Identification Of Breast Cancer Subtypes Research Articles

Identification of breast cancer subtypes based on graph convolutional network

Identification of molecular subtypes of malignant tumors plays a vital role in individualized diagnosis, personalized treatment, and prognosis prediction of cancer patients. The continuous improvement of comprehensive tumor genomics database and the ongoing breakthroughs in deep learning technology have driven further advancements in computer-aided tumor classification. Although the existing classification methods based on gene expression omnibus database take the complexity of cancer molecular classification into account, they ignore the internal correlation and synergism of genes. To solve this problem, we propose a multi-layer graph convolutional network model for breast cancer subtype classification combined with hierarchical attention network. This model constructs the graph embedding datasets of patients' genes, and develops a new end-to-end multi-classification model, which can effectively recognize molecular subtypes of breast cancer. A large number of test data prove the good performance of this new model in the classification of breast cancer subtypes. Compared to the original graph convolutional neural networks and two mainstream graph neural network classification algorithms, the new model has remarkable advantages. The accuracy, weight-F1-score, weight-recall, and weight-precision of our model in seven-category classification has reached 0.851 7, 0.823 5, 0.851 7 and 0.793 6 respectively. In the four-category classification, the results are 0.928 5, 0.894 9, 0.928 5 and 0.865 0 respectively. In addition, compared with the latest breast cancer subtype classification algorithms, the method proposed in this paper also achieved the highest classification accuracy. In summary, the model proposed in this paper may serve as an auxiliary diagnostic technology, providing a reliable option for precise classification of breast cancer subtypes in the future and laying the theoretical foundation for computer-aided tumor classification.

Identification of Breast Cancer Subtypes Based on Endoplasmic Reticulum Stress-Related Genes and Analysis of Prognosis and Immune Microenvironment in Breast Cancer Patients.

Introduction: Endoplasmic reticulum stress (ERS) was a response to the accumulation of unfolded proteins and plays a crucial role in the development of tumors, including processes such as tumor cell invasion, metastasis, and immune evasion. However, the specific regulatory mechanisms of ERS in breast cancer (BC) remain unclear. Methods: In this study, we analyzed RNA sequencing data from The Cancer Genome Atlas (TCGA) for breast cancer and identified 8 core genes associated with ERS: ELOVL2, IFNG, MAP2K6, MZB1, PCSK6, PCSK9, IGF2BP1, and POP1. We evaluated their individual expression, independent diagnostic, and prognostic values in breast cancer patients. A multifactorial Cox analysis established a risk prognostic model, validated with an external dataset. Additionally, we conducted a comprehensive assessment of immune infiltration and drug sensitivity for these genes. Results: The results indicate that these eight core genes play a crucial role in regulating the immune microenvironment of breast cancer (BRCA) patients. Meanwhile, an independent diagnostic model based on the expression of these eight genes shows limited independent diagnostic value, and its independent prognostic value is unsatisfactory, with the time ROC AUC values generally below 0.5. According to the results of logistic regression neural networks and risk prognosis models, when these eight genes interact synergistically, they can serve as excellent biomarkers for the diagnosis and prognosis of breast cancer patients. Furthermore, the research findings have been confirmed through qPCR experiments and validation. Conclusion: In conclusion, we explored the mechanisms of ERS in BRCA patients and identified 8 outstanding biomolecular diagnostic markers and prognostic indicators. The research results were double-validated using the GEO database and qPCR.

Identification of Breast Cancer Subtypes by Integrating Genomic Analysis with the Immune Microenvironment.

