Ensemble Learning for Higher Diagnostic Precision in Schizophrenia Using Peripheral Blood Gene Expression Profile.

Introduction: Stigma contributes to a significant part of the burden of schizophrenia (SCZ), therefore reducing false positives from the diagnosis would be liberating for the individuals with SCZ and desirable for the clinicians. The stigmatization associated with schizophrenia advocates the need for high-precision diagnosis. In this study, we present an ensemble learning-based approach for high-precision diagnosis of SCZ using peripheral blood gene expression profiles. Methodology: The machine learning (ML) models, support vector machines (SVM), and prediction analysis for microarrays (PAM) were developed using differentially expressed genes (DEGs) as features. The SCZ samples were classified based on a voting ensemble classifier of SVM and PAM. Further, microarray-based learning was used to classify RNA sequencing (RNA-Seq) samples from our case-control study (Pune-SCZ) to assess cross-platform compatibility. Results: Ensemble learning using ML models resulted in a significantly higher precision of 80.41% (SD: 0.04) when compared to the individual models (SVM-radial: 71.69%, SD: 0.04 and PAM 77.20%, SD: 0.02). The RNA sequencing samples from our case-control study (Pune-SCZ) resulted in a moderate precision (59.92%, SD: 0.05). The feature genes used for model building were enriched for biological processes such as response to stress, regulation of the immune system, and metabolism of organic nitrogen compounds. The network analysis identified RBX1, CUL4B, DDB1, PRPF19, and COPS4 as hub genes. Conclusion: In summary, this study developed robust models for higher diagnostic precision in psychiatric disorders. Future efforts will be directed towards multi-omic integration and developing "explainable" diagnostic models.

Export of microRNAs: A Bridge between Breast Carcinoma and Their Neighboring Cells.

Breast cancer is a leading type of cancer among women in India as well as worldwide. According to the WHO 2015 report, it has been anticipated that there would be a twofold rise in the death due to breast cancer among women. The heterogeneous property of breast carcinoma has been suggested to be linked with dedicated set of communication and signaling pathway with their surroundings, which culminate into progression and development of the cancer. Among the plethora of communication tools in the hand of breast carcinoma cells is the recently appreciated exocytosis of the tightly packed short non-coding RNA molecules, predominantly the microRNAs (miRNAs). Recent studies suggest that miRNAs may work as courier messengers to participate in endocrine and paracrine signaling to facilitate information transfer between breast carcinoma and their neighboring cells. Evidence suggests that breast tumor cells communicate via packaged miRNAs in the tumor-released microvesicles, which enrich the tumor microenvironment. There is a strong view that dissecting out the mechanistic and regulatory aspects of miRNA export and role may uncover many prospects for overcoming the signaling defects and thereby controlling aberrant cell division. The detection of circulating miRNAs associated with breast carcinoma can also be used as biomarkers for early diagnosis. This review article is an attempt to provide updated knowledge on implications of short RNAs and their transport in the breast cancer pathophysiology.

Potential of Taming MicroRNA on Driver Seat to Control Mitochondrial Horses in Breast Carcinoma.

Breast cancer among women is one of the most common carcinomas worldwide. Compared to developed countries, the breast cancer cases reported in India have boosted rapidly. At the same time, alarming statistics show that ratio of mortality cases over the total incidences is significantly high in comparison to developed world (Global Heath Estimates, WHO 2015). In recent times, several oncogenic signaling pathways have shown convergent effects on various types of cancer cell metabolism including breast cancer leading to tumor development. In 1931, German biochemist Otto Warburg revealed that cancer cells burn sugar (glycolysis) differently than normal cells. Cancer cells prefer to burn sugar over energy rich fats even when cellular oxygen conditions favor mitochondrial fat burning. Further, Warburg hypothesized that cancer is caused by mitochondrial dysfunction forcing the cells to use aerobic glycolysis instead of oxidative phosphorylation (OXPHOS). MicroRNAs (miRNAs) are critical classes of small ~22 nt non-coding endogenous RNAs implicated in gene expression regulation. To date, miRNAs have shown to regulate many cellular metabolic pathways critical for breast carcinoma patho-physiology. There is common consent that miRNAs dedicated to mitochondria and cellular metabolism have profound positive effects on breast carcinoma survival and metastasis. Therefore, in future there is huge scope for identification of miRNA types playing as a driver in mitochondria for breast tumor development. Further, several strategies to taming as well as knocking down these miRNA in breast tumor would be one of the fascinating approaches in medical sciences and cancer therapy. Here, we review updated scientific findings and possible therapeutic interventions with reference to miRNAs, mitochondria, cellular metabolism and breast carcinoma.

Aberrant DNA Double-strand Break Repair Threads in Breast Carcinoma: Orchestrating Genomic Insult Survival.

Breast carcinoma is a heterogeneous disease that has exhibited rapid resistance to treatment in the last decade. Depending genotype and phenotype of breast cancer, there are discernible differences in DNA repair protein responses including DNA double strand break repair. It is a fact that different molecular sub-types of breast carcinoma activate these dedicated protein pathways in a distinct manner. The DNA double-strand damage repair machinery is manipulated by breast carcinoma to selectively repair the damage or insults inflicted by the genotoxic effects of chemotherapy or radiation therapy. The two DNA double-strand break repair pathways employed by breast carcinoma are homologous recombination and non-homologous end joining. In recent decades, therapeutic interventions targeting one or more factors involved in repairing DNA double-strand breaks inflicted by chemo/radiation therapy have been widely studied. Herein, this review paper summarizes the recent evidence and ongoing clinical trials citing potential therapeutic combinatorial interventions targeting DNA double-strand break repair pathways in breast carcinoma.