Tree-based machine learning algorithms identified minimal set of miRNA biomarkers for breast cancer diagnosis and molecular subtyping

Screening Nonlinear miRNA Features of Breast Cancer by Using Ensemble Regularized Polynomial Logistic Regression

Differentiating breast cancer subtypes based on miRNA data helps doctors provide more personalized treatment plans for patients. This paper explored the interaction between miRNA pairs and developed a novel ensemble regularized polynomial logistic regression method for screening nonlinear features of breast cancer. Three different types of second-order polynomial logistic regression with elastic network penalty (SOPLR-EN) in which each type contains 10 identical models were integrated to determine the most suitable sample set for feature screening by using bootstrap sampling strategy. A single feature and 39 nonlinear features were obtained by screening features that appeared at least 15 times in 30 integrations and were involved in the classification of at least 4 subtypes. The second-order polynomial logistic regression with ridge penalty (SOPLR-R) built on screened feature set achieved 82.30% classification accuracy for distinguishing breast cancer subtypes, surpassing the performance of other six methods. Further, 11 nonlinear miRNA biomarkers were identified, and their significant relevance to breast cancer was illustrated through six types of biological analysis.

Explainable Artificial Intelligence in Quantifying Breast Cancer Factors: Saudi Arabia Context

Breast cancer represents a significant health concern, particularly in Saudi Arabia, where it ranks as the most prevalent cancer type among women. This study focuses on leveraging eXplainable Artificial Intelligence (XAI) techniques to predict benign and malignant breast cancer cases using various clinical and pathological features specific to Saudi Arabian patients. Six distinct models were trained and evaluated based on common performance metrics such as accuracy, precision, recall, F1 score, and AUC-ROC score. To enhance interpretability, Local Interpretable Model-Agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP) were applied. The analysis identified the Random Forest model as the top performer, achieving an accuracy of 0.72, along with robust precision, recall, F1 score, and AUC-ROC score values. Conversely, the Support Vector Machine model exhibited the poorest performance metrics, indicating its limited predictive capability. Notably, the XAI approaches unveiled variations in the feature importance rankings across models, underscoring the need for further investigation. These findings offer valuable insights into breast cancer diagnosis and machine learning interpretation, aiding healthcare providers in understanding and potentially integrating such technologies into clinical practices.

A Comprehensive Review on Synergy of Multi-Modal Data and AI Technologies in Medical Diagnosis

Disease diagnosis represents a critical and arduous endeavor within the medical field. Artificial intelligence (AI) techniques, spanning from machine learning and deep learning to large model paradigms, stand poised to significantly augment physicians in rendering more evidence-based decisions, thus presenting a pioneering solution for clinical practice. Traditionally, the amalgamation of diverse medical data modalities (e.g., image, text, speech, genetic data, physiological signals) is imperative to facilitate a comprehensive disease analysis, a topic of burgeoning interest among both researchers and clinicians in recent times. Hence, there exists a pressing need to synthesize the latest strides in multi-modal data and AI technologies in the realm of medical diagnosis. In this paper, we narrow our focus to five specific disorders (Alzheimer's disease, breast cancer, depression, heart disease, epilepsy), elucidating advanced endeavors in their diagnosis and treatment through the lens of artificial intelligence. Our survey not only delineates detailed diagnostic methodologies across varying modalities but also underscores commonly utilized public datasets, the intricacies of feature engineering, prevalent classification models, and envisaged challenges for future endeavors. In essence, our research endeavors to contribute to the advancement of diagnostic methodologies, furnishing invaluable insights for clinical decision making.

