plot_genes.py

import numpy as np
from matplotlib import pyplot as plt


col_map = {}
concentrations = ['0.5', '2', '5', '10', '20', '40']

kinds = ['R1', 'R2', 'R3', 'S1', 'S2', 'S3']
gene_names = []
gene_index = 125

with open('/home/vighnesh/data/bio/HPK.counts.txt') as f:
    c = 0
    line = f.readline()
    col_names = [(name, i) for (i, name) in enumerate(line.split())]
    col_map.update(col_names)

    count = 0
    data = []
    for line in f:
        #for w in line.split():
        #    print(w)
        #break
        words = line.split()
        name = words[0]
        gene_names.append(name)
        row = map(int, words[1:])
        data.append(row)
        count += 1

    array = np.array(data)

if gene_index >= len(gene_names):
    print('Index %d is too high, only %d genes exist in data' % 
          (gene_index, len(gene_names)))
    exit(0)

for kind in kinds:
    query_cols = ['HPK' + conc + '_' + kind for conc in concentrations]
    query_col_index = [col_map[q] for q in query_cols]

    values = array[gene_index][query_col_index]
    plt.plot(values, label = kind)

plt.xticks(range(len(query_cols)), query_cols)
plt.grid(True)
plt.legend(loc='best')
plt.xlabel('Concentrations')
plt.ylabel('Expression of ' + gene_names[gene_index])
plt.xlim([-0.5, 5.5])
plt.show()