kate-crosby

#Run tassel from the get_list.R

module load gcc jdk/1.8 tassel/5

run_pipeline.pl -Xmx64g -fork1 -h All_SeeD_2.7_chr4_no_filter.unimputed.hmp.txt -export -exportType VCF -runfork1


sed '11q;d' All_SeeD_2.7_chr4_no_filter.unimputed.vcf > header.vcf

kate-crosby

# Doesn't matter what this is just defining an object
Y <- rnorm(500)


as.formula(paste("Y~",paste("SNP",1:16657,sep="",collapse="+"),sep=" "))

# Compare the two - if set max ppsize, goes up but not enough for 160k fixed effects

as.formula(paste("Y~",paste("SNP",1:16658,sep="",collapse="+"),sep=" "))

kate-crosby

rm(list=ls())

library(raster)
#Get bio variables at 10 minutes of a degree resolution
biovar = getData('worldclim', var='bio', res=10)

biovar5 = getData('worldclim', var="bio", res=5)

###Get elevation data with SRTM - go to website to determine relevant tiles, 
#each of these tiles are large - may be easier to do on website

kate-crosby

#!/usr/bin/python

import sys
import csv
import array

def main():
    #if len(sys.argv) < 2:
    #    print 'give me a filename'
    #    sys.exit(1)

kate-crosby

library(data.table)
fulldata <- fread("AmesUSInbreds_AllZeaGBSv1.0_imputed_20130508_chr1.hmp.txt",
                       header=T, sep = "\t") 
dim(fulldata)

fulldata <-data.frame(fulldata)
# Eliminate unwanted columns prior to conversion 
drops <- c("alleles","chrom", "pos", "strand", "assembly#", "center", "protLSID",
           "assayLSID", "panelLSID", "QCcode")
new.df <- fulldata[,!(names(fulldata) %in% drops)]

kate-crosby

# Let's make some fake plink map and ped files - ped files contain the genotype and map the chrom and position

############################################################################
# Let's start with the PED file - reading in zip file downloaded from PANZEA
############################################################################

fulldata <- read.table("NAM_phasedImputed_1cM_AllZeaGBSv2.3_allChrs.hmp.txt",
  header=T,comment.char="",stringsAsFactors=F) 

dim(fulldata)