Objectives: We aim to identify the breast cancer (BC) subtype clusters and the crucial gene classifier prognostic signatures by integrating genomic analysis with the tumor immune microenvironment (TME). Methods: Data sets of BC were derived from the Cancer Genome Atlas (TCGA), METABRIC, and Gene Expression Omnibus (GEO) databases. Unsupervised consensus clustering was carried out to obtain the subtype clusters of BC patients. Weighted gene coexpression network analysis (WGCNA), least absolute shrinkage and selection operator (LASSO), and univariate and multivariate regression analysis were employed to obtain the gene classifier signatures and their biological functions, which were validated by the BC dataset from the METABRIC database. Additionally, to evaluate the overall survival rates of BC patients, Kaplan-Meier survival analysis was carried out. Moreover, to assess how BC subtype clusters are related to the TME, single-cell analysis was performed. Finally, the drug sensitivity and the immune cell infiltration for different phenotypes of BC patients were also calculated by the CIBERSORT and ESTIMATE algorithms. Results : TCGA-BC samples were divided into three subtype clusters, S1, S2, and S3, among which the prognosis of S2 was poor and that of S1 and S3 were better. Three key pathways and 10 crucial prognostic-related gene signatures are screened. Finally, single-cell analysis suggests that S1 samples have the most types of immune cells, S2 with more sensitivity to tumor treatment drugs are enriched with more neutrophils, and more multilymphoid progenitor cells are involved in subtype cluster S3. Conclusions: Our novelty was to identify the BC subtype clusters and the gene classifier signatures employing a large-amount dataset combined with multiple bioinformatics methods. All of the results provide a basis for clinical precision treatment of BC.

Rapid identification of breast cancer subtypes using micro-FTIR and machine learning methods.

Breast cancer (BC) molecular subtypes diagnosis involves improving clinical uptake by Fourier transform infrared (FTIR) spectroscopic imaging, which is a non-destructive and powerful technique, enabling label free extraction of biochemical information towards prognostic stratification and evaluation of cell functionality. However, methods of measurements of samples demand a long time to achieve high quality images, making its clinical use impractical because of the data acquisition speed, poor signal to noise ratio, and deficiency of optimized computational framework procedures. To address those challenges, machine learning (ML) tools can facilitate obtaining an accurate classification of BC subtypes with high actionability and accuracy. Here, we propose a ML-algorithm-based method to distinguish computationally BC cell lines. The method is developed by coupling the K-neighbors classifier (KNN) with neighborhood components analysis (NCA), and hence, the NCA-KNN method enables to identify BC subtypes without increasing model size as well as adding additional computational parameters. By incorporating FTIR imaging data, we show that classification accuracy, specificity, and sensitivity improve, respectively, 97.5%, 96.3%, and 98.2%, even at very low co-added scans and short acquisition times. Moreover, a clear distinctive accuracy (up to 9 %) difference of our proposed method (NCA-KNN) was obtained in comparison with the second best supervised support vector machine model. Our results suggest a key diagnostic NCA-KNN method for BC subtypes classification that may translate to advancement of its consolidation in subtype-associated therapeutics.

Identification of Breast Cancer Subtypes Based on Gene Expression Profiles in Breast Cancer Stroma

BackgroundTumor stroma is a heterogeneous cellular component in the tumor microenvironment of breast cancer. However, very few studies have explored the identification of breast cancer subtypes based on highly heterogeneous tumor stromal signatures. Materials and MethodsUsing a combined dataset composed of 8 gene expression profiling datasets for breast tumor stroma, we clustered breast cancers based on the expression levels of 100 genes whose expression values were most variable across all samples. Furthermore, we investigated the molecular features of the breast cancer subtypes identified. ResultsWe identified 2 breast cancer subtypes, termed SBCS-1 and SBCS-2. We found that the contents of stroma and immune cells were lower in SBCS-1 than in SBCS-2, while the proportion of tumor cells was higher in SBCS-1. SBCS-1 was enriched in cancer-associated pathways, including ribosomes, cell cycle, RNA degradation, RNA polymerase, DNA replication, oxidative phosphorylation, proteasome, spliceosome, and glycolysis/gluconeogenesis. SBCS-2 was enriched in pathways of graft versus host disease, type 1 diabetes mellitus, intestinal immune network for IgA production, allograft rejection, and steroid hormone biosynthesis. Moreover, many oncogenic biological processes were highly activated in SBCS-1, including proliferation, stemness, epithelial-to-mesenchymal transition (EMT), and angiogenesis. Gene co-expression network analysis identified prognostic hub genes, transcription factor encoding genes (PFDN5 and EZH2), and protein kinase encoding gene (AURKA) in a gene module highly enriched in SBCS-1. ConclusionBased on the gene expression profiles in breast cancer stroma, breast cancer can be divided into 2 subtypes, which have significantly different molecular, and clinical characteristics. The identification of new subtypes of breast cancer has clinical implications for the management of this disease.

