Tag Autocorrelation

This notebook will compute the autocorrelation of the ChIP-seq samples.

The.....


In [ ]:


In [1]:
import os
os.chdir('../')
print(os.getcwd())
import pandas as pd
import numpy as np


/ifs/projects/adam/pipeline_tests/data/test1/test_chiptools.dir

In [2]:
import matplotlib.pyplot as plt
import matplotlib.lines as mlines
from matplotlib.colors import ListedColormap
from matplotlib import cm

In [3]:
def plotAutocorrelation(TagDir):
    
    TagFile = "tagAutocorrelation.txt"
    File = "homer/Tag.dir/" + TagDir + "/" + TagFile 
    data = pd.read_csv(File, sep="\t")
    x = data.columns[0]
    y1 = data.columns[1]
    y2 = data.columns[2]

    data.plot(x)
    plt.xlabel("Relative Distance between Reads")
    plt.ylabel("Total Read Pairs")
    plt.title("Tag Autocorrelation")
    plt.show()

In [4]:
names = set()

design = pd.read_table('design.tsv')
samples = design.bamReads.values
for sample in samples:
    #print(sample.strip(".bam"))
    names.add(sample.strip(".bam"))

for (dirpath, dirnames, filenames) in os.walk(os.getcwd()):
    for dirname in dirnames:
        if dirname in names:
            plotAutocorrelation(dirname)