view dartseq_seeduk_2.R @ 22:12db48e80a98 draft

Uploaded
author cropgeeks
date Fri, 20 Apr 2018 05:58:38 -0400
parents c9686a670e60
children
line wrap: on
line source

args = commandArgs(trailingOnly=TRUE)

library("amap")
library("labdsv")

data <- read.table("plink.raw")
distances <- Dist(data[2:338,7:75189], method = "euclidean", nbproc = 144)
pco_results <- pco(distances,k=10)
#Variance explained by first three PCOs
pco_results$eig[1]/sum(pco_results$eig[pco_results$eig>0])
#[1] 0.2565937
pco_results$eig[2]/sum(pco_results$eig[pco_results$eig>0])
#[1] 0.06878127
pco_results$eig[3]/sum(pco_results$eig[pco_results$eig>0])
#[1] 0.04340111
write.csv(pco_results$points,file=args[1])
write.csv(data[,2],file="PCO_sample_names.csv")