Tabea-K

# get subsequence of a fasta file containing only one sequence
fasta_get_subseq () {
 awk '/^>/ {printf("\n%s\n",$0);next; } { printf("%s",$0);}  END {printf("\n");}' < "$1" | tail -n1 | cut -c$2-$3
}

Tabea-K

def longblob2list(longblob):
    """
    Converts a longblob variable into a list of integers.
    "90930917,90931703,90932054," > [90930917,90931703,90932054]
    """
    y = []
    for number in longblob.split(','):
        if number != "" and number != ",":
            y.append(int(number))
    return y

Tabea-K

# gives the coordinates of all 5'UTR exons
awk '
BEGIN { OFS = "\t"; FS = "\t"} ;
            {
                # $7 is cdsStart
                delete astarts;
                delete aends;
                split($10, astarts, /,/);
                split($11, aends, /,/);
                for(i=1; i <= length(astarts); i++){

Tabea-K

curl -s 'http://rest.ensembl.org/map/human/GRCh37/X:1000000..1000100:1/NCBI36?' -H 'Content-type:application/json' | python -c 'import json,sys;obj=json.load(sys.stdin);print obj["mappings"][0]["mapped"]["end"]'

Tabea-K

sort -k 1,1 -k2,2n

Tabea-K

for X in `fdupes . -r | xargs -n1`; do ls -alhS $X; done

Tabea-K

#!/usr/local/bin/python
# File created by Tabea Kischka at Thu May 19 15:24:59 CEST 2016
# This script orders the sequence in a multi fasta file by the chromosome name in
# karyotypic oder, and not lexicographically.
# I.e., it creates this order: chr1, chr2, chr10, ...
# instead of the order chr1, chr10, chr2


import sys

Tabea-K

echo -e '\033k'"Super_title_includes_directory_${PWD}"'\033\\'

Tabea-K

find . -type l ! -exec test -e {} \; -print

Tabea-K

#!/usr/bin/env python
"""
Turns tab delimited data to macdown table format.
Needs the csvtoolkit to be installed.
"""
import sys
import os
import tempfile
import argparse