Project description:Filtered selection coupled with support vector machines generate functionally relevant prediction model for colorectal cancer. In this study, we built a model that uses Support Vector Machine (SVM) to classify cancer and normal samples using Affymetrix exon microarray data obtained from 90 samples of 48 patients diagnosed with CRC. From the 22,011 genes, we selected the 20, 30, 50, 100, 200, 300 and 500 genes most relevant to CRC using the Minimum-Redundancy–Maximum-Relevance (mRMR) technique. With these gene sets, an SVM model was designed using four different kernel types (linear, polynomial, radial basis function and sigmoid).
Project description:Mesenchymal stem/stromal cells (MSCs) were harvested from subcutaneous adipose tissue of patients with obesity or healthy controls and expanded for 3-4 passages, and 5hmC profiles were examined through hydroxymethylated DNA immunoprecipitation sequencing (hMeDIP-seq). We hypothesized that obesity and cardiovascular risk factors induce functionally-relevant, locus-specific changes in overall exonic coverage of 5hmC in human adipose-derived MSCs.
Project description:Gene expression profiling of immortalized human mesenchymal stem cells with hTERT/E6/E7 transfected MSCs. hTERT may change gene expression in MSCs. Goal was to determine the gene expressions of immortalized MSCs.
