Breast Cancer Subtype Classification using Clinical and Gene Expression Integration

A breast cancer subtype classification scheme, PAM50, based on genetic information is widely accepted for clinical applications. On the other hands, experimental cancer biology studies have been successful in revealing the mechanisms of breast cancer and now the hallmarks of cancer have been determined to explain the core mechanisms of tumorigenesis. Thus, it is important to understand how the breast cancer subtypes are related to the cancer core mechanisms, but multiple studies are yet to address the hallmarks of breast cancer subtypes. Therefore, a new approach that can explain the differences among breast cancer subtypes in terms of cancer hallmarks is needed. We developed an information theoretic sub-network mining algorithm, differentially expressed sub-network and pathway analysis (DeSPA), that retrieves tumor-related genes by mining a gene regulatory network (GRN) of transcription factors and miRNAs. With extensive experiments of the cancer genome atlas (TCGA) breast cancer sequencing data, we showed that our approach was able to select genes that belong to cancer core pathways such as DNA replication, cell cycle, p53 pathways while keeping the accuracy of breast cancer subtype classification comparable to that of PAM50. In addition, our method produces a regulatory network of TF, miRNA, and their target genes that distinguish breast cancer subtypes, which is confirmed by experimental studies in the literature.

Download Full-text

Associations of two-pore domain potassium channels and triple negative breast cancer subtype in The Cancer Genome Atlas: systematic evaluation of gene expression and methylation

BMC Research Notes ◽

10.1186/s13104-017-2777-4 ◽

2017 ◽

Vol 10 (1) ◽

Cited By ~ 8

Author(s):

Keith A. Dookeran ◽

Wei Zhang ◽

Leslie Stayner ◽

Maria Argos

Keyword(s):

Breast Cancer ◽

Gene Expression ◽

Triple Negative ◽

Breast Cancer Subtype ◽

The Cancer Genome Atlas ◽

Systematic Evaluation ◽

Cancer Subtype ◽

Cancer Genome Atlas ◽

Pore Domain ◽

Genome Atlas

Download Full-text

Hubness weighted svm ensemble for prediction of breast cancer subtypes

Technology and Health Care ◽

10.3233/thc-212825 ◽

2021 ◽

pp. 1-14

Author(s):

S. Raja Sree ◽

A. Kunthavai

Keyword(s):

Breast Cancer ◽

Gene Expression ◽

Support Vector Machine ◽

Breast Cancer Subtype ◽

Breast Cancer Subtypes ◽

High Dimensional ◽

Support Vector ◽

Gene Expressions ◽

Cancer Subtypes ◽

Cancer Subtype

BACKGROUND: Breast cancer is a major disease causing panic among women worldwide. Since gene mutations are the root cause for cancer development, analyzing gene expressions can give more insights into various phenotype of cancer treatments. Breast Cancer subtype prediction from gene expression data can provide more information for cancer treatment decisions. OBJECTIVE: Gene expressions are complex for analysis due to its high dimensional nature. Machine learning algorithms such as k-Nearest Neighbors, Support Vector Machine (SVM) and Random Forest are used with selection of features for prediction of breast cancer subtypes. Prediction accuracy of the existing methods are affected due to high dimensional nature of gene expressions. The objective of the work is to propose an efficient algorithm for the prediction of breast cancer subtypes from gene expression. METHODS: For subtype prediction, a novel Hubness Weighted Support Vector machine algorithm (HWSVM) using bad hubness score as a weight measure to handle the outliers in the data has been proposed. Based on the various subtypes, features are projected into seven different feature sets and Ensemble based Hubness Aware Weighted Support Vector Machine (HWSVMEns) is implemented for breast cancer subtype prediction. RESULTS: The proposed algorithms have been compared with the classical SVM and other traditional algorithms such as Random Forest, k-Nearest Neighbor algorithms and also with various gene selection methods. CONCLUSIONS: Experimental results show that the proposed HWSVM outperforms other algorithms in terms of accuracy, precision, recall and F1 score due to the hubness weightage scheme and the ensemble approach. The experiments have shown an average accuracy of 92% across various gene expression datasets.

Download Full-text

Classification of Breast Cancer Subtypes by combining Gene Expression and DNA Methylation Data

Journal of Integrative Bioinformatics ◽

10.1515/jib-2014-236 ◽

2014 ◽

Vol 11 (2) ◽

pp. 1-14 ◽

Cited By ~ 21

Author(s):

Markus List ◽

Anne-Christin Hauschild ◽

Qihua Tan ◽

Torben A. Kruse ◽

Jan Baumbach ◽

...

