| #!/usr/bin/env python | |
| from argparse import ArgumentParser | |
| from BeautifulSoup import BeautifulSoup | |
| import csv | |
| # argparser | |
| parser = ArgumentParser(description = 'Parses MEME-MAST xml output.', | |
| usage = 'python mast2tsv.py mast.output.xml mast.output.tsv') | |
| # positional arguments |
| #!/usr/bin/env python | |
| # Mining "COSMIC: Catalogue Of Somatic Mutations In Cancer" database | |
| import os | |
| from subprocess import call | |
| import pandas as pd | |
| # Cosmic DB has requires login to download data, so neither BioMart or wget actually work. | |
| call(["wget", "http://cancer.sanger.ac.uk/files/cosmic/current_release/CosmicCompleteExport.tsv.gz"]) |
| #!/usr/env/python | |
| import os | |
| import h5py | |
| import pandas as pd | |
| projectDir = '/home/afr/workspace/cellprofiler/' | |
| # open hdf5 | |
| hdf5 = h5py.File(projectDir + '1315001__2014-01-25T18_26_59-Measurement1.h5', 'r') |
| #!/usr/env python | |
| from argparse import ArgumentParser | |
| import os, re | |
| from pybedtools import BedTool | |
| import HTSeq | |
| import numpy as np | |
| import pandas as pd | |
| import string | |
| import itertools |
| class DivideAndSlurm(object): | |
| """ | |
| DivideAndSlurm is a class to handle a map-reduce style submission of jobs to a Slurm cluster. | |
| Add a particula task to the object (though a specific function) and it will divide the input data | |
| into pools, which will be submitted (use the submit() function) in parallel to the cluster. | |
| Tasks can also further process its input in parallel, taking advantage of all processors. | |
| """ | |
| def __init__(self, tmpDir="/fhgfs/scratch/users/user/", logDir="/home/user/logs", queue="shortq", userMail=""): | |
| super(DivideAndSlurm, self).__init__() |
| import pandas as pd | |
| from biomart import BiomartServer, BiomartDataset | |
| from Bio import Entrez | |
| def get_tax_id(specie): | |
| """Get taxon ID for specie.""" | |
| specie = specie.replace(" ", "+").strip() | |
| search = Entrez.esearch(term=specie, db="taxonomy", retmode="xml") | |
| record = Entrez.read(search) |
| # New users | |
| sudo adduser username | |
| # Grant the new user sudo privileges | |
| sudo visudo | |
| # username ALL=(ALL:ALL) ALL | |
| # add this line ^^ | |
| # change to that user | |
| su - username |
| for GENOME in hg19 mm10 danRer10 | |
| do | |
| # Static files | |
| mkdir -p resources/${GENOME} | |
| cd resources/${GENOME} | |
| ### Genome | |
| wget http://hgdownload.cse.ucsc.edu/goldenPath/${GENOME}/bigZips/${GENOME}.2bit | |
| twoBitToFa ${GENOME}.2bit ${GENOME}.fa | |
| samtools faidx ${GENOME}.fa | |
| cd ../.. |
| # Install zimba | |
| R | |
| install.packages(c("R.oo")) | |
| install.packages(c("R.utils", "quantreg","doParallel","doMC","foreach")) # for R>3.0 | |
| # only version that works with R 3.0: | |
| # get it from here: https://code.google.com/p/zinba/issues/detail?id=69 | |
| install.packages("zinba_2.03.1.tar.gz", repos=NULL) | |
| # Make bed files from bams | |
| # system("bedtools bamtobed -i /data/mapped/sample.bam > ~/zinba/reads/sample.bed") |
The current used technology for next generation sequencing is Illumina sequencing - all others cannot compete with its speed, price and output power - they have therefore specialized in niche applications (not discussed here).
Nevertheless, no sequencing technology cannot simply start sequencing one end of a chromosome until the other end.
The approach therefore is: