philippmuench

# cleanup all docker files on your system
sudo docker stop $(docker ps -a -q)
sudo docker rm $(docker ps -a -q)
sudo docker rmi `docker images -a -q`

# build container from github
docker build -t eden github.com/philippmuench/eden

# bild container locally
docker build --rm=true -t eden .

philippmuench

# add this line to your Dockerfile (you also need to install Rbase)
RUN R -e 'install.packages("packrat" , repos="http://cran.us.r-project.org"); packrat::restore()'

philippmuench

__author__ = "Anand M"

'''
Takes output file generated by VarScan2 somatic programme and converts the formats.
'''

import argparse, math, re

parser = argparse.ArgumentParser(
    description="Converts VarScan2 somatic vcf to native format and vice-versa.\nInput is automatically detected")

philippmuench

### description to run EDEN without the GUI, please be aware that some check routines are implemented inside the GUI and thus will not applied to the data (for example the check for validity of input files)
### commands that must be executed inside the docker container are written as `eden@4d4a16919ce0:~$ command`

# 1. run docker using the interactive mode
sudo docker run -p 80:3838 -i -t --entrypoint /bin/bash philippmuench/eden
eden@4d4a16919ce0:~$ mkdir /home/eden/data/fasta
# now the console inside the docker container should be visible `eden@4d4a16919ce0:~$`. This contains also the number of the docker instance, you should use this number for the following commands. If you get the Error "docker: Error response from daemon: driver failed programming external connectivity on endpoint jovial_jenning" please shutdown the running docker instance first. You can do this by usind `sudo docker ps` followed by 'sudo docker stop 4d4a16919ce0' (the last number is the instance ID, please use the instance ID showed a

philippmuench

#!/usr/bin/env python

import random
import sys

# space sequence characteristics
setsize_min = 2 # min number of spacer
setsize_max = 8 # max number of spacer
minlength = 30 # min length of spacer
maxlength = 40 # max length of spacer

philippmuench

import xml.etree.ElementTree as ET
tree = ET.parse('all_crispr.xml')
root = tree.getroot()
offset = 1000
for id in root.findall("./Taxons/Taxon/Sequences/Sequence"):
	refseq = id.find('RefSeq').text
	for crispr in id.findall("CRISPRs"):
		crispr_num = crispr.find('CRISPRCount').text
		if int(crispr_num) > 0:
			for name in crispr.findall("CRISPR"):

philippmuench

#! /bin/sh

rm -rf log.txt # file where the taxid of skipped taxa will written to
max_treshold=20000
mkdir -p out
while read line; do
  pyla_name=$(echo $line | awk -F';' '{print $1}' | tr -s ' ' | tr ' ' '_')
  txid=$(echo $line | awk -F';' '{print $2}')
  echo "processing $pyla_name"
  num_found=$(esearch -db protein -query "txid$txid[Organism:exp]"\

philippmuench

# cleanup
rm(list=ls())

# load packages
require(vegan)
require(pander)
require(ggplot2)
require(ape)
library(RColorBrewer)

philippmuench

install.packages("BiocManager")
BiocManager::install("Biostrings", version = "3.8")
BiocManager::install("biomaRt", version = "3.8")
install.packages("biomartr", dependencies = TRUE)

library(biomartr)
getGenome(db = "genbank", organism = "GCA_003138775.1", reference = FALSE)

philippmuench

n1 = 9196 # total number of lysis positive genomes
y1 = 830  # number of lyssis positive genemes among colicin B positive genomes
n2 = 303 # total number of lysis negative genomes
y2 = 20 # lysis negative genomes among colicin B positive genomes

# SIMULATION
I = 10000 # simulations
theta1 = rbeta(I, y1 + 1, (n1 - y1) + 1)  
theta2 = rbeta(I, y2 + 1, (n2 - y2) + 1)
diff = theta1 - theta2  # simulated diffs