Changes

From Genome Analysis Wiki
Jump to navigationJump to search
549 bytes added ,  10:02, 2 February 2017
Line 1: Line 1: −
''ChunkChromosome'' is a helper utility for [[minimac]] and [[MaCH]]. It can be used to facilitate analyses of very large datasets in overlapping slices.
+
''ChunkChromosome'' is a helper utility for [[minimac]] and [[MaCH]]. It can be used to facilitate analyses of very large datasets in overlapping slices. For information on how to put the resulting chunks back together, see [[Ligate Minimac|this page]].
    
== Parameters ==
 
== Parameters ==
Line 16: Line 16:  
awk '{ if ($1 == "M") print $2; }' < chr1.dat > chr1.snps
 
awk '{ if ($1 == "M") print $2; }' < chr1.dat > chr1.snps
 
mach1 -d chr1.dat -p chr1.ped --rounds 20 --states 200 --phase --prefix chr1.haps
 
mach1 -d chr1.dat -p chr1.ped --rounds 20 --states 200 --phase --prefix chr1.haps
minimac --refHaps 1000genomes.chr1.haps.gz  --refSnps 1000genomes.chr1.snps --haps chr1.haps.gz --snps chr1.snps --rounds 5 --states 200 --prefix imputation-results
+
minimac --refHaps 1000genomes.chr1.haps.gz  --refSnps 1000genomes.chr1.snps --haps chr1.haps.gz --snps chr1.snps --rounds 5 --states 200 --prefix chr1.imputed
 
</source>
 
</source>
   Line 22: Line 22:     
<source lang="bash">
 
<source lang="bash">
ChunkChromosome -d chr1.dat
+
#!/bin/tcsh
 +
 
 +
@ length = 2500
 +
@ overlap = 500
 +
 
 +
# Estimate haplotypes for all individuals, in 2500 marker chunks, with 500 marker overhang
 +
foreach chr (`seq 1 22`)
 +
 
 +
  ChunkChromosome -d chr$chr.dat -n $length -o $overlap
 +
 
 +
  foreach chunk (chunk*-chr$chr.dat)
 +
 
 +
      mach -d $chunk -p chr$chr.ped --prefix ${chunk:r} \
 +
          --rounds 20 --states 200 --phase --sample 5 >& ${chunk:r}-mach.log &
 +
 
 +
  end
   −
# Phase each chunk in parallel
  −
foreach chunk (chunk*-chr1.dat)
  −
  mach1 -d $chunk -p chr1.ped --rounds 20 --states 200 --phase --prefix ${chunk:r}.haps >& ${chunk:r}-mach.log &
   
end
 
end
 
wait
 
wait
   −
# Impute each chunk in parallel
+
# Impute into phased haplotypes
foreach chunk (chunk*-chr1.dat)
+
foreach chr (`seq 1 22`)
  minimac --autoClip autoChunk-chr1.dat \
+
 
          --refHaps 1000genomes.chr1.haps.gz  --refSnps 1000genomes.chr1.snps --rounds 5 --states 200 \
+
  foreach chunk (chunk*-chr$chr.dat)
          --haps ${chunk:r}.haps.gz --snps ${chunk}.snps --prefix ${chunk:r}-results >& ${chunk:r}-minimac.log &
+
 
 +
      set haps = /data/1000g/hap/all/20101123.chr$chr.hap.gz
 +
      set snps = /data/1000g/snps/chr$chr.snps
 +
 
 +
      minimac --refHaps $haps --refSnps $snps --rounds 5 --states 200 \
 +
              --haps ${chunk:r}.gz --snps ${chunk}.snps --autoClip autoChunk-chr$chr.dat  \
 +
              --prefix ${chunk:r}.imputed >& ${chunk:r}-minimac.log &
 +
 
 +
  end
 +
 
 
end
 
end
 
wait
 
wait
Line 43: Line 64:  
== Download ==
 
== Download ==
   −
You can download source code for the ChunkChromosome program from [here]. After downloading it, unpack the archive and use Make to compile the tool.
+
You can download source code for the ChunkChromosome program in a tar-ball archive [http://csg.sph.umich.edu//cfuchsb/generic-ChunkChromosome-2014-05-27.tar.gz generic-ChunkChromosome-2014-05-27.tar.gz]. After downloading it, unpack the archive and use Make to compile the tool.
96

edits

Navigation menu