Keyword(s):

Breast Cancer ◽

Gene Expression ◽

Gene Expression Data ◽

Breast Cancer Subtype ◽

Methylation Data ◽

Expression Data ◽

Model Based ◽

Cancer Subtype ◽

Expression Model ◽

Gene Expression Model

Summary Selecting the most promising treatment strategy for breast cancer crucially depends on determining the correct subtype. In recent years, gene expression profiling has been investigated as an alternative to histochemical methods. Since databases like TCGA provide easy and unrestricted access to gene expression data for hundreds of patients, the challenge is to extract a minimal optimal set of genes with good prognostic properties from a large bulk of genes making a moderate contribution to classification. Several studies have successfully applied machine learning algorithms to solve this so-called gene selection problem. However, more diverse data from other OMICS technologies are available, including methylation. We hypothesize that combining methylation and gene expression data could already lead to a largely improved classification model, since the resulting model will reflect differences not only on the transcriptomic, but also on an epigenetic level. We compared so-called random forest derived classification models based on gene expression and methylation data alone, to a model based on the combined features and to a model based on the gold standard PAM50. We obtained bootstrap errors of 10-20% and classification error of 1-50%, depending on breast cancer subtype and model. The gene expression model was clearly superior to the methylation model, which was also reflected in the combined model, which mainly selected features from gene expression data. However, the methylation model was able to identify unique features not considered as relevant by the gene expression model, which might provide deeper insights into breast cancer subtype differentiation on an epigenetic level.

Download Full-text

Breast Cancer Subtype Classification Using Multi-omics Data Integration Based on Neural Network

Journal of KIISE ◽

10.5626/jok.2020.47.9.835 ◽

2020 ◽

Vol 47 (9) ◽

pp. 835-841

Author(s):

Joungmin Choi ◽

Jiyoung Lee ◽

Jieun Kim ◽

Jihyun Kim ◽

Heejoon Chae

Keyword(s):

Breast Cancer ◽

Neural Network ◽

Data Integration ◽

Breast Cancer Subtype ◽

Omics Data ◽

Subtype Classification ◽

Cancer Subtype ◽

Omics Data Integration

Download Full-text

Claudin-low-like mouse mammary tumors show distinct transcriptomic patterns uncoupled from genomic drivers

10.1101/557298 ◽

2019 ◽

Author(s):

Christian Fougner ◽

Helga Bergholtz ◽

Raoul Kuiper ◽

Jens Henrik Norum ◽

Therese Sørlie

Keyword(s):

Breast Cancer ◽

Gene Expression ◽

Copy Number ◽

Breast Cancer Subtype ◽

Mammary Tumors ◽

Breast Cancers ◽

Copy Number Aberrations ◽

Induced Tumors ◽

Cancer Subtype ◽

Mouse Mammary Tumors

AbstractClaudin-low breast cancer is a molecular subtype associated with poor prognosis and without targeted treatment options. The claudin-low subtype is defined by certain biological characteristics, some of which may be clinically actionable, such as high immunogenicity. In mice, the medroxyprogesterone acetate (MPA) and 7,12-dimethylbenzanthracene (DMBA) induced mammary tumor model yields a heterogeneous set of tumors, a subset of which display claudin-low features. Neither the genomic characteristics of MPA/DMBA-induced claudin-low tumors, nor those of human claudin-low breast tumors, have been thoroughly explored.The transcriptomic characteristics and subtypes of MPA/DMBA-induced mouse mammary tumors were determined using gene expression microarrays. Somatic mutations and copy number aberrations in MPA/DMBA-induced tumors were identified from whole exome sequencing data. A publicly available dataset was queried to explore the genomic characteristics of human claudin-low breast cancer and to validate findings in the murine tumors.Half of MPA/DMBA-induced tumors showed a claudin-low-like subtype. All tumors carried mutations in known driver genes. While the specific genes carrying mutations varied between tumors, there was a consistent mutational signature with an overweight of T>A transversions in TG dinucleotides. Most tumors carried copy number aberrations with a potential oncogenic driver effect. Overall, several genomic events were observed recurrently, however none accurately delineated claudin-low-like tumors. Human claudin-low breast cancers carried a distinct set of genomic characteristics, in particular a relatively low burden of mutations and copy number aberrations. The gene expression characteristics of claudin-low-like MPA/DMBA-induced tumors accurately reflected those of human claudin-low tumors, including epithelial-mesenchymal transition phenotype, high level of immune activation and low degree of differentiation. There was an elevated expression of the immunosuppressive genes PTGS2 (encoding COX-2) and CD274 (encoding PD-L1) in human and murine claudin-low tumors. Our findings show that the claudin-low breast cancer subtype is not demarcated by specific genomic aberrations, but carries potentially targetable characteristics warranting further research.Author SummaryBreast cancer is comprised of several distinct disease subtypes with different etiologies, prognoses and therapeutic targets. The claudin-low breast cancer subtype is relatively poorly understood, and no specific treatment exists targeting its unique characteristics. Animal models accurately representing human disease counterparts are vital for developing novel therapeutics, but for the claudin-low breast cancer subtype, no such uniform model exists. Here, we show that exposing mice to the carcinogen DMBA and the hormone MPA causes a diverse range of mammary tumors to grow, and half of these have a gene expression pattern similar to that seen in human claudin-low breast cancer. These tumors have numerous changes in their DNA, with clear differences between each tumor, however no specific DNA aberrations clearly demarcate the claudin-low subtype. We also analyzed human breast cancers and show that human claudin-low tumors have several clear patterns in their DNA aberrations, but no specific features accurately distinguish claudin-low from non-claudin-low breast cancer. Finally, we show that both human and murine claudin-low tumors express high levels of genes associated with suppression of immune response. In sum, we highlight claudin-low breast cancer as a clinically relevant subtype with a complex etiology, and with potential unexploited therapeutic targets.

