Tabea-K

sort -k1,1 -k12,12gr -k11,11g -k3,3gr blastout.txt | sort -u -k1,1 --merge > bestHits

Tabea-K

awk 'BEGIN{s=0}{if(NR % 4==1){print $0"_"s; s=s+1}else{print $0}}'

Tabea-K

awk '{if(NR % 4==1){printf $0"\t"}else if(NR % 4==2){print length($0)}}'

Tabea-K

#!/usr/bin/env bash
convert -density 300  -resize 25% $1 $2

Tabea-K

#!/usr/bin/env python

import sys
import os
import argparse

q_ascii = "!#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~"
q_ascii += '"'

def id_error(line_no, name, line):

Tabea-K

#!/usr/bin/env python
'''	 
This script extracts specific fastq sequences
from a multi-fastq sequence file, with the ID's
of the sequences to be extracted in a txt file.
'''
import sys
import argparse
import os

Tabea-K

#!/usr/bin/env python
"""
Creates a pdf alignment
"""

import sys
import os
import tempfile

input_filename = sys.argv[1]

Tabea-K

#!/usr/bin/env python
"""
Created by Tabea Kischka at 2015-01-27 10:34:05

converts a last maf alignment into a fasta alignment
"""
import sys

path_to_alignio = '/home/tabeah/Scripts/alignio-maf'

Tabea-K

#!/usr/bin/env bash
# Prints the number of identical rows between different columns for two
# csv files. The first argument is the column number which should be used.
# For example, you can compare the IDs given in a csv file.

cut -f $1 $2 | sort > .file1
cut -f $1 $3 | sort > .file2


# With no options, comm produces three-column output.

Tabea-K

awk '/^>/ {printf("\n%s\n",$0);next; } { printf("%s",$0);}  END {printf("\n");}' | awk 'BEGIN {RS = ">" ; FS = "\n"} NR > 1 {print "@"$1"\n"$2"\n+"$1"\n"gensub(/./, "I", "g", $2)}'