作者: Alain Barrier , Pierre-Yves Boelle , François Roser , Jennifer Gregg , Chantal Tse
关键词:
摘要: Purpose This study mainly aimed to identify and assess the performance of a microarray-based prognosis predictor (PP) for stage II colon cancer. A previously suggested 23-gene signature (PS) was also evaluated. Patients Methods Tumor mRNA samples from 50 patients were profiled using oligonucleotide microarrays. PPs built assessed by random divisions into training validation sets (TSs VSs, respectively). For each TS/VS split, 30-gene PP, identified on TS selecting 30 most differentially expressed genes applying diagonal linear discriminant analysis, used predict prognoses VS patients. Two schemes considered: single-split validation, based single split two groups equal size (group 1 group 2), Monte Carlo cross (MCCV), whereby repeatedly randomly divided various sizes. Results The patients, yielded an 80% prog...