Differential Prognostic Value of Residual Nodal Burden in Breast Cancer Subtypes.

Purpose: Residual cancer burden (RCB) index after neoadjuvant chemotherapy (NAC) is highly prognostic in patients with breast cancer (BC) but does not account for subtype or the precise impact of residual nodal burden (RNB). We aimed to precisely de ne the effect of RNB on survival by subtypes. Methods: Adult women with non-metastatic BC diagnosed from 2006-2021 in the National Cancer Database (NCDB) who received NAC followed by surgery within 8 months were included. RNB was also evaluated as a predictor of mortality with multivariable logistic regression. Kaplan-Meier analyses were performed to compare overall survival. Results: 51,917 patients were included. After adjustment, ypN stage was the strongest predictor of mortality, with an odds ratio (OR) of 2.24 (95% CI 2.08-2.41) for ypN1 vs ypN0 and increased with increasing nodal burden - ypN2 vs ypN0 OR 5.03, 95% CI 4.60-5.51 and ypN3 vs ypN0 OR 8.85, 95% CI 7.88-9.93. Stratification of survival curves with higher RNB is most pronounced for triple-negative breast cancer (TNBC) with an absolute difference of 64% in 5-year overall survival between ypN0 and ypN3 patients, and lowest for the ER+/HER2- subtype with a 25% absolute difference in 5-year OS between ypN0 and ypN3 patients. On interaction analysis, ypN status was a stronger predictor of mortality for the TNBC subtype compared to other subtypes. Conclusion: RNB has a significantly different impact on survival by BC subtypes. Future study of optimal therapeutic strategies for patients with residual nodal disease after NAC should account for subtype specific differences in prognosis.

Differential prognostic value of residual nodal burden in breast cancer subtypes.

PURPOSE: Residual cancer burden (RCB) index after neoadjuvant chemotherapy (NAC) is highly prognostic in patients with breast cancer (BC) but does not account for subtype or the precise impact of residual nodal burden (RNB). We aimed to precisely define the effect of RNB on survival by subtypes. METHODS: Adult women with non-metastatic BC diagnosed from 2006 to 2021 in the National Cancer Database (NCDB) who received NAC followed by surgery within 8 months were included. RNB was also evaluated as a predictor of mortality with multivariable logistic regression. Kaplan-Meier analyses were performed to compare overall survival. RESULTS: 51,917 patients were included. After adjustment, ypN stage was the strongest predictor of mortality, with an odds ratio (OR) of 2.24 (95% CI 2.08-2.41) for ypN1 vs ypN0 and increased with increasing nodal burden-ypN2 vs ypN0 OR 5.03, 95% CI 4.60-5.51 and ypN3 vs ypN0 OR 8.85, 95% CI 7.88-9.93. Stratification of survival curves with higher RNB is most pronounced for triple-negative breast cancer (TNBC) with an absolute difference of 64% in 5-year overall survival between ypN0 and ypN3 patients, and lowest for the ER+/HER2- subtype with a 25% absolute difference in 5-year OS between ypN0 and ypN3 patients. On interaction analysis, ypN status was a stronger predictor of mortality for the TNBC subtype compared to other subtypes. CONCLUSION: RNB has a significantly different impact on survival by BC subtypes. Future study of optimal therapeutic strategies for patients with residual nodal disease after NAC should account for subtype-specific differences in prognosis.

A triple hormone receptor ER, AR, and VDR signature is a robust prognosis predictor in breast cancer.

