@article{article_371882, title={Development of a New Supervised Principal Component Analysis Based on Artificial Neural Networks in Gene Expression Data}, journal={Osmangazi Tıp Dergisi}, volume={40}, pages={20–27}, year={2018}, DOI={10.20515/otd.371882}, author={Türe, Mevlüt and Kurt Ömürlü, İmran}, keywords={Boyut indirgeme; yapay sinir ağları; denetimli temel bileşenler analizi; random survival forests; gen ekspresyon}, abstract={<p class="MsoNormal" style="margin-bottom:.0001pt;text-align:justify;line-height:normal;"> <span style="font-size:9pt;font-family:’Times New Roman’, serif;">The
aim of this study is dimension reduction of multidimensional gene expression
data using supervised principal component analysis (S-PCA) and –proposed as a
new approach- supervised principal component analysis with artificial neural
networks (S-ANN-PCA) and to compare performances of these two methods by using
random survival forests (RSF). In simulation application 5000 genes were
generated according to multivariate normal distribution and then survival time
that is correlated to these gene data were generated for 100 units. Simulation
step was carried out with 1000 repetitions. </span> </p> <p> </p> <p class="MsoNormal" align="left" style="line-height:150%;"> </p> <p class="MsoNormal" style="margin-bottom:.0001pt;text-align:justify;line-height:normal;"> <span style="font-size:9pt;font-family:’Times New Roman’, serif;">In
addition, gene expression data for 240 individuals with extensive B-cell
lymphoma (DLBCL) were used. Dimension reduction was done using Wald statistic
in selection of important genes. The new data sets obtained from the methods
were analyzed using RSF analysis.In the simulation application, it was obtained
that the explanatoriness of S-PCA was significantly different from S-ANN-PCA
(p<0.001). In the DLBCL data application, it was found that the error rate
for the S-PCA was 36.78% and 43% for the S-ANN-PCA as a result of RSF. The
importance value of S-PCA method was found to be higher and its error rate was
found to be lower than the other method.S-PCA performed better than S-ANN-PCA
in analyzing gene expression data experiencing a multidimensional problem. </span> </p> <p> </p> <p> </p>}, number={1}, publisher={Eskişehir Osmangazi Üniversitesi}