Classification Of Breast Cancer Patients Research Articles

B-122 Improving the Diagnostic Utility of Multiplexed Assays in Laboratory Medicine with Machine Learning

Abstract Background The application of machine learning (ML) and artificial intelligence (AI) in precision medicine is of great interest and continues to grow. ML approaches offer a flexible and data-centric methodology for modeling diagnostic and prognostic trends, capable of identifying complex non-linear patterns and relationships between predictor variables and outcomes within large data sets. Although ML holds great promise, there are several common pitfalls that must be avoided for ML models to provide clinical utility. In the current study, we provide a rigorous and systematic evaluation of the utility of ML algorithms to predict disease in several representative data sets generated via multiplexed biomarker assays. We compare five major classes of ML algorithms compared to more traditional combinatorial analysis (logistic regression) to offer perspective against the current gold standard. Methods We obtained five data sets from published literature that include measurements of multiplexed biomarkers in patients with obstructive sleep apnea, sepsis, and breast and colon cancers in comparison to healthy controls. These datasets were generated by bead-based and planar multiplexed immunoassays. We chose representative ML algorithms from the classes of support vector machines (SVM), random forests (RF), neural networks (NNet), and extreme gradient boosting (xgBoost) in comparison to logistic regression (LR). Datasets were randomly split into internal validation and external validation sets via 10 iterations of permutation analysis. We tuned and validated the models using 5-fold cross validation, then tested those on external subsets. We report the average of several model classification metrics and associated variances across all resampled data sets. Results For the classification of sepsis using inflammatory cytokines measured on the Luminex bead-based immunoassay, RF outperformed LR in external validation sets by a 9.8% increase in AUROC. For classification of breast cancer patients, xgBoost and RF performed best with 20.0% and 16.9% increases in AUROC, respectively, whereas for classification of colon cancer patients, NNet outperformed LR by 11.5%. Across all datasets, on average, all ML algorithms outperformed LR in the internal validation sets by a 7.9% (6.3% - 9.9%) increase in AUROC. However, in external validation sets, only xgBoost and SVM outperformed LR, where RF and NNet showed signs of overfitting. Conclusions Overall, certain ML algorithms show improvement over LR for diagnostic applications using multiplexed assays, by up to 20% increase in AUROC. Interpretation of ML results must be performed rigorously to prevent overly optimistic and unrealistic conclusions. In the context of laboratory medicine, our results showcase the utility of ML in clinical applications, while highlighting potential disadvantages of ML. This analysis underscores the need for establishing rigorous guidelines to support data analytics during the development of novel multiplexed assays, which is needed to advance precision medicine.

High fidelity detection of miRNAs from complex physiological samples through electrochemical nanosensors empowered by proximity catalysis and magnetic separation

Electrochemical detection of miRNA biomarkers in complex physiological samples holds great promise for accurate evaluation of tumor burden in the perioperative period, yet limited by reproducibility and bias issues. Here, nanosensors installed with hybrid probes that responsively release catalytic DNAzymes (G-quadruplexes/hemin) were developed to solve the fidelity challenge in an immobilization-free detection. miRNA targets triggered toehold-mediated strand displacement reactions on the sensor surface and resulted in amplified shedding of DNAzymes. Subsequently, the interference background was removed by Fe3O4 core-facilitated magnetic separation. Binding aptamers of the electrochemical reporter (dopamine) were tethered closely to the catalytic units for boosting H2O2-mediated oxidation through proximity catalysis. The one-to-many conversion by dual amplification from biological-chemical catalysis facilitated sufficient homogeneous sensing signals on electrodes. Thereby, the nanosensor exhibited a low detection limit (2.08 fM), and high reproducibility (relative standard deviation of 1.99%). Most importantly, smaller variations (RSD of 0.51–1.04%) of quantified miRNAs were observed for detection from cell lysates, multiplexed detection from unprocessed serum, and successful discrimination of small upregulations in lysates of tumor tissue samples. The nanosensor showed superior diagnostic performance with an area under curve (AUC) of 0.97 and 94% accuracy in classifying breast cancer patients and healthy donors. These findings demonstrated the synergy of signal amplification and interference removal in achieving high-fidelity miRNA detection for practical clinical applications.

