In [ ]:

    

%matplotlib inline

#filename_call = '../../data/SingleCell/Undetermined_S0_L002_R1_001.pos_call'
filename_call = '../../data/SingleCell/tmp.pos_call'

f_call = open(filename_call,'r')

headers = f_call.readline().strip().split("\t")
print(headers)

pos_list=  []
N_list = []
A_list = []
T_list = []
G_list = []
C_list = []
for line in f_call:
    tokens = line.strip().split("\t")
    tmp_sum = sum([int(x) for x in tokens[1:]])
    pos_list.append( int(tokens[0]) )
    tmp_A_freq = float(tokens[1])/tmp_sum
    A_list.append( tmp_A_freq )
    tmp_T_freq = float(tokens[2])/tmp_sum + tmp_A_freq
    T_list.append( tmp_T_freq )
    tmp_G_freq = float(tokens[3])/tmp_sum + tmp_T_freq
    G_list.append( tmp_G_freq )
    tmp_C_freq = float(tokens[4])/tmp_sum + tmp_G_freq
    C_list.append( tmp_C_freq )
    tmp_N_freq = float(tokens[5])/tmp_sum + tmp_C_freq
    N_list.append( tmp_N_freq )
f_call.close()

import matplotlib.pyplot as plt
fig = plt.figure(figsize=(12,4))
ax1 = fig.add_subplot(1,1,1)
ax1.bar(pos_list, N_list, facecolor='black')
ax1.bar(pos_list, C_list, facecolor='red')
ax1.bar(pos_list, G_list, facecolor='green')
ax1.bar(pos_list, T_list, facecolor='orange')
ax1.bar(pos_list, A_list, facecolor='blue')
ax1.set_xticks(pos_list)
ax1.set_yticks([0, 0.25, 0.50, 0.75, 1.0])
ax1.grid()
ax1.set_ylabel("BaseCall Proportion")
ax1.set_xlabel("Position (bp): read length is %d bp"%(len(A_list)))
plt.show()


    

In [ ]: