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'

afrendeiro

#!/usr/bin/env python
import csv
import sys

# usage:
# samtools view -h file.bam | shift_reads.py genome | samtools view -S -b - | samtools sort - file.shifted

def getChrSizes(chrmFile):
    """
    Reads tab-delimiter file with two rows describing the chromossomes and its lengths.

afrendeiro

#! /usr/bin/env python

import argparse
import pandas as pd
import json
import requests


default_gene_set_libraries = [
    'GO_Biological_Process_2015',

afrendeiro

from pipelines.models import Project
import os
import pandas as pd
import pysam


# Start project
prj = Project("metadata/project_config.yaml")
prj.add_sample_sheet()

afrendeiro

# By Jörg Mensche

import matplotlib.pyplot as plt  # basic plot functionalities
import seaborn as sns
# more advanced plotting
import scipy.stats as sc
# random number generator
# generate the x-mas tree:
all_branches = []
balls_x = []

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 looper.models import Project
import argparse
import os
import pandas as pd
import re
import string
import textwrap


def get_colors(level, pallete="gist_rainbow", nan_color=[0.5, 0.5, 0.5]):

afrendeiro

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__()

afrendeiro

import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns

sns.set_style("white")

fig, axis = plt.subplots(1)
# all genes
axis.scatter(
  np.arange(0, 8, 8./10000) + np.random.normal(0, 0.1, size=10000),

afrendeiro

import os
import pandas as pd

# Human
# hg38
ensembl_release = 91
date = "20161111"

organisms = {
    "homo_sapiens": "GRCh38",