Identification of Molecular Subtypes of Breast Cancer Based on Multimodal Deep Learning

The identification of breast cancer subtypes plays a key role in the prognosis of breast cancer. In recent years, deep learning (DL) has shown good performance in intelligent identification of breast cancer subtypes. However, most of the traditional DL models use single-mode data, and the extracted features are limited, so the association between patient characteristics and breast cancer subtypes cannot be established stably. In order to improve the effect of recognition, this study proposes a multimodal fusion deep learning (MFDL) model. This model combined with the breast cancer gene modal data and image modal data established a multilayer perceptron network and the depth of the convolution neural network for feature extraction, and then based on the idea of weighted aggregation on the output of the two characteristics of the network integration. Finally, the fusion features were used to identify breast cancer subtypes. The experimental results show that compared with other models in AUC value, accuracy and other indicators, the MFDL model proposed in this study is more accurate and efficient in the identification of breast cancer subtypes.

Diagnostic Accuracy of Cross-Polarization OCT and OCT-Elastography for Differentiation of Breast Cancer Subtypes: Comparative Study.

The possibility to assess molecular-biological and morphological features of particular breast cancer types can improve the precision of resection margin detection and enable accurate determining of the tumor aggressiveness, which is important for treatment selection. To enable reliable differentiation of breast-cancer subtypes and evaluation of resection margin, without performing conventional histological procedures, here we apply cross-polarization optical coherence tomography (CP-OCT) and compare it with a novel variant of compressional optical coherence elastography (C-OCE) in terms of the diagnostic accuracy (Ac) with histological verification. The study used 70 excised breast cancer specimens with different morphological structure and molecular status (Luminal A, Luminal B, Her2/Neo+, non-luminal and triple-negative cancer). Our first aim was to formulate convenient criteria of visual assessment of CP-OCT and C-OCE images intended (i) to differentiate tumorous and non-tumorous tissues and (ii) to enable more precise differentiation among different malignant states. We identified such criteria based on the presence of heterogeneities and characteristics of signal attenuation in CP-OCT images, as well as the presence of inclusions/mosaic structures combined with visually feasible assessment of several stiffness grades in C-OCE images. Secondly, we performed a blinded reader study of the Ac of C-OCE versus CP-OCT, for delineation of tumorous versus non-tumorous tissues followed by identification of breast cancer subtypes. For tumor detection, C-OCE showed higher specificity than CP-OCT (97.5% versus 93.3%) and higher Ac (96.0 versus 92.4%). For the first time, the Ac of C-OCE and CP-OCT were evaluated for differentiation between non-invasive and invasive breast cancer (90.4% and 82.5%, respectively). Furthermore, for invasive cancers, the difference between invasive but low-aggressive and highly-aggressive subtypes can be detected. For differentiation between non-tumorous tissue and low-aggressive breast-cancer subtypes, Ac was 95.7% for C-OCE and 88.1% for CP-OCT. For differentiation between non-tumorous tissue and highly-aggressive breast cancers, Ac was found to be 98.3% for C-OCE and 97.2% for CP-OCT. In all cases C-OCE showed better diagnostic parameters independently of the tumor type. These findings confirm the high potential of OCT-based examinations for rapid and accurate diagnostics during breast conservation surgery.

Comparative analysis of intact glycopeptides from mannose receptor among different breast cancer subtypes using mass spectrometry

Breast cancer is a highly heterogeneous disease, encompassing a number of biologically distinct entities with specific pathologic features and biological behaviors. In the preliminary experiments, we identified several glycosylation sites of mannose receptors in different breast cancer subtypes and showed that the mannose receptors could be a potential marker for breast cancer. However, the glycan composition on each site is still unknown because the glycan was removed by PNGase F in previous work. Analysis of intact glycopeptides can provide the information of both the glycan composition and the glycosylation site, which can further help to reveal the difference of glycosylation in the four subtypes of breast cancer. In this work, we analyzed the intact glycopeptides of the mannose receptors in serum from breast cancer patients using isobaric tags for relative and absolute quantitation (iTRAQ) and LC-MS/MS. In total, 7 glycosylation sites and 12 glycan types corresponding to 26 intact glycopeptides were characterized from the four subtypes of breast cancer. Among them, 11 glycopeptides can be used to differentiate the subtypes of breast cancer, which further supported the previous conclusion that mannose receptor can be used as a potential marker for the identification of breast cancer subtypes.