Serum analysis based on SERS combined with 2D convolutional neural network and Gramian angular field for breast cancer screening

Breast cancer is a significant cause of death among women worldwide. It is crucial to quickly and accurately diagnose breast cancer in order to reduce mortality rates. While traditional diagnostic techniques for medical imaging and pathology samples have been commonly used in breast cancer screening, they still have certain limitations. Surface-enhanced Raman spectroscopy (SERS) is a fast, highly sensitive and user-friendly method that is often combined with deep learning techniques like convolutional neural networks. This combination helps identify unique molecular spectral features, also known as “fingerprint”, in biological samples such as serum. Ultimately, this approach is able to accurately screen for cancer. The Gramian angular field (GAF) algorithm can convert one-dimensional (1D) time series into two-dimensional (2D) images. These images can be used for data visualization, pattern recognition and machine learning tasks. In this study, 640 serum SERS from breast cancer patients and healthy volunteers were converted into 2D spectral images by Gramian angular field (GAF) technique. These images were then used to train and test a two-dimensional convolutional neural network-GAF (2D-CNN-GAF) model for breast cancer classification. We compared the performance of the 2D-CNN-GAF model with other methods, including one-dimensional convolutional neural network (1D-CNN), support vector machine (SVM), K-nearest neighbor (KNN) and principal component analysis-linear discriminant analysis (PCA-LDA), using various evaluation metrics such as accuracy, precision, sensitivity, F1-score, receiver operating characteristic (ROC) curve and area under curve (AUC) value. The results showed that the 2D-CNN model outperformed the traditional models, achieving an AUC value of 0.9884, an accuracy of 98.13%, sensitivity of 98.65% and specificity of 97.67% for breast cancer classification. In this study, we used conventional nano-silver sol as the SERS-enhanced substrate and a portable laser Raman spectrometer to obtain the serum SERS data. The 2D-CNN-GAF model demonstrated accurate and automatic classification of breast cancer patients and healthy volunteers. The method does not require augmentation and preprocessing of spectral data, simplifying the processing steps of spectral data. This method has great potential for accurate breast cancer screening and also provides a useful reference in more types of cancer classification and automatic screening.

Classification of bladder cancer based on immune cell infiltration and construction of a risk prediction model for prognosis.

To classify bladder cancer based on immune cell infiltration score and to construct a prognosis assessment model of patients with bladder cancer. The transcriptome data and clinical data of breast cancer patients were obtained from the The Cancer Genome Atlas (TCGA) database. Single sample gene set enrichment analysis was used to calculate the infiltration scores of 16 immune cells. The classification of breast cancer patients was achieved by unsupervised clustering, and the sensitivity of patients with different types to immunotherapy and chemotherapy was analyzed. The key modules significantly related to the infiltration of key immune cells were identified by weighted correlation network analysis (WGCNA), and the key genes in the modules were identified. A risk scoring model and a nomogram for prognosis assessment of bladder cancer patients were constructed and verified. B cells, mast cells, neutrophils, T helper cells and tumor infiltrating lymphocytes were determined to be the key immune cells of bladder cancer. The patients were clustered into two groups (Cluster 1 ´ and Custer 2) based on immune cell infiltration scores. Compared with patients with Cluster 1 ´, patients with Cluster 2 were more likely to benefit from immunotherapy (P<0.05), and patients with Cluster 2 were more sensitive to Enbeaten, Docetaxel, Cyclopamine, and Akadixin (P<0.05). 35 genes related to key immune cells were screened out by WGCNA and 4 genes (GPR171, HOXB3, HOXB5 and HOXB6) related to the prognosis of bladder cancer were further screened by LASSO Cox regression. The areas under the ROC curve (AUC) of the bladder cancer prognosis risk scoring model based on these 4 genes to predict the 1-, 3- and 5-year survival of patients were 0.735, 0.765 and 0.799, respectively. The nomogram constructed by combining risk score and clinical parameters has high accuracy in predicting the 1-, 3-, and 5-year overall survival of bladder cancer patients. According to the immune cell infiltration score, bladder cancer patients can be classified. Furthermore, bladder cancer prognosis risk scoring model and nomogram based on key immune cell-related genes have high accuracy in predicting the prognosis of bladder cancer patients.