The Role of MicroRNAs in Breast Cancer and the Challenges of Their Clinical Application

MicroRNAs (miRNAs) constitute a subclass of non-coding RNAs that exert substantial influence on gene-expression regulation. Their tightly controlled expression plays a pivotal role in various cellular processes, while their dysregulation has been implicated in numerous pathological conditions, including cancer. Among cancers affecting women, breast cancer (BC) is the most prevalent malignant tumor. Extensive investigations have demonstrated distinct expression patterns of miRNAs in normal and malignant breast cells. Consequently, these findings have prompted research efforts towards leveraging miRNAs as diagnostic tools and the development of therapeutic strategies. The aim of this review is to describe the role of miRNAs in BC. We discuss the identification of oncogenic, tumor suppressor and metastatic miRNAs among BC cells, and their impact on tumor progression. We describe the potential of miRNAs as diagnostic and prognostic biomarkers for BC, as well as their role as promising therapeutic targets. Finally, we evaluate the current use of artificial intelligence tools for miRNA analysis and the challenges faced by these new biomedical approaches in its clinical application. The insights presented in this review underscore the promising prospects of utilizing miRNAs as innovative diagnostic, prognostic, and therapeutic tools for the management of BC.

Addressing the Clinical Feasibility of Adopting Circulating miRNA for Breast Cancer Detection, Monitoring and Management with Artificial Intelligence and Machine Learning Platforms

Detecting breast cancer (BC) at the initial stages of progression has always been regarded as a lifesaving intervention. With modern technology, extensive studies have unraveled the complexity of BC, but the current standard practice of early breast cancer screening and clinical management of cancer progression is still heavily dependent on tissue biopsies, which are invasive and limited in capturing definitive cancer signatures for more comprehensive applications to improve outcomes in BC care and treatments. In recent years, reviews and studies have shown that liquid biopsies in the form of blood, containing free circulating and exosomal microRNAs (miRNAs), have become increasingly evident as a potential minimally invasive alternative to tissue biopsy or as a complement to biomarkers in assessing and classifying BC. As such, in this review, the potential of miRNAs as the key BC signatures in liquid biopsy are addressed, including the role of artificial intelligence (AI) and machine learning platforms (ML), in capitalizing on the big data of miRNA for a more comprehensive assessment of the cancer, leading to practical clinical utility in BC management.

Identification of miRNA biomarkers for breast cancer by combining ensemble regularized multinomial logistic regression and Cox regression

BACKGROUND

Breast cancer is one of the most common cancers in women. It is necessary to classify breast cancer subtypes because different subtypes need specific treatment. Identifying biomarkers and classifying breast cancer subtypes is essential for developing appropriate treatment methods for patients. MiRNAs can be easily detected in tumor biopsy and play an inhibitory or promoting role in breast cancer, which are considered promising biomarkers for distinguishing subtypes.

RESULTS

A new method combing ensemble regularized multinomial logistic regression and Cox regression was proposed for identifying miRNA biomarkers in breast cancer. After adopting stratified sampling and bootstrap sampling, the most suitable sample subset for miRNA feature screening was determined via ensemble 100 regularized multinomial logistic regression models. 124 miRNAs that participated in the classification of at least 3 subtypes and appeared at least 50 times in 100 integrations were screened as features. 22 miRNAs from the proposed feature set were further identified as the biomarkers for breast cancer by using Cox regression based on survival analysis. The accuracy of 5 methods on the proposed feature set was significantly higher than on the other two feature sets. The results of 7 biological analyses illustrated the rationality of the identified biomarkers.

CONCLUSIONS

The screened features can better distinguish breast cancer subtypes. Notably, the genes and proteins related to the proposed 22 miRNAs were considered oncogenes or inhibitors of breast cancer. 9 of the 22 miRNAs have been proved to be markers of breast cancer. Therefore, our results can be considered in future related research.

Bone Marrow Mesenchymal Cells (BMSCs) on Breast Cancer Cell Proliferation and Metastasis by Regulating Phosphatase and Tensin Homolog 12

Among the newly diagnosed cancers in women, breast cancer metastasis is a key factor contributing to the poor prognosis. BMSCs are critical components for the malignant microenvironment. Studies have shown that the interaction between tumor cells and BMSCs support breast cancer progression. However, BMSCs’ effect on breast cancer cells is not yet clear. BMSCs and breast cancer cell MCF-7 were co-cultured to analyze tumor cell proliferation and apoptosis along with analysis of E-cadherin and Vimentin expression by real-time PCR, interleukin-6 and matrix protease-2 and PTEN12 expression. Co-culture of BMSCs promoted breast cancer cell proliferation, decreased apoptosis-related Caspase 3 activity and downregulated the expression of EMT related factors, upregulated IL-6 secretion and MMP-2, and downregulated PTEN12 expression (P < 0.05). In conclusion, BMSCs can promote breast cancer cell proliferation and survival and affect breast cancer transformation possibly through inhibiting the expression of PTEN12.

