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.

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.

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.

The impact of space environment on gene expression in Arabidopsis thaliana seedlings

One of the important questions in space biology is the mechanisms underlying plant responses to an outer space environment,i.e.,how gene expression is altered in space.In this study,the transcriptome of Arabidopsis thaliana seedlings was analyzed as a part of Germany SIMBOX(science in microgravity box)spaceflight experiment on Shenzhou 8 spacecraft.This experiment involved the following treatments:spaceflight with microgravity(Fμg),spaceflight with 1g centrifugal force(F 1g),and ground 1g control(G 1g).Gene chips were used to screen gene expression differences in Arabidopsis thaliana seedlings among these treatments.Microarray analysis revealed that 621 genes were differentially expressed in samples Fμg vs.G 1g,249 genes in samples F 1g vs.G 1g,and 368 genes in samples Fμg vs.F 1g.Gene ontology analysis indicated that the genes were involved in metabolism of stress response,gravitropic response,and DNA damage and repair,suggesting that plants adjust these metabolic pathways to space environmental stress,microgravity,and radiation.

Genome-wide gene expression analysis for target genes to differentiate patients with intestinal tuberculosis and Crohn’s disease and discriminative value of FOXP3 mRNA expression

Background and aims:Crohn’s disease(CD)and intestinal tuberculosis(ITB)are both chronic granulomatous conditions with similar phenotypic presentations.Hence,there is need for a biomarker to differentiate between both these two diseases.This study aimed at genome-wide gene expression analysis of colonic biopsies from confirmed cases of ITB and CD in comparison with controls.To evaluate the role of T regulatory cells,forkhead box P3(FOXP3)mRNA expression was quantified in serum as well as in colonic biopsies from patients with ITB and with the controls.Methods:Paired samples,including serum and colonic biopsies,were taken from 33 study subjects(CD,ITB and controls),and total RNA was extracted.Human whole genome gene expression microarray analysis was performed using the Illumina HumanWG-6 BeadChip Kit with six total RNA samples of the three groups in duplicates.Real-time PCR for FOXP3 mRNA expression was analyzed in serum samples and colonic biopsy samples(4-CD,5-ITB,4-controls).Results:In CD and ITB there was 1.5-fold upregulation of 92 and 382 genes and 1.5-fold downregulation of 91 and 256 genes,respectively.Peroxisome proliferators via the PPARc pathway were most significantly downregulated(P<0.005)in CD.Additionally,the IL4/5/6 signaling pathways and Toll-like receptor signaling pathway were identified as significantly differentially regulated(P<0.005)at>2-fold change.In ITB,the complement activation pathway,specifically the classical pathway,was the most significantly upregulated.FOXP3 mRNA expression was significantly elevated in colonic biopsies obtained from ITB patients as compared with CD cases(4.7062.21 vs 1.4860.31,P=0.016).Conclusions:FOXP3 mRNA expression in colonic mucosa could be a discriminatory marker between ITB and CD.Upregulation of the complement activation pathway in ITB suggests that pathogenetic mechanisms for ITB are similar to those of pulmonary tuberculosis.In CD,downregulation of PPARc was seen in colonic tissue,suggesting that restoration of PPARc-dependent anti-microbial barrier function may be a therapeutic target.

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.