Comparison of Different Dynamic Contrast Enhanced-Magnetic Resonance Imaging Descriptors and Clinical Findings Among Breast Cancer Subtypes Determined Based on Molecular Assessment

Background: Breast cancer is a heterogeneous disease with different molecular and histologic subtypes, clinical behaviors and prognosis. The same stage of disease and similar histopathological characteristics may show different treatment responses. Identification of breast cancer subtypes has become important for planning the targeted therapy and personalized management of patients. Objectives: To compare the clinicopathologic findings, dynamic contrast enhanced-magnetic resonance imaging (DCE-MRI) characteristics and associated MRI findings among breast cancer molecular subtypes. Patients and Methods: 267 pathologically proven invasive breast cancers in 263 patients were included. Clinicopathological findings, DCE-MRI findings and associated MRI findings were retrospectively evaluated and compared among breast cancer subtypes. Results: Invasive ductal carcinoma was the most common histological tumor type (87.6%). There were 222 (83.1%) masses and 45 (16.9%) non-mass enhancements. The molecular subtypes were luminal A in 174 (65.1%), luminal B in 45 (16.9%), human epidermal growth factor receptor 2 (HER2) positive in 24 (9%) and triple negative (TN) in 24 (9%) of the lesions. Spiculated mass margin was significantly associated with luminal A breast cancer (45.2%) and irregular shape was significantly more common in luminal A (86.3%) and luminal B lesions (95.1%) (P < 0.001). Larger mass size (P = 0.027), non-mass enhancement (P = 0.005), perilesional + prepectoral edema and skin + perilesional + prepectoral edema were significantly associated with HER2 positive breast cancer (P = 0.001). Higher histological grade, oval mass shape, circumscribed mass margin, intratumoral high/very high signal intensity on T2 weighted image (T2WI) were significantly associated with TN breast cancer (P < 0.001). Conclusion: Histological grade, size and morphological features of masses on DCE-MRI, intratumoral signal intensity on T2WI and edema pattern would be helpful to distinguish breast cancer subtypes.

Analysis of breast cancer subtypes by AP-ISA biclustering

BackgroundGene expression profiling has led to the definition of breast cancer molecular subtypes: Basal-like, HER2-enriched, LuminalA, LuminalB and Normal-like. Different subtypes exhibit diverse responses to treatment. In the past years, several traditional clustering algorithms have been applied to analyze gene expression profiling. However, accurate identification of breast cancer subtypes, especially within highly variable LuminalA subtype, remains a challenge. Furthermore, the relationship between DNA methylation and expression level in different breast cancer subtypes is not clear.ResultsIn this study, a modified ISA biclustering algorithm, termed AP-ISA, was proposed to identify breast cancer subtypes. Comparing with ISA, AP-ISA provides the optimized strategy to select seeds and thresholds in the circumstance that prior knowledge is absent. Experimental results on 574 breast cancer samples were evaluated using clinical ER/PR information, PAM50 subtypes and the results of five peer to peer methods. One remarkable point in the experiment is that, AP-ISA divided the expression profiles of the luminal samples into four distinct classes. Enrichment analysis and methylation analysis showed obvious distinction among the four subgroups. Tumor variability within the Luminal subtype is observed in the experiments, which could contribute to the development of novel directed therapies.ConclusionsAiming at breast cancer subtype classification, a novel biclustering algorithm AP-ISA is proposed in this paper. AP-ISA classifies breast cancer into seven subtypes and we argue that there are four subtypes in luminal samples. Comparison with other methods validates the effectiveness of AP-ISA. New genes that would be useful for targeted treatment of breast cancer were also obtained in this study.

Molecular imaging using PET and SPECT for identification of breast cancer subtypes.

