决策树是通过递回分割(recursive.pptVIP

A Five-Gene Signature and Clinical Outcomein Non–Small-Cell Lung Cancer From: n engl j med 356;1 january 4, 2007 By: Hsuan-Yu Chen, M.Sc., Sung-Liang Yu, Ph.D., et al Reporter: R6 謝廣宇 Background Current staging methods are inadequate for predicting outcome developed a 5 -gene signature non– small-cell lung cancer (NSCLC) — most common cause of death from cancer worldwide relapse rate with early-stage NSCLC is 40% within 5 years after potentially curative treatment 決策樹是通過遞迴分割（recursive partitioning）建立而成，遞迴分割是一種把資料分割成不同小的部分的疊代過程 Gene-expression profiling by means of microarrays and reverse-transcriptase polymerase chain reaction (RT-PCR) examined gene expression in 125 surgical specimens of NSCLC, using microarrays and real-time RT-PCR to identify a gene signature correlated with clinical outcome Methods computer-generated random numbers to assign specimens from 185 consecutive patients for microarray analysis frozen specimens of lung-cancer tissue from 125 randomly selected patients who underwent surgical resection of NSCLC at Taichung Veterans General Hospital between December 1999 and December 2003------five-gene risk-prediction model using an independent cohort of 60 randomly selected patients 125 specimens-- 60 were adenocarcinomas, 52 were squamous-cell carcinomas, and 13 were other types of cancer not received adjuvant chemotherapy 672 genes associated with invasive activity, identified in a previous study--- rearrayed in duplicate on a nylon membrane 4 μg of total RNA from each specimen validate levels of expression of genes found on microarray analysis ? RT-PCR was performed on 16 genes and a control gene for TATA-box–binding protein (TBP), with use of specific TaqMan probes and primer sets --- transcripts were amplified with reagent (TaqMan One-Step RT-PCR Master Mix Reagent, Applied Biosystems) and a sequence detection system (ABI Prism 7900HT, Applied Biosystems) To reduce background noise ? background intensity values of less than