arq5x

attributes:
  name: cpg
  version: 0.1

recipe:
  full:
    recipe_type: bash
    recipe_cmds: 
      - > 
        mysql --user=genome --host=genome-mysql.cse.ucsc.edu \

arq5x

# update things
sudo apt-get update

# get postgres up and running
sudo apt-get install postgresql-9.3
sudo apt-get install postgresql-server-dev-9.3
sudo apt-get install postgresql-client
sudo apt-get install postgresql postgresql-contrib
sudo -u postgres psql postgres
\password postgres

arq5x

1. Deanna's biostars post
2. MAPT alt locus
3. MAPT under selection in Eurpeans
4. Zody/Eichler MAPT Inversion toggling
5. The MAPT locus—a genetic paradigm in disease susceptibility
6. Case study for reporting variants in the VCF format.
7. http://content.csbs.utah.edu/~rogers/ant6299/readings/Hardy-BST-33-582.pdf
8. Kitzman/Eichler show that sample NA10847 is heterozygous H1/H2 http://www.nature.com.proxy.its.virginia.edu/nbt/journal/v29/n1/extref/nbt.1740-S1.pdf
9. Terminology

arq5x

DIR=bam/t1d-run2a-redo/

# line 10: run flagstats on marked dup BAM
# line 11: grab the number of duplcates line and the total reads line
# line 12 grab the total and dup total
# line 13: place the total followed by duplicate count on same line
# line 14: print the duplicate fraction
for file in `ls $DIR/*.bwamem.sort.dedup.bam`;
do
    samtools flagstat $file | \

arq5x

# assumes you have SSH'ed and qlogin'ed
cd thu
cd mydata

# slide 5
curl https://s3.amazonaws.com/gemini-tutorials/trio.trim.vep.vcf.gz > trio.trim.vep.vcf.gz
curl https://s3.amazonaws.com/gemini-tutorials/dominant.ped > dominant.ped
gemini load --cores 2 \
              -v trio.trim.vep.vcf.gz \
              -t VEP \

arq5x

# test each database file individually
time bedtools intersect -wa -wb -sorted \
                            -a hg19.rmsk.bed.gz \
                            -b hg19.segdup.bed.gz \
                            > /dev/null
real	0m5.069s
user	0m5.007s
sys	0m0.056s

time bedtools intersect -wa -wb -sorted \

arq5x

# assumes that the BEDGRAPH is the output of the bedtools genomecov tool using the -bga option.
$ cat foo.bedg
chr1	0	10	5
chr1	10	20	5
chr1	20	30	10
chr1	30	40	11
chr1	40	50	9
chr1	50	60	10
chr1	60	70	11
chr1	70	80	15

arq5x

# compute a BEDGRAPH RNA-seq coverage across the entire genome for each sample:
bedtools genomecov -bga -split -ibam sample1.sorted.bam > 1.bg
bedtools genomecov -bga -split -ibam sample1.sorted.bam > 2.bg
bedtools genomecov -bga -split -ibam sample1.sorted.bam > 3.bg


# compute the mean coverage at each interval.
bedtools unionbedg -i 1.bg 2.bg 3.bg \
   | awk '{sum=0; for (col=4; col<=NF; col++) sum += $col; print $0"\t"sum/(NF-4+1); }'
chr1 900  1000 0  60 0	20

arq5x

import sys

class Line(object):
	def __init__(self, line):
		self.fields = line.split('\t')
		self.chrom = self.fields[0]
		self.start = int(self.fields[1])
		self.end = int(self.fields[2])
		self.depth = int(self.fields[3])

arq5x

#!/usr/bibn/env python

print "hi"