BACKGROUND: Despite evidence indicating the dominance of cell-of-origin signatures in molecular tumor patterns, translating these genome-wide patterns into actionable insights has been challenging. This study introduces breast cancer cell-of-origin signatures that offer significant prognostic value across all breast cancer subtypes and various clinical cohorts, compared to previously developed genomic signatures. METHODS: We previously reported that triple hormone receptor (THR) co-expression patterns of androgen (AR), estrogen (ER), and vitamin D (VDR) receptors are maintained at the protein level in human breast cancers. Here, we developed corresponding mRNA signatures (THR-50 and THR-70) based on these patterns to categorize breast tumors by their THR expression levels. The THR mRNA signatures were evaluated across 56 breast cancer datasets (5040 patients) using Kaplan-Meier survival analysis, Cox proportional hazard regression, and unsupervised clustering. RESULTS: The THR signatures effectively predict both overall and progression-free survival across all evaluated datasets, independent of subtype, grade, or treatment status, suggesting improvement over existing prognostic signatures. Furthermore, they delineate three distinct ER-positive breast cancer subtypes with significant survival in differences-expanding on the conventional two subtypes. Additionally, coupling THR-70 with an immune signature identifies a predominantly ER-negative breast cancer subgroup with a highly favorable prognosis, comparable to ER-positive cases, as well as an ER-negative subgroup with notably poor outcome, characterized by a 15-fold shorter survival. CONCLUSIONS: The THR cell-of-origin signature introduces a novel dimension to breast cancer biology, potentially serving as a robust foundation for integrating additional prognostic biomarkers. These signatures offer utility as a prognostic index for stratifying existing breast cancer subtypes and for de novo classification of breast cancer cases. Moreover, THR signatures may also hold promise in predicting hormone treatment responses targeting AR and/or VDR.

Cardiovascular health and cancer mortality: evidence from US NHANES and UK Biobank cohort studies.

BACKGROUND: The American Heart Association recently introduced a novel cardiovascular health (CVH) metric, Life's Essential 8 (LE8), for health promotion. However, the relationship between LE8 and cancer mortality risk remains uncertain. METHODS: We investigated 17,076 participants from US National Health and Nutrition Examination Survey (US NHANES) and 272,727 participants from UK Biobank, all free of cancer at baseline. The CVH score, based on LE8 metrics, incorporates four health behaviors (diet, physical activity, smoking, and sleep) and four health factors (body mass index, lipid, blood glucose, and blood pressure). Self-reported questionnaires assessed health behaviors. Primary outcomes were mortality rates for total cancer and its subtypes. The association between CVH score (continuous and categorical variable) and outcomes was examined using Cox model with adjustments. Cancer subtypes-related polygenic risk score (PRS) was constructed to evaluate its interactions with CVH on cancer death risk. RESULTS: Over 141,526 person-years in US NHANES, 424 cancer-related deaths occurred, and in UK Biobank, 8,872 cancer deaths were documented during 3,690,893 person-years. High CVH was associated with reduced overall cancer mortality compared to low CVH (HR 0.58, 95% CI 0.37-0.91 in US NHANES; 0.51, 0.46-0.57 in UK Biobank). Each one-standard deviation increase in CVH score was linked to a 19% decrease in cancer mortality (HR: 0.81; 95% CI: 0.73-0.91) in US NHANES and a 19% decrease (HR: 0.81; 95% CI: 0.79-0.83) in UK Biobank. Adhering to ideal CVH was linearly associated with decreased risks of death from lung, bladder, liver, kidney, esophageal, breast, colorectal, pancreatic, and gastric cancers in UK Biobank. Furthermore, integrating genetic data revealed individuals with low PRS and high CVH exhibited the lowest mortality from eight cancers (HRs ranged from 0.36 to 0.57) compared to those with high PRS and low CVH. No significant modification of the association between CVH and mortality risk for eight cancers by genetic predisposition was observed. Subgroup analyses showed a more pronounced protective association for overall cancer mortality among younger participants and those with lower socio-economic status. CONCLUSIONS: Maintaining optimal CVH is associated with a substantial reduction in the risk of overall cancer mortality. Adherence to ideal CVH correlates linearly with decreased mortality risk across multiple cancer subtypes. Individuals with both ideal CVH and high genetic predisposition demonstrated significant health benefits. These findings support adopting ideal CVH as an intervention strategy to mitigate cancer mortality risk and promote healthy aging.

Lung Cancer Subtyping: A Short Review.