Identification of breast cancer subgroups and immune characterization based on glutamine metabolism-related genes

Immunotherapy is a promising treatment for breast cancer (BC). However, due to individual differences and tumor heterogeneity, immunotherapy is only applicable to some BC patients. Glutamine metabolism plays a role in inhibiting immunotherapy, but its role in BC is limitedly studied. Therefore, we aimed to identify different BC subgroups based on glutamine metabolism and characterize the features of different subgroups to provide guidance for personalized immunotherapy for BC patients. Using unsupervised clustering analysis, we classified BC patients in The Cancer Genome Atlas (TCGA) with glutamine metabolism-related genes and obtained low-risk (LR) and high-risk (HR) subgroups. Survival analysis revealed that prognosis of LR subgroup was notably better than HR subgroup. Through ssGSEA and CIBERSORT methods, we disclosed that infiltration levels of B cells, Mast cells, T helper cells, and Th2 cells, and Type II IFN Response immune function were notably higher in LR subgroup than in HR subgroup. The Wilcox algorithm comparison denoted that DEPTH of LR subgroup was significantly lower than HR subgroup. The TIDE of LR subgroup was significantly higher than HR subgroup. Functional annotation of differentially expressed genes revealed that channel activity and the Estrogen signaling pathway may be related to BC prognosis. Ten hub genes were selected between the subgroups through the STRING database and Cytoscape, and their correlation with drugs was predicted on the CellMiner website. This study analyzed the immune characteristics of BC subgroups based on glutamine metabolism and provided reference for prognosis prediction and personalized immunotherapy.

Development of lymph node metastasis-related prognostic markers in breast cancer

BackgroundLymph node metastasis (LNM) from Breast cancer (BC) is commonly seen in BC progression. Currently, the identification of genes linked with LNM in BC remains in mystery. MethodsGenes related to BC LNM were screened, and a risk model was constructed based on LASSO-Cox analysis. Combined with the Kaplan-Meier curve, the ability of riskscore to distinguish different baseline characteristics was evaluated, and model was verified by the receiver operating characteristic (ROC) curve. The expression levels of prognostic marker genes were analyzed by qRT-PCR and western blot (WB). ResultsA higher survival rate and longer survival time in low-risk BC patients. The 1, 3 and 5 year AUC values of the training set were 0.79, 0.74, and 0.73, respectively. Results for the validation set was similar to the training set. The differentially expressed genes between the high- and low-risk groups were significantly enriched in immune pathways. In addition, the low-risk group had higher levels of immune infiltration. qRT-PCR and WB results showed that in BC, CDH10, SMR3A, POU3F2, and FABP7 were down-regulated, and LHX1 was up-regulated. ConclusionsWe built a prognostic model of BC based on LNM-related genes, proffering evaluation for prognosis and precise cure of BC. SignificanceAt present, the genes related to lymph node metastasis in BC are still largely unknown and need to be further explored. Searching for potential lymph node metastasis-related genes of BC will provide meaningful biomarkers for BC treatment. Based on TCGA-BRCA data, we established an effective 11-gene prognostic risk model that could predict patient outcomes independently. Our model could classify BC patients and distinguish patients with poor prognosis effectively. Besides, the feature genes we identified might exert a predictive function in immunotherapy. The results of this study provide a new reference for the prognosis and treatment of BC patients with lymph node metastasis.

A molecular classification system for estimating radiotherapy response and anticancer immunity for individual breast cancer patients.

