mgalardini

#!/bin/sh
blastn -query 1 -subject 2 -outfmt 6 -task megablast -evalue 1e-10 | awk '{if ($4 > 4999) print $3" "$3" "$9" "$10" "$2" "$7" "$8" "$1}' > 1-2

mgalardini

#!/bin/bash
# Take the flac files in a directory and turn them into mp3s
for file in *.flac; do flac -cd "$file" | lame -h --preset standard - "${file%.flac}.mp3"; done

mgalardini

#!/bin/bash
if [ "$#" -lt 1 ]; then
    search=$(cat /var/log/apache2/access.log | awk '{print $1"-"$4}')
else
    search=$(cat /var/log/apache2/access.log | grep $1 | awk '{print $1"-"$4}')
fi
single=$(for i in $search; do ip=$(echo $i | awk 'BEGIN {FS = "-"}; {print $1}'); datetime=$(echo $i | awk 'BEGIN {FS = "-"}; {print $2}' | sed 's/\[//' | awk 'BEGIN {FS = ":"}; {print $1}'); loc=$(geoiplookup $ip | awk 'BEGIN { FS = ":" }; {print $2}' | sed -e 's/^[ \t]*//' | sed 's/ /_/g'); echo -e $datetime"-"$loc"-"$ip;done)
final=$(for i in $(echo $single | tr ' ' '\n' | sort | uniq); do ip=$(echo $i | awk 'BEGIN {FS = "-"}; {print $3}'); whoz=$(whois $ip | grep NetName | awk 'BEGIN {FS = ":"}; {print $2}' | sed 's/^ *//g' | sed 's/ /_/g' | head -n 1); whoz2=$(whois $ip | grep netname | awk 'BEGIN {FS = ":"}; {print $2}' | sed 's/^ *//g'| sed 's/ /_/g' | head -n 1); whoz3=$(whois $ip | grep OrgName | awk 'BEGIN {FS = ":"}; {print $2}' | sed 's/^ *//g'| sed 's/ /_/g' | head -n 1); whoz4=$(whois $ip | grep descr | a

mgalardini

#!/usr/bin/python
class bcolors:
    HEADER = '\033[95m'
    OKBLUE = '\033[94m'
    OKGREEN = '\033[92m'
    WARNING = '\033[93m'
    FAIL = '\033[91m'
    ENDC = '\033[0m'

print '%sSingle job stats for CONTIGuator%s'%(bcolors.HEADER,bcolors.ENDC)

mgalardini

#!/usr/bin/python
'''
Launch codeml on all the alignments

Marco Galardini 2012
University of Florence
GPL v3.0
'''
from optparse import OptionParser, OptionGroup
from time import strftime

mgalardini

mgalardini

#!/usr/bin/python
'''
Reads a FASTA files and rewrites it keeping only the unique IDs

Important: we assume that if two proteins have the same ID, they have the same sequence
'''
import sys
from Bio import SeqIO

if len(sys.argv) < 3:

mgalardini

mgalardini

rsync -av rsync://ftp.ncbi.nlm.nih.gov/genomes/Bacteria --include "*/" --include "Bacteria/Escherichia*/*.fna" --exclude=* . --prune-empty-dirs

mgalardini

#!/usr/bin/env python
"""
simple example script for running and testing notebook resulting in a new workbook.

Usage: `run_notebook foo.ipynb foo_new.ipynb`

Each cell is submitted to the kernel, and the outputs are compared with those stored in the notebook.
Each cell is given half an hour to complete.
"""