Download Full-text

Molecular analysis in breast cancer subtypes and correlation with pathologic complete response (pCR) to neoadjuvant chemotherapy.

Journal of Clinical Oncology ◽

10.1200/jco.2013.31.15_suppl.e22119 ◽

2013 ◽

Vol 31 (15_suppl) ◽

pp. e22119-e22119

Author(s):

Maria Gonzalez Cao ◽

Carlota Costa ◽

Miguel Angel Molina-Vila ◽

Maria Teresa Cusido ◽

Santiago Viteri Ramirez ◽

...

Keyword(s):

Breast Cancer ◽

Gene Expression ◽

Neoadjuvant Chemotherapy ◽

Breast Cancer Subtype ◽

Pathologic Complete Response ◽

Luminal A ◽

Luminal B ◽

Mutational Status ◽

Cancer Subtype ◽

Low Levels

e22119 Background: Although it is know that pCR following neoadjuvant chemotherapy is more frequent in some subtypes of breast cancer such as Triple Negative (TN) or erb2 tumors, the predictive role of gene expression and mutation status is not well defined in this setting. Methods: We analyzed samples from 41 patients (p) prospectively treated with neoadjuvant chemotherapy (sequential AC followed by weekly TXL, or inverse sequence, plus trastuzumab for erb2 positive p). Pathologic response (PR) was classified according to Miller-Payne and RCB criteria. Radiologic evaluation was performed by ultrasonography, dynamic MR and PET-TAC after each chemotherapy sequence. We performed expression analysis of AXL, BRCA1, RAP80, BIM, EZH2, ROR1, FGFR1, PTPN12, YAP, GAS6, beta-TRCP, HIF1 alpha and ZNF217 by RT-PCR, and mutational status of p53 and PI3K genes in pretreatment biopsies. Statistical analysis was performed using Mann-Whitney U and Pearson’s chi-squared tests. Results: pCR was detected in 5 p (3TN, 2 erb2) of 25 p (9 luminal A, 5 luminal B, 6 erb2 and 5 TN) evaluated for PR at time of submitting this abstract. TN tumors had lower levels of RAP80 (p=.0013), PTPN12 (p=.003), beta TRCP (p=.001), ZNF217 (p=.014) and YAP (p=.097). Luminal B tumors had low levels of YAP and the highest levels of FGFR1 (p=.09) and ZNF217 (p=.014). Luminal A tumors had high levels of beta-TRCP (p=.003). We found no differences in BRCA1, AXL, BIM, EZH2, ROR1, GAS6 and HIF1 levels by breast cancer subtype. P with low levels of FGFR1 (p=.087), HIF1alpha (p=.07) or EZH2 (p=.005) had higher probability of pCR. No pCR was observed in p with higher levels of AXL, EZH2, RAP80, GAS6, beta TRCP, HIF alpha. Four p had p53 mutations (1 luminal B, 1 erb2 and 2 TN) and 4 p had PI3K mutations (2 luminal A, 1 erb2, 1 luminal B). There was no correlation between p53 status and PR. P with PI3K mutations did not achieve pCR vs 46% of p with wild type PI3K (p=.23). Conclusions: Gene expression profile varies by breast cancer subtype. Chemosensitivity could be higher in tumors with lower levels of FGFR1, HIF1alpha or EZH2. Further results will be presented.

Download Full-text