A Cascade Deep Forest Model for Breast Cancer Subtype Classification Using Multi-Omics Data

Automated diagnosis systems aim to reduce the cost of diagnosis while maintaining the same efficiency. Many methods have been used for breast cancer subtype classification. Some use single data source, while others integrate many data sources, the case that results in reduced computational performance as opposed to accuracy. Breast cancer data, especially biological data, is known for its imbalance, with lack of extensive amounts of histopathological images as biological data. Recent studies have shown that cascade Deep Forest ensemble model achieves a competitive classification accuracy compared with other alternatives, such as the general ensemble learning methods and the conventional deep neural networks (DNNs), especially for imbalanced training sets, through learning hyper-representations through using cascade ensemble decision trees. In this work, a cascade Deep Forest is employed to classify breast cancer subtypes, IntClust and Pam50, using multi-omics datasets and different configurations. The results obtained recorded an accuracy of 83.45% for 5 subtypes and 77.55% for 10 subtypes. The significance of this work is that it is shown that using gene expression data alone with the cascade Deep Forest classifier achieves comparable accuracy to other techniques with higher computational performance, where the time recorded is about 5 s for 10 subtypes, and 7 s for 5 subtypes.

Download Full-text

Information theoretic sub-network mining characterizes breast cancer subtypes in terms of cancer core mechanisms

Journal of Bioinformatics and Computational Biology ◽

10.1142/s0219720016440029 ◽

2016 ◽

Vol 14 (05) ◽

pp. 1644002 ◽

Cited By ~ 1

Author(s):

Jinwoo Park ◽

Benjamin Hur ◽

Sungmin Rhee ◽

Sangsoo Lim ◽

Min-Su Kim ◽

...

Keyword(s):

Breast Cancer ◽

Regulatory Network ◽

Cancer Biology ◽

Breast Cancer Subtype ◽

Breast Cancer Subtypes ◽

Information Theoretic ◽

Cancer Subtypes ◽

Network Mining ◽

Subtype Classification ◽

Cancer Subtype

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

Prediction of clusters of miRNA binding sites in mRNA candidate genes of breast cancer subtypes

PeerJ ◽

10.7717/peerj.8049 ◽

2019 ◽

Vol 7 ◽

pp. e8049 ◽

Cited By ~ 4

Author(s):

Dana Aisina ◽

Raigul Niyazova ◽

Shara Atambayeva ◽

Anatoliy Ivashchenko

Keyword(s):

Breast Cancer ◽

Candidate Genes ◽

Binding Sites ◽

Target Genes ◽

Breast Cancer Subtype ◽

Luminal A ◽

Cancer Subtypes ◽

Nucleotide Binding Sites ◽

Cancer Subtype ◽

Gene Mrna

The development of breast cancer (BC) subtypes is controlled by distinct sets of candidate genes, and the expression of these genes is regulated by the binding of their mRNAs with miRNAs. Predicting miRNA associations and target genes is thus essential when studying breast cancer. The MirTarget program identifies the initiation of miRNA binding to mRNA, the localization of miRNA binding sites in mRNA regions, and the free energy from the binding of all miRNA nucleotides with mRNA. Candidate gene mRNAs have clusters (miRNA binding sites with overlapping nucleotide sequences). mRNAs of EPOR, MAZ and NISCH candidate genes of the HER2 subtype have clusters, and there are four clusters in mRNAs of MAZ, BRCA2 and CDK6 genes. Candidate genes of the triple-negative subtype are targets for multiple miRNAs. There are 11 sites in CBL mRNA, five sites in MMP2 mRNA, and RAB5A mRNA contains two clusters in each of the three sites. In SFN mRNA, there are two clusters in three sites, and one cluster in 21 sites. Candidate genes of luminal A and B subtypes are targets for miRNAs: there are 21 sites in FOXA1 mRNA and 15 sites in HMGA2 mRNA. There are clusters of five sites in mRNAs of ITGB1 and SOX4 genes. Clusters of eight sites and 10 sites are identified in mRNAs of SMAD3 and TGFB1 genes, respectively. Organizing miRNA binding sites into clusters reduces the proportion of nucleotide binding sites in mRNAs. This overlapping of miRNA binding sites creates a competition among miRNAs for a binding site. From 6,272 miRNAs studied, only 29 miRNAs from miRBase and 88 novel miRNAs had binding sites in clusters of target gene mRNA in breast cancer. We propose using associations of miRNAs and their target genes as markers in breast cancer subtype diagnosis.