Radiotherapy is a cornerstone of breast cancer therapy, but radiotherapy resistance is a major clinical challenge. Herein, we show a molecular classification approach for estimating individual responses to radiotherapy. Consensus clustering was adopted to classify radiotherapy-sensitive and -resistant clusters in the TCGA-BRCA cohort based upon prognostic differentially expressed radiotherapy response-related genes (DERRGs). The stability of the classification was proven in the GSE58812 cohort via NTP method and the reliability was further verified by quantitative RT-PCR analyses of DERRGs. A Riskscore system was generated through Least absolute shrinkage and selection operator (LASSO) analysis, and verified in the GSE58812 and GSE17705. Treatment response and anticancer immunity were evaluated via multiple well-established computational approaches. We classified breast cancer patients as radiotherapy-sensitive and -resistant clusters, namely C1 and C2, also verified by quantitative RT-PCR analyses of DERRGs. Two clusters presented heterogeneous clinical traits, with poorer prognosis, older age, more advanced T, and more dead status in the C2. The C1 tumors had higher activity of reactive oxygen species and response to X-ray, proving better radiotherapeutic response. Stronger anticancer immunity was found in the C1 tumors that had rich immune cell infiltration, similar expression profiling to patients who responded to anti-PD-1, and activated immunogenic cell death and ferroptosis. The Riskscore was proposed for improving patient prognosis. High Riskscore samples had lower radiotherapeutic response and stronger DNA damage repair as well as poor anticancer immunity, while low Riskscore samples were more sensitive to docetaxel, doxorubicin, and paclitaxel. Our findings propose a novel radiotherapy response classification system based upon molecular profiles for estimating radiosensitivity for individual breast cancer patients, and elucidate a methodological advancement for synergy of radiotherapy with ICB.

An adaptive framework for predicting breast cancer at an early stage

Breast cancer is one of the leading medical problems in the healthcare field among women. The cancer-related death rate is a major global health problem, particularly in developing countries. Early diagnosis of breast cancer is the only effective way to deal with this mortality factor. Although there are many methods for preventing cancer, there are still some types that have unknown cures. Breast cancer is extremely common and can be effectively treated if caught in its early stages. A correct diagnosis of breast cancer is a vital first step in treatment. Predicting the subtype of breast cancer is an active area of study. In this article, an attempt has been made to present a framework to predict breast cancer using machine learning techniques at an early stage to get the best treatment for the patient. The proposed method uses the machine learning classifiers Logistic Regression and Support Vector Machine to classify breast cancer patients into benign (Non Cancerous Tumor) and salignant (Cancerous Tumor) categories. The proposed mechanism is implemented using Python and Jupyter Notebook on the real dataset, which is generated through a sensing device and collected from the UCI repository. The performance is analyzed using performance metrics such as accuracy, precision, F-measure, etc. The Logistic Regression (LR) model achieves an accuracy of 97.14%, whereas, in the SVM model, the obtained accuracy is 96%. The performance of the proposed framework was evaluated and compared with the other algorithms, and the results indicated that the proposed framework achieved better performance than other models.

Breast cancer survival prognosis using the graph convolutional network with Choquet fuzzy integral

Breast cancer is the most prevalent kind of cancer among women and there is a need for a reliable algorithm to predict its prognosis. Previous studies focused on using gene expression data to build predictive models. However, recent advancements have made multi-omics cancer data sets (gene expression, copy number alteration, etc.) accessible. This has acted as the motivation for the creation of a novel model that utilizes a graph convolutional network (GCN) and Choquet fuzzy ensemble, incorporating multi-omics and clinical data retrieved from the publicly available METABRIC Database. In this study, graphs have been used to extract structural information, and a Choquet Fuzzy Ensemble with Logistic Regression, Random Forest, and Support Vector Machine as base classifiers has been employed to classify breast cancer patients as short-term or long-term survivors. The model has been run using all possible combinations of gene expression, copy number alteration, and clinical modality, and the results have been reported. Furthermore, a comparison has been made between the obtained results and different baseline models and state-of-the-art to demonstrate the efficacy of the proposed model in terms of different metrics. The results of this model based on Accuracy, Matthews correlation coefficient, Precision, Sensitivity, Specificity, Balanced Accuracy, and F1-Measure are 0.820, 0.528, 0.630, 0.666, 0.871, 0.769, and 0.647, respectively.

