Classifying Breast Cancer Subtypes Using Multiple Kernel Learning Based on Omics Data

It is very significant to explore the intrinsic differences in breast cancer subtypes. These intrinsic differences are closely related to clinical diagnosis and designation of treatment plans. With the accumulation of biological and medicine datasets, there are many different omics data that can be viewed in different aspects. Combining these multiple omics data can improve the accuracy of prediction. Meanwhile; there are also many different databases available for us to download different types of omics data. In this article, we use estrogen receptor (ER), progesterone receptor (PR), human epidermal growth factor receptor 2 (HER2) to define breast cancer subtypes and classify any two breast cancer subtypes using SMO-MKL algorithm. We collected mRNA data, methylation data and copy number variation (CNV) data from TCGA to classify breast cancer subtypes. Multiple Kernel Learning (MKL) is employed to use these omics data distinctly. The result of using three omics data with multiple kernels is better than that of using single omics data with multiple kernels. Furthermore; these significant genes and pathways discovered in the feature selection process are also analyzed. In experiments; the proposed method outperforms other state-of-the-art methods and has abundant biological interpretations.

Download Full-text

Classifying Breast Cancer Subtypes Using Deep Neural Networks Based on Multi-Omics Data

Genes ◽

10.3390/genes11080888 ◽

2020 ◽

Vol 11 (8) ◽

pp. 888

Author(s):

Yuqi Lin ◽

Wen Zhang ◽

Huanshen Cao ◽

Gaoyang Li ◽

Wei Du

Keyword(s):

Breast Cancer ◽

Neural Networks ◽

Feature Selection ◽

Deep Neural Networks ◽

Selection Process ◽

Breast Cancer Subtype ◽

The Cancer Genome Atlas ◽

Breast Cancer Subtypes ◽

Omics Data ◽

Cancer Subtypes

With the high prevalence of breast cancer, it is urgent to find out the intrinsic difference between various subtypes, so as to infer the underlying mechanisms. Given the available multi-omics data, their proper integration can improve the accuracy of breast cancer subtype recognition. In this study, DeepMO, a model using deep neural networks based on multi-omics data, was employed for classifying breast cancer subtypes. Three types of omics data including mRNA data, DNA methylation data, and copy number variation (CNV) data were collected from The Cancer Genome Atlas (TCGA). After data preprocessing and feature selection, each type of omics data was input into the deep neural network, which consists of an encoding subnetwork and a classification subnetwork. The results of DeepMO based on multi-omics on binary classification are better than other methods in terms of accuracy and area under the curve (AUC). Moreover, compared with other methods using single omics data and multi-omics data, DeepMO also had a higher prediction accuracy on multi-classification. We also validated the effect of feature selection on DeepMO. Finally, we analyzed the enrichment gene ontology (GO) terms and biological pathways of these significant genes, which were discovered during the feature selection process. We believe that the proposed model is useful for multi-omics data analysis.

Download Full-text

The method for breast cancer grade prediction and pathway analysis based on improved multiple kernel learning

Journal of Bioinformatics and Computational Biology ◽

10.1142/s0219720016500372 ◽

2017 ◽

Vol 15 (01) ◽

pp. 1650037 ◽

Cited By ~ 3

Author(s):

Tianci Song ◽

Yan Wang ◽

Wei Du ◽

Sha Cao ◽

Yuan Tian ◽

...

Keyword(s):

Breast Cancer ◽

Multiple Kernel Learning ◽

Heterogeneous Data ◽

Kernel Learning ◽

Omics Data ◽

Learning Method ◽

Data Types ◽

Grade Prediction ◽

Multiple Kernel ◽

Biological Interpretation

Breast cancer histologic grade represents the morphological assessment of the tumor’s malignancy and aggressiveness, which is vital in clinically planning treatment and estimating prognosis for patients. Therefore, the prediction of breast cancer grade can markedly elevate the detection of early breast cancer and efficiently guide its treatment. With the advent of high-throughput profiling technology, a large number of data of different types are rapidly generated, and each data provides its unique biological insight. Although many researches focused on cancer grade prediction, hardly most of them attempted to integrate multiple data types, by which we cannot only improve and boost results obtained from learning method, but also have a good understanding or explanation of biological issues. In this paper, we take advantage of a sophisticated supervised learning method called multiple kernel learning (MKL) to design a breast cancer grading predictor fusing heterogeneous data for classification of breast cancer histopathology. Furthermore, we modify our model by involving biological pathway information. The new model can evaluate the significance of various pathways in which differential expression genes fall between different breast cancer grades. The merits of the novel model are lucubration in bridging between omics data and various phenotypes of breast cancer grades, and providing an auxiliary method integrating omics data of cancer mechanism research. In experiments, the proposed method outperforms other state-of-the-art methods and has abundant biological interpretation in explaining differences between breast cancer grades.