As of 2022, lung cancer is the most commonly diagnosed cancer worldwide, with the highest mortality rate. There are three main histological types of lung cancer, and it is more important than ever to accurately identify the subtypes since the development of personalized, type-specific targeted therapies that have improved mortality rates. Traditionally, the gold standard for the confirmation of histological subtyping is tissue biopsy and histopathology. This, however, comes with its own challenges, which call for newer sampling techniques and adjunctive tools to assist in and improve upon the existing diagnostic workflow. This review aims to list and describe studies from the last decade (n = 47) that investigate three such potential omics techniques-namely (1) transcriptomics, (2) proteomics, and (3) metabolomics, as well as immunohistochemistry, a tool that has already been adopted as a diagnostic adjunct. The novelty of this review compared to similar comprehensive studies lies with its detailed description of each adjunctive technique exclusively in the context of lung cancer subtyping. Similarities between studies evaluating individual techniques and markers are drawn, and any discrepancies are addressed. The findings of this study indicate that there is promising evidence that supports the successful use of omics methods as adjuncts to the subtyping of lung cancer, thereby directing clinician practice in an economical and less invasive manner.

The Role of Surgery for Stage IV Breast Cancer.

Surgery for the management metastatic breast cancer has traditionally been considered a palliative procedure. However, some retrospective publications indicated that there may be a survival benefit to surgery in the presence of metastatic disease. Recent randomized trials will be reviewed for both management of the intact primary tumor in de novo breast cancer and systemic secondary metastases.

Radiologic-Pathologic Correlation: Is There an Association Between Contrast-Enhanced Mammography Imaging Features and Molecular Subtypes of Breast Cancer?

OBJECTIVE: This study aims to assess the correlation between imaging features of contrast-enhanced mammography (CEM) and molecular subtypes of breast cancer. METHODS: This is a retrospective single-institution study of patients who underwent CEM from December 2019 to August 2023. Each patient had at least one histologically proven invasive breast cancer with a core biopsy performed. Patients with a history of breast cancer treatment and lesions not entirely included in the CEM images were excluded. The images were interpreted using the American College of Radiology Breast Imaging Reporting and Data System (ACR BI-RADS) lexicon for CEM, published in 2022. Different imaging features, including the presence of calcifications, architectural distortion, non-mass enhancement, mass morphology, internal enhancement pattern, the extent of enhancement, and lesion conspicuity, were analyzed. The molecular subtypes were studied as dichotomous variables, including luminal A, luminal B, HER2, and basal-like. The association between the imaging features and molecular subtypes was analyzed with a Fisher's exact test. Statistical significance was assumed when the p-value was <0.05. RESULTS: A total of 31 patients with 36 malignant lesions were included in this study. Sixteen lesions (44.4%) were luminal A, four lesions (11.1%) were luminal B, 10 lesions (27.8%) were HER2, and six (16.7%) were basal-like subtypes. The presence of calcifications was associated with the HER2 subtype (p=0.024). Rim-enhancement on recombined images was associated with a basal-like subtype (p=0.001). Heterogeneous enhancement on recombined images was associated with non-basal-like breast cancer (p=0.027). No statistically significant correlation was found between other analyzed CEM imaging features and molecular subtypes. CONCLUSION: CEM imaging features, including the presence of calcifications and certain internal enhancement patterns, were correlated with distinguishing breast cancer molecular subtypes and thus may further expand the role of CEM.

An Automated Diagnosis Method for Lung Cancer Target Detection and Subtype Classification-Based CT Scans.

