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

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

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

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

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 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 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 numpy as np
import pandas as pd


class DifferentialRegions(object):
    """
    Compute two-tailed empirical p-value for difference between values of two variables.
    """
    def __init__(self, df, a, b, permutations=100, alpha=0.05, correct=True):
        super(DifferentialRegions, self).__init__()

afrendeiro

# I just need to have these somewhere to remember them later

for F in `find . | grep -e 'CM[0-9]\{2,\}s'`
do
    echo $F $(echo $F | sed 's/CM\([0-9]\{2,\}\)s/CM\1-/g')
    mv $F $(echo $F | sed 's/CM\([0-9]\{2,\}\)s/CM\1-/g')
done

for F in `find . | grep -e '_[1-2]_' | grep -v PBMC`
do

afrendeiro

def enrichr(dataframe, gene_set_libraries=None, kind="genes"):
    """
    Use Enrichr on a list of genes (currently only genes supported through the API).
    """
    import json
    import requests
    import pandas

    ENRICHR_ADD = 'http://amp.pharm.mssm.edu/Enrichr/addList'