A DNA-based hydrogel for exosome separation and biomedical applications

Exosomes (EXOs) have been proven as biomarkers for disease diagnosis and agents for therapeutics. Great challenge remains in the separation of EXOs with high-purity and low-damage from complex biological media, which is critical for the downstream applications. Herein, we report a DNA-based hydrogel to realize the specific and nondestructive separation of EXOs from complex biological media. The separated EXOs were directly utilized in the detection of human breast cancer in clinical samples, as well as applied in the therapeutics of myocardial infarction in rat models. The materials chemistry basis of this strategy involved the synthesis of ultralong DNA chains via an enzymatic amplification, and the formation of DNA hydrogels through complementary base-pairing. These ultralong DNA chains that contained polyvalent aptamers were able to recognize and bind with the receptors on EXOs, and the specific and efficient binding ensured the selective separation of EXOs from media into the further formed networked DNA hydrogel. Based on this DNA hydrogel, rationally designed optical modules were introduced for the detection of exosomal pathogenic microRNA, which achieved the classification of breast cancer patients versus healthy donors with 100% precision. Furthermore, the DNA hydrogel that contained mesenchymal stem cell-derived EXOs was proved with significant therapeutic efficacy in repairing infarcted myocardium of rat models. We envision that this DNA hydrogel-based bioseparation system is promising as a powerful biotechnology, which will promote the development of extracellular vesicles in nanobiomedicine.

The bioinformatics analysis of the clinicopathological and prognostic significances of REG4 mRNA in gynecological cancers

To clarify the clinicopathological importance of REG4 mRNA expression, we used GEO, TCGA, xiantao, UALCAN, and Kaplan-Meier plotter for a bioinformatics analysis in breast, cervical, endometrial and ovarian cancers. Compared to normal tissues, REG4 expression was found to be upregulated in breast, cervical, endometrial, and ovarian cancers (p < 0.05). Breast cancer had a higher level of REG4 methylation than normal tissues (p < 0.05), which was negatively correlated with its mRNA expression. REG4 expression was positively correlated with oestrogen and progesterone receptor expression, and aggressiveness of PAM50 classification of breast cancer patients (p < 0.05). Breast infiltrating lobular carcinomas expressed more REG4 than ductal carcinomas (p < 0.05). The REG4-related signal pathways mainly included peptidase, keratinisation, brush border and digestion and so forth in gynecological cancers. Our results indicated that REG4 overexpression was associated with gynecological carcinogenesis and their histogenesis, and may be used as a marker for aggressive behaviour and prognosis of breast or cervical cancer. IMPACT STATEMENT What is already known on this subject? REG4 encodes a secretory c-type lectin and plays an essential role in inflammation, carcinogenesis, apoptotic and radiochemotherapeutic resistance. What do the results of this study add? As a standalone predictor, REG4 expression was positively correlated with progression-free survival. Expression of REG4 mRNA was positively associated with the T stage and adenosquamous cell carcinoma of cervical cancer. The top signal pathways related to REG4 included smell and chemical stimulus, peptidase, intermediate filament, and keratinisation in breast cancer; ligand-receptor interaction, metabolism of hormone, xenobiotic and retinol, peptidase, brush border and digestion in cervical and ovarian cancers; bile secretion, intermediate filament, chemical carcinogenesis, brush border and keratinisation in endometrial cancer. REG4 mRNA expression was positively correlated with DC cell infiltration in breast cancer, positively with Th17 cells, TFH, cytotoxic cells and T cells in cervical and endometrial cancers, and negatively with DC cell infiltration, cytotoxic cells and T cells in ovarian cancer. The top hub genes mainly included small proline rich protein 2B in breast cancer; fibrinogens and apoproteins in cervical, endometrial and ovarian cancers. What are the implications of these finding for clinical practice and/or further research? Our study has showed that REG4 mRNA expression is a potential biomarker or therapeutic target for gynaecologic cancers.

A comprehensive framework towards segmenting and classifying breast cancer patients using deep learning and Aquila optimizer

Breast cancer is among the major frequent types of cancer worldwide, causing a significant death rate every year. It is the second most prevalent malignancy in Egypt. With the increasing number of new cases, it is vital to diagnose breast cancer in its early phases to avoid serious complications and deaths. Therefore, routine screening is important. With the current evolution of deep learning, medical imaging became one of the interesting fields. The purpose of the current work is to suggest a hybrid framework for both the classification and segmentation of breast scans. The framework consists of two phases, namely the classification phase and the segmentation phase. In the classification phase, five different CNN architectures via transfer learning, namely MobileNet, MobileNetV2, NasNetMobile, VGG16, and VGG19, are applied. Aquila optimizer is used for the calculation of the optimal hyperparameters of the different TL architectures. Four different datasets representing four different modalities (i.e., MRI, Mammographic, Ultrasound images, and Histopathology slides) are used for training purposes. The framework can perform both binary- and multi-class classification. In the segmentation phase, five different structures, namely U-Net, Swin U-Net, Attention U-Net, U-Net++, and V-Net, are applied to identify the region of interest in the ultrasound breast images. The reported results prove the efficiency of the suggested framework against current state-of-the-art studies.

