afrendeiro

import numpy as np
import matplotlib.pyplot as plt


# class from here: http://nbviewer.ipython.org/gist/tillahoffmann/f844bce2ec264c1c8cb5
class gaussian_kde(object):
    """Representation of a kernel-density estimate using Gaussian kernels.

    Kernel density estimation is a way to estimate the probability density
    function (PDF) of a random variable in a non-parametric way.

afrendeiro

import sys
import json
import urllib2
import re
from collections import Counter


def get_ids(term, ids=list(), retstart=0, retmax=1000):
    """
    Return all Pubmed Ids of articles containing a term, in a recursive fashion.

afrendeiro

import sys
from argparse import ArgumentParser
import pyBigWig
import numpy as np
import multiprocessing
import parmap

"""
Produce bigWig files with the quantiles/mean of signal across a number of bigWig files.
"""

afrendeiro

import networkx as nx
import matplotlib.pyplot as plt
import seaborn as sns

# Getting a specific node
G['PAX5']
# Geting a specific edge
G['PAX5']['NFKB1']

# Getting all edge weights

afrendeiro

from argparse import ArgumentParser
import sys
from pypiper import NGSTk
import textwrap

global tk
tk = NGSTk()

def sra2bam(sra_acession, output_bam):
    # Slurm header

afrendeiro

from scipy.optimize import curve_fit
from scipy import stats
import matplotlib.pyplot as plt


def fit_exponential_neg(x, a, b, c):
    return a * np.exp(-b * x) + c

X = np.array(rpkm_log['mean'])
Y = np.array(rpkm_log['qv2'])

afrendeiro

def plot_fragment_sizes_fit(bam, plot, outputCSV, maxInsert=1500, smallestInsert=30):
    """
    Heavy inspiration from here:
    https://github.com/dbrg77/ATAC/blob/master/ATAC_seq_read_length_curve_fitting.ipynb
    """
    try:
        import pysam
        import numpy as np
        import matplotlib.mlab as mlab

afrendeiro

Introduction to next-generation sequencing (NGS)

General workflow

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:

afrendeiro

# 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")

afrendeiro

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 ../..