Applied machine learning in cancer research: A systematic review for patient diagnosis, classification and prognosis

Artificial Intelligence (AI) has recently altered the landscape of cancer research and medical oncology using traditional Machine Learning (ML) algorithms and cutting-edge Deep Learning (DL) architectures. In this review article we focus on the ML aspect of AI applications in cancer research and present the most indicative studies with respect to the ML algorithms and data used. The PubMed and dblp databases were considered to obtain the most relevant research works of the last five years. Based on a comparison of the proposed studies and their research clinical outcomes concerning the medical ML application in cancer research, three main clinical scenarios were identified. We give an overview of the well-known DL and Reinforcement Learning (RL) methodologies, as well as their application in clinical practice, and we briefly discuss Systems Biology in cancer research. We also provide a thorough examination of the clinical scenarios with respect to disease diagnosis, patient classification and cancer prognosis and survival. The most relevant studies identified in the preceding year are presented along with their primary findings. Furthermore, we examine the effective implementation and the main points that need to be addressed in the direction of robustness, explainability and transparency of predictive models. Finally, we summarize the most recent advances in the field of AI/ML applications in cancer research and medical oncology, as well as some of the challenges and open issues that need to be addressed before data-driven models can be implemented in healthcare systems to assist physicians in their daily practice.

miRNome and Functional Network Analysis of PGRMC1 Regulated miRNA Target Genes Identify Pathways and Biological Functions Associated With Triple Negative Breast Cancer

Background

Increased expression of the progesterone receptor membrane component 1, a heme and progesterone binding protein, is frequently found in triple negative breast cancer tissue. The basis for the expression of PGRMC1 and its regulation on cellular signaling mechanisms remain largely unknown. Therefore, we aim to study microRNAs that target selective genes and mechanisms that are regulated by PGRMC1 in TNBCs.

Methods

To identify altered miRNAs, whole human miRNome profiling was performed following AG-205 treatment and PGRMC1 silencing. Network analysis identified miRNA target genes while KEGG, REACTOME and Gene ontology were used to explore altered signaling pathways, biological processes, and molecular functions.

Results

KEGG term pathway analysis revealed that upregulated miRNAs target specific genes that are involved in signaling pathways that play a major role in carcinogenesis. While multiple downregulated miRNAs are known oncogenes and have been previously demonstrated to be overexpressed in a variety of cancers. Overlapping miRNA target genes associated with KEGG term pathways were identified and overexpression/amplification of these genes was observed in invasive breast carcinoma tissue from TCGA. Further, the top two genes (CCND1 and YWHAZ) which are highly genetically altered are also associated with poorer overall survival.

Conclusions

Thus, our data demonstrates that therapeutic targeting of PGRMC1 in aggressive breast cancers leads to the activation of miRNAs that target overexpressed genes and deactivation of miRNAs that have oncogenic potential.

Machine learning analysis of TCGA cancer data

In recent years, machine learning (ML) researchers have changed their focus towards biological problems that are difficult to analyse with standard approaches. Large initiatives such as The Cancer Genome Atlas (TCGA) have allowed the use of omic data for the training of these algorithms. In order to study the state of the art, this review is provided to cover the main works that have used ML with TCGA data. Firstly, the principal discoveries made by the TCGA consortium are presented. Once these bases have been established, we begin with the main objective of this study, the identification and discussion of those works that have used the TCGA data for the training of different ML approaches. After a review of more than 100 different papers, it has been possible to make a classification according to following three pillars: the type of tumour, the type of algorithm and the predicted biological problem. One of the conclusions drawn in this work shows a high density of studies based on two major algorithms: Random Forest and Support Vector Machines. We also observe the rise in the use of deep artificial neural networks. It is worth emphasizing, the increase of integrative models of multi-omic data analysis. The different biological conditions are a consequence of molecular homeostasis, driven by both protein coding regions, regulatory elements and the surrounding environment. It is notable that a large number of works make use of genetic expression data, which has been found to be the preferred method by researchers when training the different models. The biological problems addressed have been classified into five types: prognosis prediction, tumour subtypes, microsatellite instability (MSI), immunological aspects and certain pathways of interest. A clear trend was detected in the prediction of these conditions according to the type of tumour. That is the reason for which a greater number of works have focused on the BRCA cohort, while specific works for survival, for example, were centred on the GBM cohort, due to its large number of events. Throughout this review, it will be possible to go in depth into the works and the methodologies used to study TCGA cancer data. Finally, it is intended that this work will serve as a basis for future research in this field of study.