The regulatory roles of T helper cells in distinct extracellular matrix characterization in breast cancer.

BackgroundTumors are characterized by extracellular matrix (ECM) remodeling and stiffening. The ECM has been recognized as an important determinant of breast cancer progression and prognosis. Recent studies have revealed a strong link between ECM remodeling and immune cell infiltration in a variety of tumor types. However, the landscape and specific regulatory mechanisms between ECM and immune microenvironment in breast cancer have not been fully understood.MethodsUsing genomic data and clinical information of breast cancer patients obtained from The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO) databases, we conducted an extensive multi-omics analysis to explore the heterogeneity and prognostic significance of the ECM microenvironment. Masson and Sirius red staining were applied to quantify the contents of collagen in the ECM microenvironment. Tissue immunofluorescence (IF) staining was applied to identify T helper (Th) cells.ResultsWe classified breast cancer patients into two ECM-clusters and three gene-clusters by consensus clustering. Significant heterogeneity in prognosis and immune cell infiltration have been found in these distinct clusters. Specifically, in the ECM-cluster with better prognosis, the expression levels of Th2 and regulatory T (Treg) cells were reduced, while the Th1, Th17 and T follicular helper (Tfh) cells-associated activities were significantly enhanced. The correlations between ECM characteristics and Th cells infiltration were then validated by clinical tissue samples from our hospital. The ECM-associated prognostic model was then constructed by 10 core prognostic genes and stratified breast cancer patients into two risk groups. Kaplan-Meier analysis showed that the overall survival (OS) of breast cancer patients in the high-risk group was significantly worse than that of the low-risk group. The risk scores for breast cancer patients obtained from our prognostic model were further confirmed to be associated with immune cell infiltration, tumor mutation burden (TMB) and stem cell indexes. Finally, the half-maximal inhibitory concentration (IC50) values of antitumor agents for patients in different risk groups were calculated to provide references for therapy targeting distinct ECM characteristics.ConclusionOur findings identify a novel strategy for breast cancer subtyping based on the ECM characterization and reveal the regulatory roles of Th cells in ECM remodeling. Targeting ECM remodeling and Th cells hold potential to be a therapeutic alternative for breast cancer in the future.

A Framework to Predict the Molecular Classification and Prognosis of Breast Cancer Patients and Characterize the Landscape of Immune Cell Infiltration.

It is known that all current cancer therapies can only benefit a limited proportion of patients; thus, molecular classification and prognosis evaluation are critical for correctly classifying breast cancer patients and selecting the best treatment strategy. These processes usually involve the disclosure of molecular information like mutation, expression, and immune microenvironment of a breast cancer patient, which are not been fully studied until now. Therefore, there is an urgent clinical need to identify potential markers to enhance molecular classification, precision prognosis, and therapy stratification for breast cancer patients. In this study, we explored the gene expression profiles of 1,721 breast cancer patients through CIBERSORT and ESTIMATE algorithms; then, we obtained a comprehensive intratumoral immune landscape. The immune cell infiltration (ICI) patterns of breast cancer were classified into 3 separate subtypes according to the infiltration levels of 22 immune cells. The differentially expressed genes between these subtypes were further identified, and ICI scores were calculated to assess the immune landscape of BRCA patients. Importantly, we demonstrated that ICI scores correlate with patients' survival, tumor mutation burden, neoantigens, and sensitivity to specific drugs. Based on these ICI scores, we were able to predict the prognosis of patients and their response to immunotherapy. Together, these findings provide a realistic scenario to stratify breast cancer patients for precision medicine.