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

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

Identification of Novel Breast Cancer Subtype-Specific Biomarkers by Integrating Genomics Analysis of DNA Copy Number Aberrations and miRNA-mRNA Dual Expression Profiling

BioMed Research International ◽

10.1155/2015/746970 ◽

2015 ◽

Vol 2015 ◽

pp. 1-17 ◽

Cited By ~ 7

Author(s):

Dongguo Li ◽

Hong Xia ◽

Zhen-ya Li ◽

Lin Hua ◽

Lin Li

Keyword(s):

Breast Cancer ◽

Expression Profiling ◽

Copy Number ◽

Experimental Validation ◽

Breast Cancer Subtype ◽

Cancer Subtypes ◽

Copy Number Aberrations ◽

Cancer Subtype ◽

Dna Copy Number Aberrations ◽

Dual Expression

Breast cancer is a heterogeneous disease with well-defined molecular subtypes. Currently, comparative genomic hybridization arrays (aCGH) techniques have been developed rapidly, and recent evidences in studies of breast cancer suggest that tumors within gene expression subtypes share similar DNA copy number aberrations (CNA) which can be used to further subdivide subtypes. Moreover, subtype-specific miRNA expression profiles are also proposed as novel signatures for breast cancer classification. The identification of mRNA or miRNA expression-based breast cancer subtypes is considered an instructive means of prognosis. Here, we conducted an integrated analysis based on copy number aberrations data and miRNA-mRNA dual expression profiling data to identify breast cancer subtype-specific biomarkers. Interestingly, we found a group of genes residing in subtype-specific CNA regions that also display the corresponding changes in mRNAs levels and their target miRNAs’ expression. Among them, the predicted direct correlation of BRCA1-miR-143-miR-145 pairs was selected for experimental validation. The study results indicated that BRCA1 positively regulates miR-143-miR-145 expression and miR-143-miR-145 can serve as promising novel biomarkers for breast cancer subtyping. In our integrated genomics analysis and experimental validation, a new frame to predict candidate biomarkers of breast cancer subtype is provided and offers assistance in order to understand the potential disease etiology of the breast cancer subtypes.

Download Full-text

Population-Based Study on Cancer Subtypes, Guideline-Concordant Adjuvant Therapy, and Survival Among Women With Stage I–III Breast Cancer

Journal of the National Comprehensive Cancer Network ◽

10.6004/jnccn.2018.7272 ◽

2019 ◽

Vol 17 (6) ◽

pp. 676-686 ◽

Cited By ~ 2

Author(s):

Mei-Chin Hsieh ◽

Lu Zhang ◽

Xiao-Cheng Wu ◽

Mary B. Davidson ◽

Michelle Loch ◽

...

Keyword(s):

Breast Cancer ◽

Adjuvant Therapy ◽

Breast Cancer Subtype ◽

Population Based ◽

Survival Outcome ◽

Stage I ◽

Breast Cancer Subtypes ◽

Population Based Study ◽

Cancer Subtypes ◽

Cancer Subtype

Background: Breast cancer subtype is a key determinant in treatment decision-making, and also effects survival outcome. In this population-based study, in-depth analyses were performed to examine the impact that breast cancer subtype and receipt of guideline-concordant adjuvant systemic therapy (AST) have on survival using a population-based cancer registry’s data. Methods: Women aged ≥20 years with microscopically confirmed stage I–III breast cancer diagnosed in 2011 were identified from the Louisiana Tumor Registry. Breast cancer subtypes were categorized based on hormone receptor (HR) and HER2 status. Guideline-concordant treatment was defined using the NCCN Guidelines for Breast Cancer. Logistic regression was applied to identify factors associated with guideline-concordant AST receipt. Kaplan-Meier survival curves were generated to compare survival among subtypes by AST receipt status, and a semiparametric additive hazard model was used to verify the factors impacting survival outcome. Results: Of 2,214 eligible patients, most (70.8%) were HR+/HER2– followed by HR–/HER2– (14.4%), and 78.6% received guideline-concordant AST. Compared with patients with the HR+/HER2+ subtype, women with other subtypes were more likely to be guideline-concordant after adjusting for sociodemographic and clinical variables. Women with the HR–/HER2+ or HR–/HER2– subtype had a higher risk of any-cause and breast cancer–specific death than those with the HR+/HER2+ subtype. Those who did not receive AST had an additional adjusted hazard of 0.0191 (P=.0001) in overall survival and 0.0126 (P=.0011) in cause-specific survival compared with those who received AST. Conclusions: Most patients received guideline-concordant AST, except for those with the HR+/HER2+ subtype. Patients receiving guideline-adherent adjuvant therapy had better survival outcomes across all breast cancer subtypes.