A mouse tissue atlas of small noncoding RNA

We report a systematic unbiased analysis of small RNA molecule expression in 11 different tissues of the model organism mouse. We discovered uncharacterized noncoding RNA molecules and identified that ∼30% of total noncoding small RNA transcriptome are distributed across the body in a tissue-specific manner with some also being sexually dimorphic. Distinct distribution patterns of small RNA across the body suggest the existence of tissue-specific mechanisms involved in noncoding RNA processing.

Small noncoding RNAs (ncRNAs) play a vital role in a broad range of biological processes both in health and disease. A comprehensive quantitative reference of small ncRNA expression would significantly advance our understanding of ncRNA roles in shaping tissue functions. Here, we systematically profiled the levels of five ncRNA classes (microRNA [miRNA], small nucleolar RNA [snoRNA], small nuclear RNA [snRNA], small Cajal body-specific RNA [scaRNA], and transfer RNA [tRNA] fragments) across 11 mouse tissues by deep sequencing. Using 14 biological replicates spanning both sexes, we identified that ∼30% of small ncRNAs are distributed across the body in a tissue-specific manner with some also being sexually dimorphic. We found that some miRNAs are subject to “arm switching” between healthy tissues and that tRNA fragments are retained within tissues in both a gene- and a tissue-specific manner. Out of 11 profiled tissues, we confirmed that brain contains the largest number of unique small ncRNA transcripts, some of which were previously annotated while others are identified in this study. Furthermore, by combining these findings with single-cell chromatin accessibility (scATAC-seq) data, we were able to connect identified brain-specific ncRNAs with their cell types of origin. These results yield the most comprehensive characterization of specific and ubiquitous small RNAs in individual murine tissues to date, and we expect that these data will be a resource for the further identification of ncRNAs involved in tissue function in health and dysfunction in disease.

Expression of Stanniocalcin 2 in Breast Cancer and Its Clinical Significance

This study aims to explore the expression of stanniocalcin 2 (STC2) gene in breast cancer and its clinical significance. Female patients with breast cancer from Zhongnan Hospital of Wuhan University admitted during March 2014 to October 2014 were enrolled in this study. All the tissues used in this experiment included 50 cases of breast cancer tissues and corresponding 50 cases of paracancer normal breast tissues with complete patients' information. The real-time quantitative polymerase chain reaction (qPCR) was applied to detect the expression of STC2 gene in 50 cases of breast cancer and paracancer normal breast tissues. The results showed that the expression level of STC2 gene in 50 cases of breast cancer tissues was significantly higher than that in paracancer normal breast tissues (P&lt;0.001). The expression of STC2 gene was correlated with lymph node metastasis, distant metastasis, TNM stage and histological grade (P&lt;0.001). The expression level of STC2 gene was significantly higher in breast cancer tissues with higher expression of Ki-67 (P&lt;0.001). The expression level of STC2 gene was significantly higher in estrogen receptor (ER) positive breast cancer tissues than in ER negative ones (P&lt;0.001). However, different groups of age, pathological type, tumor size, PR expression and human epidermal growth factor receptor-2 (HER2) expression did not show significant differences in STC2 expression (P&gt;0.05). In conclusion, the abnormal overexpression of STC2 gene may play a role in the development and progression of breast cancer, and it can be used as an independent metastasis and prognostic factor of breast cancer. In addition, STC2 gene probably promotes the development and metastasis of breast cancer by interacting with estrogen and ER, and it may become a new direction for breast cancer endocrine therapy.

miR-139 Controls Viability Of Ovarian Cancer Cells Through Apoptosis Induction And Exosome Shedding Inhibition By Targeting ATP7A

Background

Emerging proof suggests that microRNA (miRNA) malfunction is correlated to the generation and development of multiple malignancies. It has been proven that miRNA (miR)-139 represses a variety of malignancies. However, the understanding of its impact on ovarian cancer (OC) is insufficient. We aimed to investigate the expression and function of miR-139 in OC.

