pyopenms

Install pyopenms

!pip install pyopenms --quiet

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

import pyopenms as oms
input_file = "./test.mzML"

# open mzML file
exp = oms.MSExperiment()
oms.MzMLFile().load(input_file, exp)

# convert to pd.DataFrame
df = exp.get_df(long=True)
df

	RT	mz	inty
0	0.2961	200.000183	0.0
1	0.2961	200.000427	0.0
2	0.2961	200.000671	0.0
3	0.2961	200.000916	0.0
4	0.2961	202.605835	0.0
...	...	...	...
39823	0.3561	1999.913086	0.0
39824	0.3561	1999.937256	0.0
39825	0.3561	1999.961548	0.0
39826	0.3561	1999.985718	0.0
39827	0.3561	2000.009888	0.0

39828 rows × 3 columns

Convert a single Spectrum as a pd.DataFrame

This can be achieved by filtering the dataframe above to the desired spectrum or can be done with the pyopenms interface.

spectrum = oms.MSSpectrum(exp.getSpectrum(0))
df = spectrum.get_df()
df

	mz	intensity	ion_mobility	ion_mobility_unit	ms_level	precursor_mz	precursor_charge	native_id	sequence	ion_annotation	base peak m/z	base peak intensity	total ion current	lowest observed m/z	highest observed m/z	filter string	preset scan configuration
0	200.000188	0.0	NaN	<NONE>	1	0.0	0	controllerType=0 controllerNumber=1 scan=1			810	1471973	15245068	200	2000	FTMS + p ESI Full ms [200.00-2000.00]	1
1	200.000430	0.0	NaN	<NONE>	1	0.0	0	controllerType=0 controllerNumber=1 scan=1			810	1471973	15245068	200	2000	FTMS + p ESI Full ms [200.00-2000.00]	1
2	200.000673	0.0	NaN	<NONE>	1	0.0	0	controllerType=0 controllerNumber=1 scan=1			810	1471973	15245068	200	2000	FTMS + p ESI Full ms [200.00-2000.00]	1
3	200.000915	0.0	NaN	<NONE>	1	0.0	0	controllerType=0 controllerNumber=1 scan=1			810	1471973	15245068	200	2000	FTMS + p ESI Full ms [200.00-2000.00]	1
4	202.605829	0.0	NaN	<NONE>	1	0.0	0	controllerType=0 controllerNumber=1 scan=1			810	1471973	15245068	200	2000	FTMS + p ESI Full ms [200.00-2000.00]	1
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
19909	1999.913081	0.0	NaN	<NONE>	1	0.0	0	controllerType=0 controllerNumber=1 scan=1			810	1471973	15245068	200	2000	FTMS + p ESI Full ms [200.00-2000.00]	1
19910	1999.937296	0.0	NaN	<NONE>	1	0.0	0	controllerType=0 controllerNumber=1 scan=1			810	1471973	15245068	200	2000	FTMS + p ESI Full ms [200.00-2000.00]	1
19911	1999.961513	0.0	NaN	<NONE>	1	0.0	0	controllerType=0 controllerNumber=1 scan=1			810	1471973	15245068	200	2000	FTMS + p ESI Full ms [200.00-2000.00]	1
19912	1999.985729	0.0	NaN	<NONE>	1	0.0	0	controllerType=0 controllerNumber=1 scan=1			810	1471973	15245068	200	2000	FTMS + p ESI Full ms [200.00-2000.00]	1
19913	2000.009947	0.0	NaN	<NONE>	1	0.0	0	controllerType=0 controllerNumber=1 scan=1			810	1471973	15245068	200	2000	FTMS + p ESI Full ms [200.00-2000.00]	1

19914 rows × 17 columns