【論】Shipp,2002,Diffuse large B-cell lymphoma～

Margaret A.Shipp, Ken N.Ross, Pablo Tamayo, Andrew P.Weng, Jeffery L.Kutok, Ricard C.T.Aguiar, Michelle Gaasenbeek, Michael Angelo, Michael Reich, Geraldine S.Pinkus, Tane S.Ray, Margaret A.Koval, Kim W.Last, Andrew Norton, T.Andrew Lister, Jill Mesirov, Donna S.Neuberg, Eric S.Lander, Jon C.Aster & Todd R.Golub
Diffuse large B-cell lymphoma outcome prediction by gene-expression profiling and supervised machine learning
NATURE MEDICINE Vol.8 Num.1 January 2002
[PDFダウンロード][Webサイト]

・DNAマイクロアレイの病気診断への応用。DLBCL（Diffuse large B-cell lymphoma : びまん性大細胞型リンパ腫）の予後診断。
・データ：合計77サンプル（全て別の患者）、うちDLBCLは58、FL(follicular lymphoma)は19サンプル。6,817遺伝子。
・実験1：77サンプルをsupervised learning classification algorithm ('weighted voting')にかけ、DLBCLとFLにそれぞれ特異的に発現する遺伝子を抽出する。
・実験2：DLBCL58サンプルをweighted voting にかけ、治癒(32サンプル)と難治(26サンプル)にそれぞれ特異的に発現する遺伝子を抽出する。　→　最終的に13遺伝子まで絞り込み

・結局なにをやってんだか、内容がいまいちつかみずらい。

・「The 6,817 genes were sorted by their degree of correlation with the DLBCL versus FL distinction.」
・「Such comparisons are admittedly difficult, given that, 1) different genes were measured on the arrays, 2) the microarray technology was different (oligonucleotide versus cDNA arrays), 3) different computational approaches were employed, and 4) different patient samples were studied.」
・「This observation suggests that although the signature genes may reflect cell of origin, they do not explain a significant portion of the clinical variability seen in this DLBCL dataset.」
・「Marker genes were then identified using a signal-to-noise calculation: S_x=(μ_class0 - μ_class1) / (σ_class0 + σ_class1)」
～～～～～～～
・もうとっくに10本は読んだかと思いきや、まだ7本目・・・orz　二日で一本読めるところまできたが、まだまだ遅い。