Download Full-text

Serum CEA and CA 15-3 levels according to breast cancer subtypes.

Journal of Clinical Oncology ◽

10.1200/jco.2013.31.15_suppl.e11511 ◽

2013 ◽

Vol 31 (15_suppl) ◽

pp. e11511-e11511 ◽

Cited By ~ 1

Author(s):

Isa Dede ◽

Gungor Utkan ◽

Hakan Akbulut ◽

Yuksel Urun ◽

Dilsa Mizrak ◽

...

Keyword(s):

Breast Cancer ◽

Tumor Markers ◽

Growth Factor Receptor ◽

Metastatic Breast ◽

Serum Levels ◽

Carbohydrate Antigen ◽

Breast Cancer Subtypes ◽

Her2 Status ◽

Cancer Subtypes ◽

Serum Cea

e11511 Background: Carcinoembryonic antigen (CEA) and carbohydrate antigen (CA) 15-3 are frequently elevated in patients with metastatic breast cancer (MBC). In this study we aimed to correlate levels according to breast cancersubtypes with MBC. Methods: From January 2008 to December 2012, ninety-eight patients with MBC who were treated at Ankara University School Of Medicine, Department of Medical Onkology were included in this study.Serum levels of CEA and CA 15-3were measured and compared according to tumor estrogen receptor (ER), progesteron receptor (PR), and human epidermal growth factor receptor 2 (HER2) status. Results: In this cohort, overall ER,PR and HER2 positivity rates were 65 %,68%,and 58%, retrospectively. Positivite ER status was associated with elevated levels of CA 15-3 and cea. Of these, CA 15-3 levels elevated in 40.5% of ER positivite and 24.1 % of ER negativite patients (p=0.027). Similarly, 46.8 % of ER positivite and 18.2% of ER negativite patients had elevated levels of CEA (P=0.022). no association between PR and HER2 status and tumor markers was observed. Conclusions: The breast cancer subtypes are correlated with serum levels of tumor markers in patients with MBC. Tumor markers elevation may be associated with biological background of breast cancer subtypes. Further validation is needed to determine the role of these markers in diffrent tumor types for monitoring patients with MBC.

Download Full-text

Metastatic Behavior of Breast Cancer Subtypes

Journal of Clinical Oncology ◽

10.1200/jco.2009.25.9820 ◽

2010 ◽

Vol 28 (20) ◽

pp. 3271-3277 ◽

Cited By ~ 984

Author(s):

Hagen Kennecke ◽

Rinat Yerushalmi ◽

Ryan Woods ◽

Maggie Chon U. Cheang ◽

David Voduc ◽

...

Keyword(s):

Breast Cancer ◽

Lung Metastases ◽

Early Stage ◽

Growth Factor Receptor ◽

Breast Cancer Subtypes ◽

Early Stage Breast Cancer ◽

Luminal A ◽

Cancer Subtypes ◽

Luminal B ◽

Metastatic Sites

Purpose Prognostic and predictive factors are well established in early-stage breast cancer, but less is known about which metastatic sites will be affected. Methods Patients with early-stage breast cancer diagnosed between 1986 and 1992 with archival tissue were included. Subtypes were defined as luminal A, luminal B, luminal/human epidermal growth factor receptor 2 (HER2), HER2 enriched, basal-like, and triple negative (TN) nonbasal. Distant sites were classified as brain, liver, lung, bone, distant nodal, pleural/peritoneal, and other. Cumulative incidence curves were estimated for each site according to competing risks methods. Association between the site of relapse and subtype was assessed in multivariate models using logistic regression. Results Median follow-up time among 3,726 eligible patients was 14.8 years. Median durations of survival with distant metastasis were 2.2 (luminal A), 1.6 (luminal B), 1.3 (luminal/HER2), 0.7 (HER2 enriched), and 0.5 years (basal-like; P < .001). Bone was the most common metastatic site in all subtypes except basal-like tumors. In multivariate analysis, compared with luminal A tumors, luminal/HER2 and HER2-enriched tumors were associated with a significantly higher rate of brain, liver, and lung metastases. Basal-like tumors had a higher rate of brain, lung, and distant nodal metastases but a significantly lower rate of liver and bone metastases. TN nonbasal tumors demonstrated a similar pattern but were not associated with fewer liver metastases. Conclusion Breast cancer subtypes are associated with distinct patterns of metastatic spread with notable differences in survival after relapse.

Download Full-text