Methods

The expression of mir-139 was detected and recorded, and the relationship of mir-139 remaining OC cells was explored. At the same time, we studied the correlation between ATP7A and mir-139 by the luciferase reporter test, Western blot, and quantitative real-time reverse transcription PCR.

Results

The expression of miR-139 was remarkably downregulated in OC specimens. Furthermore, excessive miR-139 expression noticeably inhibited the migration, colony generation, proliferation, and invasion of OC cells. In addition, excessive miR-139 expression remarkably repressed the death and the expression of proteins related to cell death in OC cells, as well as inhibited the shedding of exosomes. According to the luciferase reporter test, Western blot, and quantitative real-time reverse transcription PCR, miR-139 directly targeted ATP7A. Furthermore, the expression of ATP7A was found to be negatively related to miR-139 levels in OC specimens. It was revealed via a rescue experiment that excessive ATP7A expression counteracted the repressive effect of miR-139 in OC cells.

Conclusion

It was revealed via an in vivo study that miR-139 remarkably inhibited the growth of malignancies by downregulating ATP7A in nude mice. miR-139 represses the development of malignancies in OC by directly targeting ATP7A, offering an innovative approach for molecular therapy of OC.

Susan G. Komen Big Data for Breast Cancer Initiative: How Patient Advocacy Organizations Can Facilitate Using Big Data to Improve Patient Outcomes

Integrating different types of data, including electronic health records, imaging data, administrative and claims databases, large data repositories, the Internet of Things, genomics, and other omics data, is both a challenge and an opportunity that must be tackled head on. We explore some of the challenges and opportunities in optimizing data integration to accelerate breast cancer discovery and improve patient outcomes. Susan G. Komen convened three meetings (2015, 2017, and 2018) with various stakeholders to discuss challenges, opportunities, and next steps to enhance the use of big data in the field of breast cancer. Meeting participants agreed that big data approaches can enhance the identification of better therapies, improve outcomes, reduce disparities, and optimize precision medicine. One challenge is that databases must be shared, linked with each other, standardized, and interoperable. Patients want to be active participants in research and their own care, and to control how their data are used. Many patients have privacy concerns and do not understand how sharing their data can help to effectively drive discovery. Public education is essential, and breast cancer researchers who are skilled in using and analyzing big data are needed. Patient advocacy groups can play multiple roles to help maximize and leverage big data to better serve patients. Komen is committed to educating patients on big data issues, encouraging data sharing by all stakeholders, assisting in training the next generation of data science breast cancer researchers, and funding research projects that will use real-life data in real time to revolutionize the way breast cancer is understood and treated.

MLW-gcForest: A Multi-Weighted gcForest Model for Cancer Subtype Classification by Methylation Data

Effective cancer treatment requires a clear subtype. Due to the small sample size, high dimensionality, and class imbalances of cancer gene data, classifying cancer subtypes by traditional machine learning methods remains challenging. The gcForest algorithm is a combination of machine learning methods and a deep neural network and has been indicated to achieve better classification of small samples of data. However, the gcForest algorithm still faces many challenges when this method is applied to the classification of cancer subtypes. In this paper, we propose an improved gcForest algorithm (MLW-gcForest) to study the applicability of this method to the small sample sizes, high dimensionality, and class imbalances of genetic data. The main contributions of this algorithm are as follows: (1) Different weights are assigned to different random forests according to the classification ability of the forests. (2) We propose a sorting optimization algorithm that assigns different weights to the feature vectors generated under different sliding windows. The MLW-gcForest model is trained on the methylation data of five data sets from the cancer genome atlas (TCGA). The experimental results show that the MLW-gcForest algorithm achieves high accuracy and area under curve (AUC) values for the classification of cancer subtypes compared with those of traditional machine learning methods and state of the art methods. The results also show that methylation data can be effectively used to diagnose cancer.

