Graphical data mining of cancer mechanisms with SEMA

Solmaz, Mustafa; Lane, Adam; Gonen, Bilal; Akmamedova, Ogulsheker; Güneş, Mehmet Hadi; Komurov, Kakajan

doi:10.1093/bioinformatics/btz303

Cited by 7 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Liu (2009) has discussed computational data mining in cancer bioinformatics. A web platform SEMA for building models of cancer mechanisms from large cancer genomic data set is developed by Solmaz et al (2019). Herbola et al (2022) have discussed the basics of data mining techniques and their applications in genomics, proteomics, and medical analysis.…”

Section: Differential Gene Expression Analysis Involves Genes Showing Different Expressionmentioning

confidence: 99%

Extracting the candidate genes for cancer from the microarray gene expression data by stochastic computation

Behera

Sinha

2022

Preprint

View full text Add to dashboard Cite

Microarray gene expression data provides a simultaneous gene expression profile of thousands of genes. A handful of genes among the thousands of genes play dominant roles in a disease process. It is impractical to find these faulty genes from experimental data. A computational approach is necessary to find the key genes and hence it is an important area of research in bioinformatics. A new algorithm is developed in this work to identify the candidate genes of a cancer from microarray gene expression data. Gene clustering enables identification of co-expressed genes in specified biological conditions. Many algorithms have inherent limitations to understand the accurate information. This model is a hybrid of clustering algorithm and genetic. A genetic algorithm utilizes the three biological principles of evolution, such as selection, recombination, and mutation to solve an optimization problem. An interdependence measure between the genes is based on a metric which can be mutual information. In many conventional algorithms, a Euclidean genetic distance measure is used. This is basically the difference between gene expression values. Genes are similar if their expressions levels are very close. Similarity of the gene expression levels, and also positive and negative correlations between the genes are taken into account while clustering them. This property is used in mutual information which introduces a parameter called interdependence measure. This says roughly how the two genes are correlated. The genes having higher interdependence measures are the top candidate genes responsible for a diseased state. These top genes are believed to be faulty genes that contain the most diagnostic information for cancer. An analysis is done on gastric cancer, colon cancer, and brain cancer microarray gene expression datasets to pinpoint the faulty genes. In comparison with many existing computational tools, the top candidate genes found by this evolutionary computational model, are able to classify the known samples into cancerous and normal ones with high accuracy. The new model called as evolutionary clustering algorithm also creates more even-like distribution of genes in the clusters. Furthermore, the present computational tool is more coherent in clustering the genes having large differences in their expression values. This information-theoretic computational method can be potentially applied to the big data analysis from other sources.

show abstract

Section: Differential Gene Expression Analysis Involves Genes Showing Different Expressionmentioning

confidence: 99%

Extracting the candidate genes for cancer from the microarray gene expression data by stochastic computation

Behera

Sinha

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…A few brilliant web stages have been created to empower the visual investigations of sub-atomic adjustments in tumors from these datasets. Be that as it may, there are barely any devices to permit the specialists to dig these assets for systems of malignancy forms and their utilitarian cooperations in an instinctive fair-minded way [15] .…”

Section: Literature Reviewmentioning

confidence: 99%

Bladder And Kidney Cancer Genome Classification Using Neural Network

Rana

Ashraf

2021

VFAST trans. softw. eng.

View full text Add to dashboard Cite

Cancer genome classification is very important due to its importance in daily life. In few decades hundred thousand people get effected it and it cause of death for them. The major cause of late identification of cancer genome. So in our work we emphasize on three types of cancer genome which belongs to two major types which are bladder and kidney. We discuss the BLCA, KICH and KIRC. Our work explain the real time authenticity of the genome from the normal genome which are named as mutation dataset. We apply the conventional model and compare them with neural network model and found that the neural network performs very well with respect to the conventional model and the given tables also annotate its significance.

show abstract

“…SEMA: SEMA is a web-based program (https://sema.research.cchmc.org/) that creates graphical models using data from The Cancer Genome Atlas (TCGA). The user-defined model is then analyzed for fit to the data by Structural Equation Modeling (SEM) [89]. DEK mRNA levels were queried against the expression of target genes identified in the mouse model as well as "Tumor Features" from the PanCancer Atlas.…”

Section: Human Breast Cancer Databasesmentioning

confidence: 99%

DEK Expression in Breast Cancer Cells Leads to the Alternative Activation of Tumor Associated Macrophages

Pease

Shephard

Sertorio

et al. 2020

Cancers

View full text Add to dashboard Cite

Breast cancer (BC) is the second leading cause of cancer deaths among women. DEK is a known oncoprotein that is highly expressed in over 60% of breast cancers and is an independent marker of poor prognosis. However, the molecular mechanisms by which DEK promotes tumor progression are poorly understood. To identify novel oncogenic functions of DEK, we performed RNA-Seq analysis on isogenic Dek-knockout and complemented murine BC cells. Gene ontology analyses identified gene sets associated with immune system regulation and cytokine-mediated signaling and differential cytokine and chemokine expression was confirmed across Dek-proficient versus Dek-deficient cells. By exposing murine bone marrow-derived macrophages (BMDM) to tumor cell conditioned media (TCM) to mimic a tumor microenvironment, we showed that Dek-expressing breast cancer cells produce a cytokine milieu, including up-regulated Tslp and Ccl5 and down-regulated Cxcl1, Il-6, and GM-CSF, that drives the M2 polarization of macrophages. We validated this finding in primary murine mammary tumors and show that Dek expression in vivo is also associated with increased expression of M2 macrophage markers in murine tumors. Using TCGA data, we verified that DEK expression in primary human breast cancers correlates with the expression of several genes identified by RNA-Seq in our murine model and with M2 macrophage phenotypes. Together, our data demonstrate that by regulating the production of multiple secreted factors, DEK expression in BC cells creates a potentially immune suppressed tumor microenvironment, particularly by inducing M2 tumor associated macrophage (TAM) polarization.

show abstract

Graphical data mining of cancer mechanisms with SEMA

Cited by 7 publications

References 16 publications

Extracting the candidate genes for cancer from the microarray gene expression data by stochastic computation

Extracting the candidate genes for cancer from the microarray gene expression data by stochastic computation

Bladder And Kidney Cancer Genome Classification Using Neural Network

DEK Expression in Breast Cancer Cells Leads to the Alternative Activation of Tumor Associated Macrophages

Contact Info

Product

Resources

About