Download Full-text

Differences in Breast Cancer Subtypes Among Racial/Ethnic Groups

10.21203/rs.3.rs-734284/v1 ◽

2021 ◽

Author(s):

Surbhi Bansil ◽

Anthony Silva ◽

Corinne Jones ◽

Elena Hidalgo ◽

Ian Pagano ◽

...

Keyword(s):

Breast Cancer ◽

Ethnic Groups ◽

Breast Cancer Subtype ◽

Cancer Prognosis ◽

Breast Cancer Subtypes ◽

Her2 Receptor ◽

Cancer Subtypes ◽

Her2 Breast Cancer ◽

Cancer Subtype ◽

Racial Ethnic

Abstract PurposeDifferences in incidence of breast cancer subtypes among racial/ethnic groups have been evaluated as a contributing factor in the disparities seen in breast cancer prognosis. We evaluated new breast cancer cases in Hawaii to determine if there were subtype differences according to race/ethnicity that may contribute to known disparities.MethodsWe reviewed 4,318 cases of women diagnosed with breast cancer from two large tumor registries between 2013-2020. We evaluated the new breast cancer cases according to age at diagnosis, self-reported race, and breast cancer subtype (ER, PR, and HER2 receptor status).ResultsWe found both premenopausal and postmenopausal Native Hawaiian women were less likely to be diagnosed with triple negative breast cancer (OR=0.33, P=0.009; OR=0.62, P=0.03 respectively). Premenopausal Japanese women were 71% less likely to be diagnosed with triple positive (ER+/PR+/HER2+) breast cancer (OR=0.29, P=0.0003). Postmenopausal Filipino women were 89% more likely to be diagnosed with ER-/PR-/HER2+ breast cancer (OR=1.89, P=0.02). ConclusionsResults of our study support that there are racial/ethnic differences in breast cancer subtypes among our population which may contribute to the differences in outcome seen. Further evaluation of other clinical and pathological features in each breast cancer subtype may inform potential mechanisms for outcome disparities seen among different racial/ethnic groups.

Download Full-text

Analyzing mRNAsi-Related Genes Identifies Novel Prognostic Markers and Potential Drug Combination for Patients with Basal Breast Cancer

Disease Markers ◽

10.1155/2021/4731349 ◽

2021 ◽

Vol 2021 ◽

pp. 1-15

Author(s):

Kai Huang ◽

Yu Wu ◽

YunQing Xie ◽

LiYing Huang ◽

Hong Liu

Keyword(s):

Breast Cancer ◽

Prognostic Factors ◽

Prognostic Model ◽

Drug Sensitivity ◽

Learning Algorithm ◽

Breast Cancer Subtype ◽

Metabolic Reprogramming ◽

Cancer Subtypes ◽

Basal Breast Cancer ◽

Cancer Subtype

Basal breast cancer subtype is the worst prognosis subtypes among all breast cancer subtypes. Recently, a new tumor stemness index-mRNAsi is found to be able to measure the degree of oncogenic differentiation of tissues. The mRNAsi involved in a variety of cancer processes is derived from the innovative application of one-class logistic regression (OCLR) machine learning algorithm to the whole genome expression of various stem cells and tumor cells. However, it is largely unknown about mRNAsi in basal breast cancer. Here, we find that basal breast cancer carries the highest mRNAsi among all four subtypes of breast cancer, especially 385 mRNAsi-related genes are positively related to the high mRNAsi value in basal breast cancer. This high mRNAsi is also closely related to active cell cycle, DNA replication, and metabolic reprogramming in basal breast cancer. Intriguingly, in the 385 genes, TRIM59, SEPT3, RAD51AP1, and EXO1 can act as independent protective prognostic factors, but CTSF and ABHD4B can serve as independent bad prognostic factors in patients with basal breast cancer. Remarkably, we establish a robust prognostic model containing the 6 mRNAsi-related genes that can effectively predict the survival rate of patients with the basal breast cancer subtype. Finally, the drug sensitivity analysis reveals that some drug combinations may be effectively against basal breast cancer via targeting the mRNAsi-related genes. Taken together, our study not only identifies novel prognostic biomarkers for basal breast cancers but also provides the drug sensitivity data by establishing an mRNAsi-related prognostic model.

Download Full-text