Breast cancer is a major disease with high morbidity and mortality in women. As a highly heterogeneous tumor, it contains different molecular subtypes: luminal A, luminal B, human epidermal growth factor 2-positive, and triple-negative subtypes. As each subtype has unique features, it may not be universal to the optimal treatment and expected response for individual patients. Therefore, it is critical to identify different breast cancer subtypes. Targeting subcellular levels, molecular imaging, especially PET and single photon emission computed tomography, has become a promising means to identify breast cancer subtypes and monitor treatment. Different biological processes between various subtypes, including changes correlated with receptor expression, cell proliferation, or glucose metabolism, have the potential for imaging with PET and single photon emission computed tomography radiopharmaceuticals. Receptor imaging, with radiopharmaceuticals targeting estrogen receptor, progesterone receptor, or human epidermal growth factor 2, is available to distinguish receptor-positive tumors from receptor-negative ones. Cell proliferation imaging with fluorine-18 fluorothymidine PET aids identification of luminal A and B subtypes on the basis of the correlation with the immunohistochemical biomarker Ki-67. Glucose metabolism imaging with fluorine-18 fluorodeoxyglucose PET may have potential to discriminate triple-negative subtypes from others. With increasing numbers of novel radiopharmaceuticals, noninvasive molecular imaging will be applied widely for the identification of different subtypes and provide more in-vivo information on individualized management of breast cancer patients.

Expression and methylation patterns partition luminal-A breast tumors into distinct prognostic subgroups.

BackgroundBreast cancer is a heterogeneous disease comprising several biologically different types, exhibiting diverse responses to treatment. In the past years, gene expression profiling has led to definition of several “intrinsic subtypes” of breast cancer (basal-like, HER2-enriched, luminal-A, luminal-B and normal-like), and microarray based predictors such as PAM50 have been developed. Despite their advantage over traditional histopathological classification, precise identification of breast cancer subtypes, especially within the largest and highly variable luminal-A class, remains a challenge. In this study, we revisited the molecular classification of breast tumors using both expression and methylation data obtained from The Cancer Genome Atlas (TCGA).MethodsUnsupervised clustering was applied on 1148 and 679 breast cancer samples using RNA-Seq and DNA methylation data, respectively. Clusters were evaluated using clinical information and by comparison to PAM50 subtypes. Differentially expressed genes and differentially methylated CpGs were tested for enrichment using various annotation sets. Survival analysis was conducted on the identified clusters using the log-rank test and Cox proportional hazards model.ResultsThe clusters in both expression and methylation datasets had only moderate agreement with PAM50 calls, while our partitioning of the luminal samples had better five-year prognostic value than the luminal-A/luminal-B assignment as called by PAM50. Our analysis partitioned the expression profiles of the luminal-A samples into two biologically distinct subgroups exhibiting differential expression of immune-related genes, with one subgroup carrying significantly higher risk for five-year recurrence. Analysis of the luminal-A samples using methylation data identified a cluster of patients with poorer survival, characterized by distinct hyper-methylation of developmental genes. Cox multivariate survival analysis confirmed the prognostic significance of the two partitions after adjustment for commonly used factors such as age and pathological stage.ConclusionsModern genomic datasets reveal large heterogeneity among luminal breast tumors. Our analysis of these data provides two prognostic gene sets that dissect and explain tumor variability within the luminal-A subgroup, thus, contributing to the advancement of subtype-specific diagnosis and treatment.Electronic supplementary materialThe online version of this article (doi:10.1186/s13058-016-0724-2) contains supplementary material, which is available to authorized users.

Video Q&amp;A: molecular profiling of breast cancer

In this video Q&A, we talk to Professor Carlos Caldas about the identification of breast cancer subtypes through molecular profiling, and the clinical implications for diagnosis and treatment.

Prognostic value of immunohistochemical stratification of invasive duct carcinoma of the breast

Objective Gene expression profiling of breast cancer has identified five molecularly distinct subtypes of breast cancer that have different biological behavior and clinical outcomes. These subtypes are termed luminal A, luminal B, luminal HER2, HER2-enriched and triple negative breast cancers (TNBC). We aimed at identification of breast cancer subtypes among Egyptian population and their clinicopathologic features using ER, PR and HER2, Ki-67 and CK5/6.

Abstract SY42-03: Lifestyle factors and risk of aggressive forms of breast cancer among African American women.

