Current Issue : January - March Volume : 2019 Issue Number : 1 Articles : 5 Articles
The application of gene expression data to the diagnosis and classification of cancer has become a hot issue in the field of\ncancer classification. Gene expression data usually contains a large number of tumor-free data and has the characteristics of high\ndimensions. In order to select determinant genes related to breast cancer from the initial gene expression data, we propose a new\nfeature selection method, namely, support vector machine based on recursive feature elimination and parameter optimization\n(SVM-RFE-PO). The grid search (GS) algorithm, the particle swarm optimization (PSO) algorithm, and the genetic algorithm\n(GA) are applied to search the optimal parameters in the feature selection process. Herein, the new feature selection method\ncontains three kinds of algorithms: support vector machine based on recursive feature elimination and grid search (SVM-RFE-GS),\nsupport vector machine based on recursive feature elimination and particle swarm optimization (SVM-RFE-PSO), and support\nvector machine based on recursive feature elimination and genetic algorithm (SVM-RFE-GA). Then the selected optimal feature\nsubsets are used to train the SVM classifier for cancer classification.We also use random forest feature selection (RFFS), random\nforest feature selection and grid search (RFFS-GS), and minimal redundancy maximal relevance (mRMR) algorithm as feature\nselection methods to compare the effects of the SVM-RFE-PO algorithm. The results showed that the feature subset obtained\nby feature selection using SVM-RFE-PSO algorithm results has a better prediction performance of Area Under Curve (AUC)\nin the testing data set. This algorithm not only is time-saving, but also is capable of extracting more representative and useful\ngenes....
Colorectal cancer (CRC) is one of the leading causes of death by cancer worldwide. Bowel cancer screening programs enable\nus to detect early lesions and improve the prognosis of patients with CRC. However, they also generate a significant number\nof problematic polyps, e.g., adenomas with epithelial misplacement (pseudoinvasion) which can mimic early adenocarcinoma.\nTherefore, biomarkers that would enable us to distinguish between adenoma with epithelial misplacement (pseudoinvasion) and\nadenoma with early adenocarcinomas (true invasion) are needed. We hypothesized that the former are genetically similar to\nadenoma and the latter to adenocarcinoma and we used bioinformatics approach to search for candidate genes that might be\npotentially used to distinguish between the two lesions. We used publicly available data from Gene Expression Omnibus database\nand we analyzed gene expression profiles of 252 samples of normal mucosa, colorectal adenoma, and carcinoma. In total, we\nanalyzed 122 colorectal adenomas, 59 colorectal carcinomas, and 62 normal mucosa samples. We have identified 16 genes with\ndifferential expression in carcinoma compared to adenoma: COL12A1, COL1A2, COL3A1, DCN, PLAU, SPARC, SPON2, SPP1,\nSULF1, FADS1, G0S2, EPHA4, KIAA1324, L1TD1, PCKS1, and C11orf96. In conclusion, our in silico analysis revealed 16 candidate\ngenes with different expression patterns in adenoma compared to carcinoma, which might be used to discriminate between these\ntwo lesions....
Many physiology and bioinformatics research institutions and websites have opened their\nown data analysis services and other relatedWeb services. It is therefore very important to be able\nto quickly and effectively select and extract features from theWeb service pages to learn about and\nuse these services. This facilitates the automatic discovery and recognition of Representational State\nTransfer or RESTful services. However, this task is still challenging. Following the description feature\npattern of a RESTful service, the authors proposed a Feature Pattern Search and Replace (FPSR)\nmethod. First, they applied a regular expression to perform a matching lookup. Then, a custom string\nwas used to substitute the relevant feature pattern to avoid the segmentation of its feature pattern and\nthe loss of its feature information during the segmentation process. Experimental results showed in\nthe visualization that FPSR obtained a clearer and more obvious boundary with fewer overlaps than\nthe test without using FPSR, thereby enabling a higher accuracy rate. Therefore, FPSR allowed the\nauthors to extract RESTful service page feature information and achieve better classification results....
A...
Ornithine transcarbamylase deficiency (OTCD), an X-linked disorder that results from mutations in the OTC gene, causes\nhyperammonemia and leads to various clinical manifestations. Mutations occurring close to the catalytic site of OTCase can cause\nsevere OTCD phenotypes compared with those caused by mutations occurring on the surface of this protein. In this study, we\nreport two novel OTC missense mutations, Q171H and N199H, found in Malaysian patients. Q171H and N199H caused neonatal\nonset OTCD in a male and late OTCD in a female, respectively. In silico predictions and molecular docking were performed to\nexamine the effect of these novel mutations, and the results were compared with other 30 known OTC mutations. In silico servers\npredicted that Q171H and N199H, as well as 30 known missense mutations, led to the development of OTCD. Docking analysis\nindicated that N-(phosphonoacetyl)-L-ornithine (PALO) was bound to the catalytic site of OTCasemutant structurewith minimal\nconformational changes. However, the mutations disrupted interatomic interactions in the catalytic site. Therefore, depending on\nthe severity of disruption occurring at the catalytic site, the mutation may affect the efficiency of mechanism and functions of\nOTCase....
Loading....