Deep Learning Enabled Microarray Gene Expression Classification for Data Science Applications

In bioinformatics applications,examination of microarray data has received significant interest to diagnose diseases.Microarray gene expression data can be defined by a massive searching space that poses a primary challenge in the appropriate selection of genes.Microarray data classification incorporates multiple disciplines such as bioinformatics,machine learning(ML),data science,and pattern classification.This paper designs an optimal deep neural network based microarray gene expression classification(ODNN-MGEC)model for bioinformatics applications.The proposed ODNN-MGEC technique performs data normalization process to normalize the data into a uniform scale.Besides,improved fruit fly optimization(IFFO)based feature selection technique is used to reduce the high dimensionality in the biomedical data.Moreover,deep neural network(DNN)model is applied for the classification of microarray gene expression data and the hyperparameter tuning of the DNN model is carried out using the Symbiotic Organisms Search(SOS)algorithm.The utilization of IFFO and SOS algorithms pave the way for accomplishing maximum gene expression classification outcomes.For examining the improved outcomes of the ODNN-MGEC technique,a wide ranging experimental analysis is made against benchmark datasets.The extensive comparison study with recent approaches demonstrates the enhanced outcomes of the ODNN-MGEC technique in terms of different measures.

Effect of surgical procedures on prostate tumor gene expression profiles

Current surgical treatment of prostate cancer is typically accomplished by either open radical prostatectomy （ORP） or robotic-assisted laparoscopic radical prostatectomy （RALRP）. Intra-operative procedural differences between the two surgical approaches may alter the molecular composition of resected surgical specimens, which are indispensable for molecular analysis and biomarker evaluation. The objective of this study is to investigate the effect of different surgical procedures on RNA quality and genome-wide expression signature. RNA integrity number （RIN） values were compared between total RNA samples extracted from consecutive LRP （n= 11） and ORP （n= 24） prostate specimens. Expression profiling was performed using the Agilent human whole-genome expression microarrays. Expression differences by surgicat type were analyzed by Volcano plot analysis and gene ontology analysis. Quantitative reverse transcription （RT）-PCR was used for expression validation in an independent set of LRP （n=8） and ORP （n=8） samples. The LRP procedure did not compromise RNA integrity. Differential gene expression by surgery types was limited to a small subset of genes, the number of which was smaller than that expected by chance. Unexpectedly, this small subset of differentially expressed genes was enriched for those encoding transcription factors, oxygen transporters and other previously reported surgery-induced stress-response genes, and demonstrated unidirectional reduction in LRP specimens in comparison to ORP specimens. The effect of the LRP procedure on RNA quality and genome-wide transcript levels is negligible, supporting the suitability of LRP surgical specimens for routine molecular analysis. Blunted in vivo stress response in LRP specimens, likely mediated by CO2 insufflation but not by longer ischemia time, is manifested in the reduced expression of stress-response genes in these specimens.

Gene Expression Profiling of Human c-Kit Mutant D816V

The tyrosine kinase receptor III, c-Kit/stem cell factor receptor and its ligand, human stem cell factor (huSCF) are the predominant regulator of mitogenesis in the hematopoietic stem and progenitor cells. However, gain-of-function mutations alter c-Kit auto-regulatory mechanisms to aberrant c-Kit signaling, leading to the onset or progression of cancerous transformations. The most common mutation of c-Kit is the substitution of aspartic acid residue in position 816 to valine (D816V), which is majorly responsible for its ligand-independent constitutive activation, and is implicated in hematopoietic malignancies. Currently, molecular targeted therapy is increasingly becoming a hot spot due to its specificity and low toxicity. As the molecular mechanisms responsible for D816V-c-Kit mediated tumorogenicity are largely unknown, in this study, we aimed to investigate the D816V-c-Kit signaling mediated downstream molecular targets. Specifically, we created c-Kit active mutant form D816V and performed inducible gene expression of mutant D816V-c-Kit in monomyelocytic cell line U937. Mutant D816V-c-Kit expressing cells revealed significantly enhanced cellular mitogenic activity compared to wild-type c-Kit expressing cells independent of huSCF. To examine the molecular targets regulating tumorogenic proliferation, we evaluated the consequences of mutant D816V-c-Kit expression on downstream gene expression profile by high throughput microarray technology. The levels of some of the relevant genes (PIK3CB, eIF4B, PRKCDBP, MOAP1) were validated by quantitative polymerase chain reaction. SLA, STAT5B, MAP3K2 and MAPK14 emerged as important downstream molecular targets of mutant D816V-c-Kit. Further, by dissecting the signaling pathways, we also demonstrated that the D816V-c-Kit mediated hematopoietic cell proliferation is dependent on molecular target p38 MAP kinase.

