danielecook

#!/usr/bin/python
# Slightly adapted from http://blog.nextgenetics.net/?e=27

import sys

def main():
    for line in sys.stdin.xreadlines():
      #skip comment lines that start with the '#' character
      if line[0] != '#':
        #split line into columns by tab

danielecook

Download_SRP_Runs() {
    SRP_IDs=`esearch -db sra -query $1 | efetch -format docsum | xtract -pattern DocumentSummary -element Run@acc | tr '\t' '\n'`
    for r in ${SRP_IDs}; do
        url="ftp://ftp-trace.ncbi.nih.gov/sra/sra-instant/reads/ByRun/sra/SRR/${r:0:6}/${r}/${r}.sra"
        wget $url
    done;
}

Download_SRP_Runs <SRP ID GOES HERE>

danielecook

import os, gzip

GFF_URL = "ftp://ftp.wormbase.org/pub/wormbase/releases/WS245/species/c_elegans/PRJNA13758/c_elegans.PRJNA13758.WS245.annotations.gff3.gz"
BUILD = re.search("WS[0-9]+",GFF_URL).group(0)

if not os.path.isfile("c_elegans.{BUILD}.annotations.gff3.gz".format(BUILD=BUILD)):
	print "Downloading Annotation File"
	os.system("curl 'ftp://ftp.wormbase.org/pub/wormbase/releases/WS245/species/c_elegans/PRJNA13758/c_elegans.PRJNA13758.WS245.annotations.gff3.gz' > c_elegans.{BUILD}.annotations.gff3.gz".format(BUILD=BUILD))
 
acceptable_types = ['SNP', 'point_mutation']

danielecook

function rename_to_filename {
    # Renames samples with the filename.
    tmp=`mktemp -t temp`
    echo ${1/.[vb]cf/} > $tmp
    bcftools reheader -s $tmp $1 > m.$1
    mv m.$1 $1
    bcftools index $1
}

function add_sample_prefix {

danielecook

# If you are trying to view VCF 4.2 files in IGV - you may run into issues. This function might help you.
# This script will:
# 1. Rename the file as version 4.1
# 2. Replace parentheses in the INFO lines (IGV doesn't like these!)

function vcf_downgrade() {
  outfile=${1/.bcf/}
  outfile=${outfile/.gz/}
  outfile=${outfile/.vcf/}
  bcftools view --max-alleles 2 -O v $1 | \

danielecook

# Download wormbase gff file
curl 'ftp://ftp.wormbase.org/pub/wormbase/releases/WS245/species/c_elegans/PRJNA13758/c_elegans.PRJNA13758.WS245.annotations.gff3.gz' > c_elegans.WS245.annotations.gff3.gz

# Use gff parallelized tools:  brew install dmd
# Extract each type into its own GFF File

# This list obtained by running:
# gunzip -kfc c_elegans.WS245.annotations.gff3.gz | cut -f 3 | sort | uniq 
types="CDS
DNAseI_hypersensitive_site

danielecook

def SLURM_get_last_job():
	jobid = Popen("squeue --user=$USER -o %i -h -S -i | head -n 1", stdout=PIPE, shell=True).communicate()[0]
	jobid = jobid.strip()
	if jobid == "":
		return ""
	else:
		return jobid

danielecook

def chunk_genome(chunk_size, reference):
    """ 
    Parses bwa .ann file to retrieve chromosome sizes
    for chunking purposes
    """
    ann = open(reference + ".ann").read()
    # Parsing .ann files
    contigs = [x.split(" ")[1] for x in ann.split("\n")[1:-1:1]][::2]
    contig_sizes = map(int,[x.split(" ")[1] for x in ann.split("\n")[1:-1:1]][1::2])
    for chrom, size in zip(contigs, contig_sizes):

danielecook

# Run this script in a directory containing zip files from fastqc. It aggregates images of each type in individual folders
# So looking across data is quick.

zips=`ls *.zip`

for i in $zips; do
    unzip -o $i &>/dev/null;
done

fastq_folders=${zips/.zip/}

danielecook

import sys

current_feature = ""

for line in sys.stdin:
    feature = line.split("\t")[2]
    if feature != current_feature:
        f = file(feature + ".gff", "a+")
    f.write(line)