Predicting breast cancer in women using liquid biopsy-derived glycoproteomic markers.

e12545 Background: Breast cancer is the most common cancer among women worldwide.Traditional methods of cancer detection such as tissue biopsy are invasive, costly, time consuming and not amenable for repetition. As a result, minimally invasive liquid biopsies, especially blood-based biomarkers show potential value for breast cancer risk prediction and early detection. In this study, we investigated the use of serum glycoproteins circulating in blood to identify a panel of potential prognostic markers that may aid in predicting breast cancer in women. Methods: We applied a novel platform for characterizing blood glycoproteomic biomarkers, combining liquid-chromatography/mass spectrometry (LC-MS) with artificial intelligence/neural networks (AI-NN) to analyze serum samples from 279 breast cancer patients (median age 56 years, with stage 0-4 N’s: 1 / 83 / 114 / 56 / 25) and 102 healthy control samples (median age 52 years). A panel of 596 serum glycosylated and non-glycosylated peptides, representing 71 serum proteins, were analyzed. Age-adjusted differential expression analysis for 596 normalized biomarkers were performed to evaluate statistically significant differential abundances using an FDR q-value of 0.05 as a cutoff. Using the top differentially expressed markers as input, a LASSO penalized logistic regression model with 5-fold repeated cross validation was applied to identify the top biomarkers contributing to the separation between healthy controls and breast cancer patients. Results: We identified 243 out of 596 markers that were differentially expressed (FDR &lt;&lt;0.05) between breast cancer samples and healthy controls. Out of those, 11 markers were obtained as the top predictors in classifying breast cancer patients and healthy controls. The classification algorithm yielded an accuracy of 94% (95.9% sensitivity, 88.7% specificity) and an AUC of 0.983 on the training set. This classifier was validated on an independent test set with 30% of the subjects, yielding an accuracy of 93% (96.4% sensitivity, 83.9% specificity) and an AUC of 0.974. Test sensitivity was high across stages, at 96% / 90% / 95% / 90% in stages 1-4, respectively. Conclusions: Based on the results, we conclude that circulating glycoproteins in serum may be useful in screening applications in breast cancer, and strongly demonstrates the utility of glycoprotein profiles as a powerful non-invasive diagnostic tool.

Breast Cancer Classification Based on Tumor Budding and Stem Cell-Related Signatures Facilitate Prognosis Evaluation.

BackgroundTumor budding (TB) is emerging as a prognostic factor in multiple cancers. Likewise, the stemness of cancer cells also plays a vital role in cancer progression. However, nearly no research has focused on the interaction of TB and tumor stemness in cancer.MethodsTissue microarrays including 229 cases of invasive breast cancer (BC) were established and subjected to pan-cytokeratin immunohistochemical staining to evaluate molecular expression. Univariate and multivariate analyses were applied to identify prognostic factors of BC, and the Chi-square test was used for comparison of categorical variables.ResultsHigh-grade TB was significantly associated with T stage, lymph node metastasis, tumor node metastasis (TNM) stage, epithelial-mesenchymal transition, and poor disease-free survival (DFS) of BC patients. We also found that the prognostic value of TB varied widely among different subtypes and subgroups. Cox regression analysis then showed that TB grade was an independent prognostic factor. Moreover, cancer stem cell (CSC) markers CD44 and ALDH1A1 were significantly higher in high-grade TB tumors. Consequently, patients were classified into high CSC score subgroup and low CSC score subgroups. Further research found that CSC scores correlated with clinicopathological features and DFS of BC patients. Based on TB grade and CSC scores, we classified BC patients into TBlow-CSCslow (type I), TBlow-CSCshigh (type II), TBhigh-CSCslow (type III), and TBhigh-CSCshigh (type IV) subgroups. Survival analysis showed that patients in the type I subgroup had the best DFS, whereas those in the type IV subgroup had the worst DFS. Finally, a TB-CSC-based nomogram for use in BC was established. The nomogram was well calibrated to predict the probability of 5-year DFS, and the C-index was 0.837. Finally, the area under the curve value for the nomogram (0.892) was higher than that of the TNM staging system (0.713).ConclusionThe combination of TB grade with CSC score improves the prognostic evaluation of BC patients. A novel nomogram containing TB grade and CSC score provides doctors with a candidate tool to guide the individualized treatment of cancer patients.

Classification of Breast Cancer Patients Using Neural Network Technique

This work develops an Artificial Neural Network (ANN) model for performing Breast Cancer (BC) classification tasks. The design of the model considers studying different ANN architectures from the literature and chooses the one with the best performance. This ANN model aims to classify BC cases more systematically and more quickly. It provides facilities in the field of medicine to detect breast cancer among women. The ANN classification model is able to achieve an average accuracy of 98.88 % with an average run time of 0.182 seconds. Using this model, the classification of BC can be carried out much more faster than manual diagnosis and with good enough accuracy.