Expression Profiling of Hereditary versus Sporadic Prostate Cancer Suggests CYR61, EGR3, KLF6 and SNF1LK as Differentially Expressed Genes

Background: Distinguishing between sub-clinical and aggressive forms of prostate cancer is difficult due to the heterogeneity of the disease. It is, however, important to identify aggressive forms to guide proper treatment. This study compared gene expression profiles in cancer cells from hereditary and sporadic prostate cancer cases and attempted to correlate differentially regulated genes with clinico-pathological characteristics and prognosis. Materials and methods: The study population comprised patients diagnosed with clinically localized prostate cancer undergoing prostatectomy. Patients were divided into hereditary and sporadic cancer cases based on their family history. Fresh frozen biopsies from prostatectomy specimens were laser-dissected for RNA-extraction. Affymetrix HG-U133 Plus GeneChips were used to measure gene expression loaded onto Cluster 3.0 and Ingenuity Pathway Analysis softwares to examine the relationship among genes between groups. Differentially expressed genes were selected for protein expression analysis using immunohistochemistry on histological sections and tissue microarrays. Results: No single genes were signifycantly differentially expressed between hereditary and sporadic cases after adjustment for multiple testing. Using cluster analysis, four transcripts were found to be upregulated in hereditary prostate cancer tissue: CYR61, EGR3, KLF6 and SNF1LK. The intensity of CYR61, EGR2, KLF6 and SNF1LK immunostainings, however, were not significantly different in a separate sample of hereditary and sporadic prostate cancers. Furthermore, no correlations between CYR61, EGR2, KLF6, and SNF1LK staining intensities and the clinico-pathological variables or disease-free survival were detected, except for EGR3 that was significantly associated with T stage (p = 0.04). Conclusion: Overall, no single transcript level was significantly associated with hereditary prostate cancer. Cluster analysis suggested that the expression of CYR61, EGR3, KLF6 and SNF1LK were upregulated in cancer tissue from hereditary cases, but we were not able to confirm this on the protein level, and levels of these proteins were not found to correlate with clinico-pathological characteristics or biochemical recurrence.

Association of TCR-signaling pathway with the development of lacrimal gland benign lymphoepithelial lesions

·AIM: To identify the association of the T cell receptor(TCR) signaling with the development of benign lymphoepithelial lesions(BLEL) of the lacrimal gland.· METHODS: We collected affected lacrimal gland tissues from 9 patients who underwent dacryoadenectomy in the Capital Medical University Beijing Tongren Hospital Eye Center between August2010 and March 2013 and were confirmed to have lacrimal gland BLEL by histopathological analysis. Tumor tissues from 9 patients with orbital cavernous hemangioma were also collected and used as control.Whole genome gene expression microarray was used to compare gene expression profiles of affected lacrimal gland tissues from patients with lacrimal gland BLEL to those from of orbital cavernous hemangiomas.Differential expression of TCR pathway genes between these tissues was confirmed by polymerase chain reaction(PCR) and immunohistochemistry.·RESULTS: Microarray analysis showed that in lacrimal glands with BLEL, 32 signaling pathways were enriched in the upregulated genes, while 25 signaling pathways were enriched in the downregulated genes. In-depth analysis of the microarray data showed that the expression of 27 genes of the TCR signaling pathway increased significantly. To verify the differential expression of three of these genes, CD3, CD4, and interleukin(IL)-10, reverse transcription-PCR(RT-PCR)and immunohistochemistry assays were performed. RT-PCR analysis showed that CD3 and CD4 were expressed in the lacrimal glands with BLEL, but IL-10 was not expressed. Immunohistochemistry confirmed that CD3 and CD4 proteins were also present, but IL-10 protein was not. CD3, CD4, or IL-10 expression was not found in the orbital cavernous hemangiomas with either RT-PCR or immunohistochemistry.· CONCLUSION: TCR signaling pathway might be involved in the pathogenesis of lacrimal gland BLEL.

Gene expression profiles of human bone marrow derived mesenchymal stem cells and tendon cells

Objective To study the gene expression profiles of human bone marrow derived mesenchymal stem cells and tendon cells.Methods Total RNA extracted from human bone marrow derived mesenchymal stem cells and tendon cells underwent reverse transcription,and the products were labeled with α- 32 P dCTP. The cDNA probes of total RNA were hybridized to cDNA microarray with 1176 genes,and then the signals were analyzed by AtlasImage analysis software Version 1.01a.Results Fifteen genes associated with cell proliferation and signal transduction were up-regulated,and one gene that takes part in cell-to-cell adhesion was down-regulated in tendon cells.Conclusion The 15 up-regulated and one down-regulated genes may be beneficial to the orientational differentiation of mesenchymal stem cells into tendon cells.

Gene Selection for Classifications Using Multiple PCA with Sparsity

A gene selection algorithm was developed using Multiple Principal Component Analysis with Sparsity （MSPCA）. The MSPCA algorithm is used to analyze normal and disease gene expression samples and to set these component Ioadings to zero if they are smaller than a threshold for sparse solutions. Next, genes with zero Ioadings across all samples （both normal and disease） are removed before extracting feature genes. Feature genes are genes that contribute differentially to variations in normal and disease samples and, thus, can be used for classification. The MSPCA is applied to three microarray datasets to select feature genes with a linear support vector machine to evaluate its performance. This method is compared with several previous gene selection results to show that this MSPCA gene selection algorithm has good classification accuracy and model stability.