When dealing with small targets in lung cancer detection, the YOLO V8 algorithm may encounter false positives and misses. To address this issue, this study proposes an enhanced YOLO V8 detection model. The model integrates a large separable kernel attention mechanism into the C2f module to expand the information retrieval range, strengthens the extraction of lung cancer features in the Backbone section, and achieves effective interaction between multi-scale features in the Neck section, thereby enhancing feature representation and robustness. Additionally, depth-wise convolution and Coordinate Attention mechanisms are embedded in the Fast Spatial Pyramid Pooling module to reduce feature loss and improve detection accuracy. This study introduces a Minimum Point Distance-based IOU loss to enhance correlation between predicted and ground truth bounding boxes, improving adaptability and accuracy in small target detection. Experimental validation demonstrates that the improved network outperforms other mainstream detection networks in terms of average precision values and surpasses other classification networks in terms of accuracy. These findings validate the outstanding performance of the enhanced model in the localization and recognition aspects of lung cancer auxiliary diagnosis.

Deep Neural Network Integrated into Network-Based Stratification (D3NS): A Method to Uncover Cancer Subtypes from Somatic Mutations.

(1) Background: The identification of tumor subtypes is fundamental in precision medicine for accurate diagnoses and personalized therapies. Cancer development is often driven by the accumulation of somatic mutations that can cause alterations in tissue functions and morphologies. In this work, a method based on a deep neural network integrated into a network-based stratification framework (D3NS) is proposed to stratify tumors according to somatic mutations. (2) Methods: This approach leverages the power of deep neural networks to detect hidden information in the data by combining the knowledge contained in a network of gene interactions, as typical of network-based stratification methods. D3NS was applied using real-world data from The Cancer Genome Atlas for bladder, ovarian, and kidney cancers. (3) Results: This technique allows for the identification of tumor subtypes characterized by different survival rates and significant associations with several clinical outcomes (tumor stage, grade or response to therapy). (4) Conclusion: D3NS can provide a base model in cancer research and could be considered as a useful tool for tumor stratification, offering potential support in clinical settings.

p53 Genetics and Biology in Lung Carcinomas: Insights, Implications and Clinical Applications.

The TP53 gene is renowned as a tumor suppressor, playing a pivotal role in overseeing the cell cycle, apoptosis, and maintaining genomic stability. Dysregulation of p53 often contributes to the initiation and progression of various cancers, including lung cancer (LC) subtypes. The review explores the intricate relationship between p53 and its role in the development and progression of LC. p53, a crucial tumor suppressor protein, exists in various isoforms, and understanding their distinct functions in LC is essential for advancing our knowledge of this deadly disease. This review aims to provide a comprehensive literature overview of p53, its relevance to LC, and potential clinical applications.

Assessing Etiologic Heterogeneity for Multinomial Outcome with Two-Phase Outcome-Dependent Sampling Design.

Etiologic heterogeneity occurs when distinct sets of events or exposures give rise to different subtypes of disease. Inference about subtype-specific exposure effects from two-phase outcome-dependent sampling data requires adjustment for both confounding and the sampling design. Common approaches to inference for these effects do not necessarily appropriately adjust for these sources of bias, or allow for formal comparisons of effects across different subtypes. Herein, using inverse probability weighting (IPW) to fit a multinomial model is shown to yield valid inference with this sampling design for subtype-specific exposure effects and contrasts thereof. The IPW approach is compared to common regression-based methods for assessing exposure effect heterogeneity using simulations. The methods are applied to estimate subtype-specific effects of various exposures on breast cancer risk in the Carolina Breast Cancer Study.

Breast Cancer Stem Cells and Tumor Heterogeneity: Characteristics and Therapeutic Strategies.

Breast cancer is one of the most frequently detected malignancies worldwide. It is responsible for more than 15% of all death cases caused by cancer in women. Breast cancer is a heterogeneous disease representing various histological types, molecular characteristics, and clinical profiles. However, all breast cancers are organized in a hierarchy of heterogeneous cell populations, with a small proportion of cancer stem cells (breast cancer stem cells (BCSCs)) playing a putative role in cancer progression, and they are responsible for therapeutic failure. In different molecular subtypes of breast cancer, they present different characteristics, with specific marker profiles, prognoses, and treatments. Recent efforts have focused on tackling the Wnt, Notch, Hedgehog, PI3K/Akt/mTOR, and HER2 signaling pathways. Developing diagnostics and therapeutic strategies enables more efficient elimination of the tumor mass together with the stem cell population. Thus, the knowledge about appropriate therapeutic methods targeting both "normal" breast cancer cells and breast cancer stem cell subpopulations is crucial for success in cancer elimination.