Classification of Breast Cancer Patients Using Neural Network Technique

This work develops an Artificial Neural Network (ANN) model for performing Breast Cancer (BC) classification tasks. The design of the model considers studying different ANN architectures from the literature and chooses the one with the best performance. This ANN model aims to classify BCcasesmore systematically and more quickly. It provides facilities in the field of medicine to detect breast cancer among women. TheANN classification model is able to achieve an average accuracy of 98.88 %with an average run time of0.182seconds.Using this model, the classification of BC can be carried out much more faster than manual diagnosisand with good enough accuracy

A novel immune prognostic index for stratification of high-risk patients with early breast cancer

The prognostic value of current multigene assays for breast cancer is limited to hormone receptor-positive, human epidermal growth factor receptor 2-negative early breast cancer. Despite the prognostic significance of immune response-related genes in breast cancer, immune gene signatures have not been incorporated into most multigene assays. Here, using public gene expression microarray datasets, we classified breast cancer patients into three risk groups according to clinical risk and proliferation risk. We then developed the immune prognostic index based on expression of five immune response-related genes (TRAT1, IL2RB, CTLA4, IGHM and IL21R) and lymph node status to predict the risk of recurrence in the clinical and proliferation high-risk (CPH) group. The 10-year probability of disease-free survival (DFS) or distant metastasis-free survival (DMFS) of patients classified as high risk according to the immune prognostic index was significantly lower than those of patients classified as intermediate or low risk. Multivariate analysis revealed that the index is an independent prognostic factor for DFS or DMFS. Moreover, the C-index revealed that it is superior to clinicopathological variables for predicting prognosis. Its prognostic significance was also validated in independent datasets. The immune prognostic index identified low-risk patients among patients classified as CPH, regardless of the molecular subtype of breast cancer, and may overcome the limitations of current multigene assays.

Shotgun proteomics coupled to nanoparticle-based biomarker enrichment reveals a novel panel of extracellular matrix proteins as candidate serum protein biomarkers for early-stage breast cancer detection

BackgroundThe lack of specificity and high degree of false positive and false negative rates when using mammographic screening for detecting early-stage breast cancer is a critical issue. Blood-based molecular assays that could be used in adjunct with mammography for increased specificity and sensitivity could have profound clinical impact. Our objective was to discover and independently verify a panel of candidate blood-based biomarkers that could identify the earliest stages of breast cancer and complement current mammographic screening approaches.MethodsWe used affinity hydrogel nanoparticles coupled with LC-MS/MS analysis to enrich and analyze low-abundance proteins in serum samples from 20 patients with invasive ductal carcinoma (IDC) breast cancer and 20 female control individuals with positive mammograms and benign pathology at biopsy. We compared these results to those obtained from five cohorts of individuals diagnosed with cancer in organs other than breast (ovarian, lung, prostate, and colon cancer, as well as melanoma) to establish IDC-specific protein signatures. Twenty-four IDC candidate biomarkers were then verified by multiple reaction monitoring (LC-MRM) in an independent validation cohort of 60 serum samples specifically including earliest-stage breast cancer and benign controls (19 early-stage (T1a) IDC and 41 controls).ResultsIn our discovery set, 56 proteins were increased in the serum samples from IDC patients, and 32 of these proteins were specific to IDC. Verification of a subset of these proteins in an independent cohort of early-stage T1a breast cancer yielded a panel of 4 proteins, ITGA2B (integrin subunit alpha IIb), FLNA (Filamin A), RAP1A (Ras-associated protein-1A), and TLN-1 (Talin-1), which classified breast cancer patients with 100% sensitivity and 85% specificity (AUC of 0.93).ConclusionsUsing a nanoparticle-based protein enrichment technology, we identified and verified a highly specific and sensitive protein signature indicative of early-stage breast cancer with no false positives when assessing benign and inflammatory controls. These markers have been previously reported in cell-ECM interaction and tumor microenvironment biology. Further studies with larger cohorts are needed to evaluate whether this biomarker panel improves the positive predictive value of mammography for breast cancer detection.