疾病亞型預(yù)測中常用NTP方法,今天發(fā)現(xiàn)一位大神用svm
預(yù)測亞型豌注,并且在附件中還加入了代碼伤塌,下面就來圍觀下吧。
發(fā)表雜志:Frontiers in Oncology
PMID:34222009
在原文中作者這樣說:
接下來是附件中作者的代碼:(為便于學(xué)習(xí)轧铁,直接插入代碼塊吧)
library(e1071)
tObj = tune.svm(scale(t(TCGA.sigGenes.exp)),factor(TCGA.cluster),
probability = TRUE,
cost=c(0.001,0.01,0.1,1,5,10,100,1000), scale=F)
geo.cluster = predict(tObj$best.model,scale(t(GEO.sigGenes.exp)))
Supplemenatary files
參考鏈接:
Comprehensive Landscape of Ovarian Cancer Immune Microenvironment Based on Integrated Multi-Omics Analysis