NNBGWO-BRCA marker: Neural Network and binary grey wolf optimization based Breast cancer biomarker discovery framework using multi-omics dataset.

BACKGROUND AND OBJECTIVE: Breast cancer is a multifaceted condition characterized by diverse features and a substantial mortality rate, underscoring the imperative for timely detection and intervention. The utilization of multi-omics data has gained significant traction in recent years to identify biomarkers and classify subtypes in breast cancer. This kind of research idea from part to whole will also be an inevitable trend in future life science research. Deep learning can integrate and analyze multi-omics data to predict cancer subtypes, which can further drive targeted therapies. However, there are few articles leveraging the nature of deep learning for feature selection. Therefore, this paper proposes a Neural Network and Binary grey Wolf Optimization based BReast CAncer bioMarker (NNBGWO-BRCAMarker) discovery framework using multi-omics data to obtain a series of biomarkers for precise classification of breast cancer subtypes. METHODS: NNBGWO-BRCAMarker consists of two phases: in the first phase, relevant genes are selected using the weights obtained from a trained feedforward neural network; in the second phase, the binary grey wolf optimization algorithm is leveraged to further screen the selected genes, resulting in a set of potential breast cancer biomarkers. RESULTS: The SVM classifier with RBF kernel achieved a classification accuracy of 0.9242 ± 0.03 when trained using the 80 biomarkers identified by NNBGWO-BRCAMarker, as evidenced by the experimental results. We conducted a comprehensive gene set analysis, prognostic analysis, and druggability analysis, unveiling 25 druggable genes, 16 enriched pathways strongly linked to specific subtypes of breast cancer, and 8 genes linked to prognostic outcomes. CONCLUSIONS: The proposed framework successfully identified 80 biomarkers from the multi-omics data, enabling accurate classification of breast cancer subtypes. This discovery may offer novel insights for clinicians to pursue in further studies.

Advancing Peptide-Based Cancer Therapy with AI: In-Depth Analysis of State-of-the-Art AI Models.

Anticancer peptides (ACPs) play a vital role in selectively targeting and eliminating cancer cells. Evaluating and comparing predictions from various machine learning (ML) and deep learning (DL) techniques is challenging but crucial for anticancer drug research. We conducted a comprehensive analysis of 15 ML and 10 DL models, including the models released after 2022, and found that support vector machines (SVMs) with feature combination and selection significantly enhance overall performance. DL models, especially convolutional neural networks (CNNs) with light gradient boosting machine (LGBM) based feature selection approaches, demonstrate improved characterization. Assessment using a new test data set (ACP10) identifies ACPred, MLACP 2.0, AI4ACP, mACPred, and AntiCP2.0_AAC as successive optimal predictors, showcasing robust performance. Our review underscores current prediction tool limitations and advocates for an omnidirectional ACP prediction framework to propel ongoing research.

Reproductive characteristics, menopausal status, race and ethnicity, and risk of breast cancer subtypes defined by ER, PR and HER2 status: the Breast Cancer Etiology in Minorities study.

