mscook

import glob
import os

inf = glob.glob("*.gz")
rlen = 76.0

for f in inf:
    tmp = f.split(".fastq.gz")[0]
    os.system("zcat "+f+" | head -n 4 | tail -n 1 > "+tmp)
    with open(tmp) as fin:

mscook

# Takes a SeqFindR database and does some simple validation
#
# usage:
#
#   python validate_SeqFindR.py $input.fa

import sys

stored = []

mscook

import matplotlib
matplotlib.use('Agg')
import sys
import collections
import pylab as plt


from matplotlib import rcParams
rcParams.update({'figure.subplot.bottom': 0.25})

mscook

from Bio.Blast import NCBIXML

input = 'CFT073.B2_comp.fa_blast.xml'

for record in NCBIXML.parse(open('CFT073.B2_comp.fa_blast.xml')):
    for align in record.alignments:
        for idx, hsp in enumerate(align.hsps):
            if idx == 0:
                print ">"+input.split("_")[0]+"_"+record.query.split(',')[1].strip()
                print hsp.sbjct

mscook

import glob


order = open("order.dat").readlines()


#organism: Escherichia coli HVM1147 
#contigs: 93
#bases: 5131204
#rRNA: 4

mscook

import glob
import os

inf = glob.glob("*/*.fas")

for f in inf:
    #IR65/IR65_69_Contigs-against-EC958-complete.fas
    new = f.replace("-complete", "")
    os.system("fab bio_util.fasta_to_uppercase:"+f+","+new)
    #new = f.replace("ordered-", '')

mscook

import glob
import sys
import os

from Bio import Entrez


Entrez.email = "Beatson.Lab@gmail.com"

mscook

# Mitchell Stanton-Cook
# m.stantoncook@gmail.com
# github.com/mscook

import glob

"""
(> XXXXX       47,065 unmapped pairs
(> XXXXX       19,785 unmapped reads
(> XXXXX    5,098,912 reads/pairs with alignments

mscook

import sys
import textwrap

"""
Usage:

chunk_mfa.py input.fa 500

"""

mscook

from fabric.api   import task
from fabric.tasks import Task

class MyTask(Task):
    name = "deploy"
    def run(self, environment, domain="whatever.com"):
        run("git clone foo")
        sudo("service apache2 restart")

instance = MyTask()