Abstract It has been known for decades that American women of African ancestry (AA) with breast cancer have worse overall and disease-free survival than those of European (EA) descent. For many years, it was presumed that this poorer survival was due to factors associated with socio-economic status, such as less access to care and screening, resulting in later stage disease. There has also been research investigating if lack of receipt of optimal treatment, other co-morbid conditions or patient characteristics could account, in part, for this higher mortality. However, it is now generally accepted that AA women tend to be diagnosed with tumors with more aggressive characteristics, including less differentiated high-grade tumors, and lack of expression of estrogen (ER) and progesterone (PR) receptors. AA women are also more likely to be diagnosed with basal-like breast cancers, identified through gene expression profiling and validated with immunohistochemical markers, and to be diagnosed with breast cancer at a younger age than EAs. There are no facile reasons to explain these differences in breast cancer epidemiology between AAs and EAs, and a number of genome-wide association studies (GWAS) have not identified genetic variants that appear to explain a large portion of this increased incidence of aggressive tumors in AA women. The identification of breast cancer subtypes has enabled research to examine risk factors for more aggressive tumors in large cohort or case-control studies. The Carolina Breast Cancer Study (CBCS), led by Dr. Robert Millikan, was the first to categorize tumors by intrinsic subtypes and examine associations with traditional risk factors, with some surprising results. Although the standard risk factors for breast cancer include no or few children, those data were derived from studies of primarily EA women, the majority of whom likely had ER positive breast cancer. When Millikan and colleagues assessed parity and risk stratified by breast cancer subtype, they found, as expected, that having children reduced risk of luminal A breast cancer (ER, PR positive, HER2 negative), most common in older white women, but for basal-like breast cancer (ER, PR, HER2 negative, positive for cy5/6 and EGFR), having children actually was associated with a two-fold increase in risk. Importantly, breastfeeding totally ameliorated this increased risk of aggressive breast cancer. Since that initial paper in 2008, these findings have been replicated in a number of studies, including the Black Women's Health Study, a prospective cohort led by Drs. Julie Palmer and Lynn Rosenberg. Associations have also been observed in EA women. However, because AA women generally have higher parity, and are less likely to breastfeed, these lifestyle factors could, in part, play a role in the higher prevalence of aggressive breast tumors in AA women. In this presentation, the literature on associations between other lifestyle factors and risk of aggressive breast cancer in AA women will be reviewed, and new hypotheses and ongoing research will be discussed. Citation Format: Christine B. Ambrosone. Lifestyle factors and risk of aggressive forms of breast cancer among African American women. [abstract]. In: Proceedings of the 104th Annual Meeting of the American Association for Cancer Research; 2013 Apr 6-10; Washington, DC. Philadelphia (PA): AACR; Cancer Res 2013;73(8 Suppl):Abstract nr SY42-03. doi:10.1158/1538-7445.AM2013-SY42-03

Decision-making tools to assist prognosis and treatment choices in early breast cancer: a review

Breast cancer remains the most common type of cancer affecting women worldwide with an estimated lifetime risk of 1:8. With developments in adjuvant treatment and the identification of breast cancer subtypes, rising expectation of ‘personalized’ and ‘targeted’ therapy, decisions on systemic therapy have become increasingly more difficult. In a bid to assist clinicians in correctly selecting patients in whom systemic adjuvant therapy would be of most benefit, a number of decision-making tools have been developed. In this article, the authors will review some of these tools, explore how they were developed and assess the impact they have had on daily clinical practice.

Metastatic Breast Cancer: Therapeutic Options According to Molecular Subtypes and Prior Adjuvant Therapy

In spite of advances in treatment strategies, about 25%-40% of patients with breast cancer still eventually develop metastatic disease that is largely incurable. Treatment goals vary from symptom control to lengthening survival, mainly on the basis of patient age and performance status, tumor biology, site and extent of disease, and prior therapies. In particular, breast cancer molecular characterization allows for the identification of breast cancer subtypes with distinct biological features, a distinct clinical course, and distinct treatment sensitivity. Endocrine manipulation is the cornerstone of therapy in hormone receptor-positive tumors; anti-human epidermal growth factor receptor (HER)-2 agents are essential in the management of HER-2(+) tumors; and chemotherapy is the only available option so far for the triple-negative subtype. In each of these subtypes, the more efficacious agents have been progressively incorporated into adjuvant treatment. As a consequence, the choice of the optimal therapeutic strategy for patients with metastatic disease is largely influenced by prior exposure to adjuvant therapies. This review contextualizes the data from clinical trials into different clinical scenarios of metastatic disease, taking into account the molecular subtype and prior adjuvant treatments.