BACKGROUND: Associations between reproductive factors and risk of breast cancer differ by subtype defined by joint estrogen receptor (ER), progesterone receptor (PR), and HER2 expression status. Racial and ethnic differences in the incidence of breast cancer subtypes suggest etiologic heterogeneity, yet data are limited because most studies have included non-Hispanic White women only. METHODS: We analyzed harmonized data for 2,794 breast cancer cases and 4,579 controls, of whom 90% self-identified as African American, Asian American or Hispanic. Questionnaire data were pooled from three population-based studies conducted in California and data on tumor characteristics were obtained from the California Cancer Registry. The study sample included 1,530 luminal A (ER-positive and/or PR-positive, HER2-negative), 442 luminal B (ER-positive and/or PR-positive, HER2-positive), 578 triple-negative (TN; ER-negative, PR-negative, HER2-negative), and 244 HER2-enriched (ER-negative, PR-negative, HER2-positive) cases. We used multivariable unconditional logistic regression models to estimate subtype-specific ORs and 95% confidence intervals associated with parity, breast-feeding, and other reproductive characteristics by menopausal status and race and ethnicity. RESULTS: Subtype-specific associations with reproductive factors revealed some notable differences by menopausal status and race and ethnicity. Specifically, higher parity without breast-feeding was associated with higher risk of luminal A and TN subtypes among premenopausal African American women. In contrast, among Asian American and Hispanic women, regardless of menopausal status, higher parity with a breast-feeding history was associated with lower risk of luminal A subtype. Among premenopausal women only, luminal A subtype was associated with older age at first full-term pregnancy (FTP), longer interval between menarche and first FTP, and shorter interval since last FTP, with similar OR estimates across the three racial and ethnic groups. CONCLUSIONS: Subtype-specific associations with reproductive factors overall and by menopausal status, and race and ethnicity, showed some differences, underscoring that understanding etiologic heterogeneity in racially and ethnically diverse study samples is essential. Breast-feeding is likely the only reproductive factor that is potentially modifiable. Targeted efforts to promote and facilitate breast-feeding could help mitigate the adverse effects of higher parity among premenopausal African American women.

Elucidating Cancer Subtypes by Using the Relationship between DNA Methylation and Gene Expression.

Advancements in the field of next generation sequencing (NGS) have generated vast amounts of data for the same set of subjects. The challenge that arises is how to combine and reconcile results from different omics studies, such as epigenome and transcriptome, to improve the classification of disease subtypes. In this study, we introduce sCClust (sparse canonical correlation analysis with clustering), a technique to combine high-dimensional omics data using sparse canonical correlation analysis (sCCA), such that the correlation between datasets is maximized. This stage is followed by clustering the integrated data in a lower-dimensional space. We apply sCClust to gene expression and DNA methylation data for three cancer genomics datasets from the Cancer Genome Atlas (TCGA) to distinguish between underlying subtypes. We evaluate the identified subtypes using Kaplan-Meier plots and hazard ratio analysis on the three types of cancer-GBM (glioblastoma multiform), lung cancer and colon cancer. Comparison with subtypes identified by both single- and multi-omics studies implies improved clinical association. We also perform pathway over-representation analysis in order to identify up-regulated and down-regulated genes as tentative drug targets. The main goal of the paper is twofold: the integration of epigenomic and transcriptomic datasets followed by elucidating subtypes in the latent space. The significance of this study lies in the enhanced categorization of cancer data, which is crucial to precision medicine.

De-Escalated Therapy and Early Treatment of Recurrences in HPV-Associated Head and Neck Cancer: The Potential for Biomarkers to Revolutionize Personalized Therapy.

Human papillomavirus-associated (HPV+) head and neck squamous cell carcinoma (HNSCC) is the most common HPV-associated cancer in the United States, with a rapid increase in incidence over the last two decades. The burden of HPV+ HNSCC is likely to continue to rise, and given the long latency between infection and the development of HPV+ HNSCC, it is estimated that the effect of the HPV vaccine will not be reflected in HNSCC prevalence until 2060. Efforts have begun to decrease morbidity of standard therapies for this disease, and its improved characterization is being leveraged to identify and target molecular vulnerabilities. Companion biomarkers for new therapies will identify responsive tumors. A more basic understanding of two mechanisms of HPV carcinogenesis in the head and neck has identified subtypes of HPV+ HNSCC that correlate with different carcinogenic programs and that identify tumors with good or poor prognosis. Current development of biomarkers that reliably identify these two subtypes, as well as biomarkers that can detect recurrent disease at an earlier time, will have immediate clinical application.