Emerging ultrafast nucleic acid amplification technologies for next-generation molecular diagnostics

Over the last decade, nucleic acid amplification tests (NAATs) including polymerase chain reaction (PCR) were an indispensable methodology for diagnosing cancers, viral and bacterial infections owing to their high sensitivity and specificity. Because the NAATs can recognize and discriminate even a few copies of nucleic acid (NA) and species-specific NA sequences, NAATs have become the gold standard in a wide range of applications. However, limitations of NAAT approaches have recently become more apparent by reason of their lengthy run time, large reaction volume, and complex protocol. To meet the current demands of clinicians and biomedical researchers, new NAATs have developed to achieve ultrafast sample-to-answer protocols for the point-of-care testing (POCT). In this review, ultrafast NA-POCT platforms are discussed, outlining their NA amplification principles as well as delineating recent advances in ultrafast NAAT applications. The main focus is to provide an overview of NA-POCT platforms in regard to sample preparation of NA, NA amplification, NA detection process, interpretation of the analysis, and evaluation of the platform design. Increasing importance will be given to innovative, ultrafast amplification methods and tools which incorporate artificial intelligence (AI)-associated data analysis processes and mobile-healthcare networks. The future prospects of NA POCT platforms are promising as they allow absolute quantitation of NA in individuals which is essential to precision medicine.

Decision tree-based classifiers for lung cancer diagnosis and subtyping using TCGA miRNA expression data

Lung cancer has the world's highest cancer- associated mortality rate, making biomarker discovery for this cancer a pressing issue. Machine learning approaches to identify molecular biomarkers are not as prevalent as screening of potential biomarkers by differential expression analysis. However, several differentially expressed miRNAs involved in cancer have been identified using this approach. The availability of The Cancer Genome Atlas (TCGA) allows the use of machine-learning methods for the molecular profiling of tumors. The present study employed empirical negative control microRNAs (miRs) in lung cancer to normalize lung adenocarcinoma (LUAD) and lung squamous cell carcinoma (LUSC) datasets from TCGA to model decision trees in order to classify lung cancer status and subtype. The two primary classification models consisted of four miRNAs for lung cancer diagnosis and subtyping. hsa-miR-183 and hsa-miR-135b were used to distinguish lung tumors from normal samples taken from tissues adjacent to the tumor site, and hsa-miR-944 and hsa-miR-205 to further classify the tumors into LUAD and LUSC major subtypes. Specific cancer status classification models were also presented for each subtype.

Identifying a miRNA signature for predicting the stage of breast cancer

Breast cancer is a heterogeneous disease and one of the most common cancers among women. Recently, microRNAs (miRNAs) have been used as biomarkers due to their effective role in cancer diagnosis. This study proposes a support vector machine (SVM)-based classifier SVM-BRC to categorize patients with breast cancer into early and advanced stages. SVM-BRC uses an optimal feature selection method, inheritable bi-objective combinatorial genetic algorithm, to identify a miRNA signature which is a small set of informative miRNAs while maximizing prediction accuracy. MiRNA expression profiles of a 386-patient cohort of breast cancer were retrieved from The Cancer Genome Atlas. SVM-BRC identified 34 of 503 miRNAs as a signature and achieved a 10-fold cross-validation mean accuracy, sensitivity, specificity, and Matthews correlation coefficient of 80.38%, 0.79, 0.81, and 0.60, respectively. Functional enrichment of the 10 highest ranked miRNAs was analysed in terms of Kyoto Encyclopedia of Genes and Genomes and Gene Ontology annotations. Kaplan-Meier survival analysis of the highest ranked miRNAs revealed that four miRNAs, hsa-miR-503, hsa-miR-1307, hsa-miR-212 and hsa-miR-592, were significantly associated with the prognosis of patients with breast cancer.