ivan-krukov

ivan-krukov

#20 chords A simple chord diagram for amino-acid relationships ##Usage

The input data should be a 20x20 table with tabs as separators.

To run the thing, do this (uses firefox)

git clone https://gist.github.com/ivan-kryukov/c265c9df6bfeda28abc8

ivan-krukov

#Randomization script

The idea is to do bootstrap resampling on the control dataset to make sure it is appropriate as a control dataset.

#Usage

python randomize.py <input.csv> <resample_times>

ivan-krukov

>sequence 1
ACTG

ivan-krukov

! /usr/bin/osascript
on run argv
	set Volume (item 1 of argv)
end run

ivan-krukov

import argparse
from Bio import SeqIO
parser=argparse.ArgumentParser()

parser.add_argument("inputFile", help="input fasta file")
parser.add_argument("outputFile",help="output file name")
parser.add_argument("sampleName",help="sample name to be removed")

args = parser.parse_args()

ivan-krukov

#Read a fasta file and only keep the sequences with correct headers (id_pattern regex)

import re
import sys

seq_pattern = re.compile(r">[^>]+\n",re.MULTILINE)
id_pattern = re.compile(r"protein_id:(?P<id>[.\w]+)")

with open(sys.argv[1]) as f:
    text = f.read()

ivan-krukov

#!/bin/sh
#get the command line arguments
input_file=$1
divisor=$2
#run wc on the file in argv[1]
size=`wc -l $input_file`
#split the return on whitespace - first word is now in 
set $size
#get the intiger division of wc/divisor
part=$(($1/$divisor))

ivan-krukov

#!/bin/sh
cmd=$*
pid=$$

echo "$cmd @ `pwd`; Started at `date`" > $pid.out
echo "[$pid] $cmd" 
eval $cmd >> $pid.out 2>> $pid.err

echo "$cmd @ `pwd`; Finished at `date`" >> $pid.out

ivan-krukov

#Take a fraction of random sequence reads from a fastq file
from sh import wc
import argparse
import random

def first_word(string):
    return string.strip().split()[0]

#read a file in chunks of deflines
def read_segments(filename,deflines):