mzml数据处理及质谱图像绘制

数据处理

from pyteomics import mzml
import numpy as np
import pandas as pd
import matplotlib
import matplotlib.pyplot as plt
import json
import csv
import os
import math
def change_mzML(fd):
    for spectrum in mzml.read(fd):
        if(spectrum.get('base peak m/z') >= 114 and spectrum.get('base peak m/z')< 115):
            dfmz = pd.DataFrame(spectrum.get('m/z array'))
            dfin = pd.DataFrame(spectrum.get('intensity array'))
            dfmz.to_csv(fd+"114m_z.csv", mode='a+', index =False, header = True)
            dfin.to_csv(fd+"114intensity.csv", mode='a+', index =False, header = True)
    for spectrum in mzml.read(fd):
        if(spectrum.get('base peak m/z') >= 115 and spectrum.get('base peak m/z')< 116):
            dfmz = pd.DataFrame(spectrum.get('m/z array'))
            dfin = pd.DataFrame(spectrum.get('intensity array'))
            dfmz.to_csv(fd+"115m_z.csv", mode='a+', index =False, header = True)
            dfin.to_csv(fd+"115intensity.csv", mode='a+', index =False, header = True)
    for spectrum in mzml.read(fd):
        if(spectrum.get('base peak m/z') >= 116 and spectrum.get('base peak m/z')< 117):
            dfmz = pd.DataFrame(spectrum.get('m/z array'))
            dfin = pd.DataFrame(spectrum.get('intensity array'))
            dfmz.to_csv(fd+"116m_z.csv", mode='a+', index =False, header = True)
            dfin.to_csv(fd+"116intensity.csv", mode='a+', index =False, header = True)
    for spectrum in mzml.read(fd):
        if(spectrum.get('base peak m/z') >= 117 and spectrum.get('base peak m/z')< 118):
            dfmz = pd.DataFrame(spectrum.get('m/z array'))
            dfin = pd.DataFrame(spectrum.get('intensity array'))
            dfmz.to_csv(fd+"116m_z.csv", mode='a+', index =False, header = True)
            dfin.to_csv(fd+"116intensity.csv", mode='a+', index =False, header = True)
for fn in os.listdir('C:/hqh/data/breast/'):
     if fn.endswith('.mzML'):
        fd = os.path.join('C:/hqh/data/breast/', fn)
        change_mzML(fd)

质谱图绘制

import numpy as np
import pandas as pd
import matplotlib
import matplotlib.pyplot as plt
import json
import csv
import os
import math
# 获取csv其中一行
def getColumn(filename, column):
    results = csv.reader(open(filename), delimiter=",")
    return [result[column] for result in results]
# 转换成浮点数
def getFloat(result):
    res_float_m = map(float, result)
    return list(res_float_m)
# 获取数组中的最大值
def getMax(res_float):
    max_n = 0
    for res in res_float:
        if res > max_n:
            max_n = res
    return max_n
x = getColumn("C:/hqh/1.csv",0)
y = getColumn("C:/hqh/1.csv",1)
x_float = getFloat(x)
y_float = getFloat(y)
max_y = getMax(y_float)
y_float = np.array(y_float)*100/max_y # 将数组中全部值化为相对强度
plt.xlim(0, 2000)
plt.bar(x_float, y_float, width = 5)
plt.savefig("C:/hqh/examples.png")