontip Klahan ◽  
Henry Sung-Ching Wong ◽  
Shih-Hsin Tu ◽  
Wan-Hsuan Chou ◽  
Yan-Feng Zhang ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Gene Expression ◽  
Cancer Patients ◽  
Lymphovascular Invasion ◽  
Bioinformatics Analysis ◽  
Expression Profiles ◽  
Gene Expression Profiles ◽  
Breast Cancer Patients

scholarly journals Hormone Receptor-Status Prediction in Breast Cancer Using Gene Expression Profiles and Their Macroscopic Landscape

Cancers ◽  
2020 ◽  
Vol 12 (5) ◽  
pp. 1165
Author(s):  
Seokhyun Yoon ◽  
Hye Sung Won ◽  
Keunsoo Kang ◽  
Kexin Qiu ◽  
Woong June Park ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Gene Expression ◽  
Cancer Patients ◽  
Hormone Receptor ◽  
Expression Profiles ◽  
Receptor Expression ◽  
Luminal Breast Cancer ◽  
Breast Cancer Patients ◽  
Intrinsic Subtypes ◽  
Receptor Status

The cost of next-generation sequencing technologies is rapidly declining, making RNA-seq-based gene expression profiling (GEP) an affordable technique for predicting receptor expression status and intrinsic subtypes in breast cancer patients. Based on the expression levels of co-expressed genes, GEP-based receptor-status prediction can classify clinical subtypes more accurately than can immunohistochemistry (IHC). Using data from The Cancer Genome Atlas Breast Invasive Carcinoma (TCGA BRCA) and Molecular Taxonomy of Breast Cancer International Consortium (METABRIC) datasets, we identified common predictor genes found in both datasets and performed receptor-status prediction based on these genes. By assessing the survival outcomes of patients classified using GEP- or IHC-based receptor status, we compared the prognostic value of the two methods. We found that GEP-based HR prediction provided higher concordance with the intrinsic subtypes and a stronger association with treatment outcomes than did IHC-based hormone receptor (HR) status. GEP-based prediction improved the identification of patients who could benefit from hormone therapy, even in patients with non-luminal breast cancer. We also confirmed that non-matching subgroup classification affected the survival of breast cancer patients and that this could be largely overcome by GEP-based receptor-status prediction. In conclusion, GEP-based prediction provides more reliable classification of HR status, improving therapeutic decision making for breast cancer patients.

Sign in / Sign up

Export Citation Format

Share Document