Classifying breast cancer subtypes on multi-omics data via sparse canonical correlation analysis and deep learning.

BACKGROUND: Classifying breast cancer subtypes is crucial for clinical diagnosis and treatment. However, the early symptoms of breast cancer may not be apparent. Rapid advances in high-throughput sequencing technology have led to generating large number of multi-omics biological data. Leveraging and integrating the available multi-omics data can effectively enhance the accuracy of identifying breast cancer subtypes. However, few efforts focus on identifying the associations of different omics data to predict the breast cancer subtypes. RESULTS: In this paper, we propose a differential sparse canonical correlation analysis network (DSCCN) for classifying the breast cancer subtypes. DSCCN performs differential analysis on multi-omics expression data to identify differentially expressed (DE) genes and adopts sparse canonical correlation analysis (SCCA) to mine highly correlated features between multi-omics DE-genes. Meanwhile, DSCCN uses multi-task deep learning neural network separately to train the correlated DE-genes to predict breast cancer subtypes, which spontaneously tackle the data heterogeneity problem in integrating multi-omics data. CONCLUSIONS: The experimental results show that by mining the associations among multi-omics data, DSCCN is more capable of accurately classifying breast cancer subtypes than the existing methods.

Few-shot genes selection: subset of PAM50 genes for breast cancer subtypes classification.

BACKGROUND: In recent years, researchers have made significant strides in understanding the heterogeneity of breast cancer and its various subtypes. However, the wealth of genomic and proteomic data available today necessitates efficient frameworks, instruments, and computational tools for meaningful analysis. Despite its success as a prognostic tool, the PAM50 gene signature's reliance on many genes presents challenges in terms of cost and complexity. Consequently, there is a need for more efficient methods to classify breast cancer subtypes using a reduced gene set accurately. RESULTS: This study explores the potential of achieving precise breast cancer subtype categorization using a reduced gene set derived from the PAM50 gene signature. By employing a "Few-Shot Genes Selection" method, we randomly select smaller subsets from PAM50 and evaluate their performance using metrics and a linear model, specifically the Support Vector Machine (SVM) classifier. In addition, we aim to assess whether a more compact gene set can maintain performance while simplifying the classification process. Our findings demonstrate that certain reduced gene subsets can perform comparable or superior to the full PAM50 gene signature. CONCLUSIONS: The identified gene subsets, with 36 genes, have the potential to contribute to the development of more cost-effective and streamlined diagnostic tools in breast cancer research and clinical settings.

Classifying breast cancer using multi-view graph neural network based on multi-omics data.

Introduction: As the evaluation indices, cancer grading and subtyping have diverse clinical, pathological, and molecular characteristics with prognostic and therapeutic implications. Although researchers have begun to study cancer differentiation and subtype prediction, most of relevant methods are based on traditional machine learning and rely on single omics data. It is necessary to explore a deep learning algorithm that integrates multi-omics data to achieve classification prediction of cancer differentiation and subtypes. Methods: This paper proposes a multi-omics data fusion algorithm based on a multi-view graph neural network (MVGNN) for predicting cancer differentiation and subtype classification. The model framework consists of a graph convolutional network (GCN) module for learning features from different omics data and an attention module for integrating multi-omics data. Three different types of omics data are used. For each type of omics data, feature selection is performed using methods such as the chi-square test and minimum redundancy maximum relevance (mRMR). Weighted patient similarity networks are constructed based on the selected omics features, and GCN is trained using omics features and corresponding similarity networks. Finally, an attention module integrates different types of omics features and performs the final cancer classification prediction. Results: To validate the cancer classification predictive performance of the MVGNN model, we conducted experimental comparisons with traditional machine learning models and currently popular methods based on integrating multi-omics data using 5-fold cross-validation. Additionally, we performed comparative experiments on cancer differentiation and its subtypes based on single omics data, two omics data, and three omics data. Discussion: This paper proposed the MVGNN model and it performed well in cancer classification prediction based on multiple omics data.