pymzml

Install pymzml

!pip install pymzml --quiet

import pandas as pd
import pymzml

Download the test file

# # Download test file
import requests

url = 'https://raw.githubusercontent.com/levitsky/pyteomics/master/tests/test.mzML'
file_name = 'test.mzML'

# Send a GET request to the URL
response = requests.get(url)

# Save the content of the response to a file
with open(file_name, 'wb') as file:
    file.write(response.content)

print(f'File {file_name} downloaded successfully!')

File test.mzML downloaded successfully!

Load .mzML file and convert to pd.DataFrame

input_file = "./test.mzML"

run = pymzml.run.Reader(input_file)
# Get the first spec
spec = run.next()
# Convert to Pandas DataFrame
df = pd.DataFrame(spec.centroidedPeaks).rename(columns={0:'mz', 1:'int'})
df

	mz	int
0	204.760065	3901.930681
1	204.778823	3431.441349
2	204.790975	3703.068912
3	204.795946	4317.227255
4	204.797708	4267.166873
...	...	...
1735	1998.647154	2567.956920
1736	1998.908241	5539.517009
1737	1999.254369	14109.211636
1738	1999.510959	8432.185933
1739	1999.782814